Cataracts are the leading cause of visual impairment worldwide. Examination of the retina through cataracts using a fundus camera is challenging and error-prone due to degraded image quality. We sought to develop an algorithm to dehaze such images to support diagnosis by either ophthalmologists or computer-aided diagnosis systems. Based on the generative adversarial network (GAN) concept, we designed two neural networks: CataractSimGAN and CataractDehazeNet. CataractSimGAN was intended for the synthesis of cataract-like images through unpaired clear retinal images and cataract images. CataractDehazeNet was trained using pairs of synthesized cataract-like images and the corresponding clear images through supervised learning. With two networks trained independently, the number of hyper-parameters was reduced, leading to better performance. We collected 400 retinal images without cataracts and 400 hazy images from cataract patients as the training dataset. Fifty cataract images and the corresponding clear images from the same patients after surgery comprised the test dataset. The clear images after surgery were used for reference to evaluate the performance of our method. CataractDehazeNet was able to enhance the degraded image from cataract patients substantially and to visualize blood vessels and the optic disc, while actively suppressing the artifacts common in application of similar methods. Thus, we developed an algorithm to improve the quality of the retinal images acquired from cataract patients. We achieved high structure similarity and fidelity between processed images and images from the same patients after cataract surgery.

End-to-End paradigms use a unified framework to implement multi-tasks in an autonomous driving system. Despite simplicity and clarity, the performance of end-to-end autonomous driving methods on sub-tasks is still far behind the single-task methods. Meanwhile, the widely used dense BEV features in previous end-to-end methods make it costly to extend to more modalities or tasks. In this paper, we propose a Sparse query-centric paradigm for end-to-end Autonomous Driving (SparseAD), where the sparse queries completely represent the whole driving scenario across space, time and tasks without any dense BEV representation. Concretely, we design a unified sparse architecture for perception tasks including detection, tracking, and online mapping. Moreover, we revisit motion prediction and planning, and devise a more justifiable motion planner framework. On the challenging nuScenes dataset, SparseAD achieves SOTA full-task performance among end-to-end methods and significantly narrows the performance gap between end-to-end paradigms and single-task methods.

Familial exudative vitreoretinopathy (FEVR) is a hereditary disorder that can damage the retina. This retinal damage can lead to vision loss and even blindness in the late stages. Thus, early diagnosis and prevention of the disease’s progression are critical. The purpose of this study was to develop an automated diagnosis system for FEVR based on combining deep learning and domain knowledge. A transfer learning scheme was designed to train a deep convolutional neural network (DCNN) to provide segmentation of the retinal vessels. Based on this vessel segmentation and prior clinical knowledge, the vascular characteristics, including the retinal avascular area, vessel angle, fractal dimension, branching and density of blood vessels, were automatically evaluated. Finally, the diagnosis of FEVR was achieved by a feature fusion neural network. Our method was evaluated on 300 images with 168 healthy and 132 FEVR images. By combining deep features and handcrafted features (extracted vascular characteristics), the proposed method achieved an average F1-score of 0.95, with excellent accuracy (94.34%) and sensitivity (91.43%); the quadratic weighted κ was 0.88 for the diagnosis of FEVR. We demonstrated the effectiveness and robustness of the proposed method using five-fold cross-validation. The proposed automatic diagnosis system can assist doctors for better judgment and make sense of early diagnosis and prevention of the disease’s progression.