Preoperative MRI radiomic analysis for predicting local tumor progression in colorectal liver metastases before microwave ablation.

PURPOSE: Radiomics may aid in predicting prognosis in patients with colorectal liver metastases (CLM). Consistent data is available on CT, yet limited data is available on MRI. This study assesses the capability of MRI-derived radiomic features (RFs) to predict local tumor progression-free survival (LTPFS) in patients with CLMs treated with microwave ablation (MWA). METHODS: All CLM patients with pre-operative Gadoxetic acid-MRI treated with MWA in a single institution between September 2015 and February 2022 were evaluated. Pre-procedural information was retrieved retrospectively. Two observers manually segmented CLMs on T2 and T1-Hepatobiliary phase (T1-HBP) scans. After inter-observer variability testing, 148/182 RFs showed robustness on T1-HBP, and 141/182 on T2 (ICC > 0.7).Cox multivariate analysis was run to establish clinical (CLIN-mod), radiomic (RAD-T1, RAD-T2), and combined (COMB-T1, COMB-T2) models for LTPFS prediction. RESULTS: Seventy-six CLMs (43 patients) were assessed. Median follow-up was 14 months. LTP occurred in 19 lesions (25%).CLIN-mod was composed of minimal ablation margins (MAMs), intra-segment progression and primary tumor grade and exhibited moderately high discriminatory power in predicting LTPFS (AUC = 0.89, p = 0.0001). Both RAD-T1 and RAD-T2 were able to predict LTPFS: (RAD-T1: AUC = 0.83, p = 0.0003; RAD-T2: AUC = 0.79, p = 0.001). Combined models yielded the strongest performance (COMB-T1: AUC = 0.98, p = 0.0001; COMB-T2: AUC = 0.95, p = 0.0003). Both combined models included MAMs and tumor regression grade; COMB-T1 also featured 10th percentile of signal intensity, while tumor flatness was present in COMB-T2. CONCLUSION: MRI-based radiomic evaluation of CLMs is feasible and potentially useful for LTP prediction. Combined models outperformed clinical or radiomic models alone for LTPFS prediction.

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.

Pelvic bone marrow dose-volume predictors of late lymphopenia following pelvic lymph node radiation therapy for prostate cancer.

BACKGROUND AND PURPOSE: Given the substantial lack of knowledge, we aimed to assess clinical/dosimetry predictors of late hematological toxicity on patients undergoing pelvic-nodes irradiation (PNI) for prostate cancer (PCa) within a prospective multi-institute study. MATERIALS AND METHODS: Clinical/dosimetry/blood test data were prospectively collected including lymphocytes count (ALC) at baseline, mid/end-PNI, 3/6 months and every 6 months up to 5-year after PNI. DVHs of the Body, ileum (BMILEUM), lumbosacral spine (BMLS), lower pelvis (BMPELVIS), and whole pelvis (BMTOT) were extracted. Current analysis focused on 2-year CTCAEv4.03 Grade ≥ 2 (G2+) lymphopenia (ALC < 800/µL). DVH parameters that better discriminate patients with/without toxicity were first identified. After data pre-processing to limit overfitting, a multi-variable logistic regression model combining DVH and clinical information was identified and internally validated by bootstrap. RESULTS: Complete data of 499 patients were available: 46 patients (9.2 %) experienced late G2+ lymphopenia. DVH parameters of BMLS/BMPELVIS/BMTOT and Body were associated to increased G2+ lymphopenia. The variables retained in the resulting model were ALC at baseline [HR = 0.997, 95 %CI 0.996-0.998, p < 0.0001], smoke (yes/no) [HR = 2.9, 95 %CI 1.25-6.76, p = 0.013] and BMLS-V ≥ 24 Gy (cc) [HR = 1.006, 95 %CI 1.002-1.011, p = 0.003]. When acute G3+ lymphopenia (yes/no) was considered, it was retained in the model [HR = 4.517, 95 %CI 1.954-10.441, p = 0.0004]. Performances of the models were relatively high (AUC = 0.87/0.88) and confirmed by validation. CONCLUSIONS: Two-year lymphopenia after PNI for PCa is largely modulated by baseline ALC, with an independent role of acute G3+ lymphopenia. BMLS-V24 was the best dosimetry predictor: constraints for BMTOT (V10Gy < 1520 cc, V20Gy < 1250 cc, V30Gy < 850 cc), and BMLS (V24y < 307 cc) were suggested to potentially reduce the risk.

