SavedAdd your journal

Journals / Adıyaman Üniversitesi Sağlık Bilimleri Dergisi / 2026 / Cilt: 12 Sayı: 2

Radiologist versus artificial intelligence in prostate mpMRI: A PI-RADS based diagnostic performance study

Prostat MR'da radyolog ile yapay zekâ karşılaştırması: PI-RADS tabanlı tanısal performans çalışması

Hamza Eren Güzel(Ministry of Health, İzmir City Hospital)0000-0003-4228-0840
Cemre Ozenbas(Tınaztepe Unviersity Private Buca Hospital)0000-0002-6688-5003
Hilal Şahin(Ministry of Health, İzmir City Hospital)0000-0001-8726-8998
Mehmet Mehdi Cambaz(Ministry of Health, İzmir City Hospital)0009-0008-9105-7518
Özgür Yaşar(Ministry of Health, İzmir City Hospital)0009-0001-6367-3996
Fatma Yasemin Öksüzler(Derpartment of Radiology, İzmir Democracy University Izmir Buca Seyfi Demirsoy Training and Research Hospital)0000-0002-6886-9162
Pages
157–168
Publication Date
2026-08-20
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Conclusion: AI may serve as a complementary tool in prostate mpMRI interpretation.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Aim: To compare radiologist and artificial intelligence (AI) PI-RADS assessments of prostate mpMRI and their performance for clinically significant prostate cancer detection.
📊
Key Findings & Data:Materials and Methods: This retrospective single-center study included 460 mpMRI examinations interpreted by radiologists and then analyzed by an AI decision-support system.
💡
Conclusion & Impact:Conclusion: AI may serve as a complementary tool in prostate mpMRI interpretation.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:Prostat · Manyetik rezonans görüntüleme · PI-RADS

Abstract

Aim: To compare radiologist and artificial intelligence (AI) PI-RADS assessments of prostate mpMRI and their performance for clinically significant prostate cancer detection. Materials and Methods: This retrospective single-center study included 460 mpMRI examinations interpreted by radiologists and then analyzed by an AI decision-support system. Patient- and lesion-level PI-RADS scores were compared using weighted Cohen’s kappa and Spearman correlation. Diagnostic performance was assessed in biopsied patients (n=161). Results: Patient-level agreement was moderate-to-good (κ=0.587), with 48.1% exact and 83.5% within-one-category agreement. Lesion-level agreement was moderate (κ=0.442). Adenocarcinoma was found in 50.3% of biopsied patients. For clinically significant cancer (ISUP ≥2), radiologists had higher sensitivity and AI slightly higher specificity at PI-RADS 4–5. Conclusion: AI may serve as a complementary tool in prostate mpMRI interpretation.

Özet

Amaç: Bu çalışmada, prostat mpMRG değerlendirmesinde radyolog ve yapay zekâ (YZ) PI-RADS yorumları ile klinik olarak anlamlı prostat kanserini saptamadaki performansları karşılaştırıldı. Gereç ve Yöntem: Retrospektif tek merkezli çalışmaya 460 mpMRG incelemesi dahil edildi. Görüntüler önce radyologlar, ardından YZ tabanlı sistem tarafından değerlendirildi. Hasta ve lezyon düzeyinde PI-RADS skorları Cohen kappa ve Spearman korelasyonu ile karşılaştırıldı. Tanısal performans biyopsi yapılan hastalarda incelendi (n=161). Bulgular: Hasta düzeyinde orta-iyi uyum saptandı (κ=0,587); tam uyum %48,1, bir kategori içinde uyum %83,5 idi. Lezyon düzeyinde uyum orta düzeydeydi (κ=0,442). Adenokarsinom hastaların %50,3’ünde saptandı. Klinik olarak anlamlı kanser için (ISUP ≥2), PI-RADS 4–5 eşik değerinde radyologlar daha yüksek duyarlılık, YZ ise hafifçe daha yüksek özgüllük gösterdi. Sonuç: YZ, prostat mpMRG yorumlamasında tamamlayıcı bir araç olabilir.

🔖

Cite This Article

Güzel, H. E., Ozenbas, C., Şahin, H., Cambaz, M. M., Yaşar, Ö., Öksüzler, F. Y. (2026). Radiologist versus artificial intelligence in prostate mpMRI: A PI-RADS based diagnostic performance study. Adıyaman Üniversitesi Sağlık Bilimleri Dergisi, Cilt: 12 Sayı: 2, 157–168. https://doi.org/10.30569/adiyamansaglik.1935598

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (25)

