Deep Learning Automates Measurement of Spinopelvic Parameters on Lateral Lumbar Radiographs
Cross-sectional database study.STUDY DESIGNCross-sectional database study.The objective of this study was to develop an algorithm for the automated measurement of spinopelvic parameters on lateral lumbar radiographs with comparable accuracy to surgeons.OBJECTIVEThe objective of this study was to dev...
Uloženo v:
| Vydáno v: | Spine (Philadelphia, Pa. 1976) Ročník 46; číslo 12; s. E671 |
|---|---|
| Hlavní autoři: | , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
15.06.2021
|
| ISSN: | 1528-1159, 1528-1159 |
| On-line přístup: | Zjistit podrobnosti o přístupu |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Cross-sectional database study.STUDY DESIGNCross-sectional database study.The objective of this study was to develop an algorithm for the automated measurement of spinopelvic parameters on lateral lumbar radiographs with comparable accuracy to surgeons.OBJECTIVEThe objective of this study was to develop an algorithm for the automated measurement of spinopelvic parameters on lateral lumbar radiographs with comparable accuracy to surgeons.Sagittal alignment measurements are important for the evaluation of spinal disorders. Manual measurement methods are time-consuming and subject to rater-dependent error. Thus, a need exists to develop automated methods for obtaining sagittal measurements. Previous studies of automated measurement have been limited in accuracy, inapplicable to common plain films, or unable to measure pelvic parameters.SUMMARY OF BACKGROUND DATASagittal alignment measurements are important for the evaluation of spinal disorders. Manual measurement methods are time-consuming and subject to rater-dependent error. Thus, a need exists to develop automated methods for obtaining sagittal measurements. Previous studies of automated measurement have been limited in accuracy, inapplicable to common plain films, or unable to measure pelvic parameters.Images from 816 patients receiving lateral lumbar radiographs were collected sequentially and used to develop a convolutional neural network (CNN) segmentation algorithm. A total of 653 (80%) of these radiographs were used to train and validate the CNN. This CNN was combined with a computer vision algorithm to create a pipeline for the fully automated measurement of spinopelvic parameters from lateral lumbar radiographs. The remaining 163 (20%) of radiographs were used to test this pipeline. Forty radiographs were selected from the test set and manually measured by three surgeons for comparison.METHODSImages from 816 patients receiving lateral lumbar radiographs were collected sequentially and used to develop a convolutional neural network (CNN) segmentation algorithm. A total of 653 (80%) of these radiographs were used to train and validate the CNN. This CNN was combined with a computer vision algorithm to create a pipeline for the fully automated measurement of spinopelvic parameters from lateral lumbar radiographs. The remaining 163 (20%) of radiographs were used to test this pipeline. Forty radiographs were selected from the test set and manually measured by three surgeons for comparison.The CNN achieved an area under the receiver-operating curve of 0.956. Algorithm measurements of L1-S1 cobb angle, pelvic incidence, pelvic tilt, and sacral slope were not significantly different from surgeon measurement. In comparison to criterion standard measurement, the algorithm performed with a similar mean absolute difference to spine surgeons for L1-S1 Cobb angle (4.30° ± 4.14° vs. 4.99° ± 5.34°), pelvic tilt (2.14° ± 6.29° vs. 1.58° ± 5.97°), pelvic incidence (4.56° ± 5.40° vs. 3.74° ± 2.89°), and sacral slope (4.76° ± 6.93° vs. 4.75° ± 5.71°).RESULTSThe CNN achieved an area under the receiver-operating curve of 