Dataset Information

The added value of PSMA PET/MR radiomics for prostate cancer staging.

ABSTRACT:

Purpose

To evaluate the performance of combined PET and multiparametric MRI (mpMRI) radiomics for the group-wise prediction of postsurgical Gleason scores (psGSs) in primary prostate cancer (PCa) patients.

Methods

Patients with PCa, who underwent [⁶⁸ Ga]Ga-PSMA-11 PET/MRI followed by radical prostatectomy, were included in this retrospective analysis (n = 101). Patients were grouped by psGS in three categories: ISUP grades 1-3, ISUP grade 4, and ISUP grade 5. mpMRI images included T1-weighted, T2-weighted, and apparent diffusion coefficient (ADC) map. Whole-prostate segmentations were performed on each modality, and image biomarker standardization initiative (IBSI)-compliant radiomic features were extracted. Nine support vector machine (SVM) models were trained: four single-modality radiomic models (PET, T1w, T2w, ADC); three PET + MRI double-modality models (PET + T1w, PET + T2w, PET + ADC), and two baseline models (one with patient data, one image-based) for comparison. A sixfold stratified cross-validation was performed, and balanced accuracies (bAcc) of the predictions of the best-performing models were reported and compared through Student's t-tests. The predictions of the best-performing model were compared against biopsy GS (bGS).

Results

All radiomic models outperformed the baseline models. The best-performing (mean ± stdv [%]) single-modality model was the ADC model (76 ± 6%), although not significantly better (p > 0.05) than other single-modality models (T1w: 72 ± 3%, T2w: 73 ± 2%; PET: 75 ± 5%). The overall best-performing model combined PET + ADC radiomics (82 ± 5%). It significantly outperformed most other double-modality (PET + T1w: 74 ± 5%, p = 0.026; PET + T2w: 71 ± 4%, p = 0.003) and single-modality models (PET: p = 0.042; T1w: p = 0.002; T2w: p = 0.003), except the ADC-only model (p = 0.138). In this initial cohort, the PET + ADC model outperformed bGS overall (82.5% vs 72.4%) in the prediction of psGS.

Conclusion

All single- and double-modality models outperformed the baseline models, showing their potential in the prediction of GS, even with an unbalanced cohort. The best-performing model included PET + ADC radiomics, suggesting a complementary value of PSMA-PET and ADC radiomics.

SUBMITTER: Solari EL

PROVIDER: S-EPMC8803696 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAccurate prostate cancer imaging is critical for patient management. Multiple studies have demonstrated superior diagnostic accuracy of [68Ga]-PSMA-11 PET/CT over conventional imaging for disease detection, with validated clinical and biochemical predictors of disease detection. More recently [18F]PSMA-1007 offers theoretical imaging advantages, but there is limited evidence of clinical and biochemical predictors of scan findings in the staging population. This study investigates the association of clinical variables with imaging characteristics among patients who underwent [18F]PSMA-1007 PET/CT for primary staging of men with histopathologically confirmed prostate carcinoma. A retrospective review of 194 consecutive patients imaged between May 2019 to May 2020 was performed. Association between imaging variables (presence and distribution of metastatic disease, primary tumour SUVmax) and clinical variables (EAU risk criteria) were assessed using descriptive statistics, logistic regression model and ROC analysis.ResultsThe median age, PSA level and ISUP grade were 70 years, 10 ng/mL and ISUP grade 3, respectively. There were 36.6% of patients with intermediate-risk and 60.8% of patients with high-risk disease. ISUP grade was associated with the presence of metastasis overall (p = 0.008) as well as regional nodal (p = 0.003), non-regional nodal (p = 0.041) and bone (p = 0.006) metastases. PSA level was associated with metastatic disease overall (p = 0.001), regional (p = 0.001) and non-regional nodal metastases (p = 0.004), but not with bone metastases (p = 0.087). There were too few visceral metastases for meaningful analysis. SUVmax of the primary prostatic tumour was associated with ISUP grade (p = 0.004), PSA level (p < 0.001) and AJCC stage (p = 0.034). PSA > 20 ng/mL and ISUP grade > 3 had a specificity of 85% (95% CI 78-91%) and 60% (95% CI 50-68%) and a sensitivity of 36% (95% CI 25-49%) and 62% (95% CI 49-74%), respectively, for detection of metastatic disease.ConclusionMetastatic disease according to [18F]PSMA-1007 PET/CT was associated with ISUP grade and PSA level. This is the largest study using [18F]PSMA-1007 PET/CT to confirm a positive correlation of PSA level, ISUP grade and stage with primary prostate tumour SUVmax.

Project description:PurposeIn PSMA-ligand PET/CT imaging, standardized evaluation frameworks and image-derived parameters are increasingly used to support prostate cancer staging. Clinical applicability remains challenging wherever manual measurements of numerous suspected lesions are required. Deep learning methods are promising for automated image analysis, typically requiring extensive expert-annotated image datasets to reach sufficient accuracy. We developed a deep learning method to support image-based staging, investigating the use of training information from two radiotracers.MethodsIn 173 subjects imaged with 68Ga-PSMA-11 PET/CT, divided into development (121) and test (52) sets, we trained and evaluated a convolutional neural network to both classify sites of elevated tracer uptake as nonsuspicious or suspicious for cancer and assign them an anatomical location. We evaluated training strategies to leverage information from a larger dataset of 18F-FDG PET/CT images and expert annotations, including transfer learning and combined training encoding the tracer type as input to the network. We assessed the agreement between the N and M stage assigned based on the network annotations and expert annotations, according to the PROMISE miTNM framework.ResultsIn the development set, including 18F-FDG training data improved classification performance in four-fold cross validation. In the test set, compared to expert assessment, training with 18F-FDG data and the development set yielded 80.4% average precision [confidence interval (CI): 71.1-87.8] for identification of suspicious uptake sites, 77% (CI: 70.0-83.4) accuracy for anatomical location classification of suspicious findings, 81% agreement for identification of regional lymph node involvement, and 77% agreement for identification of metastatic stage.ConclusionThe evaluated algorithm showed good agreement with expert assessment for identification and anatomical location classification of suspicious uptake sites in whole-body 68Ga-PSMA-11 PET/CT. With restricted PSMA-ligand data available, the use of training examples from a different radiotracer improved performance. The investigated methods are promising for enabling efficient assessment of cancer stage and tumor burden.