Enhancing Prostate Cancer Detection: Integrating Multiparametric Magnetic Resonance Imaging and 68Ga-prostate-specific Membrane Antigen Positron Emission Tomography/Computed Tomography with Machine Learning
Journal of Medical Physics · 2025-04 · 50 (2) · 329-336
DOI: 10.4103/jmp.jmp_48_25 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Medical Physics, online erschienen am 03.07.2025. Verfasst von Mohammad Hossein Sadeghi und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nuclear Engineering, School of Mechanical Engineering, Shiraz University, Shiraz, Iran. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Purpose
Early and accurate detection of clinically significant prostate cancer (PCa) is crucial for effective patient management. Traditional diagnostic methods, including systematic biopsy guided by transrectal ultrasound, have limitations in detecting significant cancers. Multiparametric magnetic resonance imaging (mpMRI) has shown promise in overcoming these limitations, but it remains operator-dependent and may miss some significant cases. This study explores the integration of mpMRI with 68 Ga-prostate-specific membrane antigen positron emission tomography/computed tomography ( 68 Ga-PSMA PET/CT) to enhance diagnostic accuracy. Materials and Methods: This study included 15 patients with suspected PCa, who underwent mpMRI and 68 Ga-PSMA PET/CT imaging, followed by histopathological confirmation after radical prostatectomy. Imaging data were analyzed using advanced machine learning (ML) models, including support vector machine, random forest, logistic regression, and k-nearest neighbors, to assess diagnostic accuracy. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated to compare the performance of the imaging modalities.
Results
MpMRI demonstrated an AUC of 0.91, with a sensitivity of 77% and specificity of 89% at the selected threshold (Prostate Imaging-Reporting and Data System 4). PET/CT alone showed an AUC of 0.89, with higher sensitivity (90%) but lower specificity (72%). The combination of mpMRI and PET/CT did not significantly improve the overall diagnostic performance, as indicated by a net reclassification index of −3% ( P = 0.84).
Conclusions
While 68 Ga-PSMA PET/CT improves sensitivity in detecting PCa, its lower specificity limits the incremental benefit when combined with mpMRI. ML models show potential in optimizing diagnostic approaches, but further research with larger cohorts is needed to confirm these findings and refine the integration of imaging modalities.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Nuclear Engineering, School of Mechanical Engineering, Shiraz University, Shiraz, Iran.
- Radiation Biology Research Center, Iran University of Medical Sciences, Tehran, Iran.
- Radiation Sciences Research Center (ARSRC), Aja University of Medical Sciences, Tehran, Iran.
- Radiation Research Center, School of Mechanical Engineering, Shiraz University, Shiraz, Iran.
- Department of Nuclear Medicine, Abu Ali Sina Hospital, Shiraz University of Paramedical Sciences, Shiraz, Iran.
Zitieren
APA
Sadeghi, M. H., Bagheri, H., Rajaeinejad, M., Ardalan, M. A., Karami, I., Sadeghi, S., Mosadeghkhah, A., Sina, S., KhajehRahimi, F., & Sheiki, M. (2025). Enhancing Prostate Cancer Detection: Integrating Multiparametric Magnetic Resonance Imaging and 68Ga-prostate-specific Membrane Antigen Positron Emission Tomography/Computed Tomography with Machine Learning. Journal of Medical Physics, 50(2), 329-336. https://doi.org/10.4103/jmp.jmp_48_25
Vancouver
Sadeghi MH, Bagheri H, Rajaeinejad M, Ardalan MA, Karami I, Sadeghi S, et al. Enhancing Prostate Cancer Detection: Integrating Multiparametric Magnetic Resonance Imaging and 68Ga-prostate-specific Membrane Antigen Positron Emission Tomography/Computed Tomography with Machine Learning. Journal of Medical Physics. 2025;50(2):329-336. doi:10.4103/jmp.jmp_48_25
BibTeX
@article{Sadeghi2025,
author = {Sadeghi, Mohammad Hossein and Bagheri, Hamed and Rajaeinejad, Mohsen and Ardalan, Mohammad Afshar and Karami, Ismail and Sadeghi, Shahryar and Mosadeghkhah, Ali and Sina, Sedigheh and KhajehRahimi, Farnaz and Sheiki, Mahboobeh},
title = {Enhancing Prostate Cancer Detection: Integrating Multiparametric Magnetic Resonance Imaging and 68Ga-prostate-specific Membrane Antigen Positron Emission Tomography/Computed Tomography with Machine Learning},
journal = {Journal of Medical Physics},
year = {2025},
volume = {50},
number = {2},
pages = {329--336},
doi = {10.4103/jmp.jmp_48_25}
}
EUVIMED