Reproduce “Deep Learning for Cervical Cytology Screening: Methods, Algorithms, Challenges and Prospects” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Jiang Yangbo, Zheng Nenggan

The review organizes cervical-cytology AI by cell, patch, and whole-slide scale, task, and supervision. It compares slide-level confidence aggregation with cell detection and Bethesda classification. Smart-CCS reported AUCs of 0.965 internally, 0.950 externally, and 0.947–0.986 prospectively; assisted reading gained 14.3 percentage points in sensitivity. Evidence remains limited by a one-country trial and no standardized public multi-centre WSI benchmark.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.