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.

CT radiomic predictors of local relapse after SBRT for lung oligometastases from colorectal cancer: a single institute pilot study.

OBJECTIVES: To assess the potential of radiomic features (RFs) extracted from simulation computed tomography (CT) images in discriminating local progression (LP) after stereotactic body radiotherapy (SBRT) in the management of lung oligometastases (LOM) from colorectal cancer (CRC). MATERIALS AND METHODS: Thirty-eight patients with 70 LOM treated with SBRT were analyzed. The largest LOM was considered as most representative for each patient and was manually delineated by two blinded radiation oncologists. In all, 141 RFs were extracted from both contours according to IBSI (International Biomarker Standardization Initiative) recommendations. Based on the agreement between the two observers, 134/141 RFs were found to be robust against delineation (intraclass correlation coefficient [ICC] > 0.80); independent RFs were then assessed by Spearman correlation coefficients. The association between RFs and LP was assessed with Mann-Whitney test and univariate logistic regression (ULR): the discriminative power of the most informative RF was quantified by receiver-operating characteristics (ROC) analysis through area under curve (AUC). RESULTS: In all, 15/38 patients presented LP. Median time to progression was 14.6 months (range 2.4-66 months); 5/141 RFs were significantly associated to LP at ULR analysis (p < 0.05); among them, 4 RFs were selected as robust and independent: Statistical_Variance (AUC = 0.75, p = 0.002), Statistical_Range (AUC = 0.72, p = 0.013), Grey Level Size Zone Matrix (GLSZM) _zoneSizeNonUniformity (AUC = 0.70, p = 0.022), Grey Level Dependence Zone Matrix (GLDZM) _zoneDistanceEntropy (AUC = 0.70, p = 0.026). Importantly, the RF with the best performance (Statisical_Variance) is simply representative of density heterogeneity within LOM. CONCLUSION: Four RFs extracted from planning CT were significantly associated with LP of LOM from CRC treated with SBRT. Results encourage further research on a larger population aiming to define a usable radiomic score combining the most predictive RFs and, possibly, additional clinical features.

Stereotactic body radiotherapy in oligometastatic cervical cancer (MITO-RT2/RAD study): a collaboration of MITO, AIRO GYN, and MaNGO groups.

OBJECTIVE: This retrospective, multicenter study analyzes the efficacy and safety of stereotactic body radiotherapy in a large cohort of patients with oligometastatic/persistent/recurrent cervical cancer. METHODS: A standardized data collection from several radiotherapy centers that treated patients by stereotactic body radiotherapy between March 2006 and February 2021 was set up. Clinical and stereotactic body radiotherapy parameters were collected. Objective response rate was defined as a composite of complete and partial response, while clinical benefit included objective response rate plus stable disease. Radiation Therapy Oncology Group/European Organization for Research and Treatment of Cancer and Common Terminology Criteria for Adverse Events scales were used to grade toxicities. The primary endpoints were the rate of complete response to stereotactic body radiotherapy, and the 2 year actuarial local control rate on a 'per lesion' basis. The secondary end points were progression-free survival and overall survival, as well as toxicity. RESULTS: A total of 83 patients with oligometastatic/persistent/recurrent cervical cancer bearing 125 lesions treated by stereotactic body radiotherapy at 15 different centers were selected for analysis. Of the sites of metastatic disease, lymph node metastases were most common (55.2%), followed by parenchyma lesions (44.8%). Median total dose was 35 Gy (range 10-60), in five fractions (range 1-10), with a median dose/fraction of 7 Gy (range 4-26). Complete, partial, and stable response were found in 73 (58.4%), 29 (23.2%), and 16 (12.8%) lesions, respectively, reaching 94.4% of the clinical benefit rate. Forty-six (55.4%) patients had a complete response. Patients achieving complete response on a 'per lesion' basis experienced a 2 year actuarial local control rate of 89.0% versus 22.1% in lesions not achieving complete response (p<0.001). The 2 year actuarial progression-free survival rate was 42.5% in patients with complete response versus 7.8% in patients with partial response or stable or progressive disease (p=0.001). The 2 year actuarial overall survival rate was 68.9% in patients with complete response versus 44.3% in patients with partial response or stable or progressive disease (p=0.015). Fifteen patients (18.1%) had mild acute toxicity, totaling 29 side events. Late toxicity was documented in four patients (4.8%) totaling seven adverse events. CONCLUSION: Our analysis confirmed the efficacy of stereotactic body radiotherapy in oligometastatic/persistent/recurrent cervical cancer patients. The low toxicity profile encourages the wider use of stereotactic body radiotherapy in this setting.

