Original Articles
Vol. 78 No. 1 (2026)
Computed tomography of interstitial lung disease in systemic sclerosis: dataset and deep learning model for pulmonary lesion segmentation
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
Published: 25 February 2026
2381
Views
250
Downloads
Authors
Objective. Systemic sclerosis-associated interstitial lung disease (SSc-ILD) is a major cause of morbidity and mortality in systemic sclerosis patients. High-resolution computed tomography (HRCT) plays a crucial role in SSc-ILD diagnosis and management. In this study, we aimed to develop and evaluate a deep learning-based automated segmentation model for quantifying SSc-ILD lesions in HRCT images and assess its clinical relevance.
Methods. We developed a convolutional neural network model to segment normal lung, established fibrosis (EF), and ground-glass opacity (GGO) in HRCT scans from 40 SSc-ILD patients. The model was trained and evaluated using 8-fold cross-validation. Segmentation performance was assessed using the Dice similarity coefficient (DSC). Correlations between predicted lesion volumes and pulmonary function test (PFT) metrics were analyzed using Spearman’s ρ.
Results. Our model achieved a total lesion (EF+GGO) DSC of 78%. Class-wise segmentation performance was lower for EF (DSC: 70%) compared to GGO (DSC: 73%). Predicted lesion volumes showed significant negative correlations with forced expiratory volume in one second (FEV1) (ρ=-0.64, p<0.001) and FEV1/forced vital capacity (ρ=-0.73, p<0.001). We also created the SICCS dataset, a public dataset of SSc-ILD HRCT images with expert-annotated segmentation labels.
Conclusions. Deep learning-based automated segmentation can help quantify SSc-ILD lesions in HRCT images and provide clinically relevant information. The model’s performance is comparable to previous studies, and the predicted lesion volumes correlate significantly with PFT metrics. This approach shows promise for aiding in SSc-ILD diagnosis, monitoring, and clinical decision-making, although further validation with larger datasets is needed.
Downloads
Download data is not yet available.
Citations
Moghadam KG, Gharibdoost F, Parastandechehr G, Salehian P. Assessments of pulmonary involvement in patients with systemic sclerosis. Arch Iran Med 2011; 14: 22-6.
Chifflot H, Fautrel B, Sordet C, Chatelus E, Sibilia J. Incidence and prevalence of systemic sclerosis: a systematic literature review. Semin Arthritis Rheum 2008; 37: 223-35. DOI: https://doi.org/10.1016/j.semarthrit.2007.05.003
Elhai M, Meune C, Boubaya M, Avouac J, Hachulla E, Balbir-Gurman A, et al. Mapping and predicting mortality from systemic sclerosis. Ann Rheum Dis 2017; 76: 1897-905. DOI: https://doi.org/10.1136/annrheumdis-2017-211448
Ruaro B, Baratella E, Confalonieri P, Wade B, Marrocchio C, Geri P, et al. High-resolution computed tomography: lights and shadows in improving care for SSc-ILD patients. Diagnostics 2021; 11: 1960. DOI: https://doi.org/10.3390/diagnostics11111960
Hoffmann-Vold AM, Allanore Y, Alves M, Brunborg C, Airó P, Ananieva LP, et al. Progressive interstitial lung disease in patients with systemic sclerosis-associated interstitial lung disease in the EUSTAR database. Ann Rheum Dis 2021; 80: 219-27. DOI: https://doi.org/10.1136/annrheumdis-2020-217455
Moore OA, Goh N, Corte T, Rouse H, Hennessy O, Thakkar V, et al. Extent of disease on high-resolution computed tomography lung is a predictor of decline and mortality in systemic sclerosis-related interstitial lung disease. Rheumatology 2013; 52: 155-60. DOI: https://doi.org/10.1093/rheumatology/kes289
Hoffmann-Vold AM, Maher T, Philpot EE, Ashrafzadeh A, Barake R, Barsotti S, et al. The identification and management of interstitial lung disease in systemic sclerosis: evidence-based European consensus statements. Lancet Rheumatol 2020; 2: e71-83. DOI: https://doi.org/10.1183/13993003.congress-2019.PA5195
