Graphical processing unit implementation of an integrated shape-based active contour: Application to digital pathology
Commodity graphics hardware has become a cost-effective parallel platform to solve many general computational problems. In medical imaging and more so in digital pathology, segmentation of multiple structures on high-resolution images, is often a complex and computationally expensive task. Shape-bas...
Uložené v:
| Vydané v: | Journal of pathology informatics Ročník 2; číslo 2; s. 13 |
|---|---|
| Hlavní autori: | , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
India
Elsevier Inc
01.01.2012
Medknow Publications and Media Pvt. Ltd Medknow Publications & Media Pvt Ltd Elsevier |
| Predmet: | |
| ISSN: | 2153-3539, 2229-5089, 2153-3539 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Commodity graphics hardware has become a cost-effective parallel platform to solve many general computational problems. In medical imaging and more so in digital pathology, segmentation of multiple structures on high-resolution images, is often a complex and computationally expensive task. Shape-based level set segmentation has recently emerged as a natural solution to segmenting overlapping and occluded objects. However the flexibility of the level set method has traditionally resulted in long computation times and therefore might have limited clinical utility. The processing times even for moderately sized images could run into several hours of computation time. Hence there is a clear need to accelerate these segmentations schemes. In this paper, we present a parallel implementation of a computationally heavy segmentation scheme on a graphical processing unit (GPU). The segmentation scheme incorporates level sets with shape priors to segment multiple overlapping nuclei from very large digital pathology images. We report a speedup of 19× compared to multithreaded C and MATLAB-based implementations of the same scheme, albeit with slight reduction in accuracy. Our GPU-based segmentation scheme was rigorously and quantitatively evaluated for the problem of nuclei segmentation and overlap resolution on digitized histopathology images corresponding to breast and prostate biopsy tissue specimens. |
|---|---|
| AbstractList | Commodity graphics hardware has become a cost-effective parallel platform to solve m any general computational problems. In medical imaging and more so in digital pathology, segmentation of multiple structures on high-resolution images, is often a complex and computationally expensive task. Shape-based level set segmentation has recently emerged as a natural solution to segmenting overlapping and occluded objects. However the flexibility of the level set method has traditionally resulted in long computation times and therefore might have limited clinical utility. The processing times even for moderately sized images could run into several hours of computation time. Hence there is a clear need to accelerate these segmentations schemes. In this paper, we present a parallel implementation of a computationally heavy segmentation scheme on a graphical processing unit (GPU). The segmentation scheme incorporates level sets with shape priors to segment multiple overlapping nuclei from very large digital pathology images. We report a speedup of 19× compared to multithreaded C and MATLAB-based implementations of the same scheme, albeit with slight reduction in accuracy. Our GPU-based segmentation scheme was rigorously and quantitatively evaluated for the problem of nuclei segmentation and overlap resolution on digitized histopathology images corresponding to breast and prostate biopsy tissue specimens. Commodity graphics hardware has become a cost-effective parallel platform to solve many general computational problems. In medical imaging and more so in digital pathology, segmentation of multiple structures on high-resolution images, is often a complex and computationally expensive task. Shape-based level set segmentation has recently emerged as a natural solution to segmenting overlapping and occluded objects. However the flexibility of the level set method has traditionally resulted in long computation times and therefore might have limited clinical utility. The processing times even for moderately sized images could run into several hours of computation time. Hence there is a clear need to accelerate these segmentations schemes. In this paper, we present a parallel implementation of a computationally heavy segmentation scheme on a graphical processing unit (GPU). The segmentation scheme incorporates level sets with shape priors to segment multiple overlapping nuclei from very large digital pathology images. We report a speedup of 19× compared to multithreaded C and MATLAB-based implementations of the same scheme, albeit with slight reduction in accuracy. Our GPU-based segmentation scheme was rigorously and quantitatively evaluated for the problem of nuclei segmentation and overlap resolution on digitized histopathology images corresponding to breast and prostate biopsy tissue specimens. Commodity graphics hardware has become a cost-effective parallel platform to solve m any general computational problems. In medical imaging and more so in digital pathology, segmentation of multiple structures on high-resolution images, is often a complex and computationally expensive task. Shape-based level set segmentation has recently emerged as a natural solution to segmenting overlapping and occluded objects. However the flexibility of the level set method has traditionally resulted in long computation times and therefore might have limited clinical utility. The processing times even for moderately sized images could run into several hours of computation time. Hence there is a clear need to accelerate these segmentations schemes. In this paper, we present a parallel implementation of a computationally heavy segmentation scheme on a graphical processing unit (GPU). The segmentation scheme incorporates level sets with shape priors to segment multiple overlapping nuclei from very large digital pathology images. We report a speedup of 19× compared to multithreaded C and MATLAB-based implementations of the same scheme, albeit with slight reduction in accuracy. Our GPU-based segmentation scheme was rigorously and quantitatively evaluated for the problem of nuclei segmentation and overlap resolution on digitized histopathology images corresponding to breast and prostate biopsy tissue specimens.Commodity graphics hardware has become a cost-effective parallel platform to solve m any general computational problems. In medical imaging and more so in digital pathology, segmentation of multiple structures on high-resolution images, is often a complex and computationally expensive task. Shape-based level set segmentation has recently emerged as a natural solution to segmenting overlapping and occluded objects. However the flexibility of the level set method has traditionally resulted in long computation times and therefore might have limited clinical utility. The processing times even for moderately sized images could run into several hours of computation time. Hence there is a clear need to accelerate these segmentations schemes. In this paper, we present a parallel implementation of a