Biophysics Informed Pathological Regularisation for Brain Tumour Segmentation
This addresses the lack of confidence and robustness in brain tumor segmentation for medical imaging applications, though it appears incremental as it builds on existing deep learning methods with added regularization.
The paper tackles the problem of brain tumor segmentation by integrating biophysical tumor growth PDE models as regularization with deep learning, achieving significant improvements in precision and reliability on the BraTS 2023 dataset.
Recent advances in deep learning have significantly improved brain tumour segmentation techniques; however, the results still lack confidence and robustness as they solely consider image data without biophysical priors or pathological information. Integrating biophysics-informed regularisation is one effective way to change this situation, as it provides an prior regularisation for automated end-to-end learning. In this paper, we propose a novel approach that designs brain tumour growth Partial Differential Equation (PDE) models as a regularisation with deep learning, operational with any network model. Our method introduces tumour growth PDE models directly into the segmentation process, improving accuracy and robustness, especially in data-scarce scenarios. This system estimates tumour cell density using a periodic activation function. By effectively integrating this estimation with biophysical models, we achieve better capture of tumour characteristics. This approach not only aligns the segmentation closer to actual biological behaviour but also strengthens the model's performance under limited data conditions. We demonstrate the effectiveness of our framework through extensive experiments on the BraTS 2023 dataset, showcasing significant improvements in both precision and reliability of tumour segmentation.