Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multimodal classification of Radiation-Induced Contrast Enhancements and tumor recurrence using deep learning

Robin Peretzke, Marlin Hanstein, Maximilian Fischer, Lars Badhi Wessel, Obada Alhalabi, Sebastian Regnery, Andreas Kudak, Maximilian Deng, Tanja Eichkorn, Philipp Hoegen Saßmannshausen, Fabian Allmendinger, Jan-Hendrik Bolten, Philipp Schröter, Christine Jungk, Jürgen Peter Debus, Peter Neher, Laila König, Klaus Maier-Hein

Abstract

The differentiation between tumor recurrence and radiation-induced contrast enhancements in post-treatment glioblastoma patients remains a major clinical challenge. Existing approaches rely on clinically sparsely available diffusion MRI or do not consider radiation maps, which are gaining increasing interest in the tumor board for this differentiation. We introduce RICE-NET, a multimodal 3D deep learning model that integrates longitudinal MRI data with radiotherapy dose distributions for automated lesion classification using conventional T1-weighted MRI data. Using a cohort of 92 patients, the model achieved an F1 score of 0.92 on an independent test set. During extensive ablation experiments, we quantified the contribution of each timepoint and modality and showed that reliable classification largely depends on the radiation map. Occlusion-based interpretability analyses further confirmed the model's focus on clinically relevant regions. These findings highlight the potential of multimodal deep learning to enhance diagnostic accuracy and support clinical decision-making in neuro-oncology.

Multimodal classification of Radiation-Induced Contrast Enhancements and tumor recurrence using deep learning

Abstract

The differentiation between tumor recurrence and radiation-induced contrast enhancements in post-treatment glioblastoma patients remains a major clinical challenge. Existing approaches rely on clinically sparsely available diffusion MRI or do not consider radiation maps, which are gaining increasing interest in the tumor board for this differentiation. We introduce RICE-NET, a multimodal 3D deep learning model that integrates longitudinal MRI data with radiotherapy dose distributions for automated lesion classification using conventional T1-weighted MRI data. Using a cohort of 92 patients, the model achieved an F1 score of 0.92 on an independent test set. During extensive ablation experiments, we quantified the contribution of each timepoint and modality and showed that reliable classification largely depends on the radiation map. Occlusion-based interpretability analyses further confirmed the model's focus on clinically relevant regions. These findings highlight the potential of multimodal deep learning to enhance diagnostic accuracy and support clinical decision-making in neuro-oncology.
Paper Structure (7 sections, 3 figures)

This paper contains 7 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Dataset Description
  4. Deep Learning Architecture
  5. Experimental Setup
  6. Results
  7. Discussion

Figures (3)

  • Figure 1.1: Axial slice of sample subject with tumor recurrence. On the left, the post-operative MRI with the resection area highlighted with a red circle. The middle image shows the new progression, which is to be classified as recurrence or RICE. On the right, the radiation treatment plan is displayed, with the isocenter positioned in the region of the resection cavity.
  • Figure 1.2: F1 Macro after 800 training epochs on validation data (striped) aggregated across all folds and majority vote on the test data (dotted) by input volume combinations with cross validation standard deviation as error bars.
  • Figure 1.3: Occlusion visualization with RICE overlaid over all three inputs.