Yiqiu Shen

TL;DR: In this paper, a two-stage architecture and training procedure was proposed for breast cancer screening exam classification, trained and evaluated on over 200,000 exams (over 100,000 images).

TL;DR: A deep convolutional neural network for breast cancer screening exam classification, trained, and evaluated on over 200000 exams, and it is shown that a hybrid model, averaging the probability of malignancy predicted by a radiologist with a prediction of the neural network is more accurate than either of the two separately.

TL;DR: This diagnostic accuracy study evaluates whether artificial intelligence can overcome human mammography interpretation limits with a rigorous, unbiased evaluation of machine learning algorithms.

TL;DR: This work proposes a novel neural network model that is trained with only image-level labels and can generate pixel-level saliency maps indicating possible malignant findings in screening mammography interpretation: predicting the presence or absence of benign and malignant lesions.

TL;DR: A deep learning model based on the ResNet34 architecture better predicted risk of total knee replacement in osteoarthritis than did binary outcome models by using standard grading systems.