computationally heavy segmentation scheme on a graphical processing unit (GPU). The segmentation scheme incorporates level sets with shape priors to segment multiple overlapping nuclei from very large digital pathology images. We report a speedup of 19× compared to multithreaded C and MATLAB-based implementations of the same scheme, albeit with slight reduction in accuracy. Our GPU-based segmentation scheme was rigorously and quantitatively evaluated for the problem of nuclei segmentation and overlap resolution on digitized histopathology images corresponding to breast and prostate biopsy tissue specimens. |
| ArticleNumber | 13 |
| Audience | Academic |
| Author | Madabhushi, Anant Ali, Sahirzeeshan |
| AuthorAffiliation | 1 Department of Biomedical Engineering, Rutgers, The State University of New Jersey, New Brunswick, NJ, USA Department of Electrical and Computer Engineering, Rutgers, The State University of New Jersey, New Brunswick, NJ, USA |
| AuthorAffiliation_xml | – name: 1 Department of Biomedical Engineering, Rutgers, The State University of New Jersey, New Brunswick, NJ, USA – name: Department of Electrical and Computer Engineering, Rutgers, The State University of New Jersey, New Brunswick, NJ, USA |
| Author_xml | – sequence: 1 givenname: Sahirzeeshan surname: Ali fullname: Ali, Sahirzeeshan email: sahirali@eden.rutgers.edu organization: Department of Electrical and Computer Engineering, New Brunswick, NJ, USA – sequence: 2 givenname: Anant surname: Madabhushi fullname: Madabhushi, Anant organization: Department of Biomedical Engineering, Rutgers, The State University of New Jersey, New Brunswick, NJ, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/22811957$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9Us9v0zAYjdAQG2VnbigSFy7t7Di_zAGpmmBMmsQFztYX53PqkdjBdiv1v8dpRrVOqPbB1uf3nj_7vbfJhbEGk-Q9JaucEnaT0YItWcH4imck46-Sq2Pl4tn-Mrn2_pHEwRilpH6TXGZZTSkvqqtkd-dg3GgJfTo6K9F7bbp0a3RI9TD2OKAJELQ1qVUpmFSbgJ2DgG3qNzDisgEf9yCD3mEqrQl26z6n63Hso-iBGGza6k6H6QoIG9vbbv8uea2g93j9tC6SX9--_rz9vnz4cXd_u35YyrzkfAmkLQveciqhamjJFRYlKSihtIasKoEjUxwpZFTWdVlWkhBZs7YBVZdENZwtkvtZt7XwKEanB3B7YUGLQ8G6ToALWvYoGFWyboFWqihzQrBpoSCoFM9KVnBSRa0vs9a4bQZsZfwZB_2J6OmJ0RvR2Z2I355VdGrm05OAs3-26IMYtJfY92DQbr2InuYVr7Jo1CL5OEM7iK1po2xUlBNcrFnOyzynrIyo1X9QcbY46OgFKh3rJ4QPz59w7P1fHiLgZgZIZ713qI4QSsQUOjHFSkyxEofQRUbxgiH1nJjYi-7P8PjMw2j_TqMTXmo0ElvtUIbojz7DrV5wZa_NFOLfuD_L_AvLv_3z |
| CitedBy_id | crossref_primary_10_1038_srep33985 crossref_primary_10_1016_j_compeleceng_2018_01_024 crossref_primary_10_1146_annurev_bioeng_112415_114722 |
| Cites_doi | 10.1117/12.878425 10.1109/TBME.2009.2035305 10.1016/j.simpat.2005.08.005 10.1109/83.902291 10.1007/s00371-010-0532-0 10.2217/iim.09.9 |
| ContentType | Journal Article |
| Copyright | 2011 The Authors COPYRIGHT 2011 Medknow Publications and Media Pvt. Ltd. Copyright: © 2011 Ali S. 2011 |
| Copyright_xml | – notice: 2011 The Authors – notice: COPYRIGHT 2011 Medknow Publications and Media Pvt. Ltd. – notice: Copyright: © 2011 Ali S. 2011 |
| DBID | 6I. AAFTH AAYXX CITATION NPM 7X8 5PM DOA |
| DOI | 10.4103/2153-3539.92029 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef PubMed MEDLINE - Academic PubMed Central (Full Participant titles) Open Access Journals |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals (DOAJ) 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 | 2153-3539 |
| EndPage | 13 |
| ExternalDocumentID | oai_doaj_org_article_31fc8da17f56400ebda50eff92635907 PMC3312719 A349644136 22811957 10_4103_2153_3539_92029 S2153353922006885 |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: NCI NIH HHS grantid: R01 CA140772 – fundername: NCI NIH HHS grantid: R01 CA136535 – fundername: NCI NIH HHS grantid: R03 CA143991 |
