Fixed-Point GAN

PyTorch implementation of Fixed-Point GAN. Fixed-Point GAN introduces fixed-point translation which dramatically reduces artifacts in image-to-image translation and introduces a novel method for disease detection and localization using image-level annotation only.

View on GitHub

Models Genesis

We have built a set of pre-trained models called Generic Autodidactic Models, nicknamed Models Genesis, because they are created ex nihilo (with no manual labeling), self-taught (learned by self-supervision), and generic (served as source models for generating application-specific target models). We envision that Models Genesis may serve as a primary source of transfer learning for 3D medical imaging applications, in particular, with limited annotated data.

View on GitHub

Semantic Genesis

We provide a self-supervised learning framework to learn semantically enriched visual representation by self-discovery, self-classification, and self-restoration of the anatomy underneath medical images, resulting in a semantics-enriched, general-purpose, pre-trained 3D model, named Semantic Genesis. Our proposed self-supervised learning scheme should be considered as an add-on, which can be added to and boost existing self-supervised learning methods. Moreover, in terms of transfer learning for 3D medical applications, Semantic Genesis is superior to publicly available 3D models pre-trained by either self-supervision or even full supervision.

View on GitHub

PE CAD

Pulmonary embolism (PE) represents a blood clot that travels to the blood vessels in the lung, causing vascular obstruction, and in some patients, death. CT pulmonary angiography (CTPA), is the most common type of medical imaging to evaluate patients with suspected PE. These CT scans consist of hundreds of images that require detailed review to identify clots within the pulmonary arteries. Recent research in deep learning across academia and industry produced numerous architectures, various model initialization, and distinct learning paradigms. It has resulted in many competing approaches to CAD implementation in medical imaging and produced great confusion in the CAD community. we have conducted extensive experiments with various deep learning methods applicable for PE diagnosis at both slice and exam levels using the RSNA PE dataset.

View on GitHub