Hongyoon Choi1, Kyong Hwan Jin2. 1. Department of Nuclear Medicine, Cheonan Public Health Center, Chungnam, Republic of Korea. Electronic address: chy1000@gmail.com. 2. Biomedical Imaging Group, École Polytechnique Fédérale de Lausanne (EPFL), 1015 Lausanne, Switzerland. Electronic address: kyonghwan.jin@gmail.com.
Abstract
BACKGROUND: Automated segmentation of brain structures is an important task in structural and functional image analysis. We developed a fast and accurate method for the striatum segmentation using deep convolutional neural networks (CNN). NEW METHOD: T1 magnetic resonance (MR) images were used for our CNN-based segmentation, which require neither image feature extraction nor nonlinear transformation. We employed two serial CNN, Global and Local CNN: The Global CNN determined approximate locations of the striatum. It performed a regression of input MR images fitted to smoothed segmentation maps of the striatum. From the output volume of Global CNN, cropped MR volumes which included the striatum were extracted. The cropped MR volumes and the output volumes of Global CNN were used for inputs of Local CNN. Local CNN predicted the accurate label of all voxels. Segmentation results were compared with a widely used segmentation method, FreeSurfer. RESULTS: Our method showed higher Dice Similarity Coefficient (DSC) (0.893±0.017 vs. 0.786±0.015) and precision score (0.905±0.018 vs. 0.690±0.022) than FreeSurfer-based striatum segmentation (p=0.06). Our approach was also tested using another independent dataset, which showed high DSC (0.826±0.038) comparable with that of FreeSurfer. Comparison with existing method Segmentation performance of our proposed method was comparable with that of FreeSurfer. The running time of our approach was approximately three seconds. CONCLUSION: We suggested a fast and accurate deep CNN-based segmentation for small brain structures which can be widely applied to brain image analysis.
BACKGROUND: Automated segmentation of brain structures is an important task in structural and functional image analysis. We developed a fast and accurate method for the striatum segmentation using deep convolutional neural networks (CNN). NEW METHOD: T1 magnetic resonance (MR) images were used for our CNN-based segmentation, which require neither image feature extraction nor nonlinear transformation. We employed two serial CNN, Global and Local CNN: The Global CNN determined approximate locations of the striatum. It performed a regression of input MR images fitted to smoothed segmentation maps of the striatum. From the output volume of Global CNN, cropped MR volumes which included the striatum were extracted. The cropped MR volumes and the output volumes of Global CNN were used for inputs of Local CNN. Local CNN predicted the accurate label of all voxels. Segmentation results were compared with a widely used segmentation method, FreeSurfer. RESULTS: Our method showed higher Dice Similarity Coefficient (DSC) (0.893±0.017 vs. 0.786±0.015) and precision score (0.905±0.018 vs. 0.690±0.022) than FreeSurfer-based striatum segmentation (p=0.06). Our approach was also tested using another independent dataset, which showed high DSC (0.826±0.038) comparable with that of FreeSurfer. Comparison with existing method Segmentation performance of our proposed method was comparable with that of FreeSurfer. The running time of our approach was approximately three seconds. CONCLUSION: We suggested a fast and accurate deep CNN-based segmentation for small brain structures which can be widely applied to brain image analysis.
Authors: Jessica B Girault; Brent C Munsell; Danaële Puechmaille; Barbara D Goldman; Juan C Prieto; Martin Styner; John H Gilmore Journal: Neuroimage Date: 2019-02-27 Impact factor: 6.556
Authors: Mario Serrano-Sosa; Jared X Van Snellenberg; Jiayan Meng; Jacob R Luceno; Karl Spuhler; Jodi J Weinstein; Anissa Abi-Dargham; Mark Slifstein; Chuan Huang Journal: J Magn Reson Imaging Date: 2021-05-10 Impact factor: 5.119