Shelly Soffer1, Adam S Morgenthau2, Orit Shimon3, Yiftach Barash4, Eli Konen5, Benjamin S Glicksberg6, Eyal Klang7. 1. Internal Medicine B, Assuta Medical Center, Ashdod, Israel, and Ben-Gurion University of the Negev, Be'er Sheva, Israel; DeepVision Lab, Sheba Medical Center, Tel Hashomer, Israel. Electronic address: soffer.shelly@gmail.com. 2. Department of Medicine, Division of Pulmonary, Critical Care, and Sleep Medicine, Icahn School of Medicine at Mount Sinai, New York, New York. 3. Department of Anesthesia, Rabin Medical Center, Beilinson Hospital, Petach Tikvah, Israel, and Sackler Medical School, Tel Aviv University, Tel Aviv, Israel. 4. DeepVision Lab, Sheba Medical Center, Tel Hashomer, Israel; Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel, and Sackler Medical School, Tel Aviv University, Tel Aviv, Israel. 5. Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel, and Sackler Medical School, Tel Aviv University, Tel Aviv, Israel. 6. Hasso Plattner Institute for Digital Health at Mount Sinai, Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York. 7. DeepVision Lab, Sheba Medical Center, Tel Hashomer, Israel; Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel, and Sackler Medical School, Tel Aviv University, Tel Aviv, Israel; Institute for Healthcare Delivery Science, Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, New York.
Abstract
RATIONALE AND OBJECTIVES: High-resolution computed tomography (HRCT) is paramount in the assessment of interstitial lung disease (ILD). Yet, HRCT interpretation of ILDs may be hampered by inter- and intra-observer variability. Recently, artificial intelligence (AI) has revolutionized medical image analysis. This technology has the potential to advance patient care in ILD. We aimed to systematically evaluate the application of AI for the analysis of ILD in HRCT. MATERIALS AND METHODS: We searched MEDLINE/PubMed databases for original publications of deep learning for ILD analysis on chest CT. The search included studies published up to March 1, 2021. The risk of bias evaluation included tailored Quality Assessment of Diagnostic Accuracy Studies and the modified Joanna Briggs Institute Critical Appraisal checklist. RESULTS: Data was extracted from 19 retrospective studies. Deep learning techniques included detection, segmentation, and classification of ILD on HRCT. Most studies focused on the classification of ILD into different morphological patterns. Accuracies of 78%-91% were achieved. Two studies demonstrated near-expert performance for the diagnosis of idiopathic pulmonary fibrosis (IPF). The Quality Assessment of Diagnostic Accuracy Studies tool identified a high risk of bias in 15/19 (78.9%) of the studies. CONCLUSION: AI has the potential to contribute to the radiologic diagnosis and classification of ILD. However, the accuracy performance is still not satisfactory, and research is limited by a small number of retrospective studies. Hence, the existing published data may not be sufficiently reliable. Only well-designed prospective controlled studies can accurately assess the value of existing AI tools for ILD evaluation.
RATIONALE AND OBJECTIVES: High-resolution computed tomography (HRCT) is paramount in the assessment of interstitial lung disease (ILD). Yet, HRCT interpretation of ILDs may be hampered by inter- and intra-observer variability. Recently, artificial intelligence (AI) has revolutionized medical image analysis. This technology has the potential to advance patient care in ILD. We aimed to systematically evaluate the application of AI for the analysis of ILD in HRCT. MATERIALS AND METHODS: We searched MEDLINE/PubMed databases for original publications of deep learning for ILD analysis on chest CT. The search included studies published up to March 1, 2021. The risk of bias evaluation included tailored Quality Assessment of Diagnostic Accuracy Studies and the modified Joanna Briggs Institute Critical Appraisal checklist. RESULTS: Data was extracted from 19 retrospective studies. Deep learning techniques included detection, segmentation, and classification of ILD on HRCT. Most studies focused on the classification of ILD into different morphological patterns. Accuracies of 78%-91% were achieved. Two studies demonstrated near-expert performance for the diagnosis of idiopathic pulmonary fibrosis (IPF). The Quality Assessment of Diagnostic Accuracy Studies tool identified a high risk of bias in 15/19 (78.9%) of the studies. CONCLUSION: AI has the potential to contribute to the radiologic diagnosis and classification of ILD. However, the accuracy performance is still not satisfactory, and research is limited by a small number of retrospective studies. Hence, the existing published data may not be sufficiently reliable. Only well-designed prospective controlled studies can accurately assess the value of existing AI tools for ILD evaluation.
Authors: Stijn E Verleden; Peter Braubach; Christopher Werlein; Edith Plucinski; Mark P Kuhnel; Annemiek Snoeckx; Haroun El Addouli; Tobias Welte; Axel Haverich; Florian P Laenger; Sabine Dettmer; Patrick Pauwels; Veronique Verplancke; Paul E Van Schil; Therese Lapperre; Johanna M Kwakkel-Van-Erp; Maximilian Ackermann; Jeroen M H Hendriks; Danny Jonigk Journal: Front Med (Lausanne) Date: 2022-03-16