Suliman YA, Dobrota R, Huscher D, Nguyen-Kim TDL, Maurer B, Jordan S, et al. Brief report: pulmonary function tests: high rate of false-negative results in the early detection and screening of scleroderma-related interstitial lung disease. Arthritis Rheumatol 2015; 67: 3256-61. DOI: https://doi.org/10.1002/art.39405
Showalter K, Hoffmann A, Rouleau G, Aaby D, Lee J, Richardson C, et al. Performance of forced vital capacity and lung diffusion cutpoints for associated radiographic interstitial lung disease in systemic sclerosis. J Rheumatol 2018; 45: 1572-6. DOI: https://doi.org/10.3899/jrheum.171362
Khanna D, Nagaraja V, Tseng CH, Abtin F, Suh R, Kim G, et al. Predictors of lung function decline in scleroderma-related interstitial lung disease based on high-resolution computed tomography: implications for cohort enrichment in systemic sclerosis-associated interstitial lung disease trials. Arthritis Res Ther 2015; 17: 372. DOI: https://doi.org/10.1186/s13075-015-0872-2
Cui H, Yuwen C, Jiang L, Xia Y, Zhang Y. Multiscale attention guided U-Net architecture for cardiac segmentation in short-axis MRI images. Comput Methods Programs Biomed 2021; 206: 106142. DOI: https://doi.org/10.1016/j.cmpb.2021.106142
Faust O, Hagiwara Y, Hong TJ, Lih OS, Acharya UR. Deep learning for healthcare applications based on physiological signals: a review. Comput Methods Programs Biomed 2018; 161: 1-13. DOI: https://doi.org/10.1016/j.cmpb.2018.04.005
Li C, Song X, Zhao H, Feng L, Hu T, Zhang Y, et al. An 8-layer residual U-Net with deep supervision for segmentation of the left ventricle in cardiac CT angiography. Comput Methods Programs Biomed 2021; 200: 105876. DOI: https://doi.org/10.1016/j.cmpb.2020.105876
Vahdani A. SICCS: SSc-ILD chest CT segmentation. Available from: https://doi.org/10.7910/DVN/3HNP33.
van den Hoogen F, Khanna D, Fransen J, Johnson SR, Baron M, Tyndall A, et al. 2013 classification criteria for systemic sclerosis: an American College of Rheumatology/European League against Rheumatism collaborative initiative. Arthritis Rheum 2013; 65: 2737-47. DOI: https://doi.org/10.1002/art.38098
National Institutes of Health. NIfTI: neuroimaging informatics technology initiative. Available from: https://nifti.nimh.nih.gov/.
Pizer SM, Johnston RE, Ericksen JP, Yankaskas BC, Muller KE. Contrast-limited adaptive histogram equalization: speed and effectiveness. First Conference on Visualization in Biomedical Computing, pp. 337-45. DOI: https://doi.org/10.1109/VBC.1990.109340
Salem N, Malik H, Shams A. Medical image enhancement based on histogram algorithms. Procedia Comput Sci 2019; 163: 300-11. DOI: https://doi.org/10.1016/j.procs.2019.12.112
Kikinis R, Pieper SD, Vosburgh KG. 3D slicer: a platform for subject-specific image analysis, visualization, and clinical support. In: Jolesz FA, ed. Intraoperative imaging and image-guided therapy. New York, NY: Springer New York; 2014. pp. 277-89. DOI: https://doi.org/10.1007/978-1-4614-7657-3_19
Bankier AA, MacMahon H, Colby T, Gevenois PA, Goo JM, Leung ANC, et al. Fleischner Society: glossary of terms for thoracic imaging. Radiology 2024; 310: e232558. DOI: https://doi.org/10.1148/radiol.232558
Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Cham; 2015. pp. 234-41. DOI: https://doi.org/10.1007/978-3-319-24574-4_28
Woo S, Debnath S, Hu R, Chen X, Liu Z, Kweon IS, et al. Convnext v2: co-designing and scaling convnets with masked autoencoders. IN: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 16133-42. DOI: https://doi.org/10.1109/CVPR52729.2023.01548
Lin TY, Goyal P, Girshick R, He K, Dollár P. Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp. 2980–2988.