Inter-institutional variability of knowledge-based plan prediction of left whole breast irradiation.

PURPOSE: Within a multi-institutional project, we aimed to assess the transferability of knowledge-based (KB) plan prediction models in the case of whole breast irradiation (WBI) for left-side breast irradiation with tangential fields (TF). METHODS: Eight institutions set KB models, following previously shared common criteria. Plan prediction performance was tested on 16 new patients (2 pts per centre) extracting dose-volume-histogram (DVH) prediction bands of heart, ipsilateral lung, contralateral lung and breast. The inter-institutional variability was quantified by the standard deviations (SDint) of predicted DVHs and mean-dose (Dmean). The transferability of models, for the heart and the ipsilateral lung, was evaluated by the range of geometric Principal Component (PC1) applicability of a model to test patients of the other 7 institutions. RESULTS: SDint of the DVH was 1.8 % and 1.6 % for the ipsilateral lung and the heart, respectively (20 %-80 % dose range); concerning Dmean, SDint was 0.9 Gy and 0.6 Gy for the ipsilateral lung and the heart, respectively (<0.2 Gy for contralateral organs). Mean predicted doses ranged between 4.3 and 5.9 Gy for the ipsilateral lung and 1.1-2.3 Gy for the heart. PC1 analysis suggested no relevant differences among models, except for one centre showing a systematic larger sparing of the heart, concomitant to a worse PTV coverage, due to high priority in sparing the left anterior descending coronary artery. CONCLUSIONS: Results showed high transferability among models and low inter-institutional variability of 2% for plan prediction. These findings encourage the building of benchmark models in the case of TF-WBI.

Radiomics-enhanced early regression index for predicting treatment response in rectal cancer: a multi-institutional 0.35 T MRI-guided radiotherapy study.

PURPOSE: The accurate prediction of treatment response in locally advanced rectal cancer (LARC) patients undergoing MRI-guided radiotherapy (MRIgRT) is essential for optimising treatment strategies. This multi-institutional study aimed to investigate the potential of radiomics in enhancing the predictive power of a known radiobiological parameter (Early Regression Index, ERITCP) to evaluate treatment response in LARC patients treated with MRIgRT. METHODS: Patients from three international sites were included and divided into training and validation sets. 0.35 T T2*/T1-weighted MR images were acquired during simulation and at each treatment fraction. The biologically effective dose (BED) conversion was used to account for different radiotherapy schemes: gross tumour volume was delineated on the MR images corresponding to specific BED levels and radiomic features were then extracted. Multiple logistic regression models were calculated, combining ERITCP with other radiomic features. The predictive performance of the different models was evaluated on both training and validation sets by calculating the receiver operating characteristic (ROC) curves. RESULTS: A total of 91 patients was enrolled: 58 were used as training, 33 as validation. Overall, pCR was observed in 25 cases. The model showing the highest performance was obtained combining ERITCP at BED = 26 Gy with a radiomic feature (10th percentile of grey level histogram, 10GLH) calculated at BED = 40 Gy. The area under ROC curve (AUC) of this combined model was 0.98 for training set and 0.92 for validation set, significantly higher (p = 0.04) than the AUC value obtained using ERITCP alone (0.94 in training and 0.89 in validation set). CONCLUSION: The integration of the radiomic analysis with ERITCP improves the pCR prediction in LARC patients, offering more precise predictive models to further personalise 0.35 T MRIgRT treatments of LARC patients.

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.

Quality of Life Longitudinal Evaluation in Prostate Cancer Patients from Radiotherapy Start to 5 Years after IMRT-IGRT.

