Deep learning based intestine anatomical sections localization in colonoscopy

Accurate localization of intestinal anatomical sections is crucial for enhancing the efficacy of colonoscopy by enabling precise navigation and improved lesion detection. This study proposes a deep learning-based framework that integrates spatially robust models, DenseNet161 and YOLOv8m, with a temporal majority voting strategy via a sliding window mechanism. Experimental results demonstrate that this combined approach significantly improves classification stability and reduces frame-level noise, particularly in morphologically similar anatomical regions. The proposed window-threshold method effectively enhances temporal consistency, leading to substantial gains in segment-level accuracy. Notably, configurations such as DenseNet161 (5-3) and YOLOv8m (3-2) consistently achieved the lowest error rates across the test video. These findings establish a reliable and real-time solution for high-precision anatomical localization, underscoring the potential of integrating spatial and temporal modeling in automated gastrointestinal imaging systems.