High-resolution manometry has been the gold standard for examining human colon motility, but this method has significant drawbacks, including high costs, lengthy procedures, and patient discomfort. This has led us to explore ultrasonography as a potential alternative. We discovered that conventional machine-learning techniques for segmenting gut walls have been hindered by tracking errors. The present study introduces an innovative approach for monitoring and segmenting colonic walls in ultrasound videos by combining advanced computer vision techniques with U-Net models. The approach involved training a deep-learning U-Net model specifically for intestinal wall segmentation by manually preparing the dataset. Once trained, the model segments and analyzes colonic walls in real-time ultrasound videos, generating spatiotemporal contraction maps and content flow analyses. The method was validated using patient and volunteer data, achieving high Intersection over Union (IoU) scores. The U-Net model demonstrated superior performance to traditional machine learning techniques in tracking colonic walls, even in low-resolution videos. This work showcases how deep learning models can enhance the accuracy and reliability of colonic motility studies using ultrasound, paving the way for more efficient and patientfriendly diagnostic methods.