EUVIMEDDescoperă EUVIMED
Open access · CC BY 4.0

Deep‐Learning Algorithm Diagnostic Support for Usual Interstitial Pneumonia Pattern Recognition in Fibrotic Interstitial Lung Disease

Caitlin C Fermoyle iD, John A Mackintosh, Vidya Navaratnam iD, Samantha J Ellis, Wendy A Cooper, Nicole S L Goh iD, Yuben Moodley iD, Paul N Reynolds iD, Christopher J Zappala, Peter Hopkins, Ian N Glaspole iD, Tamera J Corte and 2 more

Respirology · 2026-07 · 31 (7) · 711-720

DOI: 10.1002/resp.70246 ↗

At a glance

Journal article in Respirology, published online on 2026-04-01. Written by Caitlin C Fermoyle and 13 co-authors. Institution: Faculty of Medicine and Health, University of Sydney, Sydney, Australia. Major MEDLINE topics: Deep Learning, Tomography, X-Ray Computed, Algorithms, Lung Diseases, Interstitial. Cited 3 times so far (Crossref); 36 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Health and Medical Research Council, Boehringer Ingelheim, Roche Products Pty. Limited, Lung Foundation Australia & the Centre of Research Excellence in Pulmonary Fibrosis (CRE-PF; CREATE HOPE Fellowship).

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Background and Objective High resolution computed tomography (HRCT) scan diagnostic classification for usual interstitial pneumonia (UIP) plays a critical role in therapeutic decision‐making and clinical trial eligibility for interstitial lung disease (ILD) patients, but is subject to variability. A deep learning algorithm, the Systematic Objective Fibrotic Imaging Analysis Algorithm (SOFIA), has been validated to assist classification of HRCTs based on current guidelines. In this study, we evaluate the impact of SOFIA on inter‐observer agreement for UIP classification and prognostic accuracy of clinicians' assessment of ILD HRCTs.

Methods

Radiologists and pulmonologists (reviewers) were invited to evaluate 203 HRCTs from a national fibrotic ILD registry, scoring each of four UIP categories (definite UIP, probable UIP, indeterminate, or alternative diagnosis). SOFIA outputs were then provided, and reviewers were able to reevaluate their scores. Changes in interobserver agreement for UIP classification and prognostic accuracy were calculated.

Results

Three hundred twelve reviewers (120 radiologists, 192 pulmonologists) from 49 countries evaluated 203 HRCT scans. Following SOFIA, inter‐observer diagnostic agreement improved for definite UIP from moderate to good (ICC pre = 0.54[0.50–0.60]; ICC post = 0.70[0.66–0.74]), and for probable UIP from fair to moderate (ICC pre = 0.30[0.27–0.35]; ICC post = 0.53[0.49–0.58]). Following SOFIA, there was improved prognostic accuracy for reviewers' definite UIP, probable UIP, and indeterminate scores (significant change in c‐index), and the proportion of reviewers whose probable UIP scores were significantly predictive of transplant‐free survival increased by 42%.

Conclusion

Providing SOFIA algorithm output to clinicians reviewing HRCT scans improved diagnostic agreement and prognostic accuracy for fibrotic ILD. SOFIA may be a useful automated assistive tool to support improved diagnostic consistency.

Subjects

MeSH terms (MEDLINE)

Deep LearningTomography, X-Ray ComputedAlgorithmsLung Diseases, InterstitialIdiopathic Pulmonary FibrosisHumansObserver VariationPrognosis

Author keywords

deep learningdisease progressionidiopathic pulmonary fibrosisradiologyusual interstitial pneumonia

Authors and institutions

  • Faculty of Medicine and Health, University of Sydney, Sydney, Australia.
  • Faculty of Medicine, University of Queensland, Brisbane, Australia.
  • Department of Respiratory Medicine, Sir Charles Gardiner Hospital, Perth, Australia.
  • Institute for Respiratory Health, University of Western Australia, Perth, Australia.
  • Department of Radiology, The Alfred Hospital, Melbourne, Australia.
  • Department of Surgery, School of Translational Medicine, Monash University, Melbourne, Australia.

ORCID profiles: Caitlin C Fermoyle, Vidya Navaratnam, Nicole S L Goh, Yuben Moodley, Paul N Reynolds, Ian N Glaspole

Funding

  • National Health and Medical Research Council
  • Boehringer Ingelheim, Roche Products Pty. Limited
  • Lung Foundation Australia & the Centre of Research Excellence in Pulmonary Fibrosis (CRE-PF; CREATE HOPE Fellowship)

Cite

APA

Fermoyle, C. C., Mackintosh, J. A., Navaratnam, V., Ellis, S. J., Cooper, W. A., Goh, N. S. L., Moodley, Y., Reynolds, P. N., Zappala, C. J., Hopkins, P., Glaspole, I. N., Corte, T. J., Walsh, S. L. F., & SOFIA Project Consortium (2026). Deep‐Learning Algorithm Diagnostic Support for Usual Interstitial Pneumonia Pattern Recognition in Fibrotic Interstitial Lung Disease. Respirology, 31(7), 711-720. https://doi.org/10.1002/resp.70246

Vancouver

Fermoyle CC, Mackintosh JA, Navaratnam V, Ellis SJ, Cooper WA, Goh NSL, et al. Deep‐Learning Algorithm Diagnostic Support for Usual Interstitial Pneumonia Pattern Recognition in Fibrotic Interstitial Lung Disease. Respirology. 2026;31(7):711-720. doi:10.1002/resp.70246

BibTeX
@article{Fermoyle2026,
  author = {Fermoyle, Caitlin C and Mackintosh, John A and Navaratnam, Vidya and Ellis, Samantha J and Cooper, Wendy A and Goh, Nicole S L and Moodley, Yuben and Reynolds, Paul N and Zappala, Christopher J and Hopkins, Peter and Glaspole, Ian N and Corte, Tamera J and Walsh, Simon L F and SOFIA Project Consortium, SOFIA Project Consortium},
  title = {Deep‐Learning Algorithm Diagnostic Support for Usual Interstitial Pneumonia Pattern Recognition in Fibrotic Interstitial Lung Disease},
  journal = {Respirology},
  year = {2026},
  volume = {31},
  number = {7},
  pages = {711--720},
  doi = {10.1002/resp.70246}
}
Start for free →