Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Dynamic Digital Radiography for Functional Assessment of Unilateral Main Bronchial Stenosis Before and After Treatment: A Case Report.

Respirology case reports·2026
Same author

Predictors of short-term pain relief after polidocanol foam sclerotherapy for painful venous malformations.

European radiology·2026
Same author

150-GHz wide-bandwidth balanced photodetector for high-baud-rate PSK signal detection.

Optics express·2026
Same author

Acute cholecystitis in an intrahepatic duplicated gallbladder mimicking a liver abscess: The pivotal diagnostic role of percutaneous drainage.

Radiology case reports·2026
Same author

Long-Term Survival of Right Ventricular Cardiac Metastasis From Colon Cancer Causing Outflow Tract Obstruction.

JACC. Case reports·2026
Same author

Japanese Clinical Practice Guidelines for Vascular Tumors, Vascular Malformations, Lymphatic Malformations, and Lymphangiomatosis 2022.

Journal of plastic and reconstructive surgery·2026

Related Experiment Video

Updated: May 25, 2025

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

119

Prediction of Prostate Cancer Grades Using Radiomic Features.

Yasuhiro Yamamoto1, Takafumi Haraguchi2, Kaori Matsuda1

  • 1Department of Radiology, Houshasen Daiichi Hospital.

Acta Medica Okayama
|February 27, 2025
PubMed
Summary

A new machine learning model accurately predicts prostate cancer (PCa) grades using MRI radiomic features. This Radiomics model outperforms the PI-RADS system, potentially improving treatment decisions for PCa patients.

Keywords:
Gleason scoreProstate Imaging-Reporting and Data Systemmachine learningprostate cancerradiomics

More Related Videos

miRNA Expression Analyses in Prostate Cancer Clinical Tissues
11:29

miRNA Expression Analyses in Prostate Cancer Clinical Tissues

Published on: September 8, 2015

10.8K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

Related Experiment Videos

Last Updated: May 25, 2025

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

119
miRNA Expression Analyses in Prostate Cancer Clinical Tissues
11:29

miRNA Expression Analyses in Prostate Cancer Clinical Tissues

Published on: September 8, 2015

10.8K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

Area of Science:

  • Radiology
  • Oncology
  • Machine Learning

Background:

  • Accurate grading of prostate cancer (PCa) is crucial for treatment selection.
  • Distinguishing high-grade PCa (Gleason score [GS] ≥ 8) from lower grades is clinically significant.
  • Current methods like Prostate Imaging-Reporting and Data System (PI-RADS) have limitations.

Purpose of the Study:

  • To develop and evaluate a machine learning model for predicting PCa grades.
  • To compare the performance of a Radiomics model with the PI-RADS model.
  • To assess the utility of radiomic features from magnetic resonance imaging (MRI) for PCa grading.

Main Methods:

  • A cohort of 112 patients with biopsy-confirmed PCa was analyzed.
  • Two logistic regression models were constructed: a Radiomics model (radiomic features + PSA) and a PI-RADS model (PI-RADS scores + PSA).
  • Model performance was assessed using Area Under the Curve (AUC), sensitivity, and specificity via cross-validation and holdout methods.

Main Results:

  • The Radiomics model demonstrated a significantly higher AUC (0.799) compared to the PI-RADS model (0.710).
  • Using the holdout method, the Radiomics model achieved an AUC of 0.778, with 0.769 sensitivity and 0.778 specificity.
  • The Radiomics model outperformed the PI-RADS model in differentiating high-grade from lower-grade PCa.

Conclusions:

  • Machine learning utilizing MRI radiomic features offers a promising approach for predicting prostate cancer grades.
  • The developed Radiomics model shows superior performance over the PI-RADS model.
  • This tool may assist clinicians in determining optimal treatment strategies for PCa patients.