Deep learning model calibration for improving performance in class-imbalanced medical image classification tasks
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
In medical image classification tasks, it is common to find that the number of normal samples far exceeds the number of abnormal samples. In such class-imbalanced situations, reliable training of deep neural networks continues to be a major challenge, therefore biasing the predicted class probabilities toward the majority class. Calibration has been proposed to alleviate some of these effects. However, there is insufficient analysis explaining whether and when calibrating a model would be beneficial. In this study, we perform a systematic analysis of the effect of model calibration on its performance on two medical image modalities, namely, chest X-rays and fundus images, using various deep learning classifier backbones. For this, we study the following variations: (i) the degree of imbalances in the dataset used for training; (ii) calibration methods; and (iii) two classification thresholds, namely, default threshold of 0.5, and optimal threshold from precision-recall (PR) curves. Our results indicate that at the default classification threshold of 0.5, the performance achieved through calibration is significantly superior (p < 0.05) to using uncalibrated probabilities. However, at the PR-guided threshold, these gains are not significantly different (p > 0.05). This observation holds for both image modalities and at varying degrees of imbalance. The code is available at https://github.com/sivaramakrishnan-rajaraman/Model_calibration.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697 · cited 1×
“Some examples include chest X-rays (CXRs) [2], computed tomography (CT), magnetic resonance (MR), fundus images [3], cervix images [4], and ultrasound echocardiography [5], among others.”
BackgroundSqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201
On calibration of modern neural networks
Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017) · arXiv · doi:10.48550/arxiv.1706.04599 · Cited by 3,435
Predicting good probabilities with supervised learning
Niculescu-Mizil, A., & Caruana, R. (2005) · Proceedings of the 22nd international conference on Machine learning - ICML '05 · doi:10.1145/1102351.1102430 · Cited by 1,884
Two public chest X-ray datasets for computer-aided screening of pulmonary diseases.
(2014) · PubMed Central · doi:10.3978/j.issn.2223-4292.2014.11.20 · Cited by 918
Self-citationMeasuring Calibration in Deep Learning
Nixon, J., Dusenberry, M., Jerfel, G., Nguyen, T., Liu, J., Zhang, L., & Tran, D. (2019) · arXiv · doi:10.48550/arxiv.1904.01685 · Cited by 209 · cited 2×
“A review of the literature shows several studies that analyze the effect of calibration in a model trained with fixed-size data [9, 14, 15].”
BackgroundCarneiro, G., Zorron Cheng Tao Pu, L., Singh, R., & Burt, A. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101653 · Cited by 76 · cited 1×
“In another study [20], the authors used the single-parameter version of Platt scaling to calibrate the prediction probabilities toward a multi-class polyp classification task.”
Method
Cited by
Alzubaidi, L., Bai, J., Al-Sabaawi, A., Santamaría, J., Albahri, A. S., Al-dabbagh, B. S. N., Fadhel, M. A., Manoufali, M., Zhang, J., Al-Timemy, A. H., et al. (2023) · Journal of Big Data · doi:10.1186/s40537-023-00727-2 · Cited by 907
Empirical data drift detection experiments on real-world medical imaging data
Kore, A., Abbasi Bavil, E., Subasri, V., Abdalla, M., Fine, B., Dolatabadi, E., & Abdalla, M. (2024) · Nature Communications · doi:10.1038/s41467-024-46142-w · Cited by 124
Tasci, E., Zhuge, Y., Camphausen, K., & Krauze, A. V. (2022) · Cancers · doi:10.3390/cancers14122897 · Cited by 117
“Machine learning models/ artificial intelligence (AI) systems considering all data, therefore, produce biased classifiers whose predicted class probabilities are geared toward the majority class ignoring the significance of minority classes [12,13].”
BackgroundCurrent challenges in adopting machine learning to critical care and emergency medicine
Kang, C.-Y., & Yoon, J. H. (2023) · Clinical and Experimental Emergency Medicine · doi:10.15441/ceem.23.041 · Cited by 20
Metadata
- Authors
- Rajaraman, S., Ganesan, P., & Antani, S.
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2022-01-27
- Volume
- 17
- Issue
- 1
- Pages
- e0262838
- ISSN
- 1932-6203 (ISSN-L)
- OpenAlex
- W4210374324
- Cited by
- 86
- References
- 10
- FWCI
- 4.77
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deep learning model calibration for improving performance in class-imbalanced medical image classification tasks. https://app.cochat.ai/papers/10.1371/journal.pone.0262838
- The paper
- Rajaraman, S., Ganesan, P., & Antani, S. (2022). Deep learning model calibration for improving performance in class-imbalanced medical image classification tasks. PLOS ONE. https://doi.org/10.1371/journal.pone.0262838
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.