Header menu link for other important links
Generalized Zero-shot Chest X-ray Diagnosis through Trait-Guided Multi-view Semantic Embedding with Self-training
, T.C. Shen, S. Lee, N. Balachandar, Y. Peng, Z. Lu, R.M. Summers
Published in Institute of Electrical and Electronics Engineers Inc.
PMID: 33523805
Zero-shot learning (ZSL) is one of the most promising avenues of annotation-efficient machine learning. In the era of deep learning, ZSL techniques have achieved unprecedented success. However, the developments of ZSL methods have taken place mostly for natural images. ZSL for medical images has remained largely unexplored. We design a novel strategy for generalized zero-shot diagnosis of chest radiographs. In doing so, we leverage the potential of multi-view semantic embedding, a useful yet less-explored direction for ZSL. Our design also incorporates a self-training phase to tackle the problem of noisy labels alongside improving the performance for classes not seen during training. Through rigorous experiments, we show that our model trained on one dataset can produce consistent performance across test datasets from different sources including those with very different quality. Comparisons with a number of state-of-the-art techniques show the superiority of the proposed method for generalized zero-shot chest x-ray diagnosis. IEEE
About the journal
JournalData powered by TypesetIEEE Transactions on Medical Imaging
PublisherData powered by TypesetInstitute of Electrical and Electronics Engineers Inc.