A Cascaded Segmentation-Classification Deep Learning Framework for Preoperative Prediction of Occult Peritoneal Metastasis and Early Recurrence in Advanced Gastric Cancer.

Purpose: To develop a cascaded deep learning (DL) framework integrating tumor segmentation with metastatic risk stratification for preoperative prediction of occult peritoneal metastasis (OPM) in advanced gastric cancer (GC), and validate its generalizability for early peritoneal recurrence (PR) prediction.

Methods: This multicenter study enrolled 765 patients with advanced GC from three institutions. We developed a two-stage framework as follows: (1) V-Net-based tumor segmentation on CT; (2) DL-based metastatic risk classification using segmented tumor regions.

A novel deletion in KRT75L4 mediates the frizzle trait in a Chinese indigenous chicken.

Background: Highly diversified in morphology and structure, feathers have evolved into various forms. Frizzle feathers, which result from a developmental defect of the feather, are observed in several domestic chicken breeds. The frizzle phenotype is consistent with incomplete dominance of a major gene, but the molecular mechanisms that underlie this phenotype remain obscure.