EUVIMEDEUVIMED entdecken
Crossref

Application of artificial intelligence incorporating PI-RADS v2.1 to prevent unnecessary prostate biopsies

Kun-Che Lin, Shu-Wei Liu, Yung-Ming Kuo, Gia-Shing Shieh, Yuh-Shyan Tsai, Chien-Hui Ou, Kuan-Yu Wu, Chun-Hung Yang, Che-Yuan Hu

Artificial Intelligence Surgery · 25.05.2026 · 6 (2) · 268-79

DOI: 10.20517/ais.2025.105 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Intelligence Surgery, online erschienen am 25.05.2026. Verfasst von Kun-Che Lin und 8 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aim

Artificial intelligence (AI) systems have the potential to enhance prostate magnetic resonance imaging (MRI) interpretation by providing objective image analysis, improving lesion detection, and reducing overdiagnosis. This study aimed to develop and evaluate an AI system for analyzing prostate multiparametric MRI (mpMRI) based on Prostate Imaging Reporting and Data System version 2.1 (PI-RADS v2.1) criteria.

Methods

In this retrospective, single-center study, we developed an AI system using data from 204 patients in the open-source PROSTATEx Challenge and 30 patients from National Cheng Kung University Hospital (NCKUH). The AI algorithm was retrospectively applied to mpMRI scans of 70 patients, and AI-derived PI-RADS scores were compared to those assigned by radiologists. Histopathological results from MRI-targeted biopsies served as the reference standard. The primary endpoints included the area under the receiver operating characteristic curve (AUROC) for the AI system versus radiologists, and the prostate gland segmentation metrics.

Results

The AI system achieved an average F1-score of 0.896 for prostate gland segmentation, demonstrating robust performance. In the 70 NCKUH cases, the AI system outperformed radiologists in differentiating benign prostatic hyperplasia (BPH) or non-clinically significant prostate cancer (non-csPC), with an AUROC of 0.813 [95% confidence interval (CI) 0.711-0.916; P < 0.001], compared to 0.695 (95%CI 0.572-0.818; P = 0.005) for radiologists. The AI system exhibited a more dichotomous distribution of PI-RADS scores, reducing diagnostic ambiguity in PI-RADS 3 lesions.

Conclusion

The AI system demonstrated improved performance in distinguishing BPH and non-csPC compared with radiologists. The dichotomous distribution of the AI-generated PI-RADS scores showed potential to avoid unnecessary biopsies.

Zitieren

APA

Lin, K., Liu, S., Kuo, Y., Shieh, G., Tsai, Y., Ou, C., Wu, K., Yang, C., & Hu, C. (2026). Application of artificial intelligence incorporating PI-RADS v2.1 to prevent unnecessary prostate biopsies. Artificial Intelligence Surgery, 6(2), 268-79. https://doi.org/10.20517/ais.2025.105

Vancouver

Lin K, Liu S, Kuo Y, Shieh G, Tsai Y, Ou C, et al. Application of artificial intelligence incorporating PI-RADS v2.1 to prevent unnecessary prostate biopsies. Artificial Intelligence Surgery. 2026;6(2):268-79. doi:10.20517/ais.2025.105

BibTeX
@article{Lin2026,
  author = {Lin, Kun-Che and Liu, Shu-Wei and Kuo, Yung-Ming and Shieh, Gia-Shing and Tsai, Yuh-Shyan and Ou, Chien-Hui and Wu, Kuan-Yu and Yang, Chun-Hung and Hu, Che-Yuan},
  title = {Application of artificial intelligence incorporating PI-RADS v2.1 to prevent unnecessary prostate biopsies},
  journal = {Artificial Intelligence Surgery},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {268--79},
  doi = {10.20517/ais.2025.105}
}
Kostenlos starten →