Automatic labeling of MR brain images by hierarchical learning of atlas forests. Issue 3 (9th February 2016)

• Record Type: Journal Article
• Authors: Zhang, Lichi; Wang, Qian; Gao, Yaozong; Wu, Guorong; Shen, Dinggang
• Is Part Of: Medical physics. Volume 43:Issue 3(2016)
• Page Start: 1175
• Page End: 1186
• Publication Date: 2016-02-09
• Subjects: biomedical MRI -- brain -- decision trees -- medical image processing; Magnetic resonance imaging; Involving electronic [emr] or nuclear [nmr] magnetic resonance, e.g. magnetic resonance imaging -- Biological material, e.g. blood, urine; Haemocytometers -- Digital computing or data processing equipment or methods, specially adapted for specific applications -- Image data processing or generation, in general; image segmentation -- random forest -- brain MR images -- atlas selection -- clustering; Brain -- Medical magnetic resonance imaging -- Testing procedures -- Learning -- Cluster analysis -- Medical image segmentation -- Information integration -- Encoding -- Image analysis; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1118/1.4941011
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: Automatic brain image labeling is highly demanded in the field of medical image analysis. Multiatlas‐based approaches are widely used due to their simplicity and robustness in applications. Also, random forest technique is recognized as an efficient method for labeling, although there are several existing limitations. In this paper, the authors intend to address those limitations by proposing a novel framework based on the hierarchical learning of atlas forests. Methods: Their proposed framework aims to train a hierarchy of forests to better correlate voxels in the MR images with their corresponding labels. There are two specific novel strategies for improving brain image labeling. First, different from the conventional ways of using a single level of random forests for brain labeling, the authors design a hierarchical structure to incorporate multiple levels of forests. In particular, each atlas forest in the bottom level is trained in accordance with each individual atlas, and then the bottom‐level forests are clustered based on their capabilities in labeling. For each clustered group, the authors retrain a new representative forest in the higher level by using all atlases associated with the lower‐level atlas forests in the current group, as well as the tentative label maps yielded from the lower level. This clustering and retraining procedure is conducted iteratively to yield a hierarchical structure of forests. Second, in the testing stage, the authors also present a novel atlas forest selection method to determine an optimal set of atlas forests from the constructed hierarchical structure (by disabling those nonoptimal forests) for accurately labeling the test image. Results: For validating their proposed framework, the authors evaluate it on the public datasets, including Alzheimer's disease neuroimaging initiative, Internet brain segmentation repository, and LONI LPBA40. The authors compare the results with the conventional approaches. The experiments show that the use of the two novel strategies can significantly improve the labeling performance. Note that when more levels are constructed in the hierarchy, the labeling performance can be further improved, but more computational time will be also required. Conclusions: The authors have proposed a novel multiatlas‐based framework for automatic and accurate labeling of brain anatomies, which can achieve accurate labeling results for MR brain images.