Explainable Machine Learning Model to Predict Overall Survival in Patients Treated With Palliative Radiotherapy for Bone Metastases.

PURPOSE: The estimation of prognosis and life expectancy is critical in the care of patients with advanced cancer. To aid clinical decision making, we build a prognostic strategy combining a machine learning (ML) model with explainable artificial intelligence to predict 1-year survival after palliative radiotherapy (RT) for bone metastasis. MATERIALS AND METHODS: Data collected in the multicentric PRAIS trial were extracted for 574 eligible adults diagnosed with metastatic cancer. The primary end point was the overall survival (OS) at 1 year (1-year OS) after the start of RT. Candidate covariate predictors consisted of 13 clinical and tumor-related pre-RT patient characteristics, seven dosimetric and treatment-related variables, and 45 pre-RT laboratory variables. ML models were developed and internally validated using the Python package. The effectiveness of each model was evaluated in terms of discrimination. A Shapley Additive Explanations (SHAP) explainability analysis to infer the global and local feature importance and to understand the reasons for correct and misclassified predictions was performed. RESULTS: The best-performing model for the classification of 1-year OS was the extreme gradient boosting algorithm, with AUC and F1-score values equal to 0.805 and 0.802, respectively. The SHAP technique revealed that higher chance of 1-year survival is associated with low values of interleukin-8, higher values of hemoglobin and lymphocyte count, and the nonuse of steroids. CONCLUSION: An explainable ML approach can provide a reliable prediction of 1-year survival after RT in patients with advanced cancer. The implementation of SHAP analysis provides an intelligible explanation of individualized risk prediction, enabling oncologists to identify the best strategy for patient stratification and treatment selection.

Personalizing Prophylactic Radiotherapy for Hip Heterotopic Ossification: An AMSTAR-2 Compliant Review of Meta-analyses.

BACKGROUND/AIM: Heterotopic ossification (HO) is a common complication following total hip arthroplasty. Various prophylactic treatments have been proposed, including radiotherapy (RT). This review summarizes the evidence from meta-analyses on the efficacy of RT in preventing hip HO. MATERIALS AND METHODS: A literature search was conducted on PubMed. The quality of the meta-analyses was assessed using the AMSTAR-2 tool. RESULTS: Seven meta-analyses were included. One meta-analysis reported a significant reduction in HO occurrence after RT compared to the control group. Comparing RT and non-steroidal anti-inflammatory drugs, one and two meta-analyses showed significantly greater efficacy of RT in preventing severe HO and better outcomes in patients receiving drugs, respectively. Regarding RT settings, the postoperative and preoperative RT were each supported by one meta-analysis. Furthermore, two meta-analyses showed an advantage of multi-fractionated RT over single fraction RT. The overall confidence rate of the meta-analyses was moderate, low, and critically low in one, three, and three meta-analyses, respectively. CONCLUSION: RT is a confirmed prophylactic intervention for HO. However, the precise optimization of timing, dosage, and fractionation requires elucidation. Future research should focus on the development of predictive models through large-scale data collection and advanced analytics to refine individualized treatment strategies and assess RT comparative effectiveness with drugs.

Pattern of recurrence after stereotactic body radiotherapy of nodal lesions: a single-institution analysis.

OBJECTIVES: Stereotactic body radiotherapy (SBRT) and/or single fraction stereotactic body radiosurgery (SRS) are effective treatment options for the treatment of oligometastatic disease of lymph nodes. Despite the encouraging local control rate, progression-free survival remains unfair due to relapses that might occur in the same district or at other sites. The recurrence pattern analysis after nodal local ablative RT (laRT) in oligometastatic patients is presented in this study. METHODS: The pattern of failure of patients with nodal metastases who were recruited and treated with SBRT in the Destroy-1 or SRS in the Destroy-2 trials was investigated in this single-institution, retrospective analysis. The different relapsed sites following laRT were recorded. RESULTS: Data on 190 patients who received SBRT or SRS on 269 nodal lesions were reviewed. A relapse rate of 57.2% (154 out of 269 nodal lesions) was registered. The pattern of failure was distant in 88 (57.4%) and loco-regional in 66 (42.6%) patients, respectively. The most frequent primary malignancies among patients experiencing loco-regional failure were genitourinary and gynaecological cancers. Furthermore, the predominant site of loco-regional relapse (62%) was the pelvic area. Only 26% of locoregional relapses occurred contra laterally, with 74% occurring ipsilaterally. CONCLUSIONS: The recurrence rates after laRT for nodal disease were more frequent in distant regions compared to locoregional sites. The most common scenarios for locoregional relapse appear to be genitourinary cancer and the pelvic site. In addition, recurrences often occur in the same nodal station or in a nodal station contiguous to the irradiated nodal site. ADVANCES IN KNOWLEDGE: Local ablative radiotherapy is an effective treatment in managing nodal oligometastasis. Despite the high local control rate, the progression free survival remains dismal with recurrences that can occur both loco-regionally or at distance. To understand the pattern of failure could aid the physicians to choose the best treatment strategy. This is the first study that reports the recurrence pattern of a significant number of nodal lesions treated with laRT.

