Segmentation of liver tumor using efficient global optimal tree metrics graph cuts
MICCAI'11 Proceedings of the Third international conference on Abdominal Imaging: computational and Clinical Applications
| Hi-index | 0.00 |
In this paper, we propose a novel machine learning approach for locating boundaries of liver tumors in CT (Computed Tomography) images. Given a marker indicating a rough location of a tumor, the proposed solution locates its boundary. Our approach consists of training process and locating process. In training process, we train AdaBoosted histogram classifiers to classify true boundary positions and false ones on the 1-D intensity profiles of tumor regions. In locating process, we locate the boundaries by using the trained AdaBoosted histogram classifiers. The novelty of our approach is that we use AdaBoost in the training process to learn diverse intensity distributions of the tumor regions, and utilize the trained results successfully in locating process. Experimental results show our approach locates the boundaries successfully, despite the diverse intensity distributions of the tumor regions, marker location variability and tumor region shape variability. Our framework is also generic and can be applied for locating boundaries of blob-like targets with diverse intensity distributions in other applications.