PItcHPERFeCT: Primary Intracranial Hemorrhage Probability Estimation using Random Forests on CT
Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10–15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry...
Saved in:
| Published in: | NeuroImage clinical Vol. 14; no. C; pp. 379 - 390 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Netherlands
Elsevier Inc
01.01.2017
Elsevier |
| Subjects: | |
| ISSN: | 2213-1582, 2213-1582 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10–15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry by an expert reader is the gold standard for volume estimation, but is time-consuming and has within- and across-reader variability. We propose a fully automated segmentation approach using a random forest algorithm with features extracted from X-ray computed tomography (CT) scans.
The Minimally Invasive Surgery plus rt-PA in ICH Evacuation (MISTIE) trial was a multi-site Phase II clinical trial that tested the safety of hemorrhage removal using recombinant-tissue plasminogen activator (rt-PA). For this analysis, we use 112 baseline CT scans from patients enrolled in the MISTE trial, one CT scan per patient. ICH was manually segmented on these CT scans by expert readers. We derived a set of imaging predictors from each scan. Using 10 randomly-selected scans, we used a first-pass voxel selection procedure based on quantiles of a set of predictors and then built 4 models estimating the voxel-level probability of ICH. The models used were: 1) logistic regression, 2) logistic regression with a penalty on the model parameters using LASSO, 3) a generalized additive model (GAM) and 4) a random forest classifier. The remaining 102 scans were used for model validation.For each validation scan, the model predicted the probability of ICH at each voxel. These voxel-level probabilities were then thresholded to produce binary segmentations of the hemorrhage. These masks were compared to the manual segmentations using the Dice Similarity Index (DSI) and the correlation of hemorrhage volume of between the two segmentations. We tested equality of median DSI using the Kruskal-Wallis test across the 4 models. We tested equality of the median DSI from sets of 2 models using a Wilcoxon signed-rank test.
All results presented are for the 102 scans in the validation set. The median DSI for each model was: 0.89 (logistic), 0.885 (LASSO), 0.88 (GAM), and 0.899 (random forest). Using the random forest results in a slightly higher median DSI compared to the other models. After Bonferroni correction, the hypothesis of equality of median DSI was rejected only when comparing the random forest DSI to the DSI from the logistic (p < 0.001), LASSO (p < 0.001), or GAM (p < 0.001) models. In practical terms the difference between the random forest and the logistic regression is quite small. The correlation (95% CI) between the volume from manual segmentation and the predicted volume was 0.93 (0.9,0.95) for the random forest model. These results indicate that random forest approach can achieve accurate segmentation of ICH in a population of patients from a variety of imaging centers. We provide an R package (https://github.com/muschellij2/ichseg) and a Shiny R application online (http://johnmuschelli.com/ich_segment_all.html) for implementing and testing the proposed approach.
•A hemorrhage segmentation algorithm from CT scans is proposed.•Validation using manual segmentation was done on 102 patients from multiple sites.•Software is provided as a website (http://johnmuschelli.com/ich_segment.html).•An R package (https://github.com/muschellij2/ichseg) is available. |
|---|---|
| AbstractList | •
A hemorrhage segmentation algorithm from CT scans is proposed.
•
Validation using manual segmentation was done on 102 patients from multiple sites.
•
Software is provided as a website (http://johnmuschelli.com/ich_segment.html).
•
An R package (https://github.com/muschellij2/ichseg) is available. Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10–15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry by an expert reader is the gold standard for volume estimation, but is time-consuming and has within- and across-reader variability. We propose a fully automated segmentation approach using a random forest algorithm with features extracted from X-ray computed tomography (CT) scans. The Minimally Invasive Surgery plus rt-PA in ICH Evacuation (MISTIE) trial was a multi-site Phase II clinical trial that tested the safety of hemorrhage removal using recombinant-tissue plasminogen activator (rt-PA). For this analysis, we use 112 baseline CT scans from patients enrolled in the MISTE trial, one CT scan per patient. ICH was manually segmented on these CT scans by expert readers. We derived a set of imaging predictors from each scan. Using 10 randomly-selected scans, we used a first-pass voxel selection procedure based on quantiles of a set of predictors and then built 4 models estimating the voxel-level probability of ICH. The models used were: 1) logistic regression, 2) logistic regression with a penalty on the model parameters using LASSO, 3) a generalized additive model (GAM) and 4) a random forest classifier. The remaining 102 scans were used for model validation.For each validation scan, the model predicted the probability of ICH at each voxel. These voxel-level probabilities were then thresholded to produce binary segmentations of the hemorrhage. These masks were compared to the manual segmentations using the Dice Similarity Index (DSI) and the correlation of hemorrhage volume of between the two segmentations. We tested equality of median DSI using the Kruskal-Wallis test across the 4 models. We tested equality of the median DSI from sets of 2 models using a Wilcoxon signed-rank test. All results presented are for the 102 scans in the validation set. The median DSI for each model was: 0.89 (logistic), 0.885 (LASSO), 0.88 (GAM), and 0.899 (random forest). Using the random forest results in a slightly higher median DSI compared to the other models. After Bonferroni correction, the hypothesis of equality of median DSI was rejected only when comparing the random forest DSI to the DSI from the logistic (p < 0.001), LASSO (p < 0.001), or GAM (p < 0.001) models. In practical terms the difference between the random forest and the logistic regression is quite small. The correlation (95% CI) between the volume from manual segmentation and the predicted volume was 0.93 (0.9,0.95) for the random forest model. These results indicate that random forest approach can achieve accurate segmentation of ICH in a population of patients from a variety of imaging centers. We provide an R package (https://github.com/muschellij2/ichseg) and a Shiny R application online (http://johnmuschelli.com/ich_segment_all.html) for implementing and testing the proposed approach. •A hemorrhage segmentation algorithm from CT scans is proposed.•Validation using manual segmentation was done on 102 patients from multiple sites.•Software is provided as a website (http://johnmuschelli.com/ich_segment.html).