| GroupedDBID | .1- .FO 0R~ 5VS 7X7 8FE 8FG 8FI 8FJ AAKDD AALRI AAXUO AAYWO ABDBF ABUWG ACGFS ACUHS ACVFH ADBBV ADCNI ADRAZ ADVLN AEGXH AEUPX AEXQZ AFJKZ AFKRA AFPUW AFRHN AIGII AITUG AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ AOIJS APXCP ARAPS BAWUL BCNDV BENPR BGLVJ CCPQU DIK E3Z EBS EJD EOJEC ESX F5P FDB FYUFA GROUPED_DOAJ GX1 H13 HCIFZ HMCUK HYE IAO IHR IL9 IPNFZ ITC K6V K7- KQ8 M41 M48 M~E O5R O5S OBODZ OK1 P62 PHGZM PHGZT PIMPY PQGLB PROAC RIG RNS ROL RPM TUS UKHRP Z5R 6I. AAFTH ABXLX AFCTW RMW W3E AAYXX AFFHD CITATION ALIPV NPM 7X8 5PM |
| ID | FETCH-LOGICAL-c4699-a0d659d91ca7b169fe560510118a276a9e3f9e1a21c88667c00c83dbaf860fb93 |
| IEDL.DBID | DOA |
| ISSN | 2153-3539 2229-5089 |
| IngestDate | Fri Oct 03 12:53:10 EDT 2025 Tue Nov 04 01:59:33 EST 2025 Sun Nov 09 13:24:11 EST 2025 Mon Oct 20 22:24:37 EDT 2025 Mon Oct 20 16:06:55 EDT 2025 Thu Apr 03 06:58:06 EDT 2025 Wed Nov 05 20:57:43 EST 2025 Tue Nov 18 21:11:21 EST 2025 Fri Feb 23 02:40:30 EST 2024 Tue Oct 14 19:36:34 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Keywords | Medical imaging Histopathology Level set Segmentation GPU Implementation Parallel Processing Multi-threaded programming Fast Active Contour Digital Pathology |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4699-a0d659d91ca7b169fe560510118a276a9e3f9e1a21c88667c00c83dbaf860fb93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | https://doaj.org/article/31fc8da17f56400ebda50eff92635907 |
| PMID | 22811957 |
| PQID | 1034797200 |
| PQPubID | 23479 |
| PageCount | 1 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_31fc8da17f56400ebda50eff92635907 pubmedcentral_primary_oai_pubmedcentral_nih_gov_3312719 proquest_miscellaneous_1034797200 gale_infotracmisc_A349644136 gale_infotracacademiconefile_A349644136 pubmed_primary_22811957 crossref_primary_10_4103_2153_3539_92029 crossref_citationtrail_10_4103_2153_3539_92029 elsevier_sciencedirect_doi_10_4103_2153_3539_92029 elsevier_clinicalkey_doi_10_4103_2153_3539_92029 |
| PublicationCentury | 2000 |
| PublicationDate | January 2012 |
| PublicationDateYYYYMMDD | 2012-01-01 |
| PublicationDate_xml | – month: 01 year: 2012 text: January 2012 |
| PublicationDecade | 2010 |
| PublicationPlace | India |
| PublicationPlace_xml | – name: India |
| PublicationTitle | Journal of pathology informatics |
| PublicationTitleAlternate | J Pathol Inform |
| PublicationYear | 2012 |
| Publisher | Elsevier Inc Medknow Publications and Media Pvt. Ltd Medknow Publications & Media Pvt Ltd Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Medknow Publications and Media Pvt. Ltd – name: Medknow Publications & Media Pvt Ltd – name: Elsevier |
| References | Chan, Vese (bib11) 2001; 10 Lefohn, Whitaker (bib6) 2002 Ruiz, Kong, Ujaldon, Boyer, Saltz, Gurcan (bib5) 2008 Schmid, Guitin, Jos, Gobbetti, Magnenat-Thalmann (bib9) 2011; 27 Ali, Madabhushi (bib3) 2011 Kilgariff, Fernando (bib4) 2005 Ali S, Madabhushi A. “Segmenting multiple overlapping objects via an integrated region and boundary based active contour incorporating shape priors: Applications to histopathology”, SPIE Med Imag 79622W (2011). bib8 Basavanhally, Ganesan, Agner, Monaco, Feldman, Tomaszewski (bib2) 2010; 57 Micikevicius (bib12) 2009 Tejada, Ertl (bib10) 2005; 13 Giles (bib13) Madabhushi (bib1) 2009; 1 10.4103/2153-3539.92029_bib7 Madabhushi (10.4103/2153-3539.92029_bib1) 2009; 1 Basavanhally (10.4103/2153-3539.92029_bib2) 2010; 57 Micikevicius (10.4103/2153-3539.92029_bib12) 2009 Ali (10.4103/2153-3539.92029_bib3) 2011 Schmid (10.4103/2153-3539.92029_bib9) 2011; 27 Chan (10.4103/2153-3539.92029_bib11) 2001; 10 Kilgariff (10.4103/2153-3539.92029_bib4) 2005 Ruiz (10.4103/2153-3539.92029_bib5) 2008 Lefohn (10.4103/2153-3539.92029_bib6) 2002 Giles (10.4103/2153-3539.92029_bib13) Tejada (10.4103/2153-3539.92029_bib10) 2005; 13 |