Radiotherapy at oligoprogression for metastatic castration-resistant prostate cancer patients: a multi-institutional analysis.

PURPOSE: To retrospectively estimate the impact of radiotherapy as a progression-directed therapy (PDT) in oligoprogressive metastatic castration-resistant prostate cancer (mCRPC) patients under androgen receptor-target therapy (ARTT). MATERIALS AND METHODS: mCRPC patients are treated with PDT. End-points were time to next-line systemic treatment (NEST), radiological progression-free survival (r-PFS) and overall survival (OS). Toxicity was registered according to Common Terminology Criteria for Adverse Events v4.0. Survival analysis was performed using the Kaplan-Meier method; univariate and multivariate analyses were performed. RESULTS: Fifty-seven patients were analyzed. The median follow-up after PDT was 25.2 months (interquartile, 17.1-44.5). One-year NEST-free survival, r-PFS and OS were 49.8%, 50.4% and 82.1%, respectively. At multivariate analysis, polymetastatic condition at diagnosis of metastatic hormone-sensitive prostate cancer (mHSPC) (HR 2.82, p = 0.004) and PSA doubling time at diagnosis of mCRPC (HR 2.76, p = 0.006) were associated with NEST-free survival. The same variables were associated with r-PFS (HR 2.32, p = 0.021; HR 2.24, p = 0.021). One patient developed late grade ≥ 2 toxicity. CONCLUSION: Our study shows that radiotherapy in oligoprogressive mCRPC is safe, is effective and seems to prolong the efficacy of ARTT in patients who otherwise would have gone systemic treatment switch, positively affecting disease progression. Prospective trials are needed.

Brachytherapy or external beam radiotherapy as a boost in locally advanced cervical cancer: a Gynaecology Study Group in the Italian Association of Radiation and Clinical Oncology (AIRO) review.

This review analyzes the experience and trends in external beam radiotherapy for delivering a boost in locally advanced cervical cancer, identifying whether radiation therapy modalities impact clinical outcomes with the ultimate aim of evaluating alternatives to brachytherapy. Three independent Italian radiation oncologists conducted a literature search on different external beam radiotherapy boost modalities in locally advanced cervical cancer. The search yielded 30 studies. Eight dosimetric studies, evaluating target coverage and dose to organs at risk, and nine clinical investigations, reporting clinical outcomes, were analyzed. Dosimetric studies comparing external beam radiotherapy boost with brachytherapy produced divergent results, while clinical studies were limited by their retrospective nature, heterogeneous doses, radiation schedules, volumes and techniques, diverse follow-up times, and small cohorts of patients. Evidence emerged that high-tech external beam radiotherapy seemed no better than image-guided brachytherapy for delivering a boost in locally advanced cervical cancer. Prospective clinical studies comparing high-tech external beam radiotherapy and image-guided brachytherapy should be encouraged.

A Large, Multicenter, Retrospective Study on Efficacy and Safety of Stereotactic Body Radiotherapy (SBRT) in Oligometastatic Ovarian Cancer (MITO RT1 Study): A Collaboration of MITO, AIRO GYN, and MaNGO Groups.