•An R package (https://github.com/muschellij2/ichseg) is available. INTRODUCTIONIntracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10-15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry by an expert reader is the gold standard for volume estimation, but is time-consuming and has within- and across-reader variability. We propose a fully automated segmentation approach using a random forest algorithm with features extracted from X-ray computed tomography (CT) scans.METHODSThe Minimally Invasive Surgery plus rt-PA in ICH Evacuation (MISTIE) trial was a multi-site Phase II clinical trial that tested the safety of hemorrhage removal using recombinant-tissue plasminogen activator (rt-PA). For this analysis, we use 112 baseline CT scans from patients enrolled in the MISTE trial, one CT scan per patient. ICH was manually segmented on these CT scans by expert readers. We derived a set of imaging predictors from each scan. Using 10 randomly-selected scans, we used a first-pass voxel selection procedure based on quantiles of a set of predictors and then built 4 models estimating the voxel-level probability of ICH. The models used were: 1) logistic regression, 2) logistic regression with a penalty on the model parameters using LASSO, 3) a generalized additive model (GAM) and 4) a random forest classifier. The remaining 102 scans were used for model validation.For each validation scan, the model predicted the probability of ICH at each voxel. These voxel-level probabilities were then thresholded to produce binary segmentations of the hemorrhage. These masks were compared to the manual segmentations using the Dice Similarity Index (DSI) and the correlation of hemorrhage volume of between the two segmentations. We tested equality of median DSI using the Kruskal-Wallis test across the 4 models. We tested equality of the median DSI from sets of 2 models using a Wilcoxon signed-rank test.RESULTSAll results presented are for the 102 scans in the validation set. The median DSI for each model was: 0.89 (logistic), 0.885 (LASSO), 0.88 (GAM), and 0.899 (random forest). Using the random forest results in a slightly higher median DSI compared to the other models. After Bonferroni correction, the hypothesis of equality of median DSI was rejected only when comparing the random forest DSI to the DSI from the logistic (p < 0.001), LASSO (p < 0.001), or GAM (p < 0.001) models. In practical terms the difference between the random forest and the logistic regression is quite small. The correlation (95% CI) between the volume from manual segmentation and the predicted volume was 0.93 (0.9,0.95) for the random forest model. These results indicate that random forest approach can achieve accurate segmentation of ICH in a population of patients from a variety of imaging centers. We provide an R package (https://github.com/muschellij2/ichseg) and a Shiny R application online (http://johnmuschelli.com/ich_segment_all.html) for implementing and testing the proposed approach. AbstractIntroductionIntracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10–15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry by an expert reader is the gold standard for volume estimation, but is time-consuming and has within- and across-reader variability. We propose a fully automated segmentation approach using a random forest algorithm with features extracted from X-ray computed tomography (CT) scans. MethodsThe Minimally Invasive Surgery plus rt-PA in ICH Evacuation (MISTIE) trial was a multi-site Phase II clinical trial that tested the safety of hemorrhage removal using recombinant-tissue plasminogen activator (rt-PA). For this analysis, we use 112 baseline CT scans from patients enrolled in the MISTE trial, one CT scan per patient. ICH was manually segmented on these CT scans by expert readers. We derived a set of imaging predictors from each scan. Using 10 randomly-selected scans, we used a first-pass voxel selection procedure based on quantiles of a set of predictors and then built 4 models estimating the voxel-level probability of ICH. The models used were: 1) logistic regression, 2) logistic regression with a penalty on the model parameters using LASSO, 3) a generalized additive model (GAM) and 4) a random forest classifier. The remaining 102 scans were used for model validation.For each validation scan, the model predicted the probability of ICH at each voxel. These voxel-level probabilities were then thresholded to produce binary segmentations of the hemorrhage. These masks were compared to the manual segmentations using the Dice Similarity Index (DSI) and the correlation of hemorrhage volume of between the two segmentations. We tested equality of median DSI using the Kruskal-Wallis test across the 4 models. We tested equality of the median DSI from sets of 2 models using a Wilcoxon signed-rank test. ResultsAll results presented are for the 102 scans in the validation set. The median DSI for each model was: 0.89 (logistic), 0.885 (LASSO), 0.88 (GAM), and 0.899 (random forest). Using the random forest results in a slightly higher median DSI compared to the other models. After Bonferroni correction, the hypothesis of equality of median DSI was rejected only when comparing the random forest DSI to the DSI from the logistic ( p < 0.001), LASSO ( p < 0.001), or GAM ( p < 0.001) models. In practical terms the difference between the random forest and the logistic regression is quite small. The correlation (95% CI) between the volume from manual segmentation and the predicted volume was 0.93 (0.9,0.95) for the random forest model. These results indicate that random forest approach can achieve accurate segmentation of ICH in a population of patients from a variety of imaging centers. We provide an R package ( https://github.com/muschellij2/ichseg) and a Shiny R application online ( http://johnmuschelli.com/ich_segment_all.html) for implementing and testing the proposed approach. Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10-15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry by an expert reader is the gold standard for volume estimation, but is time-consuming and has within- and across-reader variability. We propose a fully automated segmentation approach using a random forest algorithm with features extracted from X-ray computed tomography (CT) scans. The Minimally Invasive Surgery plus rt-PA in ICH Evacuation (MISTIE) trial was a multi-site Phase II clinical trial that tested the safety of hemorrhage removal using recombinant-tissue plasminogen activator (rt-PA). For this analysis, we use 112 baseline CT scans from patients enrolled in the MISTE trial, one CT scan per patient. ICH was manually segmented on these CT scans by expert readers. We derived a set of imaging predictors from each scan. Using 10 randomly-selected scans, we used a first-pass voxel selection procedure based on quantiles of a set of predictors and then built 4 models estimating the voxel-level probability of ICH. The models used were: 1) logistic regression, 2) logistic regression with a penalty on the model parameters using LASSO, 3) a generalized additive model (GAM) and 4) a random forest classifier. The remaining 102 scans were used for model validation.For each validation scan, the model predicted the probability of ICH at each voxel. These voxel-level probabilities were then thresholded to produce binary segmentations of the hemorrhage. These masks were compared to the manual segmentations using the Dice Similarity Index (DSI) and the correlation of hemorrhage volume of between the two segmentations. We tested equality of median DSI using the Kruskal-Wallis test across the 4 models. We tested equality