Milletari F, Ahmadi SA, Kroll C, Plate A, Rozanski V, Maiostre J, et al. Hough-CNN: deep learning for segmentation of deep brain regions in MRI and ultrasound. Comput Vis Image Underst 2017; 164: 92-102. DOI: https://doi.org/10.1016/j.cviu.2017.04.002
Loshchilov I, Hutter F. Fixing weight decay regularization in adam. ArXiv 2017; abs/1711.05101.
Reddi SJ, Kale S, Kumar S. On the convergence of adam and beyond. arXiv; 2019: 1904.09237.
Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. Pytorch: an imperative style, high-performance deep learning library. Adv Neural Inf Process Syst 2019; 32.
Cardoso MJ, Li W, Brown R, Ma N, Kerfoot E, Wang Y, et al. Monai: an open-source framework for deep learning in healthcare. arXiv 2022; 2211.02701.
van der Walt S, Schönberger JL, Nunez-Iglesias J, Boulogne F, Warner JD, Yager N, et al., "scikit-image: image processing in Python. PeerJ 2014; 2: e453. DOI: https://doi.org/10.7717/peerj.453
Virtanen P, Gommers R, Oliphant TE, Haberland M, Reddy T, Cournapeau D, et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods 2020; 17: 261-72. DOI: https://doi.org/10.1038/s41592-020-0772-5
Chassagnon G, Vakalopoulou M, Régent A, Zacharaki EI, Aviram G, Martin C, et al. Deep Learning-based Approach for Automated Assessment of Interstitial Lung Disease in Systemic Sclerosis on CT images. Radiol Artif Intell 2020; 2: e190006. DOI: https://doi.org/10.1148/ryai.2020190006
Hoang-Thi TN, Vakalopoulou M, Christodoulidis S, Paragios N, Reve MPl, Chassagnon G. Deep learning for lung disease segmentation on CT: Which reconstruction kernel should be used? Diagn Interv Imaging 2021; 102: 691-5. DOI: https://doi.org/10.1016/j.diii.2021.10.001
Khomduean P, Phuaudomcharoen P, Boonchu T, Taetragool U, Chamchoy K, Wimolsiri N, et al. Segmentation of lung lobes and lesions in chest CT for the classification of COVID-19 severity. Sci Rep 2023; 13: 20899. DOI: https://doi.org/10.1038/s41598-023-47743-z
Brady D, Berkowitz EA, Sharma A, Ackman JB, Bernheim A, Chung M, et al. CT morphologic characteristics and variant patterns of interstitial pulmonary fibrosis in systemic lupus erythematosus. Radiol Cardiothorac Imaging 2021; 3: e200625. DOI: https://doi.org/10.1148/ryct.2021200625
Gruden JF. CT in idiopathic pulmonary fibrosis: diagnosis and beyond. Am J Roentgenol 2016; 206: 495-507. DOI: https://doi.org/10.2214/AJR.15.15674
Park J, Jung J, Yoon SH, Hong H, Kim H, Kim H, et al. CT quantification of the heterogeneity of fibrosis boundaries in idiopathic pulmonary fibrosis. Eur Radiol 2021; 31: 5148-59. DOI: https://doi.org/10.1007/s00330-020-07594-y
Humphries SM, Yagihashi K, Huckleberry J, Rho BH, Schroeder JD, Strand M, et al. Idiopathic pulmonary fibrosis: data-driven textural analysis of extent of fibrosis at baseline and 15-month follow-up. Radiology 2017; 285: 270-8. DOI: https://doi.org/10.1148/radiol.2017161177
Humphries SM, Swigris JJ, Brown KK, Strand M, Gong Q, Sundy JS, et al. Quantitative high-resolution computed tomography fibrosis score: performance characteristics in idiopathic pulmonary fibrosis. Eur Respir J 2018; 52: 1801384. DOI: https://doi.org/10.1183/13993003.01384-2018
Carvalho ARS, Guimarães AR, Sztajnbok FR, Souza Rodrigues R, Antunes Silva BR, Lopes AJ, et al. Automatic quantification of interstitial lung disease from chest computed tomography in systemic sclerosis. Front Med 2020; 7: 577739. DOI: https://doi.org/10.3389/fmed.2020.577739
Tashkin DP, Volkmann ER, Tseng CH, Kim HJ, Goldin J, Clements P, et al. Relationship between quantitative radiographic assessments of interstitial lung disease and physiological and clinical features of systemic sclerosis. Ann Rheum Dis 2016; 75: 374-81. DOI: https://doi.org/10.1136/annrheumdis-2014-206076
Ooi GC, Mok MY, Tsang KWT, WOng Y, Khong PL, Fung PCW, et al. Interstitial lung disease in systemic sclerosis. Acta Radiol 2003; 44: 258-64. DOI: https://doi.org/10.1080/j.1600-0455.2003.00058.x
Kim HG, Tashkin DP, Clements PJ, Li G, Brown MS, Elashoff R, et al. A computer-aided diagnosis system for quantitative scoring of extent of lung fibrosis in scleroderma patients. Clin Exp Rheumatol 2010; 28: S26-35.
