arXiv subjects

Xiaoying Tang

Publications and source records attributed to Xiaoying Tang.

129 records · Page 8Linked to original sources

arXiv2019

Prostate segmentation using Z-net

In this paper, we proposed a novel architecture of convolutional neural network (CNN), namely Z-net, for segmenting prostate from magnetic resonance images (MRIs). In the proposed Z-net, 5 pairs of Z-block and decoder Z-block with different sizes and numbers of feature maps were assembled in a way similar to that of U-net. The proposed architecture can capture more multi-level features by using concatenation and dense connection. A total of 45 training images were used to train the proposed Z-net and the evaluations were conducted qualitatively on 5 validation images and quantitatively on 30 testing images. In addition, three approaches including pad and cut, 2D resize, and 3D resize for uniforming the size of samples were evaluated and compared. The experimental results demonstrated that the 2D resize is the most suitable approach for the proposed Z-net. Compared to the other two classical CNN architectures, the proposed method was observed with superior performance for segmenting prostate.

eess.IV↗

arXiv2018

Prostate Segmentation using 2D Bridged U-net

In this paper, we focus on three problems in deep learning based medical image segmentation. Firstly, U-net, as a popular model for medical image segmentation, is difficult to train when convolutional layers increase even though a deeper network usually has a better generalization ability because of more learnable parameters. Secondly, the exponential ReLU (ELU), as an alternative of ReLU, is not much different from ReLU when the network of interest gets deep. Thirdly, the Dice loss, as one of the pervasive loss functions for medical image segmentation, is not effective when the prediction is close to ground truth and will cause oscillation during training. To address the aforementioned three problems, we propose and validate a deeper network that can fit medical image datasets that are usually small in the sample size. Meanwhile, we propose a new loss function to accelerate the learning process and a combination of different activation functions to improve the network performance. Our experimental results suggest that our network is comparable or superior to state-of-the-art methods.

cs.CV↗

arXiv2018

A post-processing method to improve the white matter hyperintensity segmentation accuracy for randomly-initialized U-net

White matter hyperintensity (WMH) is commonly found in elder individuals and appears to be associated with brain diseases. U-net is a convolutional network that has been widely used for biomedical image segmentation. Recently, U-net has been successfully applied to WMH segmentation. Random initialization is usally used to initialize the model weights in the U-net. However, the model may coverage to different local optima with different randomly initialized weights. We find a combination of thresholding and averaging the outputs of U-nets with different random initializations can largely improve the WMH segmentation accuracy. Based on this observation, we propose a post-processing technique concerning the way how averaging and thresholding are conducted. Specifically, we first transfer the score maps from three U-nets to binary masks via thresholding and then average those binary masks to obtain the final WMH segmentation. Both quantitative analysis (via the Dice similarity coefficient) and qualitative analysis (via visual examinations) reveal the superior performance of the proposed method. This post-processing technique is independent of the model used. As such, it can also be applied to situations where other deep learning models are employed, especially when random initialization is adopted and pre-training is unavailable.

cs.CV↗