PURPOSE: The purpose of this study is to study the evolution of quality of life (QoL) in the first 5 years following Intensity-modulated radiation therapy (IMRT) for prostate cancer (PCa) and to determine possible associations with clinical/treatment data. MATERIAL AND METHODS: Patients were enrolled in a prospective multicentre observational trial in 2010-2014 and treated with conventional (74-80 Gy, 1.8-2 Gy/fr) or moderately hypofractionated IMRT (65-75.2 Gy, 2.2-2.7 Gy/fr). QoL was evaluated by means of EORTC QLQ-C30 at baseline, at radiation therapy (RT) end, and every 6 months up to 5 years after IMRT end. Fourteen QoL dimensions were investigated separately. The longitudinal evaluation of QoL was analysed by means of Analysis of variances (ANOVA) for multiple measures. RESULTS: A total of 391 patients with complete sets of questionnaires across 5 years were available. The longitudinal analysis showed a trend toward the significant worsening of QoL at RT end for global health, physical and role functioning, fatigue, appetite loss, diarrhoea, and pain. QoL worsening was recovered within 6 months from RT end, with the only exception being physical functioning. Based on ANOVA, the most impaired time point was RT end. QoL dimension analysis at this time indicated that acute Grade ≥ 2 gastrointestinal (GI) toxicity significantly impacted global health, physical and role functioning, fatigue, appetite loss, diarrhoea, and pain. Acute Grade ≥ 2 genitourinary (GU) toxicity resulted in lower role functioning and higher pain. Prophylactic lymph-nodal irradiation (WPRT) resulted in significantly lower QoL for global health, fatigue, appetite loss, and diarrhoea; lower pain with the use of neoadjuvant/concomitant hormonal therapy; and lower fatigue with the use of an anti-androgen. CONCLUSIONS: In this prospective, longitudinal, observational study, high radiation IMRT doses delivered for PCa led to a temporary worsening of QoL, which tended to be completely resolved at six months. Such transient worsening was mostly associated with acute GI/GU toxicity, WPRT, and higher prescription doses.

Worsening of 2-year patient-reported intestinal functionality after radiotherapy for prostate cancer including pelvic node irradiation.

BACKGROUND AND PURPOSE: To quantify patient-reported 2-year intestinal toxicity (IT) from pelvic nodal irradiation (PNI) for prostate cancer. The association between baseline/acute symptoms and 2-year worsening was investigated. MATERIALS AND METHODS: Patient-reported IT was prospectively assessed through the Inflammatory Bowel Disease Questionnaire (IBDQ), filled in at baseline, radiotherapy mid-point and end, at 3 and 6 months and every 6 months until 5 years. Two-year deterioration of IBDQ scores relative to the Bowel Domain was investigated for 400 patients with no severe baseline symptoms and with questionnaires available at baseline, 2 years, RT mid-point and/or end and at least three follow-ups between 3 and 18 months. The significance of the 2-year differences from baseline was tested. The association between baseline values and ΔAcute (the worst decline between baseline and RT mid-point/end) was investigated. RESULTS: In the IBDQ lower scores indicate worse symptoms. A significant (p < 0.0001) 2-year mean worsening, mostly in the range of -0.2/-0.4 points on a 1-7 scale, emerged excepting one question (IBDQ29, "nausea/feeling sick"). This decline was independent of treatment intent while baseline values were associated with 2-year absolute scores. The ΔAcute largely modulated 2-year worsening: patients with ΔAcute greater than the first quartile (Q1) and ΔAcute less or equal than Q1 showed no/minimal and highly significant (p < 0.0001) deterioration, respectively. Rectal incontinence, urgency, frequency and abdominal pain showed the largest mean changes (-0.5/-1): risk of severe worsening (deemed to be of clinical significance if ≤ 2) was 3-5 fold higher in the ΔAcute ≤ Q1 vs ΔAcute > Q1 group (p < 0.0001). CONCLUSION: A modest but significant deterioration of two-year patient-reported intestinal symptoms from PNI compared to baseline was found. Patients experiencing more severe acute symptoms are at higher risk of symptom persistence at 2 years, with a much larger prevalence of clinically significant symptoms.

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.

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.

Patient-reported persistent symptoms after radiotherapy and association with quality of life for prostate cancer survivors.

