Tumor Location-weighted MRI-Report Contrastive Learning: A Framework for Improving the Explainability of Pediatric Brain Tumor Diagnosis
This addresses the need for more interpretable AI tools in pediatric brain tumor diagnosis, though it appears incremental as it builds on existing multimodal contrastive learning approaches.
The paper tackles the problem of limited clinical adoption of CNN-based brain tumor diagnosis due to lack of explainability by integrating MRI scans, radiology reports, and tumor location in a contrastive learning framework, achieving a Dice score of 31.1% for explainability and 87.7% classification accuracy for pediatric Low-grade Glioma.
Despite the promising performance of convolutional neural networks (CNNs) in brain tumor diagnosis from magnetic resonance imaging (MRI), their integration into the clinical workflow has been limited. That is mainly due to the fact that the features contributing to a model's prediction are unclear to radiologists and hence, clinically irrelevant, i.e., lack of explainability. As the invaluable sources of radiologists' knowledge and expertise, radiology reports can be integrated with MRI in a contrastive learning (CL) framework, enabling learning from image-report associations, to improve CNN explainability. In this work, we train a multimodal CL architecture on 3D brain MRI scans and radiology reports to learn informative MRI representations. Furthermore, we integrate tumor location, salient to several brain tumor analysis tasks, into this framework to improve its generalizability. We then apply the learnt image representations to improve explainability and performance of genetic marker classification of pediatric Low-grade Glioma, the most prevalent brain tumor in children, as a downstream task. Our results indicate a Dice score of 31.1% between the model's attention maps and manual tumor segmentation (as an explainability measure) with test classification performance of 87.7%, significantly outperforming the baselines. These enhancements can build trust in our model among radiologists, facilitating its integration into clinical practices for more efficient tumor diagnosis.