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.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.acra.2021.05.014 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Predictive value of myositis antibodies: role of semiquantitative classification and positivity for more than one autoantibody.
RMD Open
January 2025
TYKS laboratories, Clinical Microbiology, Turku University Hospital, Turku, Finland.
Objectives: We assessed the positive predictive value (PPV) of 17 myositis antibodies for having a diagnosis of myositis and other myositis-spectrum conditions (interstitial lung disease (ILD), connective tissue diseases (CTD), malignancy) and evaluated the impact of semiquantitative classification and antibody overlap on the PPVs.
Materials And Methods: We retrospectively identified 1068 individuals ≥18 years who tested positive for ≥1 antibody in the EUROLINE myositis line blot assay or positive for anti-3-hydroxy-3-methylglutaryl-CoA reductase (HMGCR) in an ELISA-based test between 2015 and 2020 in 15 out of the 20 hospital districts in Finland. We extracted clinical diagnoses from the Care Register for Health Care between January 2013 and June 2022.
Pulmonary Arterial Hypertension Incidence in Scleroderma Patients Treated with Bosentan for Digital Ulcers: Evidence from the Italian SPRING Registry.
J Rheumatol
January 2025
Florenzo Iannone, Rheumatology Unit - Department of Precision and Regenerative Medicine of Jonian Area University of Bari, Bari, Italy.
Objective: Bosentan (BOS) is approved for treating pulmonary arterial hypertension (PAH) and preventing digital ulcers (DU) in systemic sclerosis (SSc). Our study aimed to evaluate whether BOS prescribed for DU could reduce the incidence of PAH in a large SSc cohort from the SPRING registry.
Methods: Patients with SSc from the SPRING registry, meeting ACR/EULAR 2013 classification criteria with data on PAH onset, DU status, BOS exposure, and at least a one-year follow-up between 2015 and 2020, and no known PAH at baseline were included.
Reclassification of the overlap syndrome of Behçet's disease and antineutrophil cytoplasmic antibody-associated vasculitis in patients with Behçet's disease.
Korean J Intern Med
January 2025
Division of Rheumatology, Department of Internal Medicine, Yonsei University College of Medicine, Seoul, Korea.
Background/aims: This study applied the 2022 American College of Rheumatology/European Alliance of Associations for Rheumatology (ACR/EULAR) criteria for antineutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV) to patients with Behçet's disease (BD) to investigate the proportion and clinical implications of the reclassification to the overlap syndrome of BD and AAV (OS-BD-AAV).
Methods: We included 280 BD patients presenting with ANCA positivity but without medical conditions mimicking AAV at diagnosis. Demographic data, items from the 2014 revised International Criteria for BD and 2022 American College of Rheumatology and European Alliance of Associations for Rheumatology criteria for AAV, ANCA positivity, and laboratory results were recorded as clinical data at diagnosis.
Development and validation of predictive factors influencing rheumatoid arthritis associated with interstitial lung disease.
Clin Rheumatol
December 2024
Longhua Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, Shanghai, 200032, China.
Objective: This study is aimed at identifying key risk factors associated with the onset of rheumatoid arthritis-associated interstitial lung disease (RA-ILD) and developing and validating a novel risk prediction model for RA-ILD.
Methods: This is a hospital-based retrospective cohort study. A total of 459 RA patients were selected from Longhua Hospital Affiliated with Shanghai University of Traditional Chinese Medicine between 2015 and 2020 as observation subjects.
Nailfold videocapillaroscopy findings and associations with organ involvement in mixed connective tissue disease.
Clin Exp Rheumatol
December 2024
Service de Rhumatologie, Hôpital Cochin, AP-HP Centre Université Paris Cité, Paris, and INSERM U1016, Institut Cochin, CNRS UMR8104, Paris, France.
Objectives: To investigate nailfold videocapillaroscopy (NVC) abnormalities in mixed connective tissue disease (MCTD).
Methods: Patients with MCTD followed at the Rheumatology Department in Cochin Hospital (Paris, France) were identified based on individual record review. Diagnosis of MCTD required fulfillment of one of the three sets of classification criteria.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!