PURPOSE: To evaluate the persistence of symptoms after radiotherapy (RT) for localised prostate cancer (PCa) and the association with quality of life (QOL). MATERIALS AND METHODS: Prospective patient-reported outcome (PRO) from a multi-institutional study on PCa treated with radical RT (2010-2014) was analysed. Data was collected at baseline (BL) and follow-ups (FUPs) up to 5 years. Patients with BL and ≥3 late FUPs (≥6 months) were analysed. PRO was scored by means of the IPSS and ICIQ-SF (urinary), LENT-SOMA (gastrointestinal [GI]), and EORTC-C30 (pain, insomnia, fatigue, and QOL) questionnaires. Symptoms were defined 'persistent' if the median score over FUPs was ≥3 (urinary) or ≥2 (GI, pain, insomnia, and fatigue), and worse than BL. Different thresholds were chosen to have enough events for each symptom. QOL was linearly transformed on a continuous scale (0-100). Linear-mixed models were used to identify significant differences between groups with and without persistent symptoms including age, smoking status, previous abdominal surgery, and diabetes as confounders. Mean QOL differences between groups were evaluated longitudinally over FUPs. RESULTS: The analysis included 293 patients. Persistent urinary symptoms ranged from 2% (straining) to 12% (weak stream, and nocturia). Gastrointestinal symptoms ranged from 7% (rectal pain, and incontinence) to 30% (urgency). Proportions of pain, insomnia, and fatigue were 6, 13, and 18%. Significant QOL differences of small-to-medium clinical relevance were found for urinary incontinence, frequency, urgency, and nocturia. Among GI symptoms, rectal pain and incontinence showed small-to-medium differences. Fatigue was associated with the largest differences. CONCLUSIONS: The analysis showed that symptoms after RT for PCa occur with different persistence and their association with QOL varies in magnitude. A number of persistent urinary and GI symptoms showed differences in a comparable range. Urinary incontinence and frequency, rectal pain, and faecal incontinence more often had significant associations. Fatigue was also prevalent and associated with largely deteriorated QOL.

Selective sparing of bladder and rectum sub-regions in radiotherapy of prostate cancer combining knowledge-based automatic planning and multicriteria optimization.

Background and Purpose: The association between dose to selected bladder and rectum symptom-related sub-regions (SRS) and late toxicity after prostate cancer radiotherapy has been evidenced by voxel-wise analyses. The aim of the current study was to explore the feasibility of combining knowledge-based (KB) and multi-criteria optimization (MCO) to spare SRSs without compromising planning target volume (PTV) dose delivery, including pelvic-node irradiation. Materials and Methods: Forty-five previously treated patients (74.2 Gy/28fr) were selected and SRSs (in the bladder, associated with late dysuria/hematuria/retention; in the rectum, associated with bleeding) were generated using deformable registration. A KB model was used to obtain clinically suitable plans (KB-plan). KB-plans were further optimized using MCO, aiming to reduce dose to the SRSs while safeguarding target dose coverage, homogeneity and avoiding worsening dose volume histograms of the whole bladder, rectum and other organs at risk. The resulting MCO-generated plans were examined to identify the best-compromise plan (KB + MCO-plan). Results: The mean SRS dose decreased in almost all patients for each SRS. D1% also decreased in the large majority, less frequently for dysuria/bleeding SRS. Mean differences were statistically significant (p < 0.05) and ranged between 1.3 and 2.2 Gy with maximum reduction of mean dose up to 3-5 Gy for the four SRSs. The better sparing of SRSs was obtained without compromising PTVs coverage. Conclusions: Selectively sparing SRSs without compromising PTV coverage is feasible and has the potential to reduce toxicities in prostate cancer radiotherapy. Further investigation to better quantify the expected risk reduction of late toxicities is warranted.

Limited impact of discretization/interpolation parameters on the predictive power of CT radiomic features in a surgical cohort of pancreatic cancer patients.

PURPOSE: To explore the variation of the discriminative power of CT (Computed Tomography) radiomic features (RF) against image discretization/interpolation in predicting early distant relapses (EDR) after upfront surgery. MATERIALS AND METHODS: Data of 144 patients with pre-surgical high contrast CT were processed consistently with IBSI (Image Biomarker Standardization Initiative) guidelines. Image interpolation/discretization parameters were intentionally changed, including cubic voxel size (0.21-27 mm3) and binning (32-128 grey levels) in a 15 parameter's sets. After excluding RF with poor inter-observer delineation agreement (ICC < 0.80) and not negligible inter-scanner variability, the variation of 80 RF against discretization/interpolation was first quantified. Then, their ability in classifying patients with early distant relapses (EDR, < 10 months, previously assessed at the first quartile value of time-to-relapse) was investigated in terms of AUC (Area Under Curve) variation for those RF significantly associated to EDR. RESULTS: Despite RF variability against discretization/interpolation parameters was large and only 30/80 RF showed %COV < 20 (%COV = 100*STDEV/MEAN), AUC changes were relatively limited: for 30 RF significantly associated with EDR (AUC values around 0.60-0.70), the mean values of SD of AUC variability and AUC range were 0.02 and 0.05 respectively. AUC ranges were between 0.00 and 0.11, with values ≤ 0.05 in 16/30 RF. These variations were further reduced when excluding the extreme values of 32 and 128 for grey levels (Average AUC range 0.04, with values between 0.00 and 0.08). CONCLUSIONS: The discriminative power of CT RF in the prediction of EDR after upfront surgery for pancreatic cancer is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.

