MFG-Seg: multi-level feature guide segmentation framework in endoscopy via dual-decoder fusion strategy

Endoscopy-based lesion segmentation is essential for the early detection of neoplastic lesions. Framed as a dense-prediction task on high-resolution mucosal panoramas, its automated and precise contouring alleviates clinicians’ real-time cognitive burden, while yielding quantitative biomarkers to stratify patient risk and guide subsequent therapeutic strategies. However, three key challenges persist in current methods: (1) multi-scale confusion due to diverse lesion morphologies that resemble su