EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY-NC 4.0

Artificial intelligence in prostate cancer diagnosis: A systematic review of advances in gleason grade and PI-RADS classification

Anil B. Gavade, Priyanka A. Gavade, Rajendra B. Nerli, Donald C. Cooper, Les Sztandera, Utkal Mehta

Imaging · 01.12.2025 · 17 (2) · 91-103

DOI: 10.1556/1647.2025.00325 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Imaging, erschienen am 01.12.2025. Verfasst von Anil B. Gavade und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) is reshaping prostate cancer (PCa) diagnosis by integrating advanced imaging modalities such as multi-parametric MRI (mpMRI) and whole-slide imaging (WSI). Leveraging convolutional neural networks (CNNs), these models have demonstrated over 90% accuracy in tasks like tumor localization, gleason grading (GG), and risk stratification. mpMRI modalities—including T2-weighted, diffusion-weighted (DWI), and dynamic contrast-enhanced (DCE) sequences—combined with the standardized prostate imaging reporting and data system (PI-RADS) framework, support consistent clinical interpretation. In pathology, AI methods such as CNNs and U-Net architectures achieve high performance in GG and tumor segmentation, with intersection over union (IoU) scores between 0.75 and 0.85. These systems reduce subjectivity and pathologist workload. Emerging technologies like vision transformers (ViTs) and natural language processing (NLP) further advance large-scale histopathology analysis and clinical data interpretation. Explainable AI contributes to model transparency, fostering clinical trust. This review highlights critical future directions, including multimodal data fusion, real-time diagnostics, image-to-text reporting, and personalized treatment planning—underscoring AI's growing role in improving diagnostic accuracy and patient outcomes in PCa care.

Zitieren

APA

Gavade, A. B., Gavade, P. A., Nerli, R. B., Cooper, D. C., Sztandera, L., & Mehta, U. (2025). Artificial intelligence in prostate cancer diagnosis: A systematic review of advances in gleason grade and PI-RADS classification. Imaging, 17(2), 91-103. https://doi.org/10.1556/1647.2025.00325

Vancouver

Gavade AB, Gavade PA, Nerli RB, Cooper DC, Sztandera L, Mehta U. Artificial intelligence in prostate cancer diagnosis: A systematic review of advances in gleason grade and PI-RADS classification. Imaging. 2025;17(2):91-103. doi:10.1556/1647.2025.00325

BibTeX
@article{Gavade2025,
  author = {Gavade, Anil B. and Gavade, Priyanka A. and Nerli, Rajendra B. and Cooper, Donald C. and Sztandera, Les and Mehta, Utkal},
  title = {Artificial intelligence in prostate cancer diagnosis: A systematic review of advances in gleason grade and PI-RADS classification},
  journal = {Imaging},
  year = {2025},
  volume = {17},
  number = {2},
  pages = {91--103},
  doi = {10.1556/1647.2025.00325}
}
Kostenlos starten →