Augmented reality in brachytherapy: A narrative review.

Brachytherapy (BRT) plays a pivotal role in the treatment of tumors, offering precise radiation therapy directly to the affected area. However, this technique demands extensive training and skills development, posing challenges for widespread adoption and ensuring patient safety. This narrative review explored the utilization of augmented reality (AR) in BRT, seeking to summarize existing evidence, discuss key findings, limitations, and quality of research as well as outline future research directions. The review revealed promising findings regarding the integration of AR in BRT. Studies have suggested the feasibility and potential benefits of AR in education, training, intra-operative guidance, and treatment planning. However, the evidence remains limited and heterogeneous, with most studies in preliminary phases. Standardization, prospective clinical trials, patient-centered outcomes assessment, and cost-effectiveness analysis emerge as critical areas for future research. Augmented reality holds transformative potential for BRT by enhancing precision, safety, and training efficiency. To fully implement these benefits, the field requires standardized protocols, rigorous clinical trials, and in-depth patient-centered investigations. Policy-makers and healthcare providers should closely monitor developments in AR and consider its implementation in clinical practice, contingent and robust evidence, and cost-effectiveness analysis. The pro-active pursuit of evidence-based practices will contribute to optimizing patient care in BRT.

Radiomics-based discriminant analysis of principal components to stratify the treatment response of lung metastases following stereotactic body radiation therapy.

PURPOSE: Discriminant analysis of principal components (DAPC) was introduced to describe the clusters of genetically related individuals focusing on the variation between the groups of individuals. Borrowing this approach, we evaluated the potential of DAPC for the evaluation of clusters in terms of treatment response to SBRT of lung lesions using radiomics analysis on pre-treatment CT images. MATERIALS AND METHODS: 80 pulmonary metastases from 56 patients treated with SBRT were analyzed. Treatment response was stratified as complete, incomplete and null responses. For each lesion, 107 radiomics features were extracted using the PyRadiomics software. The concordance correlation coefficients (CCC) between the radiomics features obtained by two segmentations were calculated. DAPC analysis was performed to infer the structure of "radiomically" related lesions for treatment response assessment. The DAPC was performed using the "adegenet" package for the R software. RESULTS: The overall mean CCC was 0.97 ± 0.14. The analysis yields 14 dimensions in order to explain 95 % of the variance. DAPC was able to group the 80 lesions into the 3 different clusters based on treatment response depending on the radiomics features characteristics. The first Linear Discriminant achieved the best discrimination of individuals into the three pre-defined groups. The greater radiomics loadings who contributed the most to the treatment response differentiation were associated with the "sphericity", "correlation" and "maximal correlation coefficient" features. CONCLUSION: This study demonstrates that a DAPC analysis based on radiomics features obtained from pretreatment CT is able to provide a reliable stratification of complete, incomplete or null response of lung metastases following SBRT.

Further Clarification of Pain Management Complexity in Radiotherapy: Insights from Modern Statistical Approaches.