| References_xml | – volume: 27 start-page: 85 year: 2011 end-page: 95 ident: bib9 article-title: “A GPU framework for parallel segmentation of volumetric images using discrete deformable model” publication-title: Vis Comput – start-page: 614 year: 2011 end-page: 617 ident: bib3 article-title: “Active Contour For Overlap Resolution Using Watershed Based Initialization (ACOReW): Applications To Histopathology” publication-title: IEEE Int Symp Biomed Imag: From Nano to Macro – volume: 1 start-page: 7 year: 2009 end-page: 10 ident: bib1 article-title: Digital pathology image analysis: Opportunities and challenges (editorial) publication-title: Imag Med – year: 2002 ident: bib6 article-title: “GPU based, three-dimensional level set solver with curvature flow” – ident: bib8 article-title: NVIDIA CUDA Programming Guide ver 2.2.1 – volume: 57 start-page: 642 year: 2010 end-page: 653 ident: bib2 article-title: “Computerized Image-Based Detection and Grading of Lymphocytic Infiltration in HER2+ Breast Cancer Histopathology,” publication-title: IEEE Trans Biomed Eng – reference: Ali S, Madabhushi A. “Segmenting multiple overlapping objects via an integrated region and boundary based active contour incorporating shape priors: Applications to histopathology”, SPIE Med Imag 79622W (2011). – volume: 10 start-page: 266 year: 2001 end-page: 277 ident: bib11 article-title: “Active contours without edges” publication-title: IEEE Trans. on Image Process – start-page: 296 year: 2008 end-page: 299 ident: bib5 article-title: “Pathological image segmentation for neuroblastoma using the GPU”. Biomedical Imaging: From Nano to Macro, IEEE International Symposium on – year: 2005 ident: bib4 article-title: GPU Gems 2, ch. The GeForce 6 Series GPU Architecture – volume: 13 year: 2005 ident: bib10 article-title: “Large steps in GPU-based deformable bodies simulation publication-title: Simulat Model Pract Theory – ident: bib13 article-title: Jacobi iteration for a laplace discretisation on a 3 – start-page: 79 year: 2009 end-page: 84 ident: bib12 article-title: “3D Fnite difference computation on GPUs using CUDA” publication-title: GPGPU-2: Proceedings of 2 – ident: 10.4103/2153-3539.92029_bib7 doi: 10.1117/12.878425 – volume: 57 start-page: 642 year: 2010 ident: 10.4103/2153-3539.92029_bib2 article-title: “Computerized Image-Based Detection and Grading of Lymphocytic Infiltration in HER2+ Breast Cancer Histopathology,” publication-title: IEEE Trans Biomed Eng doi: 10.1109/TBME.2009.2035305 – volume: 13 year: 2005 ident: 10.4103/2153-3539.92029_bib10 article-title: “Large steps in GPU-based deformable bodies simulation publication-title: Simulat Model Pract Theory doi: 10.1016/j.simpat.2005.08.005 – volume: 10 start-page: 266 year: 2001 ident: 10.4103/2153-3539.92029_bib11 article-title: “Active contours without edges” publication-title: IEEE Trans. on Image Process doi: 10.1109/83.902291 – year: 2002 ident: 10.4103/2153-3539.92029_bib6 – start-page: 614 year: 2011 ident: 10.4103/2153-3539.92029_bib3 article-title: “Active Contour For Overlap Resolution Using Watershed Based Initialization (ACOReW): Applications To Histopathology” – volume: 27 start-page: 85 year: 2011 ident: 10.4103/2153-3539.92029_bib9 article-title: “A GPU framework for parallel segmentation of volumetric images using discrete deformable model” publication-title: Vis Comput doi: 10.1007/s00371-010-0532-0 – start-page: 79 year: 2009 ident: 10.4103/2153-3539.92029_bib12 article-title: “3D Fnite difference computation on GPUs using CUDA” – volume: 1 start-page: 7 year: 2009 ident: 10.4103/2153-3539.92029_bib1 article-title: Digital pathology image analysis: Opportunities and challenges (editorial) publication-title: Imag Med doi: 10.2217/iim.09.9 – start-page: 296 year: 2008 ident: 10.4103/2153-3539.92029_bib5 – year: 2005 ident: 10.4103/2153-3539.92029_bib4 – ident: 10.4103/2153-3539.92029_bib13 |