0.956. Algorithm measurements of L1-S1 cobb angle, pelvic incidence, pelvic tilt, and sacral slope were not significantly different from surgeon measurement. In comparison to criterion standard measurement, the algorithm performed with a similar mean absolute difference to spine surgeons for L1-S1 Cobb angle (4.30° ± 4.14° vs. 4.99° ± 5.34°), pelvic tilt (2.14° ± 6.29° vs. 1.58° ± 5.97°), pelvic incidence (4.56° ± 5.40° vs. 3.74° ± 2.89°), and sacral slope (4.76° ± 6.93° vs. 4.75° ± 5.71°).This algorithm measures spinopelvic parameters on lateral lumbar radiographs with comparable accuracy to surgeons. The algorithm could be used to streamline clinical workflow or perform large scale studies of spinopelvic parameters.Level of Evidence: 3.CONCLUSIONThis algorithm measures spinopelvic parameters on lateral lumbar radiographs with comparable accuracy to surgeons. The algorithm could be used to streamline clinical workflow or perform large scale studies of spinopelvic parameters.Level of Evidence: 3. |
|---|---|
| AbstractList | Cross-sectional database study.STUDY DESIGNCross-sectional database study.The objective of this study was to develop an algorithm for the automated measurement of spinopelvic parameters on lateral lumbar radiographs with comparable accuracy to surgeons.OBJECTIVEThe objective of this study was to develop an algorithm for the automated measurement of spinopelvic parameters on lateral lumbar radiographs with comparable accuracy to surgeons.Sagittal alignment measurements are important for the evaluation of spinal disorders. Manual measurement methods are time-consuming and subject to rater-dependent error. Thus, a need exists to develop automated methods for obtaining sagittal measurements. Previous studies of automated measurement have been limited in accuracy, inapplicable to common plain films, or unable to measure pelvic parameters.SUMMARY OF BACKGROUND DATASagittal alignment measurements are important for the evaluation of spinal disorders. Manual measurement methods are time-consuming and subject to rater-dependent error. Thus, a need exists to develop automated methods for obtaining sagittal measurements. Previous studies of automated measurement have been limited in accuracy, inapplicable to common plain films, or unable to measure pelvic parameters.Images from 816 patients receiving lateral lumbar radiographs were collected sequentially and used to develop a convolutional neural network (CNN) segmentation algorithm. A total of 653 (80%) of these radiographs were used to train and validate the CNN. This CNN was combined with a computer vision algorithm to create a pipeline for the fully automated measurement of spinopelvic parameters from lateral lumbar radiographs. The remaining 163 (20%) of radiographs were used to test this pipeline. Forty radiographs were selected from the test set and manually measured by three surgeons for comparison.METHODSImages from 816 patients receiving lateral lumbar radiographs were collected sequentially and used to develop a convolutional neural network (CNN) segmentation algorithm. A total of 653 (80%) of these radiographs were used to train and validate the CNN. This CNN was combined with a computer vision algorithm to create a pipeline for the fully automated measurement of spinopelvic parameters from lateral lumbar radiographs. The remaining 163 (20%) of radiographs were used to test this pipeline. Forty radiographs were selected from the test set and manually measured by three surgeons for comparison.The CNN achieved an area under the receiver-operating curve of 0.956. Algorithm measurements of L1-S1 cobb angle, pelvic incidence, pelvic tilt, and sacral slope were not significantly different from surgeon measurement. In comparison to criterion standard measurement, the algorithm performed with a similar mean