AI model accurately detects rectal tumor regrowth from endoscopy images

Researchers have developed a novel Siamese Swin Transformer with Dual Cross-Attention (SSDCA) designed to detect local regrowth of rectal tumors from endoscopic images. This model analyzes sequential images from patients undergoing watch-and-wait surveillance after neoadjuvant treatment. SSDCA demonstrated superior performance in distinguishing complete response from local regrowth, achieving an 81.76% balanced accuracy and showing robustness against common imaging artifacts. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT This model could improve early detection of rectal tumor regrowth, potentially enhancing patient care and outcomes in watch-and-wait surveillance protocols.

RANK_REASON This is a research paper detailing a new model for medical image analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• Swin Transformer
• Dual Cross-Attention
• SSDCA
• arXiv
• rectal cancer
• endoscopy

• paper
• other