Reproduce “SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imaging” 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

Meng Lou, Hanning Ying, Xiaoqing Liu, Hong-Yu Zhou, Yuqing Zhang, Yizhou Yu

SDR-Former classifies liver lesions from CT and MR scans. It applies a shared-weight encoder separately to each phase, then uses cross-resolution integration and learned phase weighting to combine features. On a three-phase CT test set of 622 lesions from an independent hospital, it achieved accuracy of 0.8537, versus 0.8344 for SNN-H2Former; this is not a prospective clinical study.

Summary by alphaXiv.

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