absolute difference to spine surgeons for L1-S1 Cobb angle (4.30° ± 4.14° vs. 4.99° ± 5.34°), pelvic tilt (2.14° ± 6.29° vs. 1.58° ± 5.97°), pelvic incidence (4.56° ± 5.40° vs. 3.74° ± 2.89°), and sacral slope (4.76° ± 6.93° vs. 4.75° ± 5.71°).RESULTSThe CNN achieved an area under the receiver-operating curve of 0.956. Algorithm measurements of L1-S1 cobb angle, pelvic incidence, pelvic tilt, and sacral slope were not significantly different from surgeon measurement. In comparison to criterion standard measurement, the algorithm performed with a similar mean absolute difference to spine surgeons for L1-S1 Cobb angle (4.30° ± 4.14° vs. 4.99° ± 5.34°), pelvic tilt (2.14° ± 6.29° vs. 1.58° ± 5.97°), pelvic incidence (4.56° ± 5.40° vs. 3.74° ± 2.89°), and sacral slope (4.76° ± 6.93° vs. 4.75° ± 5.71°).This algorithm measures spinopelvic parameters on lateral lumbar radiographs with comparable accuracy to surgeons. The algorithm could be used to streamline clinical workflow or perform large scale studies of spinopelvic parameters.Level of Evidence: 3.CONCLUSIONThis algorithm measures spinopelvic parameters on lateral lumbar radiographs with comparable accuracy to surgeons. The algorithm could be used to streamline clinical workflow or perform large scale studies of spinopelvic parameters.Level of Evidence: 3. |
| Author | Cho, Brian H Tang, Peter Schefflein, Javin Doshi, Amish H Schwartz, John T Arvind, Varun Cho, Samuel K Kim, Jun S |
| Author_xml | – sequence: 1 givenname: John T surname: Schwartz fullname: Schwartz, John T – sequence: 2 givenname: Brian H surname: Cho fullname: Cho, Brian H – sequence: 3 givenname: Peter surname: Tang fullname: Tang, Peter – sequence: 4 givenname: Javin surname: Schefflein fullname: Schefflein, Javin – sequence: 5 givenname: Varun surname: Arvind fullname: Arvind, Varun – sequence: 6 givenname: Jun S surname: Kim fullname: Kim, Jun S – sequence: 7 givenname: Amish H surname: Doshi fullname: Doshi, Amish H – sequence: 8 givenname: Samuel K surname: Cho fullname: Cho, Samuel K |
| BookMark | eNpNjL1OwzAYRS1UJNrCGzB4ZEmxnR_HYym_UqqiFiaG6ov9uQQldrATnp9KMPQu5wxHd0Ymzjsk5JqzBWdK3t5tdwt2srRM2RmZ8lyUCee5mpz4BZnF-HWMipSrKfm4R-xphRBc4w50OQ6-gwEjXSPEMWCHbqDe0l3fON9j-9No-goBOhwwROodrY55gJZWY1dDoFswjT8E6D_jJTm30Ea8-uecvD8-vK2ek2rz9LJaVolOVc4SXWpdWyMzWQsAxi3PjLJWGqlqqbEURQ0msyBrbrQs0zxVDEoOWhaFFYaJObn5--2D_x4xDvuuiRrbFhz6Me5FVshCMJFx8QsJx1rE |
| CitedBy_id | crossref_primary_10_1007_s11547_025_01957_5 crossref_primary_10_1007_s10278_025_01641_0 crossref_primary_10_1177_21925682231205352 crossref_primary_10_3390_bioengineering10101236 crossref_primary_10_1186_s12891_022_05927_0 crossref_primary_10_1016_j_arth_2023_03_087 crossref_primary_10_1016_j_xnsj_2025_100787 crossref_primary_10_1038_s41598_022_19914_x crossref_primary_10_1148_ryai_2021210015 crossref_primary_10_1016_j_arth_2023_03_006 crossref_primary_10_1007_s00586_022_07155_5 crossref_primary_10_1007_s43390_024_00990_0 crossref_primary_10_3389_fphys_2021_676118 crossref_primary_10_1007_s43390_025_01111_1 crossref_primary_10_1302_0301_620X_104B8_BJJ_2022_0416 crossref_primary_10_1007_s10278_023_00830_z crossref_primary_10_1007_s00586_022_07309_5 crossref_primary_10_1186_s13018_025_05561_1 crossref_primary_10_3390_jcm13092573 crossref_primary_10_1016_j_semss_2022_100986 crossref_primary_10_2106_JBJS_22_00664 crossref_primary_10_1097_BSD_0000000000001547 crossref_primary_10_1007_s00256_024_04684_6 crossref_primary_10_1007_s00167_022_07213_x crossref_primary_10_3389_fpubh_2022_891766 crossref_primary_10_1016_j_artd_2024_101398 crossref_primary_10_1038_s41598_023_44964_0 |
| ContentType | Journal Article |
| Copyright | Copyright © 2020 Wolters Kluwer Health, Inc. All rights reserved. |
| Copyright_xml | – notice: Copyright © 2020 Wolters Kluwer Health, Inc. All rights reserved. |
| DBID | 7X8 |
