Yalin Zheng

TL;DR: A network with CNN architecture and data augmentation is developed which can identify the intricate features involved in the classification task such as micro-aneurysms, exudate and haemorrhages on the retina and consequently provide a diagnosis automatically and without user input.

TL;DR: The proposed infinite active contour model takes the advantage of using different types of region information, such as the combination of intensity information and local phase based enhancement map, and outperforms its competitors when compared with other widely used unsupervised and supervised methods.

TL;DR: A new loss function which incorporates area and size information and integrates this into a dense deep learning model is proposed which outperforms other mainstream loss function Cross-entropy on two common segmentation networks.

TL;DR: This work proposes a general unifying curvilinear structure segmentation network that works on different medical imaging modalities: optical coherence tomography angiography, color fundus image, and corneal confocal microscopy, and instead of the U-Net based convolutional neural network, a novel network which includes a self-attention mechanism in the encoder and decoder.

TL;DR: A new deep-learning-based method to segment the optic disc and optic cup and DenseNet with a fully-convolutional network, whose symmetric U-shaped architecture allows pixel-wise classification is proposed, outperforming state-of-the-art segmentation methods.