English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

AI-powered Medical Imaging has recently achieved enormous attention due toits ability to provide fast-paced healthcare diagnoses. However, it usuallysuffers from a lack of high-quality datasets due to high annotation cost,inter-observer variability, human annotator error, and errors incomputer-generated labels. Deep learning models trained on noisy labelleddatasets are sensitive to the noise type and lead to less generalization on theunseen samples. To address this challenge, we propose a Robust StochasticKnowledge Distillation (RoS-KD) framework which mimics the notion of learning atopic from multiple sources to ensure deterrence in learning noisy information.More specifically, RoS-KD learns a smooth, well-informed, and robust studentmanifold by distilling knowledge from multiple teachers trained on overlappingsubsets of training data. Our extensive experiments on popular medical imagingclassification tasks (cardiopulmonary disease and lesion classification) usingreal-world datasets, show the performance benefit of RoS-KD, its ability todistill knowledge from many popular large networks (ResNet-50, DenseNet-121,MobileNet-V2) in a comparatively small network, and its robustness toadversarial attacks (PGD, FSGM). More specifically, RoS-KD achieves >2% and >4%improvement on F1-score for lesion classification and cardiopulmonary diseaseclassification tasks, respectively, when the underlying student is ResNet-18against recent competitive knowledge distillation baseline. Additionally, oncardiopulmonary disease classification task, RoS-KD outperforms most of theSOTA baselines by ~1% gain in AUC score.

RoS-KD: A Robust Stochastic Knowledge Distillation Approach for Noisy Medical Imaging