Zhongshi He

TL;DR: A 3D atrous-convolution with a single stride to replace pooling/striding and build the backbone for feature learning and a 3D fully connected Conditional Random Field is constructed as a post-processing step for the network's output to obtain structural segmentation of both the appearance and spatial consistency.

TL;DR: Experimental results show that the proposed CNN-based anisotropic MR image reconstruction method outperforms classical interpolation methods, non-local means method (NLM), and sparse coding based algorithm in terms of peak signal-to-noise-ratio, structural similarity image index, intensity profile, and small structures.

TL;DR: This work proposes a multiframe super-resolution reconstruction technique based on sparse representation of MR images that can reduce through-plane partial volume artifact by combining multiple orthogonal MR scans, and thus can potentially improve medical image analysis, research, and clinical diagnosis.

TL;DR: Experimental results show that MOMSA can obtain the significantly better alignments than VDGA, GAPAM on the most of test cases by statistical analyses, produce better alignings than IMSA in terms of TC scores, and also indicate that MMomSA is comparable with the leading progressive alignment approaches in termsof quality of alignments.

TL;DR: A novel framework to automatically segment brain tumors using a three-dimensional (3D) dense connectivity architecture is used to build the backbone for feature reuse and a 3D deep supervision mechanism is equipped with the network to promote training.