AAC-TTA: Anti-adversarial consistency with test-time adaptation for imbalanced histopathology classification under scanner-induced domain shift.

Sehwan Yoo¹, Wilson Wen Bin Goh²

¹Lee Kong Chian School of Medicine, Nanyang Technological University, 59 Nanyang Drive, 637459, Singapore.

²Lee Kong Chian School of Medicine, Nanyang Technological University, 59 Nanyang Drive, 637459, Singapore; Centre of AI in Medicine, Nanyang Technological University, 59 Nanyang Drive, 637459, Singapore; Centre for Biomedical Informatics, Nanyang Technological University, 59 Nanyang Drive, 637459, Singapore; Institute of Mental Health, 10 Buangkok View, Buangkok Green Medical Park, 539747, Singapore; School of Biological Sciences, Nanyang Technological University, 60 Nanyang Drive, 637551, Singapore; Department of Brain Sciences, Imperial College London, London, W12 0NN, UK. Electronic address: wilsongoh@ntu.edu.sg.

PubMed DOI

Abstract

The performance of medical image classification models can degrade at deployment because of two common real-world challenges: domain shift and class imbalance. Domain shift causes whole-slide images acquired on different scanners to exhibit substantial visual variation, while class imbalance under-represents clinically important high-grade patterns. The effect of class imbalance is not limited to…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.