BACKGROUND: Recent studies have reported improvement of outcomes (progression-free survival, overall survival, and prolongation of androgen deprivation treatment-free survival) with stereotactic body radiotherapy (SBRT) in non-small cell lung cancer and prostate cancer. The aim of this retrospective, multicenter study (MITO RT-01) was to define activity and safety of SBRT in a very large, real-world data set of patients with metastatic, persistent, and recurrent ovarian cancer (MPR-OC). MATERIALS AND METHODS: The endpoints of the study were the rate of complete response (CR) to SBRT and the 24-month actuarial local control (LC) rate on "per-lesion" basis. The secondary endpoints were acute and late toxicities and the 24-month actuarial late toxicity-free survival. Objective response rate (ORR) included CR and partial response (PR). Clinical benefit (CB) included ORR and stable disease (SD). Toxicity was evaluated by the Radiation Therapy Oncology Group (RTOG) and the European Organization for Research and Treatment of Cancer (EORTC) and Common Terminology Criteria for Adverse Events (CTCAE) scales, according to center policy. Logistic and Cox regression were used for the uni- and multivariate analysis of factors predicting clinical CR and actuarial outcomes. RESULTS: CR, PR, and SD were observed in 291 (65.2%), 106 (23.8%), and 33 (7.4%) lesions, giving a rate of CB of 96.4%. Patient aged ≤60 years, planning target volume (PTV) ≤18 cm3 , lymph node disease, and biologically effective dose α/ß10 > 70 Gy were associated with higher chance of CR in the multivariate analysis. With a median follow-up of 22 months (range, 3-120), the 24-month actuarial LC rate was 81.9%. Achievement of CR and total dose >25 Gy were associated with better LC rate in the multivariate analysis. Mild toxicity was experienced in 54 (20.7%) patients; of 63 side effects, 48 were grade 1, and 15 were grade 2. The 24-month late toxicity-free survival rate was 95.1%. CONCLUSIONS: This study confirms the activity and safety of SBRT in patients with MPR-OC and identifies clinical and treatment parameters able to predict CR and LC rate. IMPLICATIONS FOR PRACTICE: This study aimed to define activity and safety of stereotactic body radiotherapy (SBRT) in a very large, real life data set of patients with metastatic, persistent, recurrent ovarian cancer (MPR-OC). Patient age <60 years, PTV <18 cm3 , lymph node disease, and biologically effective dose α/ß10 >70 Gy were associated with higher chance of complete response (CR). Achievement of CR and total dose >25 Gy were associated with better local control (LC) rate. Mild toxicity was experienced in 20.7% of patients. In conclusion, this study confirms the activity and safety of SBRT in MPR-OC patients and identifies clinical and treatment parameters able to predict CR and LC rate.

Oligorecurrent prostate cancer limited to lymph nodes: getting our ducks in a row : Nodal oligorecurrent prostate cancer.

PURPOSE: Oligorecurrent prostate cancer with exclusive nodal involvement represents a common state of disease, amenable to local therapy. New radio-labeled tracers have enriched the possibility of cancer detection and treatment. In this review, we aim to illustrate the main nuclear medicine diagnostic options and the role of radiotherapy in this setting of patients. METHODS: We performed a PubMed search referring to the PRISMA guidelines to analyze the performance of PSMA- and choline-PET in detecting oligorecurrence limited to lymph nodes, and to review the main studies supporting either ablative stereotactic body radiotherapy or regional lymph node irradiation in this clinical setting. RESULTS: PSMA-PET has shown higher efficacy in the diagnosis of nodal lesions if compared with choline-PET. More specifically, for PSA ≤ 2 ng/ml, the median detection rate of choline-PET ranges from 19.5 to 44.5%, whereas PSMA ranges from 51.5 to 74%. SBRT achieves high local control rates positively affecting progression-free survival (PFS), with androgen deprivation therapy (ADT)-free survival ranging from 25 to 44 months and with low toxicity rates (0-15%). Prophylactic nodal irradiation shows 3-year PFS rates ranging from 62 to 75%, but with a potential higher risk of toxicity. However, the chosen treatment option needs to be tailored on the single patient. CONCLUSIONS: Newer PET/CT radio-labeled tracers have increased disease detection in oligorecurrent prostate cancer patients. Growing evidence of their impact on metastasis-directed therapy encourages the use of the most advanced radiotherapy techniques in the clinical management of such patients.

Management of recurrent ovarian cancer: when platinum-based regimens are not a therapeutic option.

Ovarian cancer relapses have been traditionally classified according to the platinum-free interval, leading to an arbitrary categorization of possible scenarios and treatment options. Its relevance in assessing treatment strategies has been revised in the last several years, as the panorama is constantly changing in the era of personalized medicine and targeted therapies. Factors to be considered while defining the best management of recurrent disease, and, consequently, the available treatment alternatives are increasing. Platinum remains one of the milestones of ovarian cancer treatment, but for some patients it might not be an ideal choice for several reasons other than limited platinum sensitivity. This review aims to analyze the scenarios in which platinum is not considered suitable in the management of patients with recurrent ovarian cancer, and the currently available alternatives.

