Utilizing average symmetrical surface distance in active shape modeling for subcortical surface generation with slow-fast learning.

In this paper, we propose and validate an automatic pipeline for subcortical surface generation by making use of the average symmetrical surface distance (ASSD) loss in active shape modeling (ASM). A group of template surfaces are first generated via large deformation diffeomorphic metric mapping based surface deformation. ASM is then employed to obtain the mean shape and shape variation parameters of the template surfaces. To obtain the optimal shape variation parameters which best fit the target structure after acting upon the mean shape, a recently proposed derivative-free optimization method (the slow-fast learning method) is adopted. The ASSD loss, in addition to the typically utilized Dice similarity coefficient loss, is employed during the learning process to help enhance the boundary accuracy. We successfully validate the importance of the ASSD loss through ablation analysis. In addition, we show the effectiveness of the slow-fast learning method by comparing it with other state-of-the-art derivative-free optimization algorithms. Our proposed pipeline is found to be capable of yielding subcortical surfaces with high accuracy, correct anatomical topology, and sufficient smoothness. Clinical Relevance- This work provides a useful tool for generating subcortical surfaces which are important biomarkers for a variety of brain disorders.

Automatic hippocampal surface generation via 3D U-net and active shape modeling with hybrid particle swarm optimization.

In this paper, we proposed and validated a fully automatic pipeline for hippocampal surface generation via 3D U-net coupled with active shape modeling (ASM). Principally, the proposed pipeline consisted of three steps. In the beginning, for each magnetic resonance image, a 3D U-net was employed to obtain the automatic hippocampus segmentation at each hemisphere. Secondly, ASM was performed on a group of pre-obtained template surfaces to generate mean shape and shape variation parameters through principal component analysis. Ultimately, hybrid particle swarm optimization was utilized to search for the optimal shape variation parameters that best match the segmentation. The hippocampal surface was then generated from the mean shape and the shape variation parameters. The proposed pipeline was observed to provide hippocampal surfaces at both hemispheres with high accuracy, correct anatomical topology, and sufficient smoothness.Clinical relevance-This work provides a useful tool for generating hippocampal surfaces which are important biomarkers for a variety of brain disorders.

Brain Tumor Segmentation From Multi-Modal MR Images via Ensembling UNets.

Glioma is a type of severe brain tumor, and its accurate segmentation is useful in surgery planning and progression evaluation. Based on different biological properties, the glioma can be divided into three partially-overlapping regions of interest, including whole tumor (WT), tumor core (TC), and enhancing tumor (ET). Recently, UNet has identified its effectiveness in automatically segmenting brain tumor from multi-modal magnetic resonance (MR) images. In this work, instead of network architecture, we focus on making use of prior knowledge (brain parcellation), training and testing strategy (joint 3D+2D), ensemble and post-processing to improve the brain tumor segmentation performance. We explore the accuracy of three UNets with different inputs, and then ensemble the corresponding three outputs, followed by post-processing to achieve the final segmentation. Similar to most existing works, the first UNet uses 3D patches of multi-modal MR images as the input. The second UNet uses brain parcellation as an additional input. And the third UNet is inputted by 2D slices of multi-modal MR images, brain parcellation, and probability maps of WT, TC, and ET obtained from the second UNet. Then, we sequentially unify the WT segmentation from the third UNet and the fused TC and ET segmentation from the first and the second UNets as the complete tumor segmentation. Finally, we adopt a post-processing strategy by labeling small ET as non-enhancing tumor to correct some false-positive ET segmentation. On one publicly-available challenge validation dataset (BraTS2018), the proposed segmentation pipeline yielded average Dice scores of 91.03/86.44/80.58% and average 95% Hausdorff distances of 3.76/6.73/2.51 mm for WT/TC/ET, exhibiting superior segmentation performance over other state-of-the-art methods. We then evaluated the proposed method on the BraTS2020 training data through five-fold cross validation, with similar performance having also been observed. The proposed method was finally evaluated on 10 in-house data, the effectiveness of which has been established qualitatively by professional radiologists.