BACKGROUND: The primary objective of this study was to assess the adequacy of analgesic care in radiotherapy (RT) patients, with a secondary objective to identify predictive variables associated with pain management adequacy using a modern statistical approach, integrating the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm and the Classification and Regression Tree (CART) analysis. METHODS: This observational, multicenter cohort study involved 1387 patients reporting pain or taking analgesic drugs from 13 RT departments in Italy. The Pain Management Index (PMI) served as the measure for pain control adequacy, with a PMI score < 0 indicating suboptimal management. Patient demographics, clinical status, and treatment-related factors were examined to discern the predictors of pain management adequacy. RESULTS: Among the analyzed cohort, 46.1% reported inadequately managed pain. Non-cancer pain origin, breast cancer diagnosis, higher ECOG Performance Status scores, younger patient age, early assessment phase, and curative treatment intent emerged as significant determinants of negative PMI from the LASSO analysis. Notably, pain management was observed to improve as RT progressed, with a greater discrepancy between cancer (33.2% with PMI < 0) and non-cancer pain (73.1% with PMI < 0). Breast cancer patients under 70 years of age with non-cancer pain had the highest rate of negative PMI at 86.5%, highlighting a potential deficiency in managing benign pain in younger patients. CONCLUSIONS: The study underscores the dynamic nature of pain management during RT, suggesting improvements over the treatment course yet revealing specific challenges in non-cancer pain management, particularly among younger breast cancer patients. The use of advanced statistical techniques for analysis stresses the importance of a multifaceted approach to pain management, one that incorporates both cancer and non-cancer pain considerations to ensure a holistic and improved quality of oncological care.

Sarcopenic Obesity in Cervical Carcinoma: A Strong and Independent Prognostic Factor beyond the Conventional Predictors (ESTHER Study-AFRAID Project).

Locally advanced cervical cancer represents a significant treatment challenge. Body composition parameters such as body mass index, sarcopenia, and sarcopenic obesity, defined by sarcopenia and BMI ≥ 30 kg/m2, have been identified as potential prognostic factors, yet their overall impact remains underexplored. This study assessed the relationship between these anthropometric parameters alongside clinical prognostic factors on the prognosis of 173 cervical cancer patients. Survival outcomes in terms of local control (LC), distant metastasis-free survival (DMFS), disease-free survival (DFS), and overall survival (OS) were analyzed using Kaplan regression methods-Meier and Cox. Older age, lower hemoglobin levels, higher FIGO (International Federation of Gynecology and Obstetrics) stages, and lower total radiation doses were significantly associated with worse outcomes. Univariate analysis showed a significant correlation between BMI and the outcomes examined, revealing that normal-weight patients show higher survival rates, which was not confirmed by the multivariate analysis. Sarcopenia was not correlated with any of the outcomes considered, while sarcopenic obesity was identified as an independent negative predictor of DFS (HR: 5.289, 95% CI: 1.298-21.546, p = 0.020) and OS (HR: 2.645, 95% CI: 1.275-5.488, p = 0.009). This study highlights the potential of sarcopenic obesity as an independent predictor of clinical outcomes. These results support their inclusion in prognostic assessments and treatment planning for patients with advanced cervical cancer.

Stereotactic body radiotherapy (SIB-VMAT technique) to dominant intraprostatic lesion (DIL) for localized prostate cancer: a dose-escalation trial (DESTROY-4).

PURPOSE: DESTROY-4 (DOSE-ESCALATION STUDY OF STEREOTACTIC BODY RADIATION THERAPY) was a Phase I trial aimed to evaluate the safety and the feasibility of escalating doses of stereotactic body radiation therapy (SBRT) on MRI-defined Dominant Intraprostatic Lesion (DIL) in low- and intermediate-risk pCa patients using a simultaneous integrated boost-volumetric arc therapy (SIB-VMAT) technique. METHODS: Eligible patients included those with low- and intermediate-risk prostate carcinoma (NCCN risk classes) and an International Prostatic Symptoms Score (IPSS) ≤ 15. No restriction about DIL and prostate volumes was set. Pretreatment preparation required an enema and the placement of intraprostatic gold fiducials. SBRT was delivered in five consecutive daily fractions. For the first three patients, the DIL radiation dose was set at 8 Gy per fraction up to a total dose of 40 Gy (PTV1) and was gradually increased in succeeding cohorts to total doses of 42.5 Gy, 45.0 Gy, 47.5 Gy, and finally, 50.0 Gy, while keeping the prescription of 35 Gy/7 Gy per fraction for the entire prostate gland. Dose-limiting toxicity (DLT) was defined as grade 3 or worse gastrointestinal (GI) or genitourinary (GU) toxicity occurring within 90 days of follow-up (Common Terminology Criteria of Adverse Events scale 4.0). Patients completed quality-of-life questionnaires at defined intervals. RESULTS: Twenty-four patients with a median age of 75 (range, 58-89) years were enrolled. The median follow-up was 26.3 months (8.9-84 months). 66.7% of patients were classified as intermediate-risk groups, while the others were low-risk groups, according to the NCCN guidelines. Enrolled patients were treated as follows: 8 patients (40 Gy), 5 patients (42.5 Gy), 4 patients (45 Gy), 4 patients (47.5 Gy), and 3 patients (50 Gy). No severe acute toxicities were observed. G1 and G2 acute GU toxicities occurred in 4 (16%) and 3 patients (12.5%), respectively. Two patients (8.3%) and 3 patients (12.5%) experienced G1 and G2 GI toxicities, respectively. Since no DLTs were observed, 50 Gy in five fractions was considered the MTD. The median nadir PSA was 0.20 ng/mL. A slight improvement in QoL values was registered after the treatment. CONCLUSION: This trial confirms the feasibility and safety of a total SIB-VMAT dose of 35 Gy on the whole gland and 50 Gy on DIL in 5 fractions daily administered in a well-selected low- and intermediate-risk prostate carcinoma population. A phase II study is ongoing to confirm the tolerability of the schedule and assess the efficacy.

Efficacy of stereotactic body radiotherapy and response prediction using artificial intelligence in oligometastatic gynaecologic cancer.

PURPOSE: We present a large real-world multicentric dataset of ovarian, uterine and cervical oligometastatic lesions treated with SBRT exploring efficacy and clinical outcomes. In addition, an exploratory machine learning analysis was performed. METHODS: A pooled analysis of gynecological oligometastases in terms of efficacy and clinical outcomes as well an exploratory machine learning model to predict the CR to SBRT were carried out. The CR rate following radiotherapy (RT) was the study main endpoint. The secondary endpoints included the 2-year actuarial LC, DMFS, PFS, and OS. RESULTS: 501 patients from 21 radiation oncology institutions with 846 gynecological metastases were analyzed, mainly ovarian (53.1%) and uterine metastases(32.1%).Multiple fraction radiotherapy was used in 762 metastases(90.1%).The most frequent schedule was 24 Gy in 3 fractions(13.4%). CR was observed in 538(63.7%) lesions. The Machine learning analysis showed a poor ability to find covariates strong enough to predict CR in the whole series. Analyzing them separately, in uterine cancer, if RT dose≥78.3Gy, the CR probability was 75.4%; if volume was <13.7 cc, the CR probability became 85.1%. In ovarian cancer, if the lesion was a lymph node, the CR probability was 71.4%; if volume was <17 cc, the CR probability rose to 78.4%. No covariate predicted the CR for cervical lesions. The overall 2-year actuarial LC was 79.2%, however it was 91.5% for CR and 52.5% for not CR lesions(p < 0.001). The overall 2-year DMFS, PFS and OS rate were 27.3%, 24.8% and 71.0%, with significant differences between CR and not CR. CONCLUSIONS: CR was substantially associated to patient outcomes in our series of gynecological cancer oligometastatic lesions. The ability to predict a CR through artificial intelligence could also drive treatment choices in the context of personalized oncology.

Coronary artery evaluation during ECG-gated CT of the thoracic aorta: Do not consider it a negligible clinical information.

A CT angiography, performed for ascending aorta study, revealed, incidentally, an anomalous origin and course of right coronary artery. Anomalies in the origins and course of the coronary arteries are critical information that should not be missed, because they can worsen the patient's prognosis.

Machine-learning prediction of treatment response to stereotactic body radiation therapy in oligometastatic gynecological cancer: A multi-institutional study.

