Detection and Classification of Gastrointestinal Diseases using Machine Learning

Background: Traditional endoscopy is an invasive and painful method of examining the gastrointestinal tract (GIT) not supported by physicians and patients. To handle this issue, video endoscopy (VE) or wireless capsule endoscopy (WCE) is recommended and utilized for GIT examination. Furthermore, manual assessment of captured images is not possible for an expert physician because it's a time taking task to analyze thousands of images thoroughly. Hence, there comes the need for a Computer-Aided-Diagnosis (CAD) method to help doctors analyze images. Many researchers have proposed techniques for automated recognition and classification of abnormality in captured images. Methods: In this article, existing methods for automated classification, segmentation and detection of several GI diseases are discussed. Paper gives a comprehensive detail about these state-of-the-art methods. Furthermore, literature is divided into several subsections based on preprocessing techniques, segmentation techniques, handcrafted features based techniques and deep learning based techniques. Finally, issues, challenges and limitations are also undertaken. Results: A comparative analysis of different approaches for the detection and classification of GI infections. Conclusion: This comprehensive review article combines information related to a number of GI diseases diagnosis methods at one place. This article will facilitate the researchers to develop new algorithms and approaches for early detection of GI diseases detection with more promising results as compared to the existing ones of literature.

Automated summary

This article discusses existing methods for automated classification, segmentation, and detection of several GI diseases, providing a comprehensive overview of state-of-the-art techniques. It divides the literature into subsections based on preprocessing techniques, segmentation techniques, handcrafted features, and deep learning techniques, while also addressing issues, challenges, and limitations.