PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
May 9, 2026Journal of Medical Engineering & Technology

Multiparametric MRI-based prostate cancer classification using transfer learning, feature fusion, and ensemble methods

View Full Paper
Ask AI
Bookmark
Share

Authors

NANasser M. Al-ZidiDVD Vasumathi

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates effective classification of prostate cancer in clinical practice, implying improved diagnostic accuracy.

Key Points

  • This study aims to develop an advanced framework for classifying prostate cancer into clinically significant and insignificant categories.
  • Use of transfer learning with VGG19 and Vision Transformer for feature extraction from mpMRI sequences.
  • Employ feature fusion and support vector machine for classification.
  • Implement an ensemble approach for improved classification accuracy.
  • Achieved an AUC score of 0.85 for the ensemble output.
  • Found higher b-values in DWI sequences essential for classification performance.
  • Demonstrated effectiveness of combining CNN-based and transformer-based features.

Cite This Study

Al-Zidi et al. (2026) studied this question.

synapsesocial.com/papers/69fecf16b9154b0b8287626chttps://doi.org/10.1080/03091902.2026.2667355
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Clinically significant prostate cancer detection with deep learning in a multi-center magnetic resonance imaging study2026 · 1 citations
  2. 2Deep Learning and Clinical Data Fusion in Prostate Cancer: Diagnosis of Clinically Significant Lesions Using Multiparametric MRI2025
  3. 3Multistream fusion segmentation and classification of prostate lesions from magnetic resonance images2024 · 1 citations
  4. 4A comprehensive framework for multi-class prostate cancer classification using biparametric MRI: a multi-center retrospective study2026
  5. 5Non-invasive diagnosis strategy integrating PSMA PET/CT and mpMRI for patients with suspected prostate cancer: a multi-center study2026