lgg_regrowth: Biologically conditioned deep learning for glioma growth prediction

Read full text Summarise with VIRAT
Authors: Max Wartha, Petra Böhm, Baran Atli, Matthias Gmeiner, Martin Aichholzer, Carlo Serra, Michael Sonnberger, Nico Stroh, Stefan Aspalter, Kathrin Aufschnaiter-Hießböck, Tobias Rossmann, Annette Leibetseder
+7 more Josef Pichler, Wolfgang Thomae, Theresa Wculek, Christian Dorfer, Andreas Gruber, Harald Stefanits, Philip Rauch
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Training, evaluation, and inference code for a biologically conditioned 3D U-Net that predicts diffuse lower-grade glioma growth patterns by integrating IDH mutation status, histological subtype, and cortical architecture type via Feature-wise Linear Modulation (FiLM). The repository also contains the scripts for the external validation on the UCSF-ALPTDG dataset against a no-change reference.

Fields of Study & Subjects

Brain Tumor Detection and Classification Radiomics and Machine Learning in Medical Imaging Glioma Diagnosis and Treatment

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
28 March 2026
Language
EN