Metraipolis › archive › dc_c905e710fb52

Deep learning model calibration for improving performance in class-imbalanced medical image classification tasks — Europe PMC PMID:35085334

Source
Europe PMC (en)
Original
https://europepmc.org/article/MED/35085334
DOI
10.1371/journal.pone.0262838
License (as archived)
CC0-1.0
Archived
2026-10-31T12:35:14.161Z
SHA-256 of the archived text
71a38f67225f1011b820578f2be6c2e67caf3e325fc1490b77609a36e2f560ff
Stable URL of this page
https://metraipolis.com/documento/dc_c905e710fb52

How to cite

Deep learning model calibration for improving performance in class-imbalanced medical image classification tasks — Europe PMC PMID:35085334 — Europe PMC (en), https://europepmc.org/article/MED/35085334 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c905e710fb52 (Metraipolis archive dc_c905e710fb52, sha256 71a38f67225f1011b820578f2be6c2e67caf3e325fc1490b77609a36e2f560ff)
BibTeX
@misc{dcc905e710fb52,
  title = {Deep learning model calibration for improving performance in class-imbalanced medical image classification tasks — Europe PMC PMID:35085334},
  howpublished = {Europe PMC (en)},
  url = {https://europepmc.org/article/MED/35085334},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c905e710fb52; sha256 71a38f67225f1011b820578f2be6c2e67caf3e325fc1490b77609a36e2f560ff},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/35085334. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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). 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.

Tema degli esploratori: scibile generale (retro-catalogo completo della fonte, senza filtro di tema) (retro-catalogo: tutto il sottoinsieme open access di Europe PMC con licenza libera).
Pubblicazione: PloS one, 2022 (prima pubblicazione 2022-01-27).
Identificativi: PMID 35085334 · PMCID PMC8794113 · DOI 10.1371/journal.pone.0262838.
Descrittori MeSH principali: Fundus Oculi; Tomography, X-Ray; Models, Theoretical; Deep Learning.
Pagina: https://europepmc.org/article/MED/35085334 — https://doi.org/10.1371/journal.pone.0262838. Autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza dell'articolo dichiarata da Europe PMC: CC0 (la versione è indicata dall'editore sulla pagina). Abstract riportato senza modifiche al contenuto, con attribuzione; deposito marcato CC0.
Letto il 2026-10-31T12:22:03.123Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.