Neural network algorithm for detection of erosions and ankylosis on CT of the sacroiliac joints: multicentre development and validation of diagnostic accuracy.

Autor: Van Den Berghe T; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium. thovdnbe.vandenberghe@ugent.be., Babin D; Department of Telecommunication and Information Processing - Image Processing and Interpretation (TELIN-IPI), Faculty of Engineering and Architecture, Ghent University - IMEC, Sint-Pietersnieuwstraat 41, 9000, Ghent, Belgium., Chen M; Department of Radiology, Peking University Shenzhen Hospital, Shenzhen, 518036, China., Callens M; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Brack D; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Maes H; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Lievens J; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Lammens M; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Van Sumere M; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Morbée L; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Hautekeete S; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Schatteman S; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Jacobs T; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Thooft WJ; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Herregods N; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Huysse W; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Jaremko JL; Department of Radiology and Diagnostic Imaging and Rheumatology, University of Alberta, 8440 122 Street NW, Edmonton, Alberta, T6G 2B7, Canada., Lambert R; Department of Radiology and Diagnostic Imaging and Rheumatology, University of Alberta, 8440 122 Street NW, Edmonton, Alberta, T6G 2B7, Canada., Maksymowych W; Department of Radiology and Diagnostic Imaging and Rheumatology, University of Alberta, 8440 122 Street NW, Edmonton, Alberta, T6G 2B7, Canada., Laloo F; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium., Baraliakos X; Rheumazentrum Ruhrgebiet Herne, Ruhr-University Bochum, Claudiusstraße 45, 44649, Herne, Germany., De Craemer AS; Department of Rheumatology, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium.; Vlaams Instituut voor Biotechnologie (VIB) Centre for Inflammation Research (IRC), Ghent University, Technologiepark 927, 9052, Ghent, Belgium., Carron P; Department of Rheumatology, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium.; Vlaams Instituut voor Biotechnologie (VIB) Centre for Inflammation Research (IRC), Ghent University, Technologiepark 927, 9052, Ghent, Belgium., Van den Bosch F; Department of Rheumatology, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium.; Vlaams Instituut voor Biotechnologie (VIB) Centre for Inflammation Research (IRC), Ghent University, Technologiepark 927, 9052, Ghent, Belgium., Elewaut D; Department of Rheumatology, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium.; Vlaams Instituut voor Biotechnologie (VIB) Centre for Inflammation Research (IRC), Ghent University, Technologiepark 927, 9052, Ghent, Belgium., Jans L; Department of Radiology and Medical Imaging, Ghent University Hospital, Corneel Heymanslaan 10, 9000, Ghent, Belgium.
Jazyk: angličtina
Zdroj: European radiology [Eur Radiol] 2023 Nov; Vol. 33 (11), pp. 8310-8323. Date of Electronic Publication: 2023 May 23.
DOI: 10.1007/s00330-023-09704-y
Abstrakt: Objectives: To evaluate the feasibility and diagnostic accuracy of a deep learning network for detection of structural lesions of sacroiliitis on multicentre pelvic CT scans.
Methods: Pelvic CT scans of 145 patients (81 female, 121 Ghent University/24 Alberta University, 18-87 years old, mean 40 ± 13 years, 2005-2021) with a clinical suspicion of sacroiliitis were retrospectively included. After manual sacroiliac joint (SIJ) segmentation and structural lesion annotation, a U-Net for SIJ segmentation and two separate convolutional neural networks (CNN) for erosion and ankylosis detection were trained. In-training validation and tenfold validation testing (U-Net-n = 10 × 58; CNN-n = 10 × 29) on a test dataset were performed to assess performance on a slice-by-slice and patient level (dice coefficient/accuracy/sensitivity/specificity/positive and negative predictive value/ROC AUC). Patient-level optimisation was applied to increase the performance regarding predefined statistical metrics. Gradient-weighted class activation mapping (Grad-CAM++) heatmap explainability analysis highlighted image parts with statistically important regions for algorithmic decisions.
Results: Regarding SIJ segmentation, a dice coefficient of 0.75 was obtained in the test dataset. For slice-by-slice structural lesion detection, a sensitivity/specificity/ROC AUC of 95%/89%/0.92 and 93%/91%/0.91 were obtained in the test dataset for erosion and ankylosis detection, respectively. For patient-level lesion detection after pipeline optimisation for predefined statistical metrics, a sensitivity/specificity of 95%/85% and 82%/97% were obtained for erosion and ankylosis detection, respectively. Grad-CAM++  explainability analysis highlighted cortical edges as focus for pipeline decisions.
Conclusions: An optimised deep learning pipeline, including an explainability analysis, detects structural lesions of sacroiliitis on pelvic CT scans with excellent statistical performance on a slice-by-slice and patient level.
Clinical Relevance Statement: An optimised deep learning pipeline, including a robust explainability analysis, detects structural lesions of sacroiliitis on pelvic CT scans with excellent statistical metrics on a slice-by-slice and patient level.
Key Points: • Structural lesions of sacroiliitis can be detected automatically in pelvic CT scans. • Both automatic segmentation and disease detection yield excellent statistical outcome metrics. • The algorithm takes decisions based on cortical edges, rendering an explainable solution.
(© 2023. The Author(s), under exclusive licence to European Society of Radiology.)
Databáze: MEDLINE
Externí odkaz: