RESUMO
PURPOSE: To assess the ability of tumor apparent diffusion coefficient (ADC) values obtained from multiparametric magnetic resonance imaging (mpMRI) to predict the risk of 5-year biochemical recurrence (BCR) after radical prostatectomy (RP). MATERIALS AND METHODS: This retrospective analysis included 1207 peripheral and 232 non-peripheral zone prostate cancer (PCa) patients who underwent mpMRI before RP (2012-2015), with the outcome of interest being 5-year BCR. ADC was evaluated as a continuous variable and as categories: low (< 850 µm2/s), intermediate (850-1100 µm2/s), and high (> 1100 µm2/s). Kaplan-Meier curves with log-rank testing of BCR-free survival, multivariable Cox proportional hazard regression models were formed to estimate the risk of BCR. RESULTS: Among the 1439 males with median age 63 (± 7) years, the median follow-up was 59 months, and 306 (25%) patients experienced BCR. Peripheral zone PCa patients with BCR had lower tumor ADC values than those without BCR (874 versus 1025 µm2/s, p < 0.001). Five-year BCR-free survival rates were 52.3%, 74.4%, and 87% for patients in the low, intermediate, and high ADC value categories, respectively (p < 0.0001). Lower ADC was associated with BCR, both as continuously coded variable (HR: 5.35; p < 0.001) and as ADC categories (intermediate versus high ADC-HR: 1.56, p = 0.017; low vs. high ADC-HR; 2.36, p < 0.001). In the non-peripheral zone PCa patients, no association between ADC and BCR was observed. CONCLUSION: Tumor ADC values and categories were found to be predictive of the 5-year BCR risk after RP in patients with peripheral zone PCa and may serve as a prognostic biomarker.
RESUMO
Acknowledging the increasing use of whole-body magnetic resonance imaging (WB-MRI) in the oncological setting, we conducted a narrative review focusing on practical aspects of the examination and providing a synthesis of various acquisition protocols described in the literature. Firstly, we addressed the topic of patient preparation, emphasizing methods to enhance examination acceptance. This included strategies for reducing anxiety and patient distress, improving staff-patient interactions, and increasing overall patient comfort. Secondly, we analysed WB-MRI acquisition protocols recommended in existing imaging guidelines, such as MET-RADS-P, MY-RADS, and ONCO-RADS, and provided an overview of acquisition protocols reported in the literature regarding other expanding applications of WB-MRI in oncology, in patients with breast cancer, ovarian cancer, melanoma, colorectal and lung cancer, lymphoma, and cancers of unknown primary. Finally, we suggested possible acquisition parameters for whole-body images across MR systems from three different vendors.
RESUMO
Tofts models have failed to produce reliable quantitative markers for prostate cancer. We examined the differences between prostate zones and lesion PI-RADS categories and grade group (GG) using regions of interest drawn in tumor and normal-appearing tissue for a two-compartment uptake (2CU) model (including plasma volume (vp), plasma flow (Fp), permeability surface area product (PS), plasma mean transit time (MTTp), capillary transit time (Tc), extraction fraction (E), and transfer constant (Ktrans)) and exponential (amplitude (A), arrival time (t0), and enhancement rate (α)), sigmoidal (amplitude (A0), center time relative to arrival time (A1 - T0), and slope (A2)), and empirical mathematical models, and time to peak (TTP) parameters fitted to high temporal resolution (1.695 s) DCE-MRI data. In 25 patients with 35 PI-RADS category 3 or higher tumors, we found Fp and α differed between peripheral and transition zones. Parameters Fp, MTTp, Tc, E, α, A1 - T0, and A2 and TTP all showed associations with PI-RADS categories and with GG in the PZ when normal-appearing regions were included in the non-cancer GG. PS and Ktrans were not associated with any PI-RADS category or GG. This pilot study suggests early enhancement parameters derived from ultrafast DCE-MRI may become markers of prostate cancer.
RESUMO
OBJECTIVE: To test the ability of high-performance machine learning (ML) models employing clinical, radiological, and radiomic variables to improve non-invasive prediction of the pathological status of prostate cancer (PCa) in a large, single-institution cohort. METHODS: Patients who underwent multiparametric MRI and prostatectomy in our institution in 2015-2018 were considered; a total of 949 patients were included. Gradient-boosted decision tree models were separately trained using clinical features alone and in combination with radiological reporting and/or prostate radiomic features to predict pathological T, pathological N, ISUP score, and their change from preclinical assessment. Model behavior was analyzed in terms of performance, feature importance, Shapley additive explanation (SHAP) values, and mean absolute error (MAE). The best model was compared against a naïve model mimicking clinical workflow. RESULTS: The model including all variables was the best performing (AUC values ranging from 0.73 to 0.96 for the six endpoints). Radiomic features brought a small yet measurable boost in performance, with the SHAP values indicating that their contribution can be critical to successful prediction of endpoints for individual patients. MAEs were lower for low-risk patients, suggesting that the models find them easier to classify. The best model outperformed (p ≤ 0.0001) clinical baseline, resulting in significantly fewer false negative predictions and overall was less prone to under-staging. CONCLUSIONS: Our results highlight the potential benefit of integrative ML models for pathological status prediction in PCa. Additional studies regarding clinical integration of such models can provide valuable information for personalizing therapy offering a tool to improve non-invasive prediction of pathological status. CLINICAL RELEVANCE STATEMENT: The best machine learning model was less prone to under-staging of the disease. The improved accuracy of our pathological prediction models could constitute an asset to the clinical workflow by providing clinicians with accurate pathological predictions prior to treatment. KEY POINTS: ⢠Currently, the most common strategies for pre-surgical stratification of prostate cancer (PCa) patients have shown to have suboptimal performances. ⢠The addition of radiological features to the clinical features gave a considerable boost in model performance. Our best model outperforms the naïve model, avoiding under-staging and resulting in a critical advantage in the clinic. â¢Machine learning models incorporating clinical, radiological, and radiomics features significantly improved accuracy of pathological prediction in prostate cancer, possibly constituting an asset to the clinical workflow.