of the median DSI from sets of 2 models using a Wilcoxon signed-rank test. All results presented are for the 102 scans in the validation set. The median DSI for each model was: 0.89 (logistic), 0.885 (LASSO), 0.88 (GAM), and 0.899 (random forest). Using the random forest results in a slightly higher median DSI compared to the other models. After Bonferroni correction, the hypothesis of equality of median DSI was rejected only when comparing the random forest DSI to the DSI from the logistic ( < 0.001), LASSO ( < 0.001), or GAM ( < 0.001) models. In practical terms the difference between the random forest and the logistic regression is quite small. The correlation (95% CI) between the volume from manual segmentation and the predicted volume was 0.93 (0.9,0.95) for the random forest model. These results indicate that random forest approach can achieve accurate segmentation of ICH in a population of patients from a variety of imaging centers. We provide an R package (https://github.com/muschellij2/ichseg) and a Shiny R application online (http://johnmuschelli.com/ich_segment_all.html) for implementing and testing the proposed approach. Introduction: Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10–15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry by an expert reader is the gold standard for volume estimation, but is time-consuming and has within- and across-reader variability. We propose a fully automated segmentation approach using a random forest algorithm with features extracted from X-ray computed tomography (CT) scans. Methods: The Minimally Invasive Surgery plus rt-PA in ICH Evacuation (MISTIE) trial was a multi-site Phase II clinical trial that tested the safety of hemorrhage removal using recombinant-tissue plasminogen activator (rt-PA). For this analysis, we use 112 baseline CT scans from patients enrolled in the MISTE trial, one CT scan per patient. ICH was manually segmented on these CT scans by expert readers. We derived a set of imaging predictors from each scan. Using 10 randomly-selected scans, we used a first-pass voxel selection procedure based on quantiles of a set of predictors and then built 4 models estimating the voxel-level probability of ICH. The models used were: 1) logistic regression, 2) logistic regression with a penalty on the model parameters using LASSO, 3) a generalized additive model (GAM) and 4) a random forest classifier. The remaining 102 scans were used for model validation.For each validation scan, the model predicted the probability of ICH at each voxel. These voxel-level probabilities were then thresholded to produce binary segmentations of the hemorrhage. These masks were compared to the manual segmentations using the Dice Similarity Index (DSI) and the correlation of hemorrhage volume of between the two segmentations. We tested equality of median DSI using the Kruskal-Wallis test across the 4 models. We tested equality of the median DSI from sets of 2 models using a Wilcoxon signed-rank test. Results: All results presented are for the 102 scans in the validation set. The median DSI for each model was: 0.89 (logistic), 0.885 (LASSO), 0.88 (GAM), and 0.899 (random forest). Using the random forest results in a slightly higher median DSI compared to the other models. After Bonferroni correction, the hypothesis of equality of median DSI was rejected only when comparing the random forest DSI to the DSI from the logistic (p < 0.001), LASSO (p < 0.001), or GAM (p < 0.001) models. In practical terms the difference between the random forest and the logistic regression is quite small. The correlation (95% CI) between the volume from manual segmentation and the predicted volume was 0.93 (0.9,0.95) for the random forest model. These results indicate that random forest approach can achieve accurate segmentation of ICH in a population of patients from a variety of imaging centers. We provide an R package (https://github.com/muschellij2/ichseg) and a Shiny R application online (http://johnmuschelli.com/ich_segment_all.html) for implementing and testing the proposed approach. |
| Author | Vespa, Paul Crainiceanu, Ciprian M. Sweeney, Elizabeth M. Ullman, Natalie L. Hanley, Daniel F. Muschelli, John |
| AuthorAffiliation | c Department of Neurosurgery, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA a Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA b Department of Neurology, Division of Brain Injury Outcomes, Johns Hopkins Medical Institutions, Baltimore, MD, USA |
| AuthorAffiliation_xml | – name: c Department of Neurosurgery, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA – name: a Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA – name: b Department of Neurology, Division of Brain Injury Outcomes, Johns Hopkins Medical Institutions, Baltimore, MD, USA |
| Author_xml | – sequence: 1 givenname: John surname: Muschelli fullname: Muschelli, John email: jmusche1@jhu.edu organization: Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA – sequence: 2 givenname: Elizabeth M. surname: Sweeney fullname: Sweeney, Elizabeth M. email: emsweene1@jhu.edu organization: Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA – sequence: 3 givenname: Natalie L. surname: Ullman fullname: Ullman, Natalie L. email: nullman1@jhmi.edu organization: Department of Neurology, Division of Brain Injury Outcomes, Johns Hopkins Medical Institutions, Baltimore, MD, USA – sequence: 4 givenname: Paul surname: Vespa fullname: Vespa, Paul email: PVespa@mednet.ucla.edu organization: Department of Neurosurgery, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA – sequence: 5 givenname: Daniel F. surname: Hanley fullname: Hanley, Daniel F. email: dhanley@jhmi.edu organization: Department of Neurology, Division of Brain Injury Outcomes, Johns Hopkins Medical Institutions, Baltimore, MD, USA – sequence: 6 givenname: Ciprian M. surname: Crainiceanu fullname: Crainiceanu, Ciprian M. email: ccrainic@jhsph.edu organization: Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/28275541$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kkFvGyEQhVdVqiZN8wd6qPbYix1gYYEcKlWWXVuKVCt1zyMWWAd3DSmsI_nfh42dKKnUcAHBm2_EvPexOPHB26L4jNEYI1xfbsbe6W5MEOZjRMYI8XfFGSG4GmEmyMmL82lxkdIG5SWyqq4_FKdEEM4YxWcFLBe9ni-nNzM7WV2Vy-i2Ku7Lhe-j0lF5p7pybrchxlu1tvk9NKpxnev35TT1Wdy74Mtdcn5d3ihvwrachWhTn8p8P1l9Kt63qkv24rifF79n09VkPrr--WMx-X490ozTfqREwyRppTSSYFkrLrlljeGm0UxobZVsCaMtb6pWNcxwLgimiMumVW1lJK3Oi8WBa4LawN3hGxCUg8eLENegYp8nZoHWGWlbgaRh1JhGUC6Zrlhb24q21mTWtwPrbtdsrdF2GEb3Cvr6xbtbWId7YBURnOIM-HoExPB3l4cBW5e07TrlbdglwILXVOJK1ln65WWv5yZPDmWBOAh0DClF24J2_ePUc2vXAUYw5AE2MOQBhjwAIpCdzqXkn9In-ptFx8_b7Na9sxF057JKdX_s3qZN2EWfjQQMKRfAryFmQ8owrxCieHDi6v-A7IZ7q_sDd3jjbw |