Radiotherapy for oligometastatic cancer: a survey among radiation oncologists of Lombardy (AIRO-Lombardy), Italy.

AIMS: To evaluate the use of radiotherapy (RT) for oligometastatic cancer (OMC) among radiation oncologists in Lombardy, Italy. METHODS AND STUDY DESIGN: A survey with 12 items regarding data of 2016 was sent to all 34 Lombardy RT centers. The survey included six general items and six specific items regarding patient/disease/treatment characteristics. RESULTS: Thirteen centers answered the survey (38%). All centers responded to general items and 12 centers submitted patient/disease/treatment data. General items The majority of centers (8/13) consider OMC if metastases number is less than 5. The most commonly prescribed dose/fraction is 5-10 Gy (8/13) using schedules of 3-5 fractions (11/13). Patient data items A total of 15.681 patients were treated in 2016 with external beam RT in 12 responding centers, and 1.087 patients were treated for OMC (7%). Primary tumor included lung, prostate, breast, colorectal and other malignancies in 33%, 21%, 12%, 9% and 25% of all OMC patients, respectively. Brain, lymph node, lung, bone, liver and others were the most common treated sites (24%, 24%, 22%, 17%, 8% and 5%, respectively). One and more than one metastasis were treated in 75 and 25% of patients, respectively. The vast majority of patients (95%) were treated with image-guided intensity-modulated RT or stereotactic RT. CONCLUSIONS: Seven percent of all RT patients in Lombardy are treated for OMC. Extreme hypofractionation and high-precision RT are commonly employed. The initiative of multicenter and multidisciplinary collaboration has been undertaken in order to prepare the platform for prospective and/or observational studies in OMC.

The relationship between local recurrences and distant metastases in prostate cancer: can 11C-choline PET/CT contribute to understand the link?

PURPOSE: Previous studies in prostate cancer (PCa) patients tried to correlate the onset of local recurrence (LR) with the development of distant metastases and formulated, based on theoretical and experimental data, hypotheses linking the two events. We aimed to address this issue with 11C-choline positron emission tomography/computed tomography (PET/CT). METHODS: This retrospective study included 491 PCa patients previously treated with radical prostatectomy who had undergone 11C-choline PET/CT owing to biochemical failure. Further inclusion criteria were availability of clinical and pathological variables for survival analysis. Statistical significance was taken at P < 0.05. RESULTS: Seventy-two patients (14.7%) had evidence of LR at 11C-choline PET/CT. The frequency of LR increased from 13.8% in the interval 0-4 years after prostatectomy, to 23.9% in the 12-16-year interval (P = 0.080). On the contrary, the frequency of lymph node metastases (overall rate in the 0-16 years interval after prostatectomy: 26.3%) and of bone metastases (overall rate: 13.8%) decreased significantly over time. Kaplan-Meier curves showed no significant group difference in the rates of lymph node or bone metastases between patients with LR and patients without LR. LR significantly predicted PCa-specific survival at univariate analysis, but the statistical significance was lost at multivariate analysis. CONCLUSION: We found no differences in the rates of lymph node and bone metastases between patients with and without LR. An inverse time-dependent trend was observed in the frequency of LR on one side and of lymph node and bone metastases on the other side. These findings were discussed in relation to previous theories linking LR to distant metastases and our study design.

Toxicity and efficacy of salvage carbon 11-choline positron emission tomography/computed tomography-guided radiation therapy in patients with lymph node recurrence of prostate cancer.

