EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

When uncertainty guides learning: a highly effective approach to kidney disease classification in CT imaging

Muslima Akter, Fahmid Al Farid, Md Yousuf Ahmad, Md Azad Hossain Raju, Sowad Rahman, Jia Uddin, Hezerul Bin Abdul Karim

Frontiers in Big Data · 09.06.2026 · 9

DOI: 10.3389/fdata.2026.1825213 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Big Data, online erschienen am 09.06.2026. Verfasst von Muslima Akter und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Port City International University, Chittagong, Bangladesh. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Multimedia University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The high cost of expert annotations significantly hinders the advancement of deep learning models for clinical medical imaging. This work introduces an efficient entropy-based active learning framework that achieves outstanding classification performance for renal abnormalities (Normal, Cyst, Stone, Tumor) in CT scans while requiring only a minimal amount of labeled data. The dataset comprises 12,446 CT slices split 70/15/15 into training (8,716), validation (1,865), and test (1,865) partitions via stratified sampling. Starting with only 200 randomly selected images and employing predictive entropy for uncertainty sampling on a pretrained ResNet-50 backbone, the proposed method attains 99.71% ± 0.25% mean test accuracy (95% CI: [99.30, 99.94]) across five independent runs after just six query cycles on the standard 12,446-image CT kidney dataset. Our method uses only 2,000 labeled training images, representing 22.9% of the 8,716-image training partition (a 77.1% reduction in required annotations relative to full supervision of the training set). This performance matches or exceeds prior fully supervised methods trained on the complete labeled training partition while demonstrating substantially improved sample efficiency, particularly in early annotation cycles where entropy-guided selection converges significantly faster than random sampling. Statistical testing across five repeated runs confirms that results are stable (Shapiro-Wilk p = 0.148). The framework exhibits exceptional sample efficiency as described by an empirically fitted power-law curve with a fitted exponent of 1.2, and empirically observed uncertainty decay with a rate of 0.92. These results offer both practical insights into annotation efficiency and substantial application value in the medical imaging domain.

Schlagwörter

Stichwörter der Autor:innen

active learningdeep learningentropy acquisitioninformation theorykidney CT classificationlabel efficiencymedical imagingtransfer learning

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Port City International University, Chittagong, Bangladesh.
  • Faculty of Artificial Intelligence and Engineering (FAIE), Centre for Image and Vision Computing (CIVC), COE for Artificial Intelligence, Multimedia University, Cyberjaya, Selangor, Malaysia.
  • Faculty of Computer Science and Informatics, Berlin School of Business and Innovation, Berlin, Germany.
  • Masters of Science in Business Analytics (MSBAN), Trine University, Angola, IN, United States.
  • Department of Computer Science, University of South Dakota, Vermillion, SD, United States.
  • Department of Computer Science and Engineering, School of Data and Sciences, Dhaka, Bangladesh.

Förderung

  • Multimedia University

Zitieren

APA

Akter, M., Farid, F. A., Ahmad, M. Y., Hossain Raju, M. A., Rahman, S., Uddin, J., & Abdul Karim, H. B. (2026). When uncertainty guides learning: a highly effective approach to kidney disease classification in CT imaging. Frontiers in Big Data, 9. https://doi.org/10.3389/fdata.2026.1825213

Vancouver

Akter M, Farid FA, Ahmad MY, Hossain Raju MA, Rahman S, Uddin J, et al. When uncertainty guides learning: a highly effective approach to kidney disease classification in CT imaging. Frontiers in Big Data. 2026;9. doi:10.3389/fdata.2026.1825213

BibTeX
@article{Akter2026,
  author = {Akter, Muslima and Farid, Fahmid Al and Ahmad, Md Yousuf and Hossain Raju, Md Azad and Rahman, Sowad and Uddin, Jia and Abdul Karim, Hezerul Bin},
  title = {When uncertainty guides learning: a highly effective approach to kidney disease classification in CT imaging},
  journal = {Frontiers in Big Data},
  year = {2026},
  volume = {9},
  doi = {10.3389/fdata.2026.1825213}
}
Kostenlos starten →