Deep Learning with Skip Connection Attention for Choroid Layer Segmentation in OCT Images.

Since the thickness and shape of the choroid layer are indicators for the diagnosis of several ophthalmic diseases, the choroid layer segmentation is an important task. There exist many challenges in segmentation of the choroid layer. In this paper, in view of the lack of context information due to the ambiguous boundaries, and the subsequent inconsistent predictions of the same category targets ascribed to the lack of context information or the large regions, a novel Skip Connection Attention (SCA) module which is integrated into the U-Shape architecture is proposed to improve the precision of choroid layer segmentation in Optical Coherence Tomography (OCT) images. The main function of the SCA module is to capture the global context in the highest level to provide the decoder with stage-by-stage guidance, to extract more context information and generate more consistent predictions for the same class targets. By integrating the SCA module into the U-Net and CE-Net, we show that the module improves the accuracy of the choroid layer segmentation.

JointRCNN: A Region-Based Convolutional Neural Network for Optic Disc and Cup Segmentation.

OBJECTIVE: The purpose of this paper is to propose a novel algorithm for joint optic disc and cup segmentation, which aids the glaucoma detection. METHODS: By assuming the shapes of cup and disc regions to be elliptical, we proposed an end-to-end region-based convolutional neural network for joint optic disc and cup segmentation (referred to as JointRCNN). Atrous convolution is introduced to boost the performance of feature extraction module. In JointRCNN, disc proposal network (DPN) and cup proposal network (CPN) are proposed to generate bounding box proposals for the optic disc and cup, respectively. Given the prior knowledge that the optic cup is located in the optic disc, disc attention module is proposed to connect DPN and CPN, where a suitable bounding box of the optic disc is first selected and then continued to be propagated forward as the basis for optic cup detection in our proposed network. After obtaining the disc and cup regions, which are the inscribed ellipses of the corresponding detected bounding boxes, the vertical cup-to-disc ratio is computed and used as an indicator for glaucoma detection. RESULTS: Comprehensive experiments clearly show that our JointRCNN model outperforms state-of-the-art methods for optic disc and cup segmentation task and glaucoma detection task. CONCLUSION: Joint optic disc and cup segmentation, which utilizes the connection between optic disc and cup, could improve the performance of optic disc and cup segmentation. SIGNIFICANCE: The proposed method improves the accuracy of glaucoma detection. It is promising to be used for glaucoma screening.

Dense Dilated Network With Probability Regularized Walk for Vessel Detection.

The detection of retinal vessel is of great importance in the diagnosis and treatment of many ocular diseases. Many methods have been proposed for vessel detection. However, most of the algorithms neglect the connectivity of the vessels, which plays an important role in the diagnosis. In this paper, we propose a novel method for retinal vessel detection. The proposed method includes a dense dilated network to get an initial detection of the vessels and a probability regularized walk algorithm to address the fracture issue in the initial detection. The dense dilated network integrates newly proposed dense dilated feature extraction blocks into an encoder-decoder structure to extract and accumulate features at different scales. A multi-scale Dice loss function is adopted to train the network. To improve the connectivity of the segmented vessels, we also introduce a probability regularized walk algorithm to connect the broken vessels. The proposed method has been applied on three public data sets: DRIVE, STARE and CHASE_DB1. The results show that the proposed method outperforms the state-of-the-art methods in accuracy, sensitivity, specificity and also area under receiver operating characteristic curve.

Noise Adaptation Generative Adversarial Network for Medical Image Analysis.

Machine learning has been widely used in medical image analysis under an assumption that the training and test data are under the same feature distributions. However, medical images from difference devices or the same device with different parameter settings are often contaminated with different amount and types of noises, which violate the above assumption. Therefore, the models trained using data from one device or setting often fail to work for that from another. Moreover, it is very expensive and tedious to label data and re-train models for all different devices or settings. To overcome this noise adaptation issue, it is necessary to leverage on the models trained with data from one device or setting for new data. In this paper, we reformulate this noise adaptation task as an image-to-image translation task such that the noise patterns from the test data are modified to be similar to those from the training data while the contents of the data are unchanged. In this paper, we propose a novel Noise Adaptation Generative Adversarial Network (NAGAN), which contains a generator and two discriminators. The generator aims to map the data from source domain to target domain. Among the two discriminators, one discriminator enforces the generated images to have the same noise patterns as those from the target domain, and the second discriminator enforces the content to be preserved in the generated images. We apply the proposed NAGAN on both optical coherence tomography (OCT) images and ultrasound images. Results show that the method is able to translate the noise style. In addition, we also evaluate our proposed method with segmentation task in OCT and classification task in ultrasound. The experimental results show that the proposed NAGAN improves the analysis outcome.