BACKGROUND AND PURPOSE: We aimed to develop and validate different machine-learning (ML) prediction models for the complete response of oligometastatic gynecological cancer after SBRT. MATERIAL AND METHODS: One hundred fifty-seven patients with 272 lesions from 14 different institutions and treated with SBRT with radical intent were included. Thirteen datasets including 222 lesions were combined for model training and internal validation purposes, with an 80:20 ratio. The external testing dataset was selected as the fourteenth Institution with 50 lesions. Lesions that achieved complete response (CR) were defined as responders. Prognostic clinical and dosimetric variables were selected using the LASSO algorithm. Six supervised ML models, including logistic regression (LR), classification and regression tree analysis (CART) and support vector machine (SVM) using four different kernels, were trained and tested to predict the complete response of uterine lesions after SBRT. The performance of models was assessed by receiver operating characteristic curves (ROC), area under the curve (AUC) and calibration curves. An explainable approach based on SHapley Additive exPlanations (SHAP) method was deployed to generate individual explanations of the model's decisions. RESULTS: 63.6% of lesions had a complete response and were used as ground truth for the supervised models. LASSO strongly associated complete response with three variables, namely the lesion volume (PTV), the type of lesions (lymph-nodal versus parenchymal), and the biological effective dose (BED10), that were used as input for ML modeling. In the training set, the AUCs for complete response were 0.751 (95% CI: 0.716-0.786), 0.766 (95% CI: 0.729-0.802) and 0.800 (95% CI: 0.742-0.857) for the LR, CART and SVM with a radial basis function kernel, respectively. These models achieve AUC values of 0.727 (95% CI: 0.669-0.795), 0.734 (95% CI: 0.649-0.815) and 0.771 (95% CI: 0.717-0.824) in the external testing set, demonstrating excellent generalizability. CONCLUSION: ML models enable a reliable prediction of the treatment response of oligometastatic lesions receiving SBRT. This approach may assist radiation oncologists to tailor more individualized treatment plans for oligometastatic patients.

Imaging of Strictures in Crohn's Disease.

Crohn's disease (CD) is a chronic inflammation of the digestive tract, and it frequently affects young patients. It can involve any intestinal segment, even though it frequently affects the distal ileum. Up to 80% of patients with CD present with inflammatory behavior, and 5% to 28% develop stricturing disease. Based on the predominant mechanism causing them, strictures can be categorized as inflammatory, fibrotic, or mixed. Determining the relative amounts of inflammation and fibrosis in a stricture can influence treatment decisions. Imaging is an extremely useful tool in patients with small bowel stricturing CD to confirm the diagnosis and to evaluate disease characteristics, usually using CT or MRI. The aim of this paper is to describe how imaging can evaluate a patient with small bowel CD stricture.

Unraveling the safety of adjuvant radiotherapy in prostate cancer: impact of older age and hypofractionated regimens on acute and late toxicity - a multicenter comprehensive analysis.

Background: The objective of this study was to assess the impact of age and other patient and treatment characteristics on toxicity in prostate cancer patients receiving adjuvant radiotherapy (RT). Materials and methods: This observational study (ICAROS-1) evaluated both acute (RTOG) and late (RTOG/EORTC) toxicity. Patient- (age; Charlson's comorbidity index) and treatment-related characteristics (nodal irradiation; previous TURP; use, type, and duration of ADT, RT fractionation and technique, image-guidance systems, EQD2 delivered to the prostate bed and pelvic nodes) were recorded and analyzed. Results: A total of 381 patients were enrolled. The median EQD2 to the prostate bed (α/ß=1.5) was 71.4 Gy. The majority of patients (75.4%) were treated with intensity-modulated radiation therapy (IMRT) or volumetric-modulated arc therapy (VMAT). Acute G3 gastrointestinal (GI) and genitourinary (GU) toxicity rates were 0.5% and 1.3%, respectively. No patients experienced >G3 acute toxicity. The multivariable analysis of acute toxicity (binomial logistic regression) showed a statistically significant association between older age (> 65) and decreased odds of G≥2 GI acute toxicity (OR: 0.569; 95%CI: 0.329-0.973; p: 0.040) and decreased odds of G≥2 GU acute toxicity (OR: 0.956; 95%CI: 0.918-0.996; p: 0.031). The 5-year late toxicity-free survival rates for G≥3 GI and GU toxicity were 98.1% and 94.5%, respectively. The only significant correlation found (Cox's regression model) was a reduced risk of late GI toxicity in patients undergoing hypofractionation (HR: 0.38; 95% CI: 0.18-0.78; p: 0.008). Conclusions: The unexpected results of this analysis could be explained by a "response shift bias" concerning the protective effect of older age and by treatment in later periods (using IMRT/VMAT) concerning the favorable effect of hypofractionation. However, overall, the study suggests that age should not be a reason to avoid adjuvant RT and that the latter is well-tolerated even with moderately hypofractionated regimens.