Dixon G, Thould H, Wells M, Tsaneva-Atanasova K, Scotton CJ, Gibbons MA, et al. A systematic review of the role of quantitative CT in the prognostication and disease monitoring of interstitial lung disease. Eur Respir Rev 2025; 34: 240194. DOI: https://doi.org/10.1183/16000617.0194-2024
Volkmann ER, Tashkin DP, Leng M, Kim GHJ, Goldin J, Harui A, Roth MD. Biological correlates of radiological features of systemic sclerosis interstitial lung disease. ERJ Open Res 2025; 11: 00596-2024. DOI: https://doi.org/10.1183/23120541.00596-2024
Menze BH, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J. The multimodal brain tumor image segmentation benchmark. IEEE Trans Med Iimaging 2015; 34: 1993-2024. DOI: https://doi.org/10.1109/TMI.2014.2377694
Juvekar P, Dorent R, Kögl F, Torio E, Barr C, Rigolo L, et al. ReMIND: the brain resection multimodal imaging database. medRxiv 2024; 2023.09.14.23295596. DOI: https://doi.org/10.1101/2023.09.14.23295596
Halabi SS, Prevedello LM, Kalpathy-Cramer J, Mamonov AB, Bilbily A, Cicero M, et al. The RSNA Pediatric Bone Age Machine Learning Challenge. Radiology 2018; 290: 498-503. DOI: https://doi.org/10.1148/radiol.2018180736
de Lima Bastos A, de Amorim Corrêa R, Ferreira GA. Tomography patterns of lung disease in systemic sclerosis. Radiol Bras 2016; 49: 316-21. DOI: https://doi.org/10.1590/0100-3984.2015.0116
Landini N, Orlandi M, Bruni C, Carlesi E, Nardi C, Calistri L, et al. Computed tomography predictors of mortality or disease progression in systemic sclerosis-interstitial lung disease: a systematic review. Front Med 2022; 8: 807982. DOI: https://doi.org/10.3389/fmed.2021.807982
Simon BD, Ozyoruk KB, Gelikman DG, Harmon SA, Türkbey B. The future of multimodal artificial intelligence models for integrating imaging and clinical metadata: a narrative review. Diagn Interv Radiol 2025; 31: 303-12. DOI: https://doi.org/10.4274/dir.2024.242631
Hughes M, Bruni C, Cuomo G, Delle Sedie A, Gargani L, Gutierrez M, et al. The role of ultrasound in systemic sclerosis: On the cutting edge to foster clinical and research advancement. J Scleroderma Relat Disord 2021; 6: 123-32. DOI: https://doi.org/10.1177/2397198320970394
Ethics Approval
This study was conducted in accordance with ethical standards and relevant institutional guidelines. All procedures involving human participants were reviewed and approved by the Ethics Committee of Tehran University of Medical Sciences (approval code: IR.TUMS.MEDICINE.REC.1403.297) on 10/02/2024.How to Cite
1.
Computed tomography of interstitial lung disease in systemic sclerosis: dataset and deep learning model for pulmonary lesion segmentation. Reumatismo [Internet]. 2026 Feb. 25 [cited 2026 Jul. 29];78(1). Available from: https://www.reumatismo.org/reuma/article/view/1920
Copyright (c) 2026 the Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
