EUVIMEDEUVIMED entdecken
Crossref

Category‐Specific Uncertainty Learning for Retinal Disease Diagnosis

Lingyi Chu, Fei Lu, Luping Fang, Danli Shi, Kai Jin, Qing Pan

International Journal of Imaging Systems and Technology · 2026-07 · 36 (4)

DOI: 10.1002/ima.70377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Imaging Systems and Technology, online erschienen am 29.05.2026. Verfasst von Lingyi Chu und 5 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Integrating artificial intelligence (AI) in retinal disease diagnosis faces challenges in effectively communicating prediction confidence and managing data uncertainty, which is critical for clinical acceptance. To address these limitations, we propose Category‐Specific Uncertainty Learning (CSUL), an advanced AI framework for diagnosing eight retinopathies using optical coherence tomography (OCT) images. CSUL leverages a fine‐tuned ResNet‐50 architecture and an uncertainty‐based classification mechanism to quantify prediction confidence. It further establishes category‐specific thresholds based on uncertainty distributions from the validation set, optimizing the retention of reliable predictions. For the unlabeled test data, CSUL introduces a pseudo‐labeling strategy using K‐means++ clustering, enabling the assignment of appropriate category‐specific thresholds. The proposed framework achieves exceptional performance, with a thresholded diagnostic accuracy of 99.58% and a retention rate of 85.18% on deterministic samples, outperforming conventional single‐threshold models. Notably, for the challenging DRUSEN category, it attains a 97.10% accuracy and a 59.14% retention rate, marking a significant improvement over the existing state‐of‐the‐art methods. In conclusion, the innovative integration of category‐specific thresholding and pseudo‐labeling in CSUL enhances diagnostic accuracy and reliability, addressing the key challenges in AI‐driven retinal disease screening and advancing its clinical applicability.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Chu, L., Lu, F., Fang, L., Shi, D., Jin, K., & Pan, Q. (2026). Category‐Specific Uncertainty Learning for Retinal Disease Diagnosis. International Journal of Imaging Systems and Technology, 36(4). https://doi.org/10.1002/ima.70377

Vancouver

Chu L, Lu F, Fang L, Shi D, Jin K, Pan Q. Category‐Specific Uncertainty Learning for Retinal Disease Diagnosis. International Journal of Imaging Systems and Technology. 2026;36(4). doi:10.1002/ima.70377

BibTeX
@article{Chu2026,
  author = {Chu, Lingyi and Lu, Fei and Fang, Luping and Shi, Danli and Jin, Kai and Pan, Qing},
  title = {Category‐Specific Uncertainty Learning for Retinal Disease Diagnosis},
  journal = {International Journal of Imaging Systems and Technology},
  year = {2026},
  volume = {36},
  number = {4},
  doi = {10.1002/ima.70377}
}
Kostenlos starten →