%0 Journal Article
%A Salome, Patrick
%A Sforazzini, Francesco
%A Grugnara, Gianluca
%A Kudak, Andreas
%A Dostal, Matthias
%A Herold-Mende, Christel
%A Heiland, Sabine
%A Debus, Jürgen
%A Abdollahi, Amir
%A Knoll, Maximilian
%T MR-Class: A Python Tool for Brain MR Image Classification Utilizing One-vs-All DCNNs to Deal with the Open-Set Recognition Problem.
%J Cancers
%V 15
%N 6
%@ 2072-6694
%C Basel
%I MDPI
%M DKFZ-2023-00633
%P 1820
%D 2023
%Z #EA:E210#LA:E210#
%X MR image classification in datasets collected from multiple sources is complicated by inconsistent and missing DICOM metadata. Therefore, we aimed to establish a method for the efficient automatic classification of MR brain sequences.Deep convolutional neural networks (DCNN) were trained as one-vs-all classifiers to differentiate between six classes: T1 weighted (w), contrast-enhanced T1w, T2w, T2w-FLAIR, ADC, and SWI. Each classifier yields a probability, allowing threshold-based and relative probability assignment while excluding images with low probability (label: unknown, open-set recognition problem). Data from three high-grade glioma (HGG) cohorts was assessed; C1 (320 patients, 20,101 MRI images) was used for training, while C2 (197, 11,333) and C3 (256, 3522) were for testing. Two raters manually checked images through an interactive labeling tool. Finally, MR-Class' added value was evaluated via radiomics model performance for progression-free survival (PFS) prediction in C2, utilizing the concordance index (C-I).Approximately 10
%K artificial intelligence (AI) (Other)
%K content-based image classification (Other)
%K convolutional neural networks (CNN) (Other)
%K data curation and preparation (Other)
%K deep learning (Other)
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:36980707
%R 10.3390/cancers15061820
%U https://inrepo02.dkfz.de/record/274490