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.

Deep learning-based segmentation of prostatic urethra on computed tomography scans for treatment planning.

Background and purpose: The intraprostatic urethra is an organ at risk in prostate cancer radiotherapy, but its segmentation in computed tomography (CT) is challenging. This work sought to: i) propose an automatic pipeline for intraprostatic urethra segmentation in CT, ii) analyze the dose to the urethra, iii) compare the predictions to magnetic resonance (MR) contours. Materials and methods: First, we trained Deep Learning networks to segment the rectum, bladder, prostate, and seminal vesicles. Then, the proposed Deep Learning Urethra Segmentation model was trained with the bladder and prostate distance transforms and 44 labeled CT with visible catheters. The evaluation was performed on 11 datasets, calculating centerline distance (CLD) and percentage of centerline within 3.5 and 5 mm. We applied this method to a dataset of 32 patients treated with intensity-modulated radiation therapy (IMRT) to quantify the urethral dose. Finally, we compared predicted intraprostatic urethra contours to manual delineations in MR for 15 patients without catheter. Results: A mean CLD of 1.6 ± 0.8 mm for the whole urethra and 1.7 ± 1.4, 1.5 ± 0.9, and 1.7 ± 0.9 mm for the top, middle, and bottom thirds were obtained in CT. On average, 94% and 97% of the segmented centerlines were within a 3.5 mm and 5 mm radius, respectively. In IMRT, the urethra received a higher dose than the overall prostate. We also found a slight deviation between the predicted and manual MR delineations. Conclusion: A fully-automatic segmentation pipeline was validated to delineate the intraprostatic urethra in CT images.

Validation of prediction models for radiation-induced late rectal bleeding: Evidence from a large pooled population of prostate cancer patients.

PURPOSE: To validate published models for the risk estimate of grade ≥ 1 (G1+), grade ≥ 2 (G2+) and grade = 3 (G3) late rectal bleeding (LRB) after radical radiotherapy for prostate cancer in a large pooled population from three prospective trials. MATERIALS AND METHODS: The external validation population included patients from Europe, and Oceanian centres enrolled between 2003 and 2014. Patients received 3DCRT or IMRT at doses between 66-80 Gy. IMRT was administered with conventional or hypofractionated schemes (2.35-2.65 Gy/fr). LRB was prospectively scored using patient-reported questionnaires (LENT/SOMA scale) with a 3-year follow-up. All Normal Tissue Complication Probability (NTCP) models published until 2021 based on the Equivalent Uniform Dose (EUD) from the rectal Dose Volume Histogram (DVH) were considered for validation. Model performance in validation was evaluated through calibration and discrimination. RESULTS: Sixteen NTCP models were tested on data from 1633 patients. G1+ LRB was scored in 465 patients (28.5%), G2+ in 255 patients (15.6%) and G3 in 112 patients (6.8%). The best performances for G2+ and G3 LRB highlighted the importance of the medium-high doses to the rectum (volume parameters n = 0.24 and n = 0.18, respectively). Good performance was seen for models of severe LRB. Moreover, a multivariate model with two clinical factors found the best calibration slope. CONCLUSION: Five published NTCP models developed on non-contemporary cohorts were able to predict a relative increase in the toxicity response in a more recent validation population. Compared to QUANTEC findings, dosimetric results pointed toward mid-high doses of rectal DVH. The external validation cohort confirmed abdominal surgery and cardiovascular diseases as risk factors.

External validation of an 18F-FDG-PET radiomic model predicting survival after radiotherapy for oropharyngeal cancer.