OBJECTIVE: To report the 3-year toxicity and outcomes of carbon 11 (11C)-choline-positron emission tomography (PET)/computed tomography (CT)-guided radiotherapy (RT), delivered via helical tomotherapy (HTT; Tomotherapy® Hi-Art II® Treatment System, Accuray Inc., Sunnyvale, CA, USA) after lymph node (LN) relapses in patients with prostate cancer. PATIENTS AND METHODS: From January 2005 to March 2013, 81 patients with biochemical recurrence after surgery, with or without adjuvant/salvage RT or radical RT, and with evidence of LN 11C-choline-PET/CT pathological uptake, underwent HTT (median [range] prostate-specific antigen level 2.59 [0.61-187] ng/mL). Of the 81 patients, 72 were treated at the pelvic and/or lumbar-aortic LN chain with HTT at 51.8 Gy/28 fr and with simultaneous integrated boost to a median dose of 65.5 Gy on the pathological uptake sites detected by 11C-choline-PET/CT. Nine patients were treated without simultaneous integrated boost (50-65.5 Gy, 25-30 fr). RESULTS: With a median (range) follow-up of 36 (9-116) months, 91.4% of the patients had a PSA reduction 3 months after HTT. The 3-year overall, local relapse-free and clinical relapse-free survival rates were 80.0, 89.8 and 61.8%, respectively. The 3-year actuarial incidences of ≥grade 2 rectal and ≥grade 2 genitourinary toxicity were 6.6% (±2.9%) and 26.3% (±5.5%), respectively. A PSA nadir of ≥0.26 ng/mL (hazard ratio [HR] 3.6, 95% confidence interval [CI] 1.7-7.7; P = 0.001), extrapelvic 11C-choline-PET/CT-positive LN location (HR 2.4, 95% CI 0.9-6.4; P = 0.07), RT previous to HTT (HR 2.7; 95% CI 1.07-6.9, P = 0.04) and number of positive LNs (HR 1.13, 95% CI 1.04-1.22; P = 0.003) were the main predictors of clinical relapse after HTT. CONCLUSIONS: 11C-choline-PET/CT-guided HTT is safe and effective in the treatment of LN relapses of prostate cancer in previously treated patients.

Impact of low skeletal muscle mass in oropharyngeal cancer patients treated with radical chemo-radiotherapy: A mono-institutional experience.

AIMS: Low skeletal muscle mass index (SMI) has recently emerged as an independent prognostic factor in oncological patients and it is linked with poor survival and higher treatment toxicity. The present study aims to determine the possible impact of low SMI on survival and acute toxicity in oropharyngeal patients. METHODS: Seventy-six patients with locally advanced oropharyngeal squamous cell carcinoma (stage III-IVC) were treated in our institution with Helical TomoTherapy® (HT - Accuray, Maddison, WI, USA) between 2005 and 2021. All patients received concomitant platinum-based chemotherapy (CT) (at least 200 mg/m2). The SMI was determined using the calculation of cross-sectional area at C3. Twenty patients (26%) presented pre-treatment low SMI, according to Chargi definitions. RESULTS: All patients concluded the treatment. Thirteen patients with low SMI (65%) and 22 patients with normal SMI (39%) presented acute toxicity greater than or equal to grade 3, but this difference was not statistically significant (p-value = 0.25). Overall survival was analyzed in 65 patients, excluding those who finished CT-RT less than six months before the analysis. Overall survival was significantly lower in low SMI versus normal SMI patients (p-value = 0.035). Same difference was observed in N0-N2a patients, suggesting an important role of SMI also in lower nodal burden and putatively better prognosis. CONCLUSIONS: Although the results are limited to a small population, our case series has the advantage to be very homogeneous in patients and treatment characteristics. In our setting, SMI demonstrated a crucial impact on overall survival. Further investigation with larger samples is necessary to confirm our results to improve patient outcomes.

Hypofractionated radiotherapy concomitant to capecitabine after induction chemotherapy for advanced pancreatic adenocarcinoma.

Background and purpose: To assess feasibility, toxicity and outcome of moderately hypofractionated radiotherapy concomitant to capecitabine after induction chemotherapy for advanced pancreatic cancer. Materials and methods: Patients with advanced pancreatic cancer without distant progression after induction chemotherapy (CHT) were considered. Radiochemotherapy (RCT) consisted of 44.25 Gy in 15 fractions to the tumor and involved lymph-nodes concomitant to capecitabine 1250 mg/m2/day. Feasibility and toxicity were evaluated in all pts. Overall survival (OS), progression free survival (PFS), distant PFS (DPFS) and local PFS (LPFS) were assessed only in stage III patients. Results: 254 patients, 220 stage III, 34 stage IV, were treated. Median follow up was 19 months. Induction CHT consisted of Gemcitabine (35 patients), or drug combination (219 patients); median duration was 6 months.Four patients (1.6 %) did not complete RT (1 early progression, 3 toxicity), median duration of RT was 20 days, 209 patients (82 %) received ≥ 75 % of capecitabine dose.During RCT G3 gastrointestinal toxicity occurred in 3.2% of patients, G3-G4 hematologic toxicity in 5.4% of patients. Subsequently, G3, G4, G5 gastric or duodenal lesions occurred in 10 (4%), 2 (0.8%) and 1 patients (0.4%), respectively.Median PFS, LPFS, and DPFS were 11.9 months (95 % CI:11.4-13), 16 months (95 % CI:14.2-17.3) and 14.0 months (95 % CI:12.6-146.5), respectively.Median OS was 19.5 months (95 % CL:18.1-21.3). One- and two-year survival were 85.2 % and 36 %, respectively. Conclusions: The present schedule of hypofractionated RT after induction CHT is feasible with acceptable toxicity rate and provides an outcome comparable with that achievable with standard doses and fractionation.