CE-Net: Context Encoder Network for 2D Medical Image Segmentation.

Medical image segmentation is an important step in medical image analysis. With the rapid development of a convolutional neural network in image processing, deep learning has been used for medical image segmentation, such as optic disc segmentation, blood vessel detection, lung segmentation, cell segmentation, and so on. Previously, U-net based approaches have been proposed. However, the consecutive pooling and strided convolutional operations led to the loss of some spatial information. In this paper, we propose a context encoder network (CE-Net) to capture more high-level information and preserve spatial information for 2D medical image segmentation. CE-Net mainly contains three major components: a feature encoder module, a context extractor, and a feature decoder module. We use the pretrained ResNet block as the fixed feature extractor. The context extractor module is formed by a newly proposed dense atrous convolution block and a residual multi-kernel pooling block. We applied the proposed CE-Net to different 2D medical image segmentation tasks. Comprehensive results show that the proposed method outperforms the original U-Net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation, cell contour segmentation, and retinal optical coherence tomography layer segmentation.

Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Grading.

Diabetic Retinopathy (DR) is a non-negligible eye disease among patients with Diabetes Mellitus, and automatic retinal image analysis algorithm for the DR screening is in high demand. Considering the resolution of retinal image is very high, where small pathological tissues can be detected only with large resolution image and large local receptive field are required to identify those late stage disease, but directly training a neural network with very deep architecture and high resolution image is both time computational expensive and difficult because of gradient vanishing/exploding problem, we propose a Multi-Cell architecture which gradually increases the depth of deep neural network and the resolution of input image, which both boosts the training time but also improves the classification accuracy. Further, considering the different stages of DR actually progress gradually, which means the labels of different stages are related. To considering the relationships of images with different stages, we propose a Multi-Task learning strategy which predicts the label with both classification and regression. Experimental results on the Kaggle dataset show that our method achieves a Kappa of 0.841 on test set which is the 4th rank of all state-of-the-arts methods. Further, our Multi-Cell Multi-Task Convolutional Neural Networks (M2CNN) solution is a general framework, which can be readily integrated with many other deep neural network architectures.

Structure-Preserving Guided Retinal Image Filtering and Its Application for Optic Disk Analysis.

Retinal fundus photographs have been used in the diagnosis of many ocular diseases such as glaucoma, pathological myopia, age-related macular degeneration, and diabetic retinopathy. With the development of computer science, computer aided diagnosis has been developed to process and analyze the retinal images automatically. One of the challenges in the analysis is that the quality of the retinal image is often degraded. For example, a cataract in human lens will attenuate the retinal image, just as a cloudy camera lens which reduces the quality of a photograph. It often obscures the details in the retinal images and posts challenges in retinal image processing and analyzing tasks. In this paper, we approximate the degradation of the retinal images as a combination of human-lens attenuation and scattering. A novel structure-preserving guided retinal image filtering (SGRIF) is then proposed to restore images based on the attenuation and scattering model. The proposed SGRIF consists of a step of global structure transferring and a step of global edge-preserving smoothing. Our results show that the proposed SGRIF method is able to improve the contrast of retinal images, measured by histogram flatness measure, histogram spread, and variability of local luminosity. In addition, we further explored the benefits of SGRIF for subsequent retinal image processing and analyzing tasks. In the two applications of deep learning-based optic cup segmentation and sparse learning-based cup-to-disk ratio (CDR) computation, our results show that we are able to achieve more accurate optic cup segmentation and CDR measurements from images processed by SGRIF.