Spatio-temporal classification for polyp diagnosis

Abstract

Colonoscopy remains the gold standard investigation for colorectal cancer screening as it offers the opportunity to both detect and resect pre-cancerous polyps. Computer-aided polyp characterisation can determine which polyps need polypectomy and recent deep learning-based approaches have shown promising results as clinical decision support tools. Yet polyp appearance during a procedure can vary, making automatic predictions unstable. In this paper, we investigate the use of spatio-temporal information to improve the performance of lesions classification as adenoma or non-adenoma. Two methods are implemented showing an increase in performance and robustness during extensive experiments both on internal and openly available benchmark datasets.

PolyDSS: computer-aided decision support system for multiclass polyp segmentation and classification using deep learning

“…These systems have the capacity to analyze complex data and provide real-time line guidance. A significant role is played by computeraided diagnosis (CADx), a medical imaging and diagnosis technology, particularly in colonoscopy [7]. Using machine learning and deep learning methods, CADx helps medical professionals analyze anomalies or possible diseases in images such as colonoscopy images [8].…”