Xiyang Liu

TL;DR: It is shown that an AI agent using deep learning, and involving convolutional neural networks for diagnostics, risk stratification and treatment suggestions, accurately diagnoses and provides treatment decisions for congenital cataracts in an in silico test, a website-based study, in a ‘finding a needle in a haystack’ test and in a multihospital clinical trial.

TL;DR: A computer vision-based framework for the automatic localization and diagnosis of slit-lamp images by identifying the lens region of interest (ROI) and employing a deep learning convolutional neural network (CNN).

TL;DR: Deep learning algorithms are developed that are superior to those of human specialists in detecting scoliosis, detecting cases with a curve ≥20°, and severity grading for both binary classifications and the four-class classification.

TL;DR: A interpretable, weakly supervised deep learning framework incorporating prior knowledge is proposed to analyse hepatocellular carcinoma (HCC) and explore new prognostic phenotypes on pathological whole-slide images, providing a valuable means for HCC risk stratification and precise patient treatment.

TL;DR: Wang et al. as discussed by the authors proposed a deep learning framework for analyzing lymph node whole-slide images (WSIs) to identify lymph nodes and tumor regions, and then to uncover tumor-area-to-MLN-area ratio (T/MLN).