21 March 2016 Active appearance model and deep learning for more accurate prostate segmentation on MRI
Author Affiliations +
Prostate segmentation on 3D MR images is a challenging task due to image artifacts, large inter-patient prostate shape and texture variability, and lack of a clear prostate boundary specifically at apex and base levels. We propose a supervised machine learning model that combines atlas based Active Appearance Model (AAM) with a Deep Learning model to segment the prostate on MR images. The performance of the segmentation method is evaluated on 20 unseen MR image datasets. The proposed method combining AAM and Deep Learning achieves a mean Dice Similarity Coefficient (DSC) of 0.925 for whole 3D MR images of the prostate using axial cross-sections. The proposed model utilizes the adaptive atlas-based AAM model and Deep Learning to achieve significant segmentation accuracy.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ruida Cheng, Ruida Cheng, Holger R. Roth, Holger R. Roth, Le Lu, Le Lu, Shijun Wang, Shijun Wang, Baris Turkbey, Baris Turkbey, William Gandler, William Gandler, Evan S. McCreedy, Evan S. McCreedy, Harsh K. Agarwal, Harsh K. Agarwal, Peter Choyke, Peter Choyke, Ronald M. Summers, Ronald M. Summers, Matthew J. McAuliffe, Matthew J. McAuliffe, } "Active appearance model and deep learning for more accurate prostate segmentation on MRI", Proc. SPIE 9784, Medical Imaging 2016: Image Processing, 97842I (21 March 2016); doi: 10.1117/12.2216286; https://doi.org/10.1117/12.2216286

Back to Top