  1. Bray F, Laversanne M, Sung H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024;74(3):229-263. doi:10.3322/caac.21834
  2. O’Connor LP, Lebastchi AH, Horuz R, et al. Role of multiparametric prostate MRI in the management of prostate cancer. World J Urol. 2021;39(3):651-659. doi:10.1007/s00345-020-03310-z
  3. Mottet N, van den Bergh RCN, Briers E, et al. EAU-EANM-ESTRO-ESUR-SIOG guidelines on prostate cancer—2020 update. Part 1: screening, diagnosis, and local treatment with curative intent. Eur Urol. 2021;79(2):243-262. doi:10.1016/j.eururo.2020.09.042
  4. Eastham JA, Auffenberg GB, Barocas DA, et al. Clinically localized prostate cancer: AUA/ASTRO guideline, part I: introduction, risk assessment, staging, and risk-based management. J Urol. 2022;208(1):10-18. doi:10.1097/JU.0000000000002757
  5. Turkbey B, Rosenkrantz AB, Haider MA, et al. Prostate Imaging Reporting and Data System version 2.1: 2019 update of Prostate Imaging Reporting and Data System version 2. Eur Urol. 2019;76(3):340-351. doi:10.1016/j.eururo.2019.02.033
  6. Jóźwiak R, Sobecki P, Lorenc T. Intraobserver and interobserver agreement between six radiologists describing mpMRI features of prostate cancer using a PI-RADS 2.1 structured reporting scheme. Life (Basel). 2023;13(2):580. doi:10.3390/life13020580
  7. Rosenkrantz AB, Ginocchio LA, Cornfeld D, et al. Interobserver reproducibility of the PI-RADS version 2 lexicon: a multicenter study of six experienced prostate radiologists. Radiology. 2016;280(3):793-804. doi:10.1148/radiol.2016152542
  8. Westphalen AC, McCulloch CE, Anaokar JM, et al. Variability of the positive predictive value of PI-RADS for prostate MRI across 26 centers: experience of the Society of Abdominal Radiology Prostate Cancer Disease-Focused Panel. Radiology. 2020;296(1):76-84. doi:10.1148/radiol.2020190646
  9. de Rooij M, Israël B, Tummers M, et al. ESUR/ESUI consensus statements on multiparametric MRI for the detection of clinically significant prostate cancer: quality requirements for image acquisition, interpretation and radiologists’ training. Eur Radiol. 2020;30(10):5404-5416. doi:10.1007/s00330-020-06929-z
  10. Zhao Y, Zhang L, Zhang S, et al. Machine learning-based MRI imaging for prostate cancer diagnosis: systematic review and meta-analysis. Prostate Cancer Prostatic Dis. 2026;29(1):159-166. doi:10.1038/s41391-025-00997-2
  11. Bolocan VO, Mitoi A, Nicu-Canareica O, et al. Artificial intelligence in prostate MRI: current evidence and clinical translation challenges—a narrative review. J Imaging. 2025;11(10):335. doi:10.3390/jimaging11100335
  12. Bayerl N, Adams LC, Cavallaro A, et al. Assessment of a fully automated diagnostic AI software in prostate MRI: clinical evaluation and histopathological correlation. Eur J Radiol. 2024;181:111790. doi:10.1016/j.ejrad.2024.111790
  13. Saha A, Bosma JS, Twilt JJ, et al. Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study. Lancet Oncol. 2024;25(7):879-887. doi:10.1016/S1470-2045(24)00220-1
  14. Schelb P, Kohl S, Radtke JP, et al. Classification of cancer at prostate MRI: deep learning versus clinical PI-RADS assessment. Radiology. 2019;293(3):607-617. doi:10.1148/radiol.2019190938
  15. Arif M, Schoots IG, Castillo Tovar J, et al. Clinically significant prostate cancer detection and segmentation in low-risk patients using a convolutional neural network on multiparametric MRI. Eur Radiol. 2020;30(12):6582-6592. doi:10.1007/s00330-020-07008-z
  16. Yoo S, Gujrathi I, Haider MA, et al. Prostate cancer detection using deep convolutional neural networks. Sci Rep. 2019;9(1):19518. doi:10.1038/s41598-019-55972-4
  17. Saha A, Hosseinzadeh M, Huisman H. End-to-end prostate cancer detection in bpMRI via 3D CNNs: effects of attention mechanisms, clinical priori and decoupled false positive reduction. Med Image Anal. 2021;73:102155. doi:10.1016/j.media.2021.102155
  18. Oerther B, Engel H, Wilpert C, et al. Multi-center benchmarking of a commercially available artificial intelligence algorithm for Prostate Imaging Reporting and Data System (PI-RADS) score assignment and lesion detection in prostate MRI. Cancers (Basel). 2025;17(5):815. doi:10.3390/cancers17050815
  19. Bhayana R, O’Shea A, Anderson MA, et al. PI-RADS versions 2 and 2.1: interobserver agreement and diagnostic performance in peripheral and transition zone lesions among six radiologists. AJR Am J Roentgenol. 2021;217(1):141-151. doi:10.2214/AJR.20.24199
  20. Hötker AM, Blüthgen C, Rupp NJ, et al. Comparison of the PI-RADS 2.1 scoring system to PI-RADS 2.0: impact on diagnostic accuracy and inter-reader agreement. PLoS One. 2020;15(10):e0239975. doi:10.1371/journal.pone.0239975
  21. Ren H, Peng Y, Si Y, Ye Y, Gong L. Accuracy, intra-, and inter-radiologist variability of PI-RADS v2.1 scoring for clinically significant prostate cancer detection. Quant Imaging Med Surg. 2025;15(8):7080-7089. doi:10.21037/qims-2025-37
  22. Wen J, Ji Y, Han J, Shen X, Qiu Y. Inter-reader agreement of the Prostate Imaging Reporting and Data System version 2.1 for detection of prostate cancer: a systematic review and meta-analysis. Front Oncol. 2022;12:1013941. doi:10.3389/fonc.2022.1013941
  23. Alqahtani S. Systematic review of AI-assisted MRI in prostate cancer diagnosis: enhancing accuracy through second opinion tools. Diagnostics (Basel). 2024;14(22):2576. doi:10.3390/diagnostics14222576
  24. Twilt JJ, Saha A, Bosma JS, et al. AI-assisted vs unassisted identification of prostate cancer in magnetic resonance images. JAMA Netw Open. 2025;8(6):e2515672. doi:10.1001/jamanetworkopen.2025.15672
  25. Nakrour N, Cochran RL, Mercaldo ND, et al. Impact of artificial intelligence-assisted lesion detection on radiologists’ interpretation at multiparametric prostate MRI. Clin Imaging. 2025;122:110484. doi:10.1016/j.clinimag.2025.110484