A nomogram for accurately predicting the pathological upgrading of prostate cancer, based on 68 Ga-PSMA PET/CT

Prediction of clinically significant prostate cancer by [68 Ga]Ga-PSMA-11 PET/CT: a potential tool for selecting patients for active surveillance

PURPOSE

In our study, our aim was to investigate the role of [68 Ga]Ga-PSMA-11 PET /CT imaging in the diagnosis of clinically significant prostate cancer (csPCa) (ISUP GG 2 and higher) in patients initially diagnosed with ISUP GG 1 and 2 after prostate biopsy.

MATERIALS AND METHODS

We retrospectively reviewed 147 patient records in whom [68 Ga]Ga-PSMA-11 PET/CT imaging was performed preoperatively. All patients were initially diagnosed with ISUP GG 1 and 2 PCa by biopsy. Final pathology reports were obtained after radical prostatectomy. The [68 Ga]Ga-PSMA-11 PET/CT images were evaluated to determine the PRIMARY score. Patients' mpMRI-PIRADS scores were also recorded when available and analyzed in correlation with the pathology results.

RESULTS

For the 114 patients scored using PRIMARY, 19 out of 37 patients with scores of 1 and 2 (51%) were diagnosed with csPCa. Of the 77 patients with PRIMARY scores between 3 and 5, 64 (83%) had csPCa. Notably, every patient with a PRIMARY score of 5 had csPCa. PRIMARY scoring had a sensitivity of 77% and specificity of 58%, with a positive predictive value of 83%. A moderate correlation was observed between PRIMARY scores and ISUP GG (Rho = 0.54, p < 0.001). In contrast, the PIRADS score displayed a sensitivity and specificity of 86% and 25% respectively, with a positive predictive value of 68%. No substantial correlation was found between PIRADS and ISUP GG. Statistical analysis revealed a significant correlation between PRIMARY and ISUP GG (p < 0.001), but not between PIRADS and ISUP GG (p = 0.281). Comparatively, PRIMARY scoring was significantly more reliable than PIRADS scoring in identifying csPCa.

CONCLUSION

[68 Ga]Ga-PSMA-11 PET/CT imaging is promising for distinguishing high-risk prostate cancer patients from those apt for active surveillance, potentially aiding in the identification of csPCa.

Deep learning based on 68Ga-PSMA-11 PET/CT for predicting pathological upgrading in patients with prostate cancer

Objectives

To explore the feasibility and importance of deep learning (DL) based on 68Ga-prostate-specific membrane antigen (PSMA)-11 PET/CT in predicting pathological upgrading from biopsy to radical prostatectomy (RP) in patients with prostate cancer (PCa).

Methods

In this retrospective study, all patients underwent 68Ga-PSMA-11 PET/CT, transrectal ultrasound (TRUS)-guided systematic biopsy, and RP for PCa sequentially between January 2017 and December 2022. Two DL models (three-dimensional [3D] ResNet-18 and 3D DenseNet-121) based on 68Ga-PSMA-11 PET and support vector machine (SVM) models integrating clinical data with DL signature were constructed. The model performance was evaluated using area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

Results

Of 109 patients, 87 (44 upgrading, 43 non-upgrading) were included in the training set and 22 (11 upgrading, 11 non-upgrading) in the test set. The combined SVM model, incorporating clinical features and signature of 3D ResNet-18 model, demonstrated satisfactory prediction in the test set with an AUC value of 0.628 (95% confidence interval [CI]: 0.365, 0.891) and accuracy of 0.727 (95% CI: 0.498, 0.893).

Conclusion

A DL method based on 68Ga-PSMA-11 PET may have a role in predicting pathological upgrading from biopsy to RP in patients with PCa.