Learning-Based Multi-atlas Segmentation of the Lungs and Lobes in Proton MR Images
Delineation of the lung and lobar anatomy in MR images is challenging due to the limited image contrast and the absence of visible interlobar fissures. Here we propose a novel automated lung and lobe segmentation method for pulmonary MR images. This segmentation method employs prior information of the lungs and lobes extracted from CT in the form of multiple MRI atlases, and adopts a learning-based atlas-encoding scheme, based on random forests, to improve the performance of multi-atlas segmentation. In particular, we encode each CT-derived MRI atlas by training an atlas-specific random forest for each structure of interest. In addition to appearance features, we also extract label context features from the registered atlases to introduce additional information to the non-linear mapping process. We evaluated our proposed framework on 10 clinical MR images acquired from COPD patients. It outperformed state-of-the-art approaches in segmenting the lungs and lobes, yielding a mean Dice score of 95.7%.
KeywordsMulti-atlas segmentation Lungs Pulmonary lobes MRI Machine learning Random forests
HL is supported by a fellowship funded by the Ministry of Higher Education Malaysia and Universiti Malaysia Perlis. The research was partly supported by the CRUK and EPSRC Cancer Imaging Centre in Oxford.
- 6.Kohlmann, P., Strehlow, J., Jobst, B., Krass, S., Kuhnigk, J.M., Anjorin, A., Sedlaczek, O., Ley, S., Kauczor, H.U., Wielpütz, M.O.: Automatic lung segmentation method for MRI-based lung perfusion studies of patients with chronic obstructive pulmonary disease. Int. J. Comput. Assist. Radiol. Surg. 10(4), 403–417 (2015)CrossRefGoogle Scholar