| CitedBy_id | crossref_primary_10_1001_jamanetworkopen_2024_27772 crossref_primary_10_1016_j_cmpb_2020_105546 crossref_primary_10_1088_1361_6560_aba166 crossref_primary_10_1007_s12028_019_00705_8 crossref_primary_10_1111_jon_12997 crossref_primary_10_1016_j_wneu_2024_05_065 crossref_primary_10_1016_j_zemedi_2022_11_009 crossref_primary_10_1016_j_jstrokecerebrovasdis_2021_105996 crossref_primary_10_3389_fneur_2022_791816 crossref_primary_10_1109_ACCESS_2019_2906605 crossref_primary_10_1002_mp_13880 crossref_primary_10_1093_biostatistics_kxx068 crossref_primary_10_1007_s40747_020_00257_x crossref_primary_10_1016_j_hest_2025_04_003 crossref_primary_10_1371_journal_pone_0286485 crossref_primary_10_1016_j_wneu_2022_10_051 crossref_primary_10_1038_s41598_023_30581_4 crossref_primary_10_1016_j_nicl_2021_102785 crossref_primary_10_1186_s41747_024_00510_9 crossref_primary_10_3389_fneur_2021_666875 crossref_primary_10_3390_jcm12124005 crossref_primary_10_3892_etm_2025_12797 crossref_primary_10_2147_IJGM_S408725 crossref_primary_10_1109_ACCESS_2022_3225671 crossref_primary_10_32604_cmc_2023_041855 crossref_primary_10_1007_s12021_020_09493_5 crossref_primary_10_1109_ACCESS_2023_3339560 crossref_primary_10_1007_s00234_024_03311_4 crossref_primary_10_1007_s10278_018_00172_1 crossref_primary_10_1186_s12883_023_03258_8 crossref_primary_10_1016_j_ipm_2020_102352 crossref_primary_10_3389_fneur_2023_1244672 crossref_primary_10_1016_j_hsr_2023_100126 crossref_primary_10_1016_j_nic_2020_07_001 crossref_primary_10_1038_s41598_020_76459_7 crossref_primary_10_1242_dmm_048785 crossref_primary_10_3390_informatics9010004 crossref_primary_10_32604_cmc_2021_015480 crossref_primary_10_1016_j_eswa_2022_118016 crossref_primary_10_3390_data5010014 crossref_primary_10_1038_s41598_019_54491_6 crossref_primary_10_1088_1742_6596_1187_4_042088 crossref_primary_10_1155_2022_3560507 crossref_primary_10_1016_j_wneu_2022_10_105 crossref_primary_10_1049_cit2_12302 crossref_primary_10_1161_STROKEAHA_119_027657 crossref_primary_10_3390_ijerph18126499 crossref_primary_10_1007_s00330_021_08352_4 |
| Cites_doi | 10.1097/00003246-199903000-00045 10.1136/jnnp.2004.044347 10.1161/STROKEAHA.107.512202 10.1007/s11548-012-0670-0 10.1161/01.STR.27.8.1304 10.32614/RJ-2015-013 10.1097/00008506-200307000-00010 10.1161/01.STR.32.4.891 10.1016/j.neuroimage.2012.03.020 10.1002/hbm.10062 10.1016/j.neuroimage.2010.09.025 10.1109/TMI.2014.2377694 10.1161/STROKEAHA.109.561795 10.1161/STROKEAHA.113.001638 10.1016/S1474-4422(08)70069-3 10.1016/j.nicl.2014.03.009 10.1111/j.2517-6161.1996.tb02080.x 10.1007/s12021-011-9109-y 10.1161/STROKEAHA.114.007343 10.1016/j.media.2007.06.004 10.2307/1932409 10.1161/STROKEAHA.110.607861 10.1155/2000/421719 10.1023/A:1010933404324 10.1161/01.STR.24.7.987 10.1111/j.1467-9868.2010.00749.x 10.1016/j.neuroimage.2015.03.074 10.18637/jss.v033.i01 10.1161/STROKEAHA.115.010369 10.1161/STROKEAHA.112.667220 10.1111/j.1552-6569.2011.00588.x 10.1161/STROKEAHA.108.541383 10.1016/j.neuroimage.2011.09.015 10.1056/NEJMoa042991 10.1007/s12028-011-9541-8 10.1161/STROKEAHA.111.000411 10.1016/j.mric.2006.06.002 10.1111/rssc.12068 |
| ContentType | Journal Article |
| Copyright | 2017 The Authors The Authors 2017 The Authors 2017 |
| Copyright_xml | – notice: 2017 The Authors – notice: The Authors – notice: 2017 The Authors 2017 |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7U8 7X8 C1K JXQ 5PM DOA |
| DOI | 10.1016/j.nicl.2017.02.007 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed TOXLINE MEDLINE - Academic Environmental Sciences and Pollution Management Toxline PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) TOXLINE MEDLINE - Academic Environmental Sciences and Pollution Management |
| DatabaseTitleList | TOXLINE MEDLINE |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 2213-1582 |
| EndPage | 390 |
| ExternalDocumentID | oai_doaj_org_article_4658cef809d54ddb84795c35f6e34fed PMC5328741 28275541 10_1016_j_nicl_2017_02_007 1_s2_0_S2213158217300414 S2213158217300414 |
| Genre | Multicenter Study Clinical Trial, Phase II Journal Article |
| GrantInformation_xml | – fundername: NHLBI NIH HHS grantid: R01 HL123407 – fundername: NINDS NIH HHS grantid: U01 NS062851 – fundername: NINDS NIH HHS grantid: R01 NS085211 – fundername: NINDS NIH HHS grantid: R01 NS060910 – fundername: NIA NIH HHS grantid: T32 AG000247 – fundername: NINDS NIH HHS grantid: U01 NS080824 – fundername: NIMH NIH HHS grantid: R01 MH095836 – fundername: NIBIB NIH HHS grantid: R01 EB012547 – fundername: NINDS NIH HHS grantid: R01 NS046309 |
| GroupedDBID | .1- .FO 0R~ 1P~ 457 53G 5VS AAEDT AAEDW AAIKJ AALRI AAXUO AAYWO ABMAC ACGFS ACVFH ADBBV ADCNI ADEZE ADRAZ ADVLN AEUPX AEXQZ AFJKZ AFPUW AFRHN AFTJW AGHFR AIGII AITUG AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ AOIJS APXCP BAWUL BCNDV DIK EBS EJD FDB GROUPED_DOAJ HYE HZ~ IPNFZ IXB KQ8 M41 M48 M~E O-L O9- OK1 RIG ROL RPM SSZ Z5R AFCTW AAYXX CITATION CGR CUY CVF ECM EIF NPM 7U8 7X8 C1K JXQ 5PM |
| ID | FETCH-LOGICAL-c574t-a8b592f99d92196a797e5bd7dbc58ccea9f254f7b3fab5d778214079bfaf3d943 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 57 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000405984300041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2213-1582 |
| IngestDate | Fri Oct 03 12:38:01 EDT 2025 Tue Sep 30 16:46:36 EDT 2025 Fri Sep 05 11:53:39 EDT 2025 Mon Jul 21 06:05:59 EDT 2025 Tue Nov 18 22:18:35 EST 2025 Wed Nov 05 20:47:57 EST 2025 Wed Jun 18 06:48:26 EDT 2025 Tue Aug 26 17:37:56 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | C |
| Keywords | CT Stroke ICH segmentation Intracerebral hemorrhage |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c574t-a8b592f99d92196a797e5bd7dbc58ccea9f254f7b3fab5d778214079bfaf3d943 |
| Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
| OpenAccessLink | https://doaj.org/article/4658cef809d54ddb84795c35f6e34fed |
| PMID | 28275541 |
| PQID | 1876491396 |
| PQPubID | 23479 |
| PageCount | 12 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_4658cef809d54ddb84795c35f6e34fed pubmedcentral_primary_oai_pubmedcentral_nih_gov_5328741 proquest_miscellaneous_1876491396 pubmed_primary_28275541 crossref_citationtrail_10_1016_j_nicl_2017_02_007 crossref_primary_10_1016_j_nicl_2017_02_007 elsevier_clinicalkeyesjournals_1_s2_0_S2213158217300414 elsevier_clinicalkey_doi_10_1016_j_nicl_2017_02_007 |
| PublicationCentury | 2000 |
| PublicationDate | 2017-01-01 |
| PublicationDateYYYYMMDD | 2017-01-01 |
| PublicationDate_xml | – month: 01 year: 2017 text: 2017-01-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | NeuroImage clinical |
| PublicationTitleAlternate | Neuroimage Clin |
| PublicationYear | 2017 |
| Publisher | Elsevier Inc Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier |
| References | Pedraza, Puig, Blasco, Daunis-i Estadella, Boada, Bardera, Castellanos, Serena (bb0175) 2012; 22 Wood (bb0255) 2011; 73 Sahni, Weinberger (bb0220) 2007; 3 Rorden, Bonilha, Fridriksson, Bender, Karnath (bb0205) 2012; 61 Prakash, Zhou, Morgan, Hanley, Nowinski (bb0190) 2012; 7 Kothari, Brott, Broderick, Barsan, Sauerbeck, Zuccarello, Khoury (bb0115) 1996; 27 Smith, Rosand, Greenberg (bb0225) 2006; 14 Bergström, Ericson, Levander, Svendsen, Larsson (bb0035) 1977; 1 Wang, Lou, Liu, Cui, Chen, Wang (bb0245) 2013; 44 Menze, Jakab, Bauer, Kalpathy-Cramer, Farahani, Kirby, Burren, Porz, Slotboom, Wiest (bb0140) 2015; 34 Hastie, Tibshirani (bb0090) 1990; 43 Muschelli, Sweeney, Lindquist, Crainiceanu (bb0160) 2015; 7 Smith (bb0230) 2002; 17 Loncaric, Cosic, Dhawan (bb0125) 1996; 10 Muschelli, Ullman, Mould, Vespa, Hanley, Crainiceanu (bb0165) 2015 Avants, Tustison, Song, Cook, Klein, Gee (bb0025) 2011; 54 Rost, Smith, Chang, Snider, Chanderraj, Schwab, FitzMaurice, Wendell, Goldstein, Greenberg, Rosand (bb0215) 2008; 39 Jenkinson, Beckmann, Behrens, Woolrich, Smith (bb0105) 2012; 62 Tuhrim, Horowitz, Sacher, Godbold (bb0240) 1999; 27 Jordan, Kleinman, Hillis (bb0110) 2009; 40 Muschelli, Ullman, Sweeney, Eloyan, Martin, Vespa, Hanley, Crainiceanu (bb0170) 2015; 46 Broderick, Brott, Duldner, Tomsick, Huster (bb0045) 