OBJECTIVE:To stratify the treatment outcomes of patients with oligometastatic gynecologic cancer receiving stereotactic body radiation therapy using an un-supervised clustering machine-learning method. METHODS:This multi-centric study was based on a cohort of 172 patients receiving curative-intent stereotactic body radiation therapy for oligometastatic uterine tumors, yielding a total of 268 lesions. The following clinical and dosimetric variables were collected: age, number of lesions per patient, type of lesion (lymph nodes vs parenchyma), lesion burden (number of treated lesions per patient), treatment site of lesion, number of fractions, total dose, biologically effective dose, and planning target volume. An un-supervised clustering method based on the K-means algorithm was used to identify clusters of lesions. The groups of lesions were compared in terms of local control, distant-metastases-free survival, and overall survival. RESULTS:The optimal number of clusters was found to be equal to 3. The analysis of variance indicated that the variables contributing the most to the separation of the clusters were the planning target volume, the biologically effective dose, and the type of lesion. Significant differences were found between the 3 groups of lesions in terms of local control (p =.002). At 2 years, local control was 84.6%, 74.7%, 47.5% for the 3 clusters that were "a posteriori" named as high-control, medium-control, and low-control, respectively. Distant-metastases-free survival was also found to be significantly different (p =.04) at 2 years, with values of 27.0%, 22.2%, 48.0% for the high-control, medium-control, and low-control, respectively. No differences were found for the overall survival (p =.22). CONCLUSIONS:In this study, un-supervised machine-learning partitioned oligometastatic lesions into 3 clusters associated with different treatment responses. A prospective validation is needed for prediction purposes.

ABSTRACT Background This study investigates the impact of radiotherapy (RT) on fatigue levels in prostate cancer (PC) patients, considering the significant physical and psychological impact of fatigue associated with cancer and its treatments. Methods PC patients undergoing a radical treatment from December 2002 to September 2022 were retrospectively evaluated. Fatigue was assessed using the Cancer Linear Analogue Scale (CLAS) across three dimensions: wellbeing (CLAS1), energy level (CLAS2), and daily activity performance (CLAS3), measured at baseline (T0), 1 month (T1), and 12 months (T2) post‐RT. Changes in CLAS scores ≥ 2 points from T0 were deemed clinically significant for RT‐induced fatigue. Results The cohort consisted of 1253 patients, with a median age of 72 years (range 45–90). Approximately 30% of patients experienced moderate or high levels of fatigue at baseline. At T1, RT‐related fatigue onset (decrease of CLAS1, 2, and 3 values) was observed in 10.8%, 14.3%, and 14.8% of patients, respectively. These figures slightly increased at T2 (12.7%, 18.8%, and 19.4%, respectively). Logistic regression identified hypofractionated RT, ADT, surgery, alcohol consumption, and higher‐grade toxicities as predictors of worsened fatigue across various dimensions. Conclusion In this extensive cohort of PC patients, approximately 30% experienced moderate to severe fatigue before initiating RT, with less than 20% reporting new or exacerbated fatigue post‐treatment. Factors including treatment‐related toxicities, hypofractionation, alcohol use, and ADT were significant contributors to fatigue. These findings underscore the complexity of managing fatigue in PC, highlighting the influence of both treatment modalities and lifestyle factors.

Purpose To report the final results of the xxxxx dose-escalation study evaluating an SBRT boost for persistent disease within 4 months after in-field radiotherapy. Material/Methods Within the xxxxx trial, arms (f) and (g) were designed to evaluate an SBRT boost for persistent disease after prior in-field radiotherapy. Arm (f) included patients previously irradiated with doses <50 Gy or with persistent disease in regions previously exposed to small bowel irradiation, whereas arm (g) enrolled patients with persistence in sites receiving prior doses >50 Gy. Dose escalation proceeded through three levels up to a total dose of 35 Gy in arm (f) and 30 Gy in arm (g), respectively. Each cohort was assessed for dose-limiting adverse events, defined as any radiation-related adverse events > grade 3 occurring within 6 months after SBRT. Results Sixty-nine lesions in 57 patients were treated between 2005 and 2018. Acute adverse events were mostly grade 1–2, with one grade 3 gastrointestinal event in arm (g). Late adverse events were limited, with a single grade 3 lower gastrointestinal event in arm (f). Clinical response was available for 65 lesions, with a disease control rate of 98.4%. One-year local control was 86.5%, while 1-year DMFS, DFS, and OS were 70.8%, 63.8%, and 91.9%, respectively. Conclusion Dose escalation up to 35 Gy and 30 Gy in the two study arms was feasible and associated with acceptable adverse events and favourable local control outcomes.

