Reproduce “Reference Manual of MEDiml” 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
Mahdi Ait Lhaj Loutfi, Simon Provost, Élodie Gillard, Moustafa Amine Bezzahi, Alexander Chum, Ben Coull-Nveu, Duran Juan, Mariem Kallel and 8 more
MEDiml provides a graphical desktop interface and Python package for radiomics analysis. It compares feature sets of increasing complexity rather than assuming larger sets perform better. Across five binary classification tasks, selected feature families varied by task. For renal CT subtype classification, a 15-feature intensity model achieved an AUC of 0.82, rising to 0.86 after ROI re-segmentation adjustment. Generalizability across populations and imaging protocols remains unestablished.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.