Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT
Background: Metastatic epidural spinal cord compression (MESCC) is a disastrous complication of advanced malignancy. Deep learning (DL) models for automatic MESCC classification on staging CT were developed to aid earlier diagnosis. Methods: This retrospective study included 444 CT staging studies f...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/14/13/3219 |
| _version_ | 1797480613994823680 |
|---|---|
| author | James Thomas Patrick Decourcy Hallinan Lei Zhu Wenqiao Zhang Tricia Kuah Desmond Shi Wei Lim Xi Zhen Low Amanda J. L. Cheng Sterling Ellis Eide Han Yang Ong Faimee Erwan Muhamat Nor Ahmed Mohamed Alsooreti Mona I. AlMuhaish Kuan Yuen Yeong Ee Chin Teo Nesaretnam Barr Kumarakulasinghe Qai Ven Yap Yiong Huak Chan Shuxun Lin Jiong Hao Tan Naresh Kumar Balamurugan A. Vellayappan Beng Chin Ooi Swee Tian Quek Andrew Makmur |
| author_facet | James Thomas Patrick Decourcy Hallinan Lei Zhu Wenqiao Zhang Tricia Kuah Desmond Shi Wei Lim Xi Zhen Low Amanda J. L. Cheng Sterling Ellis Eide Han Yang Ong Faimee Erwan Muhamat Nor Ahmed Mohamed Alsooreti Mona I. AlMuhaish Kuan Yuen Yeong Ee Chin Teo Nesaretnam Barr Kumarakulasinghe Qai Ven Yap Yiong Huak Chan Shuxun Lin Jiong Hao Tan Naresh Kumar Balamurugan A. Vellayappan Beng Chin Ooi Swee Tian Quek Andrew Makmur |
| author_sort | James Thomas Patrick Decourcy Hallinan |
| collection | DOAJ |
| description | Background: Metastatic epidural spinal cord compression (MESCC) is a disastrous complication of advanced malignancy. Deep learning (DL) models for automatic MESCC classification on staging CT were developed to aid earlier diagnosis. Methods: This retrospective study included 444 CT staging studies from 185 patients with suspected MESCC who underwent MRI spine studies within 60 days of the CT studies. The DL model training/validation dataset consisted of 316/358 (88%) and the test set of 42/358 (12%) CT studies. Training/validation and test datasets were labeled in consensus by two subspecialized radiologists (6 and 11-years-experience) using the MRI studies as the reference standard. Test sets were labeled by the developed DL models and four radiologists (2–7 years of experience) for comparison. Results: DL models showed almost-perfect interobserver agreement for classification of CT spine images into normal, low, and high-grade MESCC, with kappas ranging from 0.873–0.911 (<i>p</i> < 0.001). The DL models (lowest κ = 0.873, 95% CI 0.858–0.887) also showed superior interobserver agreement compared to two of the four radiologists for three-class classification, including a specialist (κ = 0.820, 95% CI 0.803–0.837) and general radiologist (κ = 0.726, 95% CI 0.706–0.747), both <i>p</i> < 0.001. Conclusion: DL models for the MESCC classification on a CT showed comparable to superior interobserver agreement to radiologists and could be used to aid earlier diagnosis. |
| first_indexed | 2024-03-09T22:02:36Z |
| format | Article |
| id | doaj.art-723e458c6d0845af8f7d09d6c4ecd962 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-09T22:02:36Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-723e458c6d0845af8f7d09d6c4ecd9622023-11-23T19:46:20ZengMDPI AGCancers2072-66942022-06-011413321910.3390/cancers14133219Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CTJames Thomas Patrick Decourcy Hallinan0Lei Zhu1Wenqiao Zhang2Tricia Kuah3Desmond Shi Wei Lim4Xi Zhen Low5Amanda J. L. Cheng6Sterling Ellis Eide7Han Yang Ong8Faimee Erwan Muhamat Nor9Ahmed Mohamed Alsooreti10Mona I. AlMuhaish11Kuan Yuen Yeong12Ee Chin Teo13Nesaretnam Barr Kumarakulasinghe14Qai Ven Yap15Yiong Huak Chan16Shuxun Lin17Jiong Hao Tan18Naresh Kumar19Balamurugan A. Vellayappan20Beng Chin Ooi21Swee Tian Quek22Andrew Makmur23Department of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeIntegrative Sciences and Engineering Programme, NUS Graduate School, National University of Singapore, 21 Lower Kent Ridge Road, Singapore 119077, SingaporeDepartment of Computer Science, School of Computing, National University of Singapore, 13 Computing Drive, Singapore 117417, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Radiology, Ng Teng Fong General Hospital, 1 Jurong East Street 21, Singapore 609606, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeNational University Cancer Institute, NUH Medical Centre (NUHMC), Levels 8–10, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeBiostatistics Unit, Yong Loo Lin School of Medicine, National University of Singapore, 10 Medical Drive, Singapore 117597, SingaporeBiostatistics Unit, Yong Loo Lin School of Medicine, National University of Singapore, 10 Medical Drive, Singapore 117597, SingaporeDivision of Spine Surgery, Department of Orthopaedic Surgery, Ng Teng Fong General Hospital, 1 Jurong East Street 21, Singapore 609606, SingaporeUniversity Spine Centre, Department of Orthopaedic Surgery, National University Health System, 1E, Lower Kent Ridge Road, Singapore 119228, SingaporeUniversity Spine Centre, Department of Orthopaedic Surgery, National University Health System, 1E, Lower Kent Ridge Road, Singapore 119228, SingaporeDepartment