Improving 3D U-Net for Brain Tumor Segmentation by Utilizing Lesion Prior
This incremental improvement addresses brain tumor segmentation for medical imaging applications.
The authors tackled brain tumor segmentation by integrating lesion prior heatmaps with a 3D U-Net, achieving improved performance over baseline methods and competitive results compared to state-of-the-art on a public benchmark dataset.
We propose a novel, simple and effective method to integrate lesion prior and a 3D U-Net for improving brain tumor segmentation. First, we utilize the ground-truth brain tumor lesions from a group of patients to generate the heatmaps of different types of lesions. These heatmaps are used to create the volume-of-interest (VOI) map which contains prior information about brain tumor lesions. The VOI map is then integrated with the multimodal MR images and input to a 3D U-Net for segmentation. The proposed method is evaluated on a public benchmark dataset, and the experimental results show that the proposed feature fusion method achieves an improvement over the baseline methods. In addition, our proposed method also achieves a competitive performance compared to state-of-the-art methods.