1993; 24 Anderson, Huang, Arima, Heeley, Skulina, Parsons, Peng, Li, Su, Tao, Li, Jiang, Tai, Zhang, Xu, Cheng, Morgenstern, Chalmers, Wang (bb0010) 2010; 41 . Mayer, Brun, Begtrup, Broderick, Davis, Diringer, Skolnick, Steiner (bb0135) 2005; 352 Avants, Epstein, Grossman, Gee (bb0020) 2008; 12 Hastie, Tibshirani (bb0085) 1986 Dice (bb0065) 1945; 26 Anderson, Huang, Wang, Arima, Neal, Peng, Heeley, Skulina, Parsons, Kim (bb0015) 2008; 7 Hussein, Tariq, Palesch, Qureshi (bb0100) 2013; 44 Wood, Goude, Shaw (bb0260) 2015; 64 Hemphill, Bonovich, Besmertis, Manley, Johnston (bb0095) 2001; 32 Qureshi, Palesch, Martin, Novitzke, Cruz-Flores, Ehtisham, Ezzeddine, Goldstein, Kirmani, Hussein, Suri, Tariq, Liu, Investigators (bb0195) 2011; 15 Breiman (bb0040) 2001; 45 Chang, Cheng, Allaire, Xie, McPherson (bb0060) 2015 Mould, Carhuapoma, Muschelli, Lane, Morgan, McBee, Bistran-Hall, Ullman, Vespa, Martin, Awad, Zuccarello, Hanley (bb0155) 2013; 44 Gillebert, Humphreys, Mantini (bb0080) 2014; 4 Liaw, Wiener (bb0120) 2002; 2 Pérez, Valdés, Guevara, Rodríguez, Molina (bb0180) 2007 Morgan, Zuccarello, Narayan, Keyl, Lane, Hanley (bb0150) 2008 Divani, Majidi, Luo, Souslian, Zhang, Abosch, Tummala (bb0070) 2011; 42 Carhuapoma, Hanley, Banerjee, Beauchamp (bb0050) 2003; 15 Core Team (bb0200) 2015 Rorden, Brett (bb0210) 2000; 12 Loncaric, Dhawan, Cosic, Kovacević, Broderick, Brott (bb0130) 1999 Castellanos, Leira, Tejada, Gil-Peralta, Dàvalos, Castillo (bb0055) 2005; 76 Tibshirani (bb0235) 1996; 58 Frequently Asked Questions for FLIRT. Webb, Ullman, Morgan, Muschelli, Kornbluth, Awad, Mayo, Rosenblum, Ziai, Zuccarrello, Aldrich, John, Harnof, Lopez, Broaddus, Wijman, Vespa, Bullock, Haines, Cruz-Flores, Tuhrim, Hill, Narayan, Hanley, Tayal, Diaz, Hoffer, Moheet, Agarwal, Markowski, Rosenthal, Kureshi (bb0250) 2015; 46 Perona, Shiota, Malik (bb0185) 1994 Avants, Tustison, Wu, Cook, Gee (bb0030) 2011; 9 Friedman, Hastie, Tibshirani (bb0075) 2010; 33 Morgan, Awad, Keyl, Lane, Hanley (bb0145) 2008 Avants (10.1016/j.nicl.2017.02.007_bb0030) 2011; 9 Menze (10.1016/j.nicl.2017.02.007_bb0140) 2015; 34 Pérez (10.1016/j.nicl.2017.02.007_bb0180) 2007 Avants (10.1016/j.nicl.2017.02.007_bb0025) 2011; 54 Kothari (10.1016/j.nicl.2017.02.007_bb0115) 1996; 27 Rost (10.1016/j.nicl.2017.02.007_bb0215) 2008; 39 Chang (10.1016/j.nicl.2017.02.007_bb0060) 2015 Hemphill (10.1016/j.nicl.2017.02.007_bb0095) 2001; 32 Tuhrim (10.1016/j.nicl.2017.02.007_bb0240) 1999; 27 Dice (10.1016/j.nicl.2017.02.007_bb0065) 1945; 26 Anderson (10.1016/j.nicl.2017.02.007_bb0015) 2008; 7 Avants (10.1016/j.nicl.2017.02.007_bb0020) 2008; 12 Castellanos (10.1016/j.nicl.2017.02.007_bb0055) 2005; 76 Hastie (10.1016/j.nicl.2017.02.007_bb0090) 1990; 43 Loncaric (10.1016/j.nicl.2017.02.007_bb0125) 1996; 10 Bergström (10.1016/j.nicl.2017.02.007_bb0035) 1977; 1 Muschelli (10.1016/j.nicl.2017.02.007_bb0170) 2015; 46 Prakash (10.1016/j.nicl.2017.02.007_bb0190) 2012; 7 Muschelli (10.1016/j.nicl.2017.02.007_bb0165) 2015 Hussein (10.1016/j.nicl.2017.02.007_bb0100) 2013; 44 Loncaric (10.1016/j.nicl.2017.02.007_bb0130) 1999 Webb (10.1016/j.nicl.2017.02.007_bb0250) 2015; 46 Mould (10.1016/j.nicl.2017.02.007_bb0155) 2013; 44 Muschelli (10.1016/j.nicl.2017.02.007_bb0160) 2015; 7 Jordan (10.1016/j.nicl.2017.02.007_bb0110) 2009; 40 Carhuapoma (10.1016/j.nicl.2017.02.007_bb0050) 2003; 15 Gillebert (10.1016/j.nicl.2017.02.007_bb0080) 2014; 4 Broderick (10.1016/j.nicl.2017.02.007_bb0045) 1993; 24 Qureshi (10.1016/j.nicl.2017.02.007_bb0195) 2011; 15 10.1016/j.nicl.2017.02.007_bb0005 Tibshirani (10.1016/j.nicl.2017.02.007_bb0235) 1996; 58 Rorden (10.1016/j.nicl.2017.02.007_bb0210) 2000; 12 Wood (10.1016/j.nicl.2017.02.007_bb0260) 2015; 64 Sahni (10.1016/j.nicl.2017.02.007_bb0220) 2007; 3 Wood (10.1016/j.nicl.2017.02.007_bb0255) 2011; 73 Core Team (10.1016/j.nicl.2017.02.007_bb0200) 2015 Divani (10.1016/j.nicl.2017.02.007_bb0070) 2011; 42 Mayer (10.1016/j.nicl.2017.02.007_bb0135) 2005; 352 Breiman (10.1016/j.nicl.2017.02.007_bb0040) 2001; 45 Anderson (10.1016/j.nicl.2017.02.007_bb0010) 2010; 41 Friedman (10.1016/j.nicl.2017.02.007_bb0075) 2010; 33 Rorden (10.1016/j.nicl.2017.02.007_bb0205) 2012; 61 Smith (10.1016/j.nicl.2017.02.007_bb0230) 2002; 17 Hastie (10.1016/j.nicl.2017.02.007_bb0085) 1986 Smith (10.1016/j.nicl.2017.02.007_bb0225) 2006; 14 Liaw (10.1016/j.nicl.2017.02.007_bb0120) 2002; 2 Wang (10.1016/j.nicl.2017.02.007_bb0245) 2013; 44 Perona (10.1016/j.nicl.2017.02.007_bb0185) 1994 Pedraza (10.1016/j.nicl.2017.02.007_bb0175) 2012; 22 Jenkinson (10.1016/j.nicl.2017.02.007_bb0105) 2012; 62 Morgan (10.1016/j.nicl.2017.02.007_bb0145) 2008 Morgan (10.1016/j.nicl.2017.02.007_bb0150) 2008 |
| References_xml | – volume: 45 start-page: 5 year: 2001 end-page: 32 ident: bb0040 article-title: Random forests publication-title: Mach. Learn. – volume: 46 start-page: 3270 year: 2015 end-page: 3273 ident: bb0170 article-title: Quantitative intracerebral hemorrhage localization publication-title: Stroke – volume: 61 start-page: 957 year: 2012 end-page: 965 ident: bb0205 article-title: Age-specific CT and MRI templates for spatial normalization publication-title: NeuroImage – volume: 44 start-page: 237 year: 2013 end-page: 239 ident: bb0100 article-title: Reliability of hematoma volume measurement at local sites in a multicenter acute intracerebral hemorrhage clinical trial publication-title: Stroke – volume: 62 start-page: 782 year: 2012 end-page: 790 ident: bb0105 article-title: FSL publication-title: NeuroImage – volume: 7 start-page: 785 year: 2012 end-page: 798 ident: bb0190 article-title: Segmentation and quantification of intra-ventricular/cerebral hemorrhage in CT scans by modified distance regularized level set evolution technique publication-title: Int. J. Comput. Assist. Radiol. Surg. – volume: 4 start-page: 540 year: 2014 end-page: 548 ident: bb0080 article-title: Automated delineation of stroke lesions using brain CT images publication-title: NeuroImage Clin. – volume: 43 year: 1990 ident: bb0090 article-title: Generalized Additive Models – volume: 54 start-page: 2033 year: 2011 end-page: 2044 ident: bb0025 article-title: A reproducible evaluation of ANTs similarity metric performance in brain image registration publication-title: NeuroImage – volume: 15 start-page: 428 year: 2011 end-page: 435 ident: bb0195 article-title: Association of serum glucose concentrations during acute hospitalization with hematoma expansion, perihematomal edema, and three month outcome among patients with intracerebral hemorrhage publication-title: Neurocrit. Care – start-page: 212 year: 2007 end-page: 220 ident: bb0180 article-title: Set of methods for spontaneous ICH segmentation and tracking from CT head images publication-title: Progress in Pattern Recognition, Image Analysis and Applications – volume: 27 start-page: 1304 year: 1996 end-page: 1305 ident: bb0115 article-title: The ABCs of measuring intracerebral hemorrhage volumes publication-title: Stroke – volume: 10 start-page: 1109 year: 1996 ident: bb0125 article-title: Hierarchical segmentation of CT head images publication-title: Proc IEEE EMBS – volume: 17 start-page: 143 year: 2002 end-page: 155 ident: bb0230 article-title: Fast robust automated brain extraction publication-title: Hum. Brain Mapp. – volume: 76 start-page: 691 year: 2005 end-page: 695 ident: bb0055 article-title: Predictors of good outcome