PURPOSE/OBJECTIVE: The purpose of the study is to externally validate published 18F-FDG-PET radiomic models for outcome prediction in patients with oropharyngeal cancer treated with chemoradiotherapy. MATERIAL/METHODS: Outcome data and pre-radiotherapy PET images of 100 oropharyngeal cancer patients (stage IV:78) treated with concomitant chemotherapy to 66-69 Gy/30 fr were available. Tumors were segmented using a previously validated semi-automatic method; 450 radiomic features (RF) were extracted according to IBSI (Image Biomarker Standardization Initiative) guidelines. Only one model for cancer-specific survival (CSS) prediction was suitable to be independently tested, according to our criteria. This model, in addition to HPV status, SUVmean and SUVmax, included two independent meta-factors (Fi), resulting from combining selected RF clusters. In a subgroup of 66 patients with complete HPV information, the global risk score R was computed considering the original coefficients and was tested by Cox regression as predictive of CSS. Independently, only the radiomic risk score RF derived from Fi was tested on the same subgroup to learn about the radiomics contribution to the model. The metabolic tumor volume (MTV) was also tested as a single predictor and its prediction performances were compared to the global and radiomic models. Finally, the validation of MTV and the radiomic score RF were also tested on the entire dataset. RESULTS: Regarding the analysis of the subgroup with HPV information, with a median follow-up of 41.6 months, seven patients died due to cancer. R was confirmed to be associated to CSS (p value = 0.05) with a C-index equal 0.75 (95% CI=0.62-0.85). The best cut-off value (equal to 0.15) showed high ability in patient stratification (p=0.01, HR=7.4, 95% CI=1.6-11.4). The 5-year CSS for R were 97% (95% CI: 93-100%) vs 74% (56-92%) for low- and high-risk groups, respectively. RF and MTV alone were also significantly associated to CSS for the subgroup with an almost identical C-index. According to best cut-off value (RF>0.12 and MTV>15.5cc), the 5-year CSS were 96% (95% CI: 89-100%) vs 65% (36-94%) and 97% (95% CI: 88-100%) vs 77% (58-93%) for RF and MTV, respectively. Results regarding RF and MTV were confirmed in the overall group. CONCLUSION: A previously published PET radiomic model for CSS prediction was independently validated. Performances of the model were similar to the ones of using only the MTV, without improvement of prediction accuracy.

Prediction of the characteristics of aggressiveness of pancreatic neuroendocrine neoplasms (PanNENs) based on CT radiomic features.

OBJECTIVES: To predict tumor grade (G1 vs. G2/3), presence of distant metastasis (M+), metastatic lymph nodes (N+), and microvascular invasion (VI) of pancreatic neuroendocrine neoplasms (PanNEN) based on preoperative CT radiomic features (RFs), by applying a machine learning approach aimed to limit overfit. METHODS: This retrospective study included 101 patients who underwent surgery for PanNEN; the entire population was split into training (n = 70) and validation cohort (n = 31). Based on a previously validated methodology, after tumor segmentation on contrast-enhanced CT, RFs were extracted from unenhanced CT images. In addition, conventional radiological and clinical features were combined with RFs into multivariate logistic regression models using minimum redundancy and a bootstrap-based machine learning approach. For each endpoint, models were trained and validated including only RFs (RF_model), and both (radiomic and clinicoradiological) features (COMB_model). RESULTS: Twenty-five patients had G2/G3 tumor, 37 N+, and 14 M+ and 38 were shown to have VI. From a total of 182 RFs initially extracted, few independent radiomic and clinicoradiological features were identified. For M+ and G, the resulting models showed moderate to high performances: areas under the curve (AUC) for training/validation cohorts were 0.85/0.77 (RF_model) and 0.81/0.81 (COMB_model) for M+ and 0.67/0.72 and 0.68/0.70 for G. Concerning N+ and VI, only the COMB_model could be built, with poorer performance for N+ (AUC = 0.72/0.61) compared to VI (0.82/0.75). For all endpoints, the negative predictive value was good (≥ 0.75). CONCLUSIONS: Combining few radiomic and clinicoradiological features resulted in presurgical prediction of histological characteristics of PanNENs. Despite the limited risk of overfit, external validations are warranted. KEY POINTS: • Histology is the only tool currently available allowing characterization of PanNEN biological characteristics important for prognostic assessment; significant limitations to this approach exist. • Based upon preoperative contrast-enhanced CT images, a machine learning approach optimized to favor models' generalizability was successfully applied to train predictive models for tumor grading (G1 vs. G2/3), microvascular invasion, metastatic lymph nodes, and distant metastatic spread. • Moderate to high discriminative models (AUC: 0.67-0.85) based on few parameters (≤ 3) showing high negative predictive value (0.75-0.98) were generated and then successfully validated.

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.