Improving 3D U-Net for Brain Tumor Segmentation by Utilizing Lesion Prior
Autor: | Kao, Po-Yu, Chen, Jefferson W., Manjunath, B. S. |
---|---|
Rok vydání: | 2019 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | 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. Comment: 5 pages, 4 figures, 1 table, LNCS format |
Databáze: | arXiv |
Externí odkaz: |