in medium to large spontaneous supratentorial intracerebral haemorrhages publication-title: J. Neurol. Neurosurg. Psychiatry – volume: 44 start-page: 627 year: 2013 end-page: 634 ident: bb0155 article-title: Minimally invasive surgery plus recombinant tissue-type plasminogen activator for intracerebral hemorrhage evacuation decreases perihematomal edema publication-title: Stroke – volume: 9 start-page: 381 year: 2011 end-page: 400 ident: bb0030 article-title: An open source multivariate framework for n-tissue segmentation with evaluation on public data publication-title: Neuroinformatics – volume: 7 start-page: 391 year: 2008 end-page: 399 ident: bb0015 article-title: Intensive blood pressure reduction in acute cerebral haemorrhage trial (INTERACT): a randomised pilot trial publication-title: Lancet Neurol. – year: 2015 ident: bb0200 article-title: R: a language and environment for statistical computing publication-title: R Foundation for Statistical Computing, Vienna, Austria – volume: 2 start-page: 18 year: 2002 end-page: 22 ident: bb0120 article-title: Classification and regression by randomforest publication-title: R News – volume: 3 start-page: 701 year: 2007 end-page: 709 ident: bb0220 article-title: Management of intracerebral hemorrhage publication-title: Vasc. Health Risk Manag. – volume: 27 start-page: 617 year: 1999 end-page: 621 ident: bb0240 article-title: Volume of ventricular blood is an important determinant of outcome in supratentorial intracerebral hemorrhage publication-title: Crit. Care Med. – volume: 26 start-page: 297 year: 1945 end-page: 302 ident: bb0065 article-title: Measures of the amount of ecologic association between species publication-title: Ecology – volume: 39 start-page: 2304 year: 2008 end-page: 2309 ident: bb0215 article-title: Prediction of functional outcome in patients with primary intracerebral hemorrhage the FUNC score publication-title: Stroke – volume: 33 start-page: 1 year: 2010 end-page: 22 ident: bb0075 article-title: Regularization paths for generalized linear models via coordinate descent publication-title: J. Stat. Softw. – volume: 34 start-page: 1993 year: 2015 end-page: 2024 ident: bb0140 article-title: The multimodal brain tumor image segmentation benchmark (BRATS) publication-title: IEEE Trans. Med. Imaging – volume: 64 start-page: 139 year: 2015 end-page: 155 ident: bb0260 article-title: Generalized additive models for large data sets publication-title: J. R. Stat. Soc.: Ser. C: Appl. Stat. – start-page: 886 year: 1999 end-page: 894 ident: bb0130 article-title: Quantitative intracerebral brain hemorrhage analysis publication-title: Medical Imaging’99 – volume: 44 start-page: 2315 year: 2013 end-page: 2317 ident: bb0245 article-title: Hematoma volume measurement in gradient echo MRI using quantitative susceptibility mapping publication-title: Stroke – volume: 1 start-page: 57 year: 1977 end-page: 63 ident: bb0035 article-title: Variation with time of the attenuation values of intracranial hematomas publication-title: Stroke – year: 2015 ident: bb0060 article-title: Shiny: Web Application Framework for R – volume: 41 start-page: 307 year: 2010 end-page: 312 ident: bb0010 article-title: Effects of early intensive blood pressure-lowering treatment on the growth of hematoma and perihematomal edema in acute intracerebral hemorrhage the intensive blood pressure reduction in acute cerebral haemorrhage trial (INTERACT) publication-title: Stroke – volume: 12 start-page: 26 year: 2008 end-page: 41 ident: bb0020 article-title: Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain publication-title: Med. Image Anal. – start-page: 217 year: 2008 end-page: 220 ident: bb0145 article-title: Preliminary report of the clot lysis evaluating accelerated resolution of intraventricular hemorrhage (CLEAR-IVH) clinical trial publication-title: Cerebral Hemorrhage – volume: 73 start-page: 3 year: 2011 end-page: 36 ident: bb0255 article-title: Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models publication-title: J. R. Stat. Soc. Ser. B Stat Methodol. – volume: 352 start-page: 777 year: 2005 end-page: 785 ident: bb0135 article-title: Recombinant activated factor VII for acute intracerebral hemorrhage publication-title: N. Engl. J. Med. – start-page: 147 year: 2008 end-page: 151 ident: bb0150 article-title: Preliminary findings of the minimally-invasive surgery plus rtPA for intracerebral hemorrhage evacuation (MISTIE) clinical trial publication-title: Cerebral Hemorrhage – volume: 7 start-page: 163 year: 2015 end-page: 175 ident: bb0160 article-title: FSLR: connecting the FSL software with R publication-title: R J. – volume: 46 start-page: 2470 year: 2015 end-page: 2476 ident: bb0250 article-title: Accuracy of the ABC/2 score for intracerebral hemorrhage systematic review and analysis of MISTIE, CLEAR-IVH, and CLEAR III publication-title: Stroke – volume: 14 start-page: 127 year: 2006 end-page: 140 ident: bb0225 article-title: Imaging of hemorrhagic stroke publication-title: Magn. Reson. Imaging Clin. N. Am. – start-page: 73 year: 1994 end-page: 92 ident: bb0185 article-title: Anisotropic diffusion publication-title: Geometry-driven Diffusion in Computer Vision – volume: 40 start-page: 1666 year: 2009 end-page: 1671 ident: bb0110 article-title: Intracerebral hemorrhage volume predicts poor neurologic outcome in children publication-title: Stroke – volume: 42 start-page: 1569 year: 2011 end-page: 1574 ident: bb0070 article-title: The ABCs of accurate volumetric measurement of cerebral hematoma publication-title: Stroke – volume: 32 start-page: 891 year: 2001 end-page: 897 ident: bb0095 article-title: The ICH score a simple, reliable grading scale for intracerebral hemorrhage publication-title: Stroke – volume: 15 start-page: 230 year: 2003 end-page: 233 ident: bb0050 article-title: Brain edema after human cerebral hemorrhage a magnetic resonance imaging volumetric analysis publication-title: J. Neurosurg. Anesthesiol. – volume: 12 start-page: 191 year: 2000 end-page: 200 ident: bb0210 article-title: Stereotaxic display of brain lesions publication-title: Behav. Neurol. – reference: Frequently Asked Questions for FLIRT. – reference: . – year: 2015 ident: bb0165 article-title: Validated automatic brain extraction of head CT images publication-title: NeuroImage – volume: 58 start-page: 267 year: 1996 end-page: 288 ident: bb0235 article-title: Regression shrinkage and selection via the lasso publication-title: J. R. Stat. Soc. Ser. B Methodol. – volume: 24 start-page: 987 year: 1993 end-page: 993 ident: bb0045 article-title: Volume of intracerebral hemorrhage. A powerful and easy-to-use predictor of 30-day mortality publication-title: Stroke – start-page: 297 year: 1986 end-page: 310 ident: bb0085 article-title: Generalized additive models publication-title: Stat. Sci. – volume: 22 start-page: 155 year: 2012 end-page: 159 ident: bb0175 article-title: Reliability of the ABC/2 method in determining acute infarct volume publication-title: J. Neuroimaging – start-page: 212 year: 2007 ident: 10.1016/j.nicl.2017.02.007_bb0180 article-title: Set of methods for spontaneous ICH segmentation and tracking from CT head images – volume: 27 start-page: 617 issue: 3 year: 1999 ident: 10.1016/j.nicl.2017.02.007_bb0240 article-title: Volume of ventricular blood is an important determinant of outcome in supratentorial intracerebral hemorrhage