Chest radiographs and machine learning – Past, present and future. Issue 5 (25th June 2021)

• Record Type: Journal Article
• Authors: Jones, Catherine M; Buchlak, Quinlan D; Oakden‐Rayner, Luke; Milne, Michael; Seah, Jarrel; Esmaili, Nazanin; Hachey, Ben
• Is Part Of: Journal of medical imaging and radiation oncology. Volume 65:Issue 5(2021)
• Page Start: 538
• Page End: 544
• Publication Date: 2021-06-25
• Subjects: chest X‐ray -- clinical decision support -- deep learning -- machine learning -- radiomics; Radiology, Medical -- Periodicals; Radiology, Medical -- Australasia -- Periodicals; 616.0757
• DOI: 10.1111/1754-9485.13274
• Languages: English
• ISSNs: 1754-9477

Abstract

Summary: Despite its simple acquisition technique, the chest X‐ray remains the most common first‐line imaging tool for chest assessment globally. Recent evidence for image analysis using modern machine learning points to possible improvements in both the efficiency and the accuracy of chest X‐ray interpretation. While promising, these machine learning algorithms have not provided comprehensive assessment of findings in an image and do not account for clinical history or other relevant clinical information. However, the rapid evolution in technology and evidence base for its use suggests that the next generation of comprehensive, well‐tested machine learning algorithms will be a revolution akin to early advances in X‐ray technology. Current use cases, strengths, limitations and applications of chest X‐ray machine learning systems are discussed.