Comparing Performances of Predictive Models of Toxicity after Radiotherapy for Breast Cancer Using Different Machine Learning Approaches.

PURPOSE: Different ML models were compared to predict toxicity in RT on a large cohort (n = 1314). METHODS: The endpoint was RTOG G2/G3 acute toxicity, resulting in 204/1314 patients with the event. The dataset, including 25 clinical, anatomical, and dosimetric features, was split into 984 for training and 330 for internal tests. The dataset was standardized; features with a high p-value at univariate LR and with Spearman ρ>0.8 were excluded; synthesized data of the minority were generated to compensate for class imbalance. Twelve ML methods were considered. Model optimization and sequential backward selection were run to choose the best models with a parsimonious feature number. Finally, feature importance was derived for every model. RESULTS: The model's performance was compared on a training-test dataset over different metrics: the best performance model was LightGBM. Logistic regression with three variables (LR3) selected via bootstrapping showed performances similar to the best-performing models. The AUC of test data is slightly above 0.65 for the best models (highest value: 0.662 with LightGBM). CONCLUSIONS: No model performed the best for all metrics: more complex ML models had better performances; however, models with just three features showed performances comparable to the best models using many (n = 13-19) features.

Skin dose-volume predictors of moderate-severe late side effects after whole breast radiotherapy.

BACKGROUND: Toxicity after whole breast Radiotherapy is a relevant issue, impacting the quality-of-life of a not negligible number of patients. We aimed to develop a Normal Tissue Complication Probability (NTCP) model predicting late toxicities by combining dosimetric parameters of the breast dermis and clinical factors. METHODS: The skin structure was defined as the outer CT body contour's 5 mm inner isotropic expansion. It was retrospectively segmented on a large mono-institutional cohort of early-stage breast cancer patients enrolled between 2009 and 2017 (n = 1066). Patients were treated with tangential-field RT, delivering 40 Gy in 15 fractions to the whole breast. Toxicity was reported during Follow-Up (FU) using SOMA/LENT scoring. The study endpoint was moderate-severe late side effects consisting of Fibrosis-Atrophy-Telangiectasia-Pain (FATP G ≥ 2) developed within 42 months after RT completion. A machine learning pipeline was designed with a logistic model combining clinical factors and absolute skin DVH (cc) parameters as output. RESULTS: The FATP G2 + rate was 3.8 %, with 40/1066 patients experiencing side effects. After the preprocessing of variables, a cross-validation was applied to define the best-performing model. We selected a 4-variable model with Post-Surgery Cosmetic alterations (Odds Ratio, OR = 7.3), Aromatase Inhibitors (as a protective factor with OR = 0.45), V20 Gy (50 % of the prescribed dose, OR = 1.02), and V42 Gy (105 %, OR = 1.09). Factors were also converted into an adjusted V20Gy. CONCLUSIONS: The association between late reactions and skin DVH when delivering 40 Gy/15 fr was quantified, suggesting an independent role of V20 and V42. Few clinical factors heavily modulate the risk.

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.

Granulosa cell tumors (GCTs) of the ovary: What is the role of radiotherapy?

Granulosa cell tumors of the ovary have an indolent behavior and a good prognosis, but a high incidence of local recurrence after surgery. The best treatment in the recurrent setting is unclear and randomized clinical trials on the management in the recurrent setting are lacking. The role of radiotherapy is controversial in adjuvant settings and unknown in case of relapse after surgery. This review aims to summarize the level of evidence of the role of radiation treatments for granulosa cell tumors of the ovary.

Knowledge-based plan optimization for prostate SBRT delivered with CyberKnife according to RTOG0938 protocol.

