3D Semantic Segmentation of Brain Tumor for Overall Survival Prediction
This work addresses glioma segmentation and survival prediction for medical applications, but it is incremental as it builds on existing deep learning methods.
The paper tackles 3D semantic segmentation of brain tumors to predict patient overall survival, achieving dice scores of 0.74, 0.88, and 0.73 for enhancing tumor, whole tumor, and tumor core, and a survival prediction accuracy of 44.8% on the validation set.
Glioma, the malignant brain tumor, requires immediate treatment to improve the survival of patients. Gliomas heterogeneous nature makes the segmentation difficult, especially for sub-regions like necrosis, enhancing tumor, non-enhancing tumor, and Edema. Deep neural networks like full convolution neural networks and ensemble of fully convolution neural networks are successful for Glioma segmentation. The paper demonstrates the use of a 3D fully convolution neural network with a three layer encoder decoder approach for layer arrangement. The encoder blocks include the dense modules, and decoder blocks include convolution modules. The input to the network is 3D patches. The loss function combines dice loss and focal loss functions. The validation set dice score of the network is 0.74, 0.88, and 0.73 for enhancing tumor, whole tumor, and tumor core, respectively. The Random Forest Regressor uses shape, volumetric, and age features extracted from ground truth for overall survival prediction. The regressor achieves an accuracy of 44.8% on the validation set.