Confidence-based classification of clinically significant prostate cancer on biparametric MRI using Monte…

Abstract

Objective

Accurate early diagnosis of Clinically Significant prostate cancer (csPCa) is crucial for improving patient survival rates. This study aimed to develop and validate an interpretable, confidence-based deep learning model for csPCa classification using biparametric MRI (bpMRI).Methods

A retrospective analysis was conducted on bpMRI data from 410 patients. A classification model was constructed using the visual geometry group 16-layer (VGG-16) network, incorporating gradient-weighted class activation mapping (Grad-CAM) for visual interpretability, Monte Carlo Dropout (MC-Dropout) for uncertainty estimation, and a rejection mechanism. The model's performance was evaluated using receiver operating characteristic (ROC) curves and area under the ROC curve (AUC).Results

Across all predictions, the confidence-based model achieved an overall accuracy of 79.3% before rejection. At a confidence threshold of 0.8, 80.8% of predictions were retained, among which the selective accuracy was 94.6%, with 99 false-positive and 2 false-negative predictions. Besides, the model's accuracy outperformed that of a senior radiologist (94.6% vs 90.8%). Qualitative Grad-CAM visualization demonstrated that the classifier frequently assigned high activation to MRI regions considered suspicious for csPCa; however, quantitative spatial agreement with lesion annotations was not assessed.Conclusion

This confidence-based model identifies csPCa lesions and provides reliable confidence scores without pixel-level annotations. By rejecting uncertain predictions, it enhances the transparency and safety of clinical decision-making.

Cross-attention fusion of biparametric MRI sequences with demographic and clinical variables for patient-level classification of clinically significant prostate cancer
Avtantil Dimitriadis, Grigorios Kalliatakis, Richard Osuala +78
Scientific Reports8 Oct 2026Peer-reviewedCC BY 4.0Full textMedical imaging & radiologyCrossref
Characterization and Antimicrobial Susceptibility Patterns of Clinically Significant Non-fermenting Gram-Negative Bacilli Isolated From Clinical Specimens
Dhanashree R Chavan, Ravindra V Shinde, Satish R Patil
Cureus16 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC
Transcatheter atrial septal defect closure in infants weighing 3 to 6 kg with clinically significant bronchopulmonary dysplasia
Ernesto Mejia, Anne C Taylor, Martin L Bocks +1
JTCVS Structural and Endovascular23 Sep 2026Peer-reviewedCC BY-NC-ND 4.0Full textGeneral medicinePMCEurope PMC
Validation of the discriminatory performance of the iPREFACE score for clinically significant fetal acidemia: an outcome-enriched nested case–control study
Ayumu Ito, Mio Kamiya, Eijiro Hayata +2
AJOG global reports10 Sep 2026Peer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC
Clinically significant neck pain and tablet tilt angles in real-world educational settings: A nationwide cross-sectional study of university students
Saikaew Chuachan, Jetsadakorn Thawornrattanachot, Jakrapan Sen +3
PLOS One24 Sep 2026Peer-reviewedCC BY 4.0Full textEpidemiology & public healthPLOS

Cite

BibTeX RIS

BibTeX

@article{hao2026confidencebased,
  title = {{Confidence-based classification of clinically significant prostate cancer on biparametric MRI using Monte Carlo dropout and Grad-CAM visualization.}},
  author = {Cheng Hao and Yuze Meng and Yong Peng and Xia Du},
  journal = {Frontiers in oncology},
  year = {2026},
  month = oct,
  doi = {10.3389/fonc.2026.1819986},
  url = {https://europepmc.org/article/MED/42908607},
  note = {CC BY},
}

RIS

TY  - JOUR
TI  - Confidence-based classification of clinically significant prostate cancer on biparametric MRI using Monte Carlo dropout and Grad-CAM visualization.
AU  - Cheng Hao
AU  - Yuze Meng
AU  - Yong Peng
AU  - Xia Du
PY  - 2026
DA  - 2026/10/07
JO  - Frontiers in oncology
DO  - 10.3389/fonc.2026.1819986
UR  - https://europepmc.org/article/MED/42908607
AB  - Objective  Accurate early diagnosis of Clinically Significant prostate cancer (csPCa) is crucial for improving patient survival rates. This study aimed to develop and validate an interpretable, confidence-based deep learning model for csPCa classification using biparametric MRI (bpMRI).Methods  A retrospective analysis was conducted on bpMRI data from 410 patients. A classification model was constructed using the visual geometry group 16-layer (VGG-16) network, incorporating gradient-weighted class activation mapping (Grad-CAM) for visual interpretability, Monte Carlo Dropout (MC-Dropout) for uncertainty estimation, and a rejection mechanism. The model's performance was evaluated using receiver operating characteristic (ROC) curves and area under the ROC curve (AUC).Results  Across all predictions, the confidence-based model achieved an overall accuracy of 79.3% before rejection. At a confidence threshold of 0.8, 80.8% of predictions were retained, among which the selective accuracy was 94.6%, with 99 false-positive and 2 false-negative predictions. Besides, the model's accuracy outperformed that of a senior radiologist (94.6% vs 90.8%). Qualitative Grad-CAM visualization demonstrated that the classifier frequently assigned high activation to MRI regions considered suspicious for csPCa; however, quantitative spatial agreement with lesion annotations was not assessed.Conclusion  This confidence-based model identifies csPCa lesions and provides reliable confidence scores without pixel-level annotations. By rejecting uncertain predictions, it enhances the transparency and safety of clinical decision-making.
SN  - 2234-943X
ER  -

Abstract

Related

Cite