A Comprehensive Survey of Deep Learning Methods in Gastro‐Intestinal Wireless Capsule Endoscopy Images

ABSTRACT The increasing prevalence of gastrointestinal (GI) disorders necessitates the development of effective diagnostic tools. The major drawback is that it takes longer and generates a lot of images that need to be examined by a doctor. To categorize GI tract disorders and speed up processing, numerous deep‐learning (DL) models and image‐processing methods have been created recently. But, there is no research focusing on surveying the GI disorders detection in wireless capsule endoscopy (WCE) images. Hence, this survey is conducted to evaluate the role of DL techniques in improving the study of WCE images, which provide a non‐invasive means of categorizing different GI tract disorders. Together with DL‐based methods, this survey gives a detailed picture of the methods utilized to detect GI diseases. Additionally, this survey emphasizes comparative analysis to demonstrate the efficacy of different GI anomaly detecting methods under DL approaches. Moreover, surveying existing methodologies and their applications, this study aims to identify gaps in research and provide future directions to overcome the existing impact of various techniques in GI disease detection. This article is categorized under: Application Areas > Health Care Technologies > Artificial Intelligence