PURPOSE: To extend the knowledge-based (KB) automatic planning approach to CyberKnife in the case of Stereotactic Body Radiation Therapy (SBRT) for prostate cancer. METHODS: Seventy-two clinical plans of patients treated according to the RTOG0938 protocol (36.25 Gy/5fr) with CyberKnife were exported from the CyberKnife system to Eclipse to train a KB-model using the Rapid Plan tool. The KB approach provided dose-volume objectives for specific OARs only and not PTV. Bladder, rectum and femoral heads were considered in the model. The KB-model was successfully trained on 51 plans and then validated on 20 new patients. A KB-based template was tuned in the Precision system for both sequential optimization (SO) and VOLO optimization algorithms. Plans of the validation group were re-optimized (KB-TP) using both algorithms without any operator intervention and compared against the original plans (TP) in terms of OARs/PTV dose-volume parameters. Paired Wilcoxon signed-rank tests were performed to assess statistically significant differences (p < 0.05). RESULTS: Regarding SO, automatic KB-TP plans were generally better than or equivalent to TP plans. PTVs V95% was slightly worse while OARs sparing for KB-TP was significantly improved. Regarding VOLO optimization, the PTVs coverage was significantly better for KB-TP while there was a limited worsening in the rectum. A significant improvement was observed in the bladder in the range of low-intermediate doses. CONCLUSIONS: An extension of the KB optimization approach to the CyberKnife system has been successfully developed and validated in the case of SBRT prostate cancer.

Radiation Therapy for Gestational Trophoblastic Neoplasia: Forward-Looking Lessons Learnt.

Gestational trophoblastic neoplasia (GTN) includes several rare malignant diseases occurring after pregnancy: invasive moles, choriocarcinoma, placental site trophoblastic tumours, and epithelioid trophoblastic tumours. Multidisciplinary protocols including multi-agent chemotherapy, surgery, and occasionally radiotherapy achieve good outcomes for some high-risk metastatic patients. In this narrative review of the published studies on the topic, we have tried to identify the role of radiotherapy. The available studies are mainly small, old, and retrospective, with incomplete data regarding radiotherapy protocols delivering low doses (which can make this disease appear radioresistant in some cases despite high response rates with palliative doses) to wide fields (whole-brain, whole-liver, etc.), which can increase toxicity. Studies considering modern techniques are needed to overcome these limitations and determine the full potential of radiotherapy beyond its antihemorrhagic and palliative roles.

Real-world validation of Artificial Intelligence-based Computed Tomography auto-contouring for prostate cancer radiotherapy planning.

Background and purpose: Artificial Intelligence (AI)-based auto-contouring for treatment planning in radiotherapy needs extensive clinical validation, including the impact of editing after automatic segmentation. The aims of this study were to assess the performance of a commercial system for Clinical Target Volumes (CTVs) (prostate/seminal vesicles) and selected Organs at Risk (OARs) (rectum/bladder/femoral heads + femurs), evaluating also inter-observer variability (manual vs automatic + editing) and the reduction of contouring time. Materials and methods: Two expert observers contoured CTVs/OARs of 20 patients in our Treatment Planning System (TPS). Computed Tomography (CT) images were sent to the automatic contouring workstation: automatic contours were generated and sent back to TPS, where observers could edit them if necessary. Inter- and intra-observer consistency was estimated using Dice Similarity Coefficients (DSC). Radiation oncologists were also asked to score the quality of automatic contours, ranging from 1 (complete re-contouring) to 5 (no editing). Contouring times (manual vs automatic + edit) were compared. Results: DSCs (manual vs automatic only) were consistent with inter-observer variability (between 0.65 for seminal vesicles and 0.94 for bladder); editing further improved performances (range: 0.76-0.94). The median clinical score was 4 (little editing) and it was <4 in 3/2 patients for the two observers respectively. Inter-observer variability of automatic + editing contours improved significantly, being lower than manual contouring (e.g.: seminal vesicles: 0.83vs0.73; prostate: 0.86vs0.83; rectum: 0.96vs0.81). Oncologist contouring time reduced from 17 to 24 min of manual contouring time to 3-7 min of editing time for the two observers (p < 0.01). Conclusion: Automatic contouring with a commercial AI-based system followed by editing can replace manual contouring, resulting in significantly reduced time for segmentation and better consistency between operators.