Can we predict pathology without surgery? Weighing the added value of multiparametric MRI and whole prostate radiomics in integrative machine learning models.

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. •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.

Photon vs proton hypofractionation in prostate cancer: A systematic review and meta-analysis.

BACKGROUND: High-level evidence on hypofractionated proton therapy (PT) for localized and locally advanced prostate cancer (PCa) patients is currently missing. The aim of this study is to provide a systematic literature review to compare the toxicity and effectiveness of curative radiotherapy with photon therapy (XRT) or PT in PCa. METHODS: PubMed, Embase, and the Cochrane Library databases were systematically searched up to April 2022. Men with a diagnosis of PCa who underwent curative hypofractionated RT treatment (PT or XRT) were included. Risk of grade (G) ≥ 2 acute and late genitourinary (GU) OR gastrointestinal (GI) toxicity were the primary outcomes of interest. Secondary outcomes were five-year biochemical relapse-free survival (b-RFS), clinical relapse-free, distant metastasis-free, and prostate cancer-specific survival. Heterogeneity between study-specific estimates was assessed using Chi-square statistics and measured with the I2 index (heterogeneity measure across studies). RESULTS: A total of 230 studies matched inclusion criteria and, due to overlapped populations, 160 were included in the present analysis. Significant lower rates of G ≥ 2 acute GI incidence (2 % vs 7 %) and improved 5-year biochemical relapse-free survival (95 % vs 91 %) were observed in the PT arm compared to XRT. PT benefits in 5-year biochemical relapse-free survival were maintained for the moderate hypofractionated arm (p-value 0.0122) and among patients in intermediate and low-risk classes (p-values < 0.0001 and 0.0368, respectively). No statistically relevant differences were found for the other considered outcomes. CONCLUSION: The present study supports that PT is safe and effective for localized PCa treatment, however, more data from RCTs are needed to draw solid evidence in this setting and further effort must be made to identify the patient subgroups that could benefit the most from PT.

Image-Guided Stereotactic Body Radiotherapy on Detectable Prostate Bed Recurrence after Prostatectomy in RT-Naïve Patients.

Purpose or Objective-The aim of the study is to evaluate the efficacy and safety of SBRT on detectable prostate bed recurrence in RT-naïve prostate cancer patients. MATERIALS AND METHODS: Eighty-six patients who underwent SBRT for macroscopic bed recurrence after prostatectomy were retrospectively included. Patients were treated based on mpMRI or choline/PSMA PET. RESULTS: The median time to biochemical relapse (BCR) after RP was 46 months, with a median PSA at restaging of 1.04 ng/mL. Forty-six patients were staged with mpMRI and choline/PSMA PET, while ten and thirty were treated based on PET and MRI only, respectively. Only one late G ≥ 2 GI toxicity was observed. With a median BCR follow-up of 14 months, twenty-nine patients experienced a BCR with a median PSA at recurrence of 1.66 ng/mL and a median survival free from the event of 40.1 months. The median time to BCR was 17.9 months. Twenty-seven patients had clinical relapse (CR), with a median CR follow-up of 16.27 months and a median time to CR of 23.0 months. Biochemical recurrence-free survival at one and two years was 88% and 66%, respectively, while clinical recurrence-free survival at one and two years was 92% and 82%, respectively. Regarding local relapses, seven were in the field of treatment, while eight of them were outside the field of treatment. CONCLUSIONS: Data showed that SBRT targeting only the macroscopic bed recurrence instead of the whole prostate bed is safe and effective. Additional data and longer follow-ups will provide a clearer indication of the appropriate treatment and staging methodology for these patients.

Oral Surgery and Osteoradionecrosis in Patients Undergoing Head and Neck Radiation Therapy: An Update of the Current Literature.

Osteoradionecrosis (ORN) is a serious long-term complication of head and neck radiotherapy (RT), which is often triggered by dental extractions. It results from avascular aseptic necrosis due to irradiated bone damage. ORN is challenging to treat and can lead to severe complications. Furthermore, ORN causes pain and distress, significantly reducing the patient's quality of life. There is currently no established preventive strategy. This narrative review aims to provide an update for the clinicians on the risk of ORN associated with oral surgery in head and neck RT patients, with a focus on the timing suitable for the oral surgery and possible ORN preventive treatments. An electronic search of articles was performed by consulting the PubMed database. Intervention and observational studies were included. A multidisciplinary approach to the patient is highly recommended to mitigate the risk of RT complications. A dental visit before commencing RT is highly advised to minimize the need for future dental extractions after irradiation, and thus the risk of ORN. Post-RT preventive strategies, in case of dento-alveolar surgery, have been proposed and include antibiotics, hyperbaric oxygen (HBO), and the combined use of pentoxifylline and tocopherol ("PENTO protocol"), but currently there is a lack of established standards of care. Some limitations in the use of HBO involve the low availability of HBO facilities, its high costs, and specific clinical contraindications; the PENTO protocol, on the other hand, although promising, lacks clinical trials to support its efficacy. Due to the enduring risk of ORN, removable prostheses are preferable to dental implants in these patients, as there is no consensus on the appropriate timing for their safe placement. Overall, established standards of care and high-quality evidence are lacking concerning both preventive strategies for ORN as well as the timing of the dental surgery. There is an urgent need to improve research for more efficacious clinical decision making.