Inference time correction based on confidence and uncertainty for improved deep-learning model performance and explainability in medical image classification.

Joel Jeffrey¹, Ashwin RajKumar¹, Sudhanshu Pandey¹, Lokesh Bathala², Phaneendra K Yalavarthy³

¹Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, 560012, India.

²Aster-CMI Hospital, Bangalore, Karnataka, 560092, India.

³Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, 560012, India. Electronic address: yalavarthy@iisc.ac.in.

PubMed DOI

Abstract

The major challenge faced by artificial intelligence (AI) models for medical image analysis is the class imbalance of training data and limited explainability. This study introduces a Confidence and Entropy-based Uncertainty Thresholding Algorithm (CEbUTAl), which is a novel post-processing method, designed to enhance both model performance and explainability. CEbUTAl modifies model predictions du…

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.