publication-title: Crit. Care Med. doi: 10.1097/00003246-199903000-00045 – volume: 76 start-page: 691 issue: 5 year: 2005 ident: 10.1016/j.nicl.2017.02.007_bb0055 article-title: Predictors of good outcome in medium to large spontaneous supratentorial intracerebral haemorrhages publication-title: J. Neurol. Neurosurg. Psychiatry doi: 10.1136/jnnp.2004.044347 – volume: 39 start-page: 2304 issue: 8 year: 2008 ident: 10.1016/j.nicl.2017.02.007_bb0215 article-title: Prediction of functional outcome in patients with primary intracerebral hemorrhage the FUNC score publication-title: Stroke doi: 10.1161/STROKEAHA.107.512202 – volume: 7 start-page: 785 issue: 5 year: 2012 ident: 10.1016/j.nicl.2017.02.007_bb0190 article-title: Segmentation and quantification of intra-ventricular/cerebral hemorrhage in CT scans by modified distance regularized level set evolution technique publication-title: Int. J. Comput. Assist. Radiol. Surg. doi: 10.1007/s11548-012-0670-0 – volume: 27 start-page: 1304 issue: 8 year: 1996 ident: 10.1016/j.nicl.2017.02.007_bb0115 article-title: The ABCs of measuring intracerebral hemorrhage volumes publication-title: Stroke doi: 10.1161/01.STR.27.8.1304 – start-page: 217 year: 2008 ident: 10.1016/j.nicl.2017.02.007_bb0145 article-title: Preliminary report of the clot lysis evaluating accelerated resolution of intraventricular hemorrhage (CLEAR-IVH) clinical trial – volume: 10 start-page: 1109 year: 1996 ident: 10.1016/j.nicl.2017.02.007_bb0125 article-title: Hierarchical segmentation of CT head images publication-title: Proc IEEE EMBS – volume: 7 start-page: 163 issue: 1 year: 2015 ident: 10.1016/j.nicl.2017.02.007_bb0160 article-title: FSLR: connecting the FSL software with R publication-title: R J. doi: 10.32614/RJ-2015-013 – volume: 15 start-page: 230 issue: 3 year: 2003 ident: 10.1016/j.nicl.2017.02.007_bb0050 article-title: Brain edema after human cerebral hemorrhage a magnetic resonance imaging volumetric analysis publication-title: J. Neurosurg. Anesthesiol. doi: 10.1097/00008506-200307000-00010 – volume: 32 start-page: 891 issue: 4 year: 2001 ident: 10.1016/j.nicl.2017.02.007_bb0095 article-title: The ICH score a simple, reliable grading scale for intracerebral hemorrhage publication-title: Stroke doi: 10.1161/01.STR.32.4.891 – volume: 61 start-page: 957 issue: 4 year: 2012 ident: 10.1016/j.nicl.2017.02.007_bb0205 article-title: Age-specific CT and MRI templates for spatial normalization publication-title: NeuroImage doi: 10.1016/j.neuroimage.2012.03.020 – volume: 17 start-page: 143 issue: 3 year: 2002 ident: 10.1016/j.nicl.2017.02.007_bb0230 article-title: Fast robust automated brain extraction publication-title: Hum. Brain Mapp. doi: 10.1002/hbm.10062 – volume: 54 start-page: 2033 issue: 3 year: 2011 ident: 10.1016/j.nicl.2017.02.007_bb0025 article-title: A reproducible evaluation of ANTs similarity metric performance in brain image registration publication-title: NeuroImage doi: 10.1016/j.neuroimage.2010.09.025 – volume: 34 start-page: 1993 issue: 10 year: 2015 ident: 10.1016/j.nicl.2017.02.007_bb0140 article-title: The multimodal brain tumor image segmentation benchmark (BRATS) publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2014.2377694 – volume: 41 start-page: 307 issue: 2 year: 2010 ident: 10.1016/j.nicl.2017.02.007_bb0010 article-title: Effects of early intensive blood pressure-lowering treatment on the growth of hematoma and perihematomal edema in acute intracerebral hemorrhage the intensive blood pressure reduction in acute cerebral haemorrhage trial (INTERACT) publication-title: Stroke doi: 10.1161/STROKEAHA.109.561795 – start-page: 886 year: 1999 ident: 10.1016/j.nicl.2017.02.007_bb0130 article-title: Quantitative intracerebral brain hemorrhage analysis – volume: 44 start-page: 2315 issue: 8 year: 2013 ident: 10.1016/j.nicl.2017.02.007_bb0245 article-title: Hematoma volume measurement in gradient echo MRI using quantitative susceptibility mapping publication-title: Stroke doi: 10.1161/STROKEAHA.113.001638 – volume: 7 start-page: 391 issue: 5 year: 2008 ident: 10.1016/j.nicl.2017.02.007_bb0015 article-title: Intensive blood pressure reduction in acute cerebral haemorrhage trial (INTERACT): a randomised pilot trial publication-title: Lancet Neurol. doi: 10.1016/S1474-4422(08)70069-3 – volume: 4 start-page: 540 year: 2014 ident: 10.1016/j.nicl.2017.02.007_bb0080 article-title: Automated delineation of stroke lesions using brain CT images publication-title: NeuroImage Clin. doi: 10.1016/j.nicl.2014.03.009 – volume: 58 start-page: 267 issue: 1 year: 1996 ident: 10.1016/j.nicl.2017.02.007_bb0235 article-title: Regression shrinkage and selection via the lasso publication-title: J. R. Stat. Soc. Ser. B Methodol. doi: 10.1111/j.2517-6161.1996.tb02080.x – volume: 1 start-page: 57 issue: 1 year: 1977 ident: 10.1016/j.nicl.2017.02.007_bb0035 article-title: Variation with time of the attenuation values of intracranial hematomas publication-title: Stroke – volume: 3 start-page: 701 issue: 5 year: 2007 ident: 10.1016/j.nicl.2017.02.007_bb0220 article-title: Management of intracerebral hemorrhage publication-title: Vasc. Health Risk Manag. – start-page: 147 year: 2008 ident: 10.1016/j.nicl.2017.02.007_bb0150 article-title: Preliminary findings of the minimally-invasive surgery plus rtPA for intracerebral hemorrhage evacuation (MISTIE) clinical trial – volume: 43 year: 1990 ident: 10.1016/j.nicl.2017.02.007_bb0090 – volume: 9 start-page: 381 issue: 4 year: 2011 ident: 10.1016/j.nicl.2017.02.007_bb0030 article-title: An open source multivariate framework for n-tissue segmentation with evaluation on public data publication-title: Neuroinformatics doi: 10.1007/s12021-011-9109-y – volume: 46 start-page: 2470 issue: 9 year: 2015 ident: 10.1016/j.nicl.2017.02.007_bb0250 article-title: Accuracy of the ABC/2 score for intracerebral hemorrhage systematic review and analysis of MISTIE, CLEAR-IVH, and CLEAR III publication-title: Stroke doi: 10.1161/STROKEAHA.114.007343 – year: 2015 ident: 10.1016/j.nicl.2017.02.007_bb0060 – volume: 12 start-page: 26 issue: 1 year: 2008 ident: 10.1016/j.nicl.2017.02.007_bb0020 article-title: Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain publication-title: Med. Image Anal. doi: 10.1016/j.media.2007.06.004 – volume: 26 start-page: 297 issue: 3 year: 1945 ident: 10.1016/j.nicl.2017.02.007_bb0065 article-title: Measures of the amount of ecologic association between species publication-title: Ecology doi: 10.2307/1932409 – volume: 42 start-page: 1569 issue: 6 year: 2011 ident: 10.1016/j.nicl.2017.02.007_bb0070 article-title: The ABCs of accurate volumetric measurement of cerebral hematoma publication-title: Stroke doi: 10.1161/STROKEAHA.110.607861 – year: 2015 ident: 10.1016/j.nicl.2017.02.007_bb0200 article-title: R: a language and environment for statistical computing – ident: 10.1016/j.nicl.2017.02.007_bb0005 – volume: 12 start-page: 191 issue: 4 year: 2000 ident: 10.1016/j.nicl.2017.02.007_bb0210 article-title: Stereotaxic display of brain lesions publication-title: Behav. Neurol. doi: 10.1155/2000/421719 – volume: 2 start-page: 18 issue: 3 year: 2002 ident: 10.1016/j.nicl.2017.02.007_bb0120 article-title: Classification and regression by randomforest publication-title: R News – start-page: 73 year: 1994 ident: 10.1016/j.nicl.2017.02.007_bb0185 article-title: Anisotropic diffusion – volume: 45 start-page: 5 