Deep learning in gastric tissue diseases: a systematic review

• Published in: BMJ open gastroenterology Vol. 7; no. 1; p. e000371
• Main Authors: Gonçalves, Wanderson Gonçalves e, Santos, Marcelo Henrique de Paula dos, Lobato, Fábio Manoel França, Ribeiro-dos-Santos, Ândrea, Araújo, Gilderlanio Santana de
• Format: Journal Article
• Language: English
• Published: England BMJ Publishing Group Ltd 26-03-2020; BMJ Publishing Group LTD; BMJ Publishing Group
• Subjects: Bibliographic literature; Deep Learning; Gastric Cancer; gastric diseases; Gastritis; Health informatics; Humans; image analysis; Library collections; Machine learning; medical decision analysis; Medical imaging; Neural networks; Precision medicine; Radiography; Radiology; Reproducibility of Results; Software; Studies; Systematic review; gastric diseases; image analysis; medical decision analysis
• ISSN: 2054-4774; 2054-4774
• DOI: 10.1136/bmjgast-2019-000371

BackgroundIn recent years, deep learning has gained remarkable attention in medical image analysis due to its capacity to provide results comparable to specialists and, in some cases, surpass them. Despite the emergence of deep learning research on gastric tissues diseases, few intensive reviews are addressing this topic.MethodWe performed a systematic review related to applications of deep learning in gastric tissue disease analysis by digital histology, endoscopy and radiology images.ConclusionsThis review highlighted the high potential and shortcomings in deep learning research studies applied to gastric cancer, ulcer, gastritis and non-malignant diseases. Our results demonstrate the effectiveness of gastric tissue analysis by deep learning applications. Moreover, we also identified gaps of evaluation metrics, and image collection availability, therefore, impacting experimental reproducibility.