Zongwei Zhou

TL;DR: This work has built a set of models, called Generic Autodidactic Models, nicknamed Models Genesis, because they are created ex nihilo (with no manual labeling), self-taught (learnt by self-supervision), and generic (served as source models for generating application-specific target models).

TL;DR: In this article, the authors compared one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from 18F-FDG PET/CT images.

TL;DR: Li et al. as discussed by the authors proposed a fixed-point GAN to identify a minimal subset of target pixels for domain translation, an ability that no GAN is equipped with yet, and trained by supervising same domain translation through a conditional identity loss, and regularizing cross-domain translation through revised adversarial, domain classification, and cycle consistency loss.

TL;DR: Li et al. as discussed by the authors proposed a self-supervised learning framework for 3D medical image segmentation and classification using generative autodidactic models (GAMs), which serve as source models for generating application-specific target models.

TL;DR: CNN does not make use of the import diagnostic features, which have been proved more discriminative than the texture features for classifying small-sized lymph nodes, so incorporating the diagnostic features into CNN is a promising direction for future research.