Digital Technology and the Future of Interstitial Lung Diseases 2 Machine learning in radiology: the new frontier in interstitial lung diseases

被引：51

作者：

Barnes, Hayley ^{[1
,2
,3
]}

Humphries, Stephen M. ^{[4
]}

George, Peter M. ^{[5
,6
]}

Assayag, Deborah ^{[7
]}

Glaspole, Ian ^{[1
,2
]}

Mackintosh, John A. ^{[8
]}

Corte, Tamera J. ^{[9
,10
]}

Glassberg, Marilyn ^{[11
]}

Johannson, Kerri A. ^{[12
]}

Calandriello, Lucio ^{[13
]}

Felder, Federico ^{[6
]}

Wells, Athol ^{[5
,6
]}

Walsh, Simon ^{[6
]}

机构：

[1] Alfred Hlth, Dept Resp Med, Alfred, Vic, Australia

[2] Monash Univ, Cent Clin Sch, Melbourne, Vic, Australia

[3] Monash Univ, Ctr Occupat & Environm Hlth, Melbourne, Vic, Australia

[4] Natl Jewish Hlth, Dept Radiol, Denver, CO USA

[5] Royal Brompton & Harefield Hosp, Interstitial Lung Dis Unit, London, England

[6] Imperial Coll London, Natl Heart & Lung Inst, London, England

[7] McGill Univ, Dept Med, Montreal, PQ, Canada

[8] Prince Charles Hosp, Dept ofThorac Med, Brisbane, Qld, Australia

[9] Royal Prince Alfred Hosp, Dept Resp Med, Sydney, NSW, Australia

[10] Univ Sydney, Cent Clin Sch, Sydney, NSW, Australia

[11] Univ Arizona, Coll Med Phoenix, Div Pulm Crit Care & Sleep Med, Phoenix, AR USA

[12] Univ Calgary, Dept Med, Calgary, AB, Canada

[13] Fdn Policlin Univ Gemelli, IRCCS, Dept Diagnost Imaging Oncol Radiotherapy & Haemat, Rome, Italy

来源：

LANCET DIGITAL HEALTH | 2023年 / 5卷 / 01期

关键词：

IDIOPATHIC PULMONARY-FIBROSIS; QUANTITATIVE CT INDEXES; COMPUTED-TOMOGRAPHY; PATTERNS; CLASSIFICATION; ABNORMALITIES; PIRFENIDONE; ASSOCIATION; PROGRESSION; PREDICTION;

D O I：

10.1016/S2589-7500(22)00230-8

中图分类号：

R-058 [];

学科分类号：

摘要：

Challenges for the effective management of interstitial lung diseases (ILDs) include difficulties with the early detection of disease, accurate prognostication with baseline data, and accurate and precise response to therapy. The purpose of this Review is to describe the clinical and research gaps in the diagnosis and prognosis of ILD, and how machine learning can be applied to image biomarker research to close these gaps. Machine-learning algorithms can identify ILD in at-risk populations, predict the extent of lung fibrosis, correlate radiological abnormalities with lung function decline, and be used as endpoints in treatment trials, exemplifying how this technology can be used in care for people with ILD. Advances in image processing and analysis provide further opportunities to use machine learning that incorporates deep-learning-based image analysis and radiomics. Collaboration and consistency are required to develop optimal algorithms, and candidate radiological biomarkers should be validated against appropriate predictors of disease outcomes.

引用

页码：E41 / E50

页数：10

共 85 条

[1] Deep learning for screening of interstitial lung disease patterns in high-resolution CT images [J].