| DOI | 10.1097/BRS.0000000000003830 |
| DatabaseName | MEDLINE - Academic |
| DatabaseTitle | MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1528-1159 |
| GroupedDBID | --- .-D .XZ .Z2 01R 0R~ 123 1J1 354 40H 4Q1 4Q2 4Q3 53G 5RE 5VS 6PF 71W 77Y 7O~ 7X8 A9M AAAAV AAAXR AAGIX AAHPQ AAIQE AAJCS AAMOA AAMTA AAQKA AAQQT AARTV AASCR AASOK AAUEB AAWTL AAXQO ABASU ABBUW ABDIG ABJNI ABOCM ABPXF ABVCZ ABXVJ ABXYN ABZAD ABZZY ACDDN ACDOF ACEWG ACGFO ACGFS ACILI ACLDA ACWDW ACWRI ACXJB ACXNZ ACZKN ADGGA ADHPY ADKSD ADSXY AE3 AE6 AEBDS AENEX AFBFQ AFDTB AFEXH AFMBP AFNMH AFSOK AFUWQ AGINI AHOMT AHQNM AHQVU AHVBC AIJEX AINUH AJCLO AJIOK AJNWD AJZMW AKCTQ AKULP ALKUP ALMA_UNASSIGNED_HOLDINGS ALMTX AMJPA AMKUR AMNEI AOHHW AOQMC BOYCO BQLVK BYPQX C45 CS3 DIWNM DU5 E.X EBS EEVPB ERAAH EX3 F2K F2L F2M F2N F5P FCALG FL- GNXGY GQDEL H0~ HLJTE HZ~ IKREB IKYAY IN~ IPNFZ JF9 JG8 JK3 JK8 K8S KD2 KMI L-C L7B N9A N~7 N~B O9- OAG OAH ODMTH OHH OHYEH OL1 OLG OLH OLU OLV OLY OLZ OPUJH OVD OVDNE OVIDH OVLEI OVOZU OWBYB OWU OWV OWW OWX OWY OWZ OXXIT P2P R2J RIG RLZ S4R S4S SJN TEORI TSPGW V2I VVN W3M WH7 WOQ WOW X3V X3W XXN XYM YFH YOC ZB8 ZFV ZY1 |
| ID | FETCH-LOGICAL-c3950-c8ccbfd747b2aa01f14d9ff7d79b7ce826bad4fa7b1dc7835390a81ac766f2d02 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 39 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=00007632-202106150-00010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1528-1159 |
| IngestDate | Mon Sep 08 13:53:54 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 12 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3950-c8ccbfd747b2aa01f14d9ff7d79b7ce826bad4fa7b1dc7835390a81ac766f2d02 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PQID | 2467620241 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2467620241 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-June-15 |
| PublicationDateYYYYMMDD | 2021-06-15 |
| PublicationDate_xml | – month: 06 year: 2021 text: 2021-June-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | Spine (Philadelphia, Pa. 1976) |
| PublicationYear | 2021 |
| SSID | ssj0006319 |
| Score | 2.5231175 |
| Snippet | Cross-sectional database study.STUDY DESIGNCross-sectional database study.The objective of this study was to develop an algorithm for the automated measurement... |
| SourceID | proquest |
| SourceType | Aggregation Database |
| StartPage | E671 |
| Title | Deep Learning Automates Measurement of Spinopelvic Parameters on Lateral Lumbar Radiographs |
| URI | https://www.proquest.com/docview/2467620241 |
| Volume | 46 |
| WOSCitedRecordID | wos00007632-202106150-00010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEA5qRbz4Ft9E8Bq62c1udk9SH8VDW0qrUPAgeUqh3V27rb_fyTalBy-Ce85hSSYz881Mvg-hO8BnFsxGEx3FkrAkzogIM0ZiToWOqTOktBab4L1eOhplfV9wq_xY5con1o5aF8rVyJsh3OgEkDqj9-UXcapRrrvqJTQ2USOCVMaNdPHRmi08iWphDwhRgJQgbq-ezmW8-TAYLqkL_QdALfjljusY097_798doD2fXeLW0hwO0YbJj9BO1_fPj9H7kzEl9pyqn7i1mBdTl2zi7rpUiAuLh-U4L0ozATeC-8LNbzkSTlzkuCPck-UJ7iymUszwQOjxkvS6OkFv7efXxxfi5RWIirI4ICpVSloNeEKGQgTUUqZdBVfzTHJlAHdIoZkVXFKtXIEoygKRUqF4kthQB-Ep2sqL3JwhzJjVUQJHC6k6S0Ip0phZGihHfSi5TM_R7WrbPsB8XU9C5KZYVB_rjbv4w5pLtBu6mRKnHRRfoYaFK2qu0bb6no-r2U19-j_a8Lij |
| linkProvider | ProQuest |
| 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=Deep+Learning+Automates+Measurement+of+Spinopelvic+Parameters+on+Lateral+Lumbar+Radiographs&rft.jtitle=Spine+%28Philadelphia%2C+Pa.+1976%29&rft.au=Schwartz%2C+John+T&rft.au=Cho%2C+Brian+H&rft.au=Tang%2C+Peter&rft.au=Schefflein%2C+Javin&rft.date=2021-06-15&rft.issn=1528-1159&rft.eissn=1528-1159&rft.volume=46&rft.issue=12&rft.spage=E671&rft_id=info:doi/10.1097%2FBRS.0000000000003830&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1528-1159&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1528-1159&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1528-1159&client=summon |