Augmenting Gastrointestinal Health: A Deep Learning Approach to Human Stool Recognition and Characterization in Macroscopic Images
This addresses the challenge of poor compliance and lack of objective measurements in bowel diaries for patients with functional bowel diseases like irritable bowel syndrome, chronic constipation, and chronic diarrhea.
The researchers tackled the problem of objectively measuring stool consistency in chronic gastrointestinal diseases by developing a deep learning-based stool detection and tracking system using computer vision and convolutional neural networks, aimed at improving assessment for patients, providers, and researchers.
Purpose - Functional bowel diseases, including irritable bowel syndrome, chronic constipation, and chronic diarrhea, are some of the most common diseases seen in clinical practice. Many patients describe a range of triggers for altered bowel consistency and symptoms. However, characterization of the relationship between symptom triggers using bowel diaries is hampered by poor compliance and lack of objective stool consistency measurements. We sought to develop a stool detection and tracking system using computer vision and deep convolutional neural networks (CNN) that could be used by patients, providers, and researchers in the assessment of chronic gastrointestinal (GI) disease.