Diffusion MRI Anomaly Detection in Glioma Patients

Research Square

Abstract

Abstract Diffusion-MRI measures molecular diffusion, which allows to characterize microstructural properties of the human brain. Gliomas strongly alter these microstructural properties. Delineation of brain tumors currently mainly rely on conventional MRI-techniques, which are known to underestimate tumor volumes in diffusely infiltrating glioma. We hypothesized that diffusion-MRI is well suited for tumor delineation and developed two different deep learning approaches. The first diffusion anomaly detection architecture is a denoising autoencoder, the second consists of a reconstruction and a discrimination network. Each model was exclusively trained on non-annotated diffusion-MRI of healthy subjects and then applied on glioma patients´ data. To validate these models, a state-of-the-art supervised tumor segmentation network was modified to generate groundtruth tumor volumes based on structural-MRI. Compared to groundtruth segmentations, a dice score of 0.67 ± 0.2 was obtained. Further inspecting mismatches between diffusion-anomalous regions and groundtruth segmentations revealed, that these colocalized with lesions delineated only later on in structural-MRI follow-up scans, but which were not visible at the time of recording. Anomaly- detection methods are suitable for tumor delineation in diffusion-MRI acquisitions and may further enhance brain imaging analysis by detection of occult tumor infiltration in glioma patients, which could improve prognostication of disease evolution and tumor treatment strategies.

Authors 6

1. Leon Weninger Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

2. Jarek Ecke Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

3. Kerstin Jütten Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

4. Hans Clusmann Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

5. Martin Wiesmann Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

6. Dorit Merhof

   University of Regensburg

   Affiliation as printed

   University of Regensburg