Pitfalls of Conformal Predictions for Medical Image Classification

• URL: http://arxiv.org/abs/2506.18162v1
• Date: Sun, 22 Jun 2025 20:33:38 GMT
• Title: Pitfalls of Conformal Predictions for Medical Image Classification
• Authors: Hendrik Mehrtens, Tabea Bucher, Titus J. Brinker,
• Abstract summary: Con conformal predictions can provide provable calibration guarantees.<n>Con conformal predictions are unreliable under distributional shifts in input and label variables.<n>In classification settings with a small number of classes, conformal predictions have limited practical value.
• Score: 1.2289361708127877
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reliable uncertainty estimation is one of the major challenges for medical classification tasks. While many approaches have been proposed, recently the statistical framework of conformal predictions has gained a lot of attention, due to its ability to provide provable calibration guarantees. Nonetheless, the application of conformal predictions in safety-critical areas such as medicine comes with pitfalls, limitations and assumptions that practitioners need to be aware of. We demonstrate through examples from dermatology and histopathology that conformal predictions are unreliable under distributional shifts in input and label variables. Additionally, conformal predictions should not be used for selecting predictions to improve accuracy and are not reliable for subsets of the data, such as individual classes or patient attributes. Moreover, in classification settings with a small number of classes, which are common in medical image classification tasks, conformal predictions have limited practical value.

Related papers

• Validation of Conformal Prediction in Cervical Atypia Classification [1.8988964758950546]
  deep learning based cervical cancer classification can potentially increase access to screening in low-resource regions.<n>Deep learning models are often overconfident and do not reliably reflect diagnostic uncertainty.<n>Con conformal prediction is a model-agnostic framework for generating prediction sets that contain likely classes for trained deep-learning models.
  arXiv  Detail & Related papers  (2025-05-13T14:37:58Z)
• SConU: Selective Conformal Uncertainty in Large Language Models [59.25881667640868]
  We propose a novel approach termed Selective Conformal Uncertainty (SConU)<n>We develop two conformal p-values that are instrumental in determining whether a given sample deviates from the uncertainty distribution of the calibration set at a specific manageable risk level.<n>Our approach not only facilitates rigorous management of miscoverage rates across both single-domain and interdisciplinary contexts, but also enhances the efficiency of predictions.
  arXiv  Detail & Related papers  (2025-04-19T03:01:45Z)
• Conformal Prediction Sets with Improved Conditional Coverage using Trust Scores [52.92618442300405]
  It is impossible to achieve exact, distribution-free conditional coverage in finite samples.<n>We propose an alternative conformal prediction algorithm that targets coverage where it matters most.
  arXiv  Detail & Related papers  (2025-01-17T12:01:56Z)
• Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning [53.42244686183879]
  Conformal prediction provides model-agnostic and distribution-free uncertainty quantification.<n>Yet, conformal prediction is not reliable under poisoning attacks where adversaries manipulate both training and calibration data.<n>We propose reliable prediction sets (RPS): the first efficient method for constructing conformal prediction sets with provable reliability guarantees under poisoning.
  arXiv  Detail & Related papers  (2024-10-13T15:37:11Z)
• A conformalized learning of a prediction set with applications to medical imaging classification [14.304858613146536]
  We present an algorithm that can produce a prediction set containing the true label with a user-specified probability, such as 90%. We applied the proposed algorithm to several standard medical imaging classification datasets.
  arXiv  Detail & Related papers  (2024-08-09T12:49:04Z)
• A Saliency-based Clustering Framework for Identifying Aberrant Predictions [49.1574468325115]
  We introduce the concept of aberrant predictions, emphasizing that the nature of classification errors is as critical as their frequency. We propose a novel, efficient training methodology aimed at both reducing the misclassification rate and discerning aberrant predictions. We apply this methodology to the less-explored domain of veterinary radiology, where the stakes are high but have not been as extensively studied compared to human medicine.
  arXiv  Detail & Related papers  (2023-11-11T01:53:59Z)
• Improving Trustworthiness of AI Disease Severity Rating in Medical Imaging with Ordinal Conformal Prediction Sets [0.7734726150561088]
  A lack of statistically rigorous uncertainty quantification is a significant factor undermining trust in AI results. Recent developments in distribution-free uncertainty quantification present practical solutions for these issues. We demonstrate a technique for forming ordinal prediction sets that are guaranteed to contain the correct stenosis severity.
  arXiv  Detail & Related papers  (2022-07-05T18:01:20Z)
• Distribution-Free Federated Learning with Conformal Predictions [0.0]
  Federated learning aims to leverage separate institutional datasets while maintaining patient privacy. Poor calibration and lack of interpretability may hamper widespread deployment of federated models into clinical practice. We propose to address these challenges by incorporating an adaptive conformal framework into federated learning.
  arXiv  Detail & Related papers  (2021-10-14T18:41:17Z)
• Distribution-free uncertainty quantification for classification under label shift [105.27463615756733]
  We focus on uncertainty quantification (UQ) for classification problems via two avenues. We first argue that label shift hurts UQ, by showing degradation in coverage and calibration. We examine these techniques theoretically in a distribution-free framework and demonstrate their excellent practical performance.
  arXiv  Detail & Related papers  (2021-03-04T20:51:03Z)
• Distribution-Free, Risk-Controlling Prediction Sets [112.9186453405701]
  We show how to generate set-valued predictions from a black-box predictor that control the expected loss on future test points at a user-specified level. Our approach provides explicit finite-sample guarantees for any dataset by using a holdout set to calibrate the size of the prediction sets.
  arXiv  Detail & Related papers  (2021-01-07T18:59:33Z)
• Uncertainty estimation for classification and risk prediction on medical tabular data [0.0]
  This work advances the understanding of uncertainty estimation for classification and risk prediction on medical data. In a data-scarce field such as healthcare, the ability to measure the uncertainty of a model's prediction could potentially lead to improved effectiveness of decision support tools.
  arXiv  Detail & Related papers  (2020-04-13T08:46:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.