Related Experiment Video
Updated: Jul 10, 2025
Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
Published on: July 28, 2013
Diffusion MRI anomaly detection in glioma patients
Leon Weninger1,2, Jarek Ecke2, Kerstin Jütten3
1Department of Psychiatry, Psychotherapy and Psychosomatics, RWTH Aachen University, Aachen, Germany.
Abstract:
Diffusion-MRI (dMRI) 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 relies on conventional MRI-techniques, which are, however, known to underestimate tumor volumes in diffusely infiltrating glioma. We hypothesized that dMRI 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 dMRI 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 data, which were not visible at the initial time of recording. Anomaly-detection methods are suitable for tumor delineation in dMRI 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.
Insights
Deep learning models using diffusion MRI can detect subtle brain tumor infiltration missed by conventional methods. This anomaly detection approach shows promise for improved glioma diagnosis and treatment planning.
Area of Science:
- Neuroimaging
- Artificial Intelligence
- Oncology
Background:
- Conventional MRI often underestimates glioma tumor volumes due to diffuse infiltration.
- Diffusion MRI (dMRI) offers insights into brain microstructural properties altered by gliomas.
Purpose of the Study:
- To evaluate deep learning-based diffusion anomaly detection for glioma delineation.
- To assess the potential of dMRI for identifying occult tumor infiltration.
Main Methods:
- Developed two deep learning architectures (denoising autoencoder, reconstruction-discrimination network) trained on healthy dMRI data.
- Applied models to glioma patient data and validated against groundtruth segmentations derived from structural MRI.
- Utilized a modified supervised segmentation network for generating groundtruth tumor volumes.
Main Results:
- Achieved a Dice score of 0.67 ± 0.2 when comparing diffusion anomaly detection to groundtruth segmentations.
- Identified diffusion-anomalous regions that corresponded to lesions visible only in later structural MRI follow-up.
- Demonstrated that anomaly detection can identify occult tumor infiltration not apparent in initial scans.
Conclusions:
- Anomaly-detection methods applied to dMRI are effective for brain tumor delineation.
- These methods can enhance glioma imaging analysis by detecting hidden tumor infiltration.
- Improved detection may lead to better prognostication and treatment strategies for glioma patients.