issue: 1 year: 2001 ident: 10.1016/j.nicl.2017.02.007_bb0040 article-title: Random forests publication-title: Mach. Learn. doi: 10.1023/A:1010933404324 – volume: 24 start-page: 987 issue: 7 year: 1993 ident: 10.1016/j.nicl.2017.02.007_bb0045 article-title: Volume of intracerebral hemorrhage. A powerful and easy-to-use predictor of 30-day mortality publication-title: Stroke doi: 10.1161/01.STR.24.7.987 – volume: 73 start-page: 3 issue: 1 year: 2011 ident: 10.1016/j.nicl.2017.02.007_bb0255 article-title: Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models publication-title: J. R. Stat. Soc. Ser. B Stat Methodol. doi: 10.1111/j.1467-9868.2010.00749.x – year: 2015 ident: 10.1016/j.nicl.2017.02.007_bb0165 article-title: Validated automatic brain extraction of head CT images publication-title: NeuroImage doi: 10.1016/j.neuroimage.2015.03.074 – volume: 33 start-page: 1 issue: 1 year: 2010 ident: 10.1016/j.nicl.2017.02.007_bb0075 article-title: Regularization paths for generalized linear models via coordinate descent publication-title: J. Stat. Softw. doi: 10.18637/jss.v033.i01 – volume: 46 start-page: 3270 issue: 11 year: 2015 ident: 10.1016/j.nicl.2017.02.007_bb0170 article-title: Quantitative intracerebral hemorrhage localization publication-title: Stroke doi: 10.1161/STROKEAHA.115.010369 – volume: 44 start-page: 237 issue: 1 year: 2013 ident: 10.1016/j.nicl.2017.02.007_bb0100 article-title: Reliability of hematoma volume measurement at local sites in a multicenter acute intracerebral hemorrhage clinical trial publication-title: Stroke doi: 10.1161/STROKEAHA.112.667220 – volume: 22 start-page: 155 issue: 2 year: 2012 ident: 10.1016/j.nicl.2017.02.007_bb0175 article-title: Reliability of the ABC/2 method in determining acute infarct volume publication-title: J. Neuroimaging doi: 10.1111/j.1552-6569.2011.00588.x – volume: 40 start-page: 1666 issue: 5 year: 2009 ident: 10.1016/j.nicl.2017.02.007_bb0110 article-title: Intracerebral hemorrhage volume predicts poor neurologic outcome in children publication-title: Stroke doi: 10.1161/STROKEAHA.108.541383 – volume: 62 start-page: 782 issue: 2 year: 2012 ident: 10.1016/j.nicl.2017.02.007_bb0105 article-title: FSL publication-title: NeuroImage doi: 10.1016/j.neuroimage.2011.09.015 – start-page: 297 year: 1986 ident: 10.1016/j.nicl.2017.02.007_bb0085 article-title: Generalized additive models publication-title: Stat. Sci. – volume: 352 start-page: 777 issue: 8 year: 2005 ident: 10.1016/j.nicl.2017.02.007_bb0135 article-title: Recombinant activated factor VII for acute intracerebral hemorrhage publication-title: N. Engl. J. Med. doi: 10.1056/NEJMoa042991 – volume: 15 start-page: 428 issue: 3 year: 2011 ident: 10.1016/j.nicl.2017.02.007_bb0195 article-title: Association of serum glucose concentrations during acute hospitalization with hematoma expansion, perihematomal edema, and three month outcome among patients with intracerebral hemorrhage publication-title: Neurocrit. Care doi: 10.1007/s12028-011-9541-8 – volume: 44 start-page: 627 issue: 3 year: 2013 ident: 10.1016/j.nicl.2017.02.007_bb0155 article-title: Minimally invasive surgery plus recombinant tissue-type plasminogen activator for intracerebral hemorrhage evacuation decreases perihematomal edema publication-title: Stroke doi: 10.1161/STROKEAHA.111.000411 – volume: 14 start-page: 127 issue: 2 year: 2006 ident: 10.1016/j.nicl.2017.02.007_bb0225 article-title: Imaging of hemorrhagic stroke publication-title: Magn. Reson. Imaging Clin. N. Am. doi: 10.1016/j.mric.2006.06.002 – volume: 64 start-page: 139 issue: 1 year: 2015 ident: 10.1016/j.nicl.2017.02.007_bb0260 article-title: Generalized additive models for large data sets publication-title: J. R. Stat. Soc.: Ser. C: Appl. Stat. doi: 10.1111/rssc.12068 |
| SSID | ssj0000800766 |
| Score | 2.3453097 |
| Snippet | Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10–15% of all strokes. X-ray computed... AbstractIntroductionIntracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10–15% of all strokes.... Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10-15% of all strokes. X-ray computed... INTRODUCTIONIntracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10-15% of all strokes. X-ray... • A hemorrhage segmentation algorithm from CT scans is proposed. • Validation using manual segmentation was done on 102 patients from multiple sites. •... Introduction: Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10–15% of all strokes. X-ray... |
| SourceID | doaj pubmedcentral proquest pubmed crossref elsevier |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 379 |
| SubjectTerms | Adolescent Adult Aged Aged, 80 and over Algorithms Brain - diagnostic imaging Brain - drug effects Brain - surgery Female Humans ICH segmentation Image Processing, Computer-Assisted Intracerebral hemorrhage Intracranial Hemorrhages - diagnostic imaging Intracranial Hemorrhages - drug therapy Intracranial Hemorrhages - surgery Logistic Models Male Middle Aged Minimally Invasive Surgical Procedures - methods Outcome Assessment, Health Care Probability Radiology Regular Stroke Tissue Plasminogen Activator - therapeutic use Tomography, X-Ray Computed Young Adult |
| Title | PItcHPERFeCT: Primary Intracranial Hemorrhage Probability Estimation using Random Forests on CT |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S2213158217300414 https://www.clinicalkey.es/playcontent/1-s2.0-S2213158217300414 https://www.ncbi.nlm.nih.gov/pubmed/28275541 https://www.proquest.com/docview/1876491396 https://pubmed.ncbi.nlm.nih.gov/PMC5328741 https://doaj.org/article/4658cef809d54ddb84795c35f6e34fed |
| Volume | 14 |
| WOSCitedRecordID | wos000405984300041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2213-1582 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000800766 issn: 2213-1582 databaseCode: DOA dateStart: 20120101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2213-1582 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000800766 issn: 2213-1582 databaseCode: M~E dateStart: 20120101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lj9MwELZghRAXtLzDY2UkbiiiSew65gZVq67ErqqloN4sP9muIEVNFokLv31n4qRqAC0XLjkkfsgz43nE428IeeWCYZ4ZlzqrTcoct6m23KQ5wksJx0Zl--vi8wdxelquVnKxV-oLc8IiPHAk3BsGJtL6UI6k48w5A9pUclvwMPYFC96h9gWvZy-Yuuj8INEeVOZ5VqQZL_PuxkxM7kLUWczrEhGwUwysUgvePzBOfzqfv-dQ7hml2SG523mT9F1cxT1yw1f3ye2T7rz8AVGL48bOF9OzmZ8s39JFhJagxziYBSsFwkfnmGu7PQe9At9hd7fZsj_pFPZ-vNZIMTf-Cz3Tldt8o1jLs25qCu8ny4fk02y6nMzTrqRCarlgTapLw2UepHQSVNVYCyk8N044Y4HM1msZIGIMwhRBG-4E-A8QgQlpgg6Fk6x4RA6qTeWfEJqJYDKM90boUzmjrYNoU9qxNyU4mS4hWU9SZTu8cSx78VX1iWUXCtmgkA1qlCtgQ0Je7_p8jyS5tvV75NSuJSJlty9AflQnP-pf8pOQouez6i-jgvqEgdbXTi3-1svXnQaoVaZqaKk-ovyh-GWixTZjCXnZC5OCnYzHM7rym0voAYaJIUrrOCGPo3DtlgaBsQDHL4N5B2I3WPvwS7U-b9HCeYElDbKn_4NYz8gdJEL8BfWcHDTbS_-C3LI_mnW9PSI3xao8ajciPE9-Ta8AksA4CA |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=PItcHPERFeCT%3A+Primary+Intracranial+Hemorrhage+Probability+Estimation+using+Random+Forests+on+CT&rft.jtitle=NeuroImage+clinical&rft.au=Muschelli%2C+John&rft.au=Sweeney%2C+Elizabeth+M&rft.au=Ullman%2C+Natalie+L&rft.au=Vespa%2C+Paul&rft.date=2017-01-01&rft.eissn=2213-1582&rft.volume=14&rft.spage=379&rft_id=info:doi/10.1016%2Fj.nicl.2017.02.007&rft_id=info%3Apmid%2F28275541&rft.externalDocID=28275541 |
| thumbnail_m | http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F22131582%2FS2213158217X00028%2Fcov150h.gif |