Deep level set method for optic disc and cup segmentation on fundus images.

Glaucoma is a leading cause of blindness. The measurement of vertical cup-to-disc ratio combined with other clinical features is one of the methods used to screen glaucoma. In this paper, we propose a deep level set method to implement the segmentation of optic cup (OC) and optic disc (OD). We present a multi-scale convolutional neural network as the prediction network to generate level set initial contour and evolution parameters. The initial contour will be further refined based on the evolution parameters. The network is integrated with augmented prior knowledge and supervised by active contour loss, which makes the level set evolution yield more accurate shape and boundary details. The experimental results on the REFUGE dataset show that the IoU of the OC and OD are 93.61% and 96.69%, respectively. To evaluate the robustness of the proposed method, we further test the model on the Drishthi-GS1 dataset. The segmentation results show that the proposed method outperforms the state-of-the-art methods.

Image-level supervised segmentation for human organs with confidence cues.

Image segmentation for human organs is an important task for the diagnosis and treatment of diseases. Current deep learning-based methods are fully supervised and need pixel-level labels. Since the medical images are highly specialized and complex, the work of delineating pixel-level segmentation masks is very time-consuming. Weakly supervised methods are then chosen to lighten the workload, which only needs physicians to determine whether an image contains the organ regions of interest. These weakly supervised methods have a common drawback, in that they do not incorporate prior knowledge that alleviates the lack of pixel-level information for segmentation. In this work, we propose a weakly supervised method based on prior knowledge for the segmentation of human organs. The proposed method was validated on three data sets of human organ segmentation. Experimental results show that the proposed image-level supervised segmentation method outperforms several state-of-the-art methods.

Graph convolutional network based optic disc and cup segmentation on fundus images.

Calculating the cup-to-disc ratio is one of the methods for glaucoma screening with other clinical features. In this paper, we propose a graph convolutional network (GCN) based method to implement the optic disc (OD) and optic cup (OC) segmentation task. We first present a multi-scale convolutional neural network (CNN) as the feature map extractor to generate feature map. The GCN takes the feature map concatenated with the graph nodes as the input for segmentation task. The experimental results on the REFUGE dataset show that the Jaccard index (Jacc) of the proposed method on OD and OC are 95.64% and 91.60%, respectively, while the Dice similarity coefficients (DSC) are 97.76% and 95.58%, respectively. The proposed method outperforms the state-of-the-art methods on the REFUGE leaderboard. We also evaluate the proposed method on the Drishthi-GS1 dataset. The results show that the proposed method outperforms the state-of-the-art methods.

Graph-convolutional-network-based interactive prostate segmentation in MR images.

PURPOSE: Accurate and robust segmentation of the prostate from magnetic resonance (MR) images is extensively applied in many clinical applications in prostate cancer diagnosis and treatment. The purpose of this study is the development of a robust interactive segmentation method for accurate segmentation of the prostate from MR images. METHODS: We propose an interactive segmentation method based on a graph convolutional network (GCN) to refine the automatically segmented results. An atrous multiscale convolutional neural network (CNN) encoder is proposed to learn representative features to obtain accurate segmentations. Based on the multiscale feature, a GCN block is presented to predict the prostate contour in both automatic and interactive manners. To preserve the prostate boundary details and effectively train the GCN, a contour matching loss is proposed. The performance of the proposed algorithm was evaluated on 41 in-house MR subjects and 30 PROMISE12 test subjects. RESULT: The proposed method yields mean Dice similarity coefficients of 93.8 ± 1.2% and 94.4 ± 1.0% on our in-house and PROMISE12 datasets, respectively. The experimental results show that the proposed method outperforms several state-of-the-art segmentation methods. CONCLUSION: The proposed interactive segmentation method based on the GCN can accurately segment the prostate from MR images. Our method has a variety of applications in prostate cancer imaging.