Multimodal imaging deep learning model for predicting extraprostatic extension in prostate cancer using MpMRI and
Fei Yao1,2, Heng Lin1, Ying-Nan Xue1,2
1Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, No. 1 of Xuefubei Road, Ouhai District, Wenzhou, 325000, Zhejiang Province, China.
Objective:
This study aimed to construct a multimodal imaging deep learning (DL) model integrating mpMRI and 18F-PSMA-PET/CT for the prediction of extraprostatic extension (EPE) in prostate cancer, and to assess its effectiveness in enhancing the diagnostic accuracy of radiologists.
Methods:
Clinical and imaging data were retrospectively collected from patients with pathologically confirmed prostate cancer (PCa) who underwent radical prostatectomy (RP). Data were collected from a primary institution (Center 1, n = 197) between January 2019 and June 2022 and an external institution (Center 2, n = 36) between July 2021 and November 2022. A multimodal DL model incorporating mpMRI and 18F-PSMA-PET/CT was developed to support radiologists in assessing EPE using the EPE-grade scoring system. The predictive performance of the DL model was compared with that of single-modality models, as well as with radiologist assessments with and without model assistance. Clinical net benefit of the model was also assessed.
Results:
For patients in Center 1, the area under the curve (AUC) for predicting EPE was 0.76 (0.72-0.80), 0.77 (0.70-0.82), and 0.82 (0.78-0.87) for the mpMRI-based DL model, PET/CT-based DL model, and the combined mpMRI + PET/CT multimodal DL model, respectively. In the external test set (Center 2), the AUCs for these models were 0.75 (0.60-0.88), 0.77 (0.72-0.88), and 0.81 (0.63-0.97), respectively. The multimodal DL model demonstrated superior predictive accuracy compared to single-modality models in both internal and external validations. The deep learning-assisted EPE-grade scoring model significantly improved AUC and sensitivity compared to radiologist EPE-grade scoring alone (P < 0.05), with a modest reduction in specificity. Additionally, the deep learning-assisted scoring model provided greater clinical net benefit than the radiologist EPE-grade score used by radiologists alone.
Conclusion:
The multimodal imaging deep learning model, integrating mpMRI and 18 F-PSMA PET/CT, demonstrates promising predictive performance for EPE in prostate cancer and enhances the accuracy of radiologists in EPE assessment. The model holds potential as a supportive tool for more individualized and precise therapeutic decision-making.
Insights
A new deep learning model combining MRI and PET/CT scans accurately predicts extraprostatic extension in prostate cancer. This tool improves radiologist accuracy, aiding in personalized treatment decisions.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence
Background:
- Accurate prediction of extraprostatic extension (EPE) is crucial for prostate cancer (PCa) treatment planning.
- Current diagnostic methods have limitations in precisely determining EPE.
- Multimodal imaging offers potential for improved diagnostic accuracy.
Purpose of the Study:
- To develop a multimodal deep learning (DL) model integrating magnetic resonance imaging (mpMRI) and 18F-PSMA-PET/CT for EPE prediction in PCa.
- To evaluate the DL model's effectiveness in enhancing radiologist diagnostic accuracy for EPE.
- To assess the clinical net benefit of the developed DL model.
Main Methods:
- Retrospective collection of clinical and imaging data from PCa patients who underwent radical prostatectomy.
- Development of a multimodal DL model combining mpMRI and 18F-PSMA-PET/CT.
- Comparison of the multimodal DL model's performance against single-modality models and radiologist assessments with and without model assistance.
Main Results:
- The combined mpMRI + PET/CT multimodal DL model achieved an AUC of 0.82 in the primary institution and 0.81 in the external validation set.
- The multimodal DL model demonstrated superior predictive accuracy compared to single-modality models.
- Deep learning-assisted assessment significantly improved AUC and sensitivity (P < 0.05) compared to radiologists alone, with a modest specificity reduction.
Conclusions:
- A multimodal deep learning model integrating mpMRI and 18F-PSMA-PET/CT shows strong predictive performance for EPE in prostate cancer.
- The model effectively enhances radiologist accuracy in EPE assessment.
- This AI tool shows potential for supporting individualized and precise therapeutic decision-making in prostate cancer management.
More Related Videos
Related Concept Videos
01:29Positron Emission Tomography
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body being...
01:27Imaging Studies IV: Magnetic Resonance Imaging