Abstract 7 — Deep Learning Differentiation of Inflammatory Lesions in Sacroiliac Joint MRI Based on Spondyloarthritis Research Consortium of Canada (SPARCC) System
Objective To develop a deep learning algorithm for grading sacroiliitis based on SPARCC in magnetic resonance imaging (MRI). Method A total of 996 images with inflammatory lesions from 210 participants with MRI sacroiliitis were used for training and validation. The testing cohort consisted of 18 pa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Publishing
2023-11-01
|
| Series: | Journal of Clinical Rheumatology and Immunology |
| Online Access: | https://www.worldscientific.com/doi/10.1142/S2661341723740231 |
| _version_ | 1797447887146188800 |
|---|---|
| author | Ho Yin Chung Shirley Chiu Wai Chan Yingying Lin Peng Cao |
| author_facet | Ho Yin Chung Shirley Chiu Wai Chan Yingying Lin Peng Cao |
| author_sort | Ho Yin Chung |
| collection | DOAJ |
| description | Objective To develop a deep learning algorithm for grading sacroiliitis based on SPARCC in magnetic resonance imaging (MRI). Method A total of 996 images with inflammatory lesions from 210 participants with MRI sacroiliitis were used for training and validation. The testing cohort consisted of 18 participants with and 19 without MRI sacroiliitis. One hundred and fifty four images from the testing cohort had inflammatory lesions identified by a pre-trained algorithm from our previous study[1]. The ground truth was defined by manually outlined regions of interests (ROIs) consisting of bone marrow edema (BME) at the sacroiliac joint. The performance of the deep learning pipeline in predicting the SPARCC score was compared to manual interpretation by two experienced readers. Result The intra-observer reliability and the Pearson coefficient between the SPARCC scores from two experienced readers and the deep learning pipeline were 0.83 and 0.86, respectively. The sensitivities in identifying all inflammatory lesions, deep lesions, and intense lesions were 0.83, 0.79 and 0.81, respectively. The Dice coefficients of the sacrum and ilium segmentation were 0.82 and 0.80, respectively. The accuracies of identifying the SI joint and reference vessel were 0.90 and 0.88, respectively. Conclusion The performance of AI algorithms in SPARCC scoring was compatible with manual scoring by experienced readers. This proposed deep learning pipeline could be the first demonstration of a complete and SPARCC-informed deep-learning approach in scoring STIR images in SpA. |
| first_indexed | 2024-03-09T14:02:28Z |
| format | Article |
| id | doaj.art-f5540b22238e4bb899fe4c45dfee4d10 |
| institution | Directory Open Access Journal |
| issn | 2661-3417 2661-3425 |
| language | English |
| last_indexed | 2024-03-09T14:02:28Z |
| publishDate | 2023-11-01 |
| publisher | World Scientific Publishing |
| record_format | Article |
| series | Journal of Clinical Rheumatology and Immunology |
| spelling | doaj.art-f5540b22238e4bb899fe4c45dfee4d102023-11-30T07:52:32ZengWorld Scientific PublishingJournal of Clinical Rheumatology and Immunology2661-34172661-34252023-11-0123Supp01252510.1142/S2661341723740231Abstract 7 — Deep Learning Differentiation of Inflammatory Lesions in Sacroiliac Joint MRI Based on Spondyloarthritis Research Consortium of Canada (SPARCC) SystemHo Yin Chung0Shirley Chiu Wai Chan1Yingying Lin2Peng Cao3The University of Hong Kong, Hong Kong SARThe University of Hong Kong, Hong Kong SARThe University of Hong Kong, Hong Kong SARThe University of Hong Kong, Hong Kong SARObjective To develop a deep learning algorithm for grading sacroiliitis based on SPARCC in magnetic resonance imaging (MRI). Method A total of 996 images with inflammatory lesions from 210 participants with MRI sacroiliitis were used for training and validation. The testing cohort consisted of 18 participants with and 19 without MRI sacroiliitis. One hundred and fifty four images from the testing cohort had inflammatory lesions identified by a pre-trained algorithm from our previous study[1]. The ground truth was defined by manually outlined regions of interests (ROIs) consisting of bone marrow edema (BME) at the sacroiliac joint. The performance of the deep learning pipeline in predicting the SPARCC score was compared to manual interpretation by two experienced readers. Result The intra-observer reliability and the Pearson coefficient between the SPARCC scores from two experienced readers and the deep learning pipeline were 0.83 and 0.86, respectively. The sensitivities in identifying all inflammatory lesions, deep lesions, and intense lesions were 0.83, 0.79 and 0.81, respectively. The Dice coefficients of the sacrum and ilium segmentation were 0.82 and 0.80, respectively. The accuracies of identifying the SI joint and reference vessel were 0.90 and 0.88, respectively. Conclusion The performance of AI algorithms in SPARCC scoring was compatible with manual scoring by experienced readers. This proposed deep learning pipeline could be the first demonstration of a complete and SPARCC-informed deep-learning approach in scoring STIR images in SpA.https://www.worldscientific.com/doi/10.1142/S2661341723740231 |
| spellingShingle | Ho Yin Chung Shirley Chiu Wai Chan Yingying Lin Peng Cao Abstract 7 — Deep Learning Differentiation of Inflammatory Lesions in Sacroiliac Joint MRI Based on Spondyloarthritis Research Consortium of Canada (SPARCC) System Journal of Clinical Rheumatology and Immunology |
| title | Abstract 7 — Deep Learning Differentiation of Inflammatory Lesions in Sacroiliac Joint MRI Based on Spondyloarthritis Research Consortium of Canada (SPARCC) System |
| title_full | Abstract 7 — Deep Learning Differentiation of Inflammatory Lesions in Sacroiliac Joint MRI Based on Spondyloarthritis Research Consortium of Canada (SPARCC) System |
| title_fullStr | Abstract 7 — Deep Learning Differentiation of Inflammatory Lesions in Sacroiliac Joint MRI Based on Spondyloarthritis Research Consortium of Canada (SPARCC) System |
| title_full_unstemmed | Abstract 7 — Deep Learning Differentiation of Inflammatory Lesions in Sacroiliac Joint MRI Based on Spondyloarthritis Research Consortium of Canada (SPARCC) System |
| title_short | Abstract 7 — Deep Learning Differentiation of Inflammatory Lesions in Sacroiliac Joint MRI Based on Spondyloarthritis Research Consortium of Canada (SPARCC) System |
| title_sort | abstract 7 deep learning differentiation of inflammatory lesions in sacroiliac joint mri based on spondyloarthritis research consortium of canada sparcc system |
| url | https://www.worldscientific.com/doi/10.1142/S2661341723740231 |
| work_keys_str_mv | AT hoyinchung abstract7deeplearningdifferentiationofinflammatorylesionsinsacroiliacjointmribasedonspondyloarthritisresearchconsortiumofcanadasparccsystem AT shirleychiuwaichan abstract7deeplearningdifferentiationofinflammatorylesionsinsacroiliacjointmribasedonspondyloarthritisresearchconsortiumofcanadasparccsystem AT yingyinglin abstract7deeplearningdifferentiationofinflammatorylesionsinsacroiliacjointmribasedonspondyloarthritisresearchconsortiumofcanadasparccsystem AT pengcao abstract7deeplearningdifferentiationofinflammatorylesionsinsacroiliacjointmribasedonspondyloarthritisresearchconsortiumofcanadasparccsystem |