of Radiation Oncology, National University Cancer Institute Singapore, National University Hospital, Singapore 119074, SingaporeDepartment of Computer Science, School of Computing, National University of Singapore, 13 Computing Drive, Singapore 117417, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeDepartment of Diagnostic Imaging, National University Hospital, 5 Lower Kent Ridge Road, Singapore 119074, SingaporeBackground: Metastatic epidural spinal cord compression (MESCC) is a disastrous complication of advanced malignancy. Deep learning (DL) models for automatic MESCC classification on staging CT were developed to aid earlier diagnosis. Methods: This retrospective study included 444 CT staging studies from 185 patients with suspected MESCC who underwent MRI spine studies within 60 days of the CT studies. The DL model training/validation dataset consisted of 316/358 (88%) and the test set of 42/358 (12%) CT studies. Training/validation and test datasets were labeled in consensus by two subspecialized radiologists (6 and 11-years-experience) using the MRI studies as the reference standard. Test sets were labeled by the developed DL models and four radiologists (2–7 years of experience) for comparison. Results: DL models showed almost-perfect interobserver agreement for classification of CT spine images into normal, low, and high-grade MESCC, with kappas ranging from 0.873–0.911 (<i>p</i> < 0.001). The DL models (lowest κ = 0.873, 95% CI 0.858–0.887) also showed superior interobserver agreement compared to two of the four radiologists for three-class classification, including a specialist (κ = 0.820, 95% CI 0.803–0.837) and general radiologist (κ = 0.726, 95% CI 0.706–0.747), both <i>p</i> < 0.001. Conclusion: DL models for the MESCC classification on a CT showed comparable to superior interobserver agreement to radiologists and could be used to aid earlier diagnosis.https://www.mdpi.com/2072-6694/14/13/3219deep learning modelmetastatic spinal cord compressionmetastatic epidural spinal cord compressionCTMRIBilsky classification |
| spellingShingle | James Thomas Patrick Decourcy Hallinan Lei Zhu Wenqiao Zhang Tricia Kuah Desmond Shi Wei Lim Xi Zhen Low Amanda J. L. Cheng Sterling Ellis Eide Han Yang Ong Faimee Erwan Muhamat Nor Ahmed Mohamed Alsooreti Mona I. AlMuhaish Kuan Yuen Yeong Ee Chin Teo Nesaretnam Barr Kumarakulasinghe Qai Ven Yap Yiong Huak Chan Shuxun Lin Jiong Hao Tan Naresh Kumar Balamurugan A. Vellayappan Beng Chin Ooi Swee Tian Quek Andrew Makmur Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT Cancers deep learning model metastatic spinal cord compression metastatic epidural spinal cord compression CT MRI Bilsky classification |
| title | Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT |
| title_full | Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT |
| title_fullStr | Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT |
| title_full_unstemmed | Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT |
| title_short | Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT |
| title_sort | deep learning model for grading metastatic epidural spinal cord compression on staging ct |
| topic | deep learning model metastatic spinal cord compression metastatic epidural spinal cord compression CT MRI Bilsky classification |
| url | https://www.mdpi.com/2072-6694/14/13/3219 |
| work_keys_str_mv | AT jamesthomaspatrickdecourcyhallinan deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT leizhu deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT wenqiaozhang deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT triciakuah deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT desmondshiweilim deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT xizhenlow deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT amandajlcheng deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT sterlingelliseide deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT hanyangong deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT faimeeerwanmuhamatnor deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT ahmedmohamedalsooreti deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT monaialmuhaish deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT kuanyuenyeong deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT eechinteo deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT nesaretnambarrkumarakulasinghe deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT qaivenyap deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT yionghuakchan deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT shuxunlin deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT jionghaotan deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT nareshkumar deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT balamuruganavellayappan deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT bengchinooi deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT sweetianquek deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct AT andrewmakmur deeplearningmodelforgradingmetastaticepiduralspinalcordcompressiononstagingct |