Oligometastatic breast cancer patients can today could benefit from a multimodal approach, combining systemic therapy with metastasis-directed treatment using stereotactic body radiotherapy (SBRT). However, the possibility to synchronously treat multiple lesions is still challenging, needing the ability to generate complex dose distributions with steep dose gradients outside the lesions and major sparing of surrounding organs at risk and accurately track and reproduce the patient's position before and during radiation therapy. We report the case of an oligometastatic patient from left breast cancer, which occurred after a full course of whole breast radiotherapy, treated using the potential of modern technology including single-isocenter setup, plan automation, breath-hold technique and surface guided tracking and reproducibility of patient's position before and during radiation therapy. A 44-year-old female patient with a history of left breast cancer, specifically a luminal-B-like invasive ductal carcinoma with Her2 overexpression, was admitted to our department. The patient previously underwent a left mastectomy (pT2N0M0), 4 cycles of adjuvant chemotherapy, adjuvant radiotherapy on the chest wall and lymph nodes drainage, and 5 years of hormonal therapy. A chest wall ultrasound and positron emission tomography revealed the presence of new lesions in the area of the surgical scar from the previous mastectomy, internal mammary, axillary and retropectoral levels. The 3 lesions were simultaneously treated with a mono-isocentric VMAT plan using SBRT technique with a total dose of 30 Gy delivered in 5 fractions. Due to the technical challenges, this treatment was supported by the use of planning automation, breath-hold technique and surface-guided radiation therapy to improve the accuracy of the dose delivery. Two different plans were generated and compared to pursue the best dosimetric result, including a summed plan obtained from 3 individual SBRT plans for each lesion with a separate isocenter placed in each of them (MIP), and a single-isocenter SBRT plan able to treat multiple lesions synchronously (SIP). Because of the advantages in terms of dosimetry and dose delivery efficiency, the patient was successfully treated with the SIP plan. The treatment time was reduced to about 4.5 minutes, allowing the comfortably use of breath-hold technique. After treatment, the condition of the patient was normal, and no toxicities have been observed in follow-up. SBRT with mono isocentric VMAT planning represents the recommended approach to simultaneously treat multiple lesions in close proximity in the thoracic district.

BACKGROUND:Patient-specific quality assurance (PSQA) is essential to guarantee the requested accuracy and safety of high-precision radiotherapy treatments. With the widespread adoption of modulated-intensity techniques, there is a growing need for increased operational efficiency. The potential of machine learning (ML) to accurately predict PSQA results has been investigated in recent years. In particular, plan complexity metrics have been used as model input features to be related to the PSQA outcome results in a number of supervised ML models. However, an unsupervised cluster analysis, able to uncover hidden patterns or groupings in data, has not been yet performed. PURPOSE:The primary aim of this research was to investigate the potential of different unsupervised ML methods to unravel hidden patterns and groupings in PSQA data based on a clustering analysis of plan complexity. METHODS AND MATERIALS:A total of 1329 pretreatment verification data from 660 consecutive patients with different tumour sites treated using volumetric modulated arc therapy (VMAT) were analyzed using the modulation complexity score (MCS) and the dynamic log-files generated by the linac. Predicted and measured fluences were compared using γ-analysis in terms of mean γ-values (γmean) and γ-pass rate (γ%) at the 2%(local)/2 mm criterion. Three unsupervised clustering algorithms, including agglomerative hierarchical clustering (AHC), K-means (KM) and Gaussian mixture models (GMM), were implemented to investigate the existence of natural groupings or clusters based on plan complexity. In addition, we subsequently trained several supervised models to validate cluster assignments on an external cohort of 202 VMAT arcs. RESULTS:For each clustering algorithms, the silhouette scores and the dendrogram analysis indicate the optimal number of clusters is three. The GMM clustered 65 arcs (4.9% of total arcs) into cluster 1 with mean values of γ%, γmean and MCS of 76.7%, 0.85 and 0.112, respectively. 916 arcs (68.9% of total arcs) were grouped into cluster 2 with mean values of γ%, γmean and MCS of 86.5%, 0.58 and 0.209, respectively. Lastly, 348 arcs (26.2% of total arcs) were grouped into cluster 3 with mean values of γ%, γmean and MCS of 92.9%, 0.40 and 0.359, respectively. Cluster 1 was associated with overmodulated plans, providing a warning MCS cutoff value of 0.145 for prompt replanning. Similarly, cluster 3 was associated with PSQA optimality, providing a MCS cutoff value of 0.278, beyond which plans have an a-priori very high QA pass results and can avoid the pretreatment dosimetric verification. Head-and-neck cases reported the higher (12.0%) and the lower (4.0%) classification rates in clusters 1 and 3, respectively, suggesting a major increase of the complexity score for these plans. CONCLUSION:This study demonstrated the potential of clustering analysis to unravel hidden patterns of plan complexity in dosimetric quality assurance of VMAT treatments. The results suggested that a three-clusters classification scheme has a true basis in plan complexity, supporting the hypothesis that the MCS metric strongly underlies PSQA results.

OBJECTIVES:To develop and validate a CT-based radiomic-clinical-dosimetric model to assess the treatment response of lung metastasis following stereotactic body radiation therapy (SBRT). METHODS:Eighty lung metastases treated with SBRT curative intent in a single institution were analysed. The treatment responses of lung lesions were categorized as a complete responding (CR) group vs a non-complete responding (NCR) group according to Response Evaluation Criteria in Solid Tumors (RECIST) criteria. For each lesion, 107 features were extracted from the CT planning images. The least absolute shrinkage and selection operator (LASSO) was used for features selection. An eXtreme Gradient Boosting (XGBoost) model was trained and validated. Shapley additive explanations (SHAP) analysis was used to provide insights into the impact of each variable on the model's predictions. RESULTS:Eight radiomic features, 1 dosimetric variable, and no clinical variables were identified by LASSO and used to build the XGBoost model. The model yielded areas under the curve (AUCs) of 0.897 (95% CI 0.860-0.935) and 0.864 (95% CI 0.803-0.924) in the training cohort and validation cohort, respectively. Skewness, surface-to-volume ratio, sphericity, and biological equivalent dose (BED10) were the most significant variables in predicting CR. The SHAP plots illustrated the feature's global and local impact to the model, explaining the model output in a clinician-friendly way. CONCLUSION:The integration of the XGBoost model with the SHAP strategy was able to assess lung lesions CR following SBRT, with the potential to assist clinicians in directing personalized SBRT strategies in an understandable manner. ADVANCES IN KNOWLEDGE:The explainable radiomics model we propose can better predict the treatment response of lung metastasis after SBRT and provide further guidance for clinical practice.