Back to search

West Virginia University

Data Augmentation and the Reliability of Conformal Prediction for Uncertainty Quantification in Medical Imaging

Abstract

dc:description.abstract

The safe clinical deployment of deep learning models for high-stakes medical imaging tasks requires more than high average accuracy; it requires demonstrable, per-case reliability. Uncertainty quantification (UQ) provides the missing signal that tells a clinician when a model prediction can be trusted and when a case should be escalated for expert review. Among UQ approaches, conformal prediction (CP) is especially attractive because it produces prediction sets that are guaranteed, under the assumption of exchangeability, to contain the true label with a user chosen probability, and it does so without assumptions about the model or the data distribution. This report first develops why UQ is a central problem for trustworthy medical imaging and why conformal prediction is a principled way to address it. It then examines a practical tension that has received little attention: data augmentation is a near universal ingredient of modern training pipelines, yet by design it alters the training distribution and may therefore interact with the exchangeability assumption that underpins conformal guarantees. To study this interaction in a concrete, clinically meaningful setting, we use diabetic retinopathy (DR) grading as our experimental case study. Using the publicly available DDR dataset, we evaluate two backbone architectures, ResNet-50 and a Co-Scale Conv-Attentional Transformer (CoaT), each trained under five augmentation regimes: no augmentation, standard geometric transforms, Contrast Limited Adaptive Histogram Equalization (CLAHE), Mixup, and CutMix. We analyze the downstream effects on conformal metrics, including empirical coverage, average prediction set size, and correct efficiency. Our results show that sample mixing strategies such as Mixup and CutMix not only improve predictive accuracy but also tend to yield more reliable and efficient uncertainty estimates, whereas contrast enhancement through CLAHE can degrade model certainty. These findings support a central recommendation: augmentation strategies should be co-designed with downstream uncertainty quantification in mind, rather than optimized for accuracy alone, if we are to build genuinely trustworthy artificial intelligence systems for medical imaging.

Degree

thesis:*
Name thesis:degree_name
MS
Level thesis:degree_level
Problem/Project Report
Discipline thesis:degree_discipline
Lane Department of Computer Science and Electrical Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ahamed, Rizwan
Contributors dc:contributor
  • Prashnna Gyawali
  • Jeremy Dawson
  • Anthony Sicilia

Subjects

dc:subject × 8

Identifiers

dc:identifier.*
Identifier
<p><a href="https://orcid.org/0009-0007-3948-2608">https://orcid.org/0009-0007-3948-2608</a></p>
https://researchrepository.wvu.edu/etd/13484

Chain of custody

source
Harvested from
West Virginia University
Base URL
researchrepository.wvu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Ahamed, Rizwan. Data Augmentation and the Reliability of Conformal Prediction for Uncertainty Quantification in Medical Imaging. Problem/Project Report thesis, https://doi.org/10.33915/etd.13484