| SSID | ssj0000331108 |
| Score | 1.7837839 |
| Snippet | Commodity graphics hardware has become a cost-effective parallel platform to solve many general computational problems. In medical imaging and more so in... Commodity graphics hardware has become a cost-effective parallel platform to solve m any general computational problems. In medical imaging and more so in... |
| SourceID | doaj pubmedcentral proquest gale pubmed crossref elsevier |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 13 |
| SubjectTerms | Digital Pathology Fast Active Contour GPU Implementation Histopathology Level set Medical imaging Medical imaging equipment Multi-threaded programming Parallel Processing Segmentation Symposium - Original Research |
| Title | Graphical processing unit implementation of an integrated shape-based active contour: Application to digital pathology |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S2153353922006885 https://dx.doi.org/10.4103/2153-3539.92029 https://www.ncbi.nlm.nih.gov/pubmed/22811957 https://www.proquest.com/docview/1034797200 https://pubmed.ncbi.nlm.nih.gov/PMC3312719 https://doaj.org/article/31fc8da17f56400ebda50eff92635907 |
| Volume | 2 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: Directory of Open Access Journals (DOAJ) customDbUrl: eissn: 2153-3539 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000331108 issn: 2153-3539 databaseCode: DOA dateStart: 20100101 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: 2153-3539 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000331108 issn: 2153-3539 databaseCode: M~E dateStart: 20100101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagQogL4s2WUhkJCS5p49iJbW4LauHSigNIe7McP2ikkl11d3vkt3cmTsIGqXDhkkNsx8rMeB7JzDeEvBUs1s7yOgNbzjNR1yKzuSszXgqrbeXBpImu2YQ8P1eLhf660-oLc8ISPHAi3DFn0SlvmYxlBfIWam_LPMSoEUVFpzryXOqdYKrTwZxjfjt2loMjDTtznXB9BMv58XjvSEPsrycmqUPun1imP1X1jq2a5lHuGKbTR-Rh71HSeXqTx-ROaJ-Q-2f9P_On5PozYlIjL-gqVQWAtaJbOMq0-TlkjyN76DJS29IRQMLT9YVdhQwNnae2U4wUU9thxw90_vvPN90sqW9-YPsRih2Ouy_1z8j305Nvn75kfbeFzEGIrIFFviq118xZWbNKxwDOEJ5YpmwhK6sDjzowWzCnVFVJl-dOcV_bqKo81po_J3vtsg0vCUUQMCFiLIs6Fx59UF9G5YWE4AbC4GJGjgaCG9dDkWNHjEsDIQlyyCCHDHLIdByakffjglVC4bh96kfk4DgN4bO7GyBUphcq8y-hmpF84L8ZKlRBp8KDmtv3LcYlvfOSnJK_L3qHwmVQmQABnO1rIoCMCMtl5gjnDw4rr2bkYDITlICbDL8ZxNPgEGbOtWG5XcPOWCssQRnOyIskriNtikIh4h-8rpwI8oR405G2uegwyOF8FZLp_f9B7VfkAbihRfqwdUD2Nlfb8Jrcc9ebZn11SO7KhTrsjjdcz36d3ADK7U5_ |
| 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=Graphical+processing+unit+implementation+of+an+integrated+shape-based+active+contour%3A+Application+to+digital+pathology&rft.jtitle=Journal+of+pathology+informatics&rft.au=Sahirzeeshan+Ali&rft.au=Anant+Madabhushi&rft.date=2012-01-01&rft.pub=Elsevier&rft.issn=2153-3539&rft.eissn=2153-3539&rft.volume=2&rft.issue=2&rft.spage=13&rft.epage=13&rft_id=info:doi/10.4103%2F2153-3539.92029&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_31fc8da17f56400ebda50eff92635907 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2153-3539&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2153-3539&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2153-3539&client=summon |