Background: The Prognostic Nutritional Index (PNI) is a parameter of nutritional and inflammation status related to toxicity in cancer treatment. Since data for head and neck cancer are scanty, this study aims to investigate the association between PNI and acute and late toxicity for this malignancy. Methods: A retrospective cohort of 179 head and neck cancer patients treated with definitive radiotherapy with induction/concurrent chemotherapy was followed-up (median follow-up: 38 months) for toxicity and vital status between 2010 and 2017. PNI was calculated according to Onodera formula and low/high PNI levels were defined according to median value. Odds ratio (OR) for acute toxicity were calculated through logistic regression model; hazard ratios (HR) for late toxicity and survival were calculated through the Cox proportional hazards model. Results: median PNI was 50.0 (interquartile range: 45.5–53.5). Low PNI was associated with higher risk of weight loss > 10% during treatment (OR = 4.84, 95% CI: 1.73–13.53 for PNI < 50 versus PNI ≥ 50), which was in turn significantly associated with worse overall survival, and higher risk of late mucositis (HR = 1.84; 95% CI:1.09–3.12). PNI predicts acute weight loss >10% and late mucositis. Conclusions: PNI could help clinicians to identify patients undergoing radiotherapy who are at high risk of acute and late toxicity.

To retrospectively evaluate the difference in terms of pathologic complete response (pCR) according to time elapsed between chemoradiation (CRT) and total mesorectal excision (TME) on a large unselected real-life dataset of locally advanced rectal cancer (LARC) patients. A multicentre retrospective cohort study of LARC patients from 21 Italian Radiotherapy Institutions was performed. Patients were stratified into 3 different time intervals from CRT. The 1st group included 300 patients who underwent TME within 6 weeks, the 2nd 1598 patients (TME within 7-12 weeks) and the 3rd 196 patients (TME within 13 or more weeks after CRT), respectively. Data on 2094 LARC patients treated between 1997 and 2016 were considered suitable for analysis. Overall, 578 patients had stage II while 1516 had stage III histological proven invasive rectal adenocarcinoma. A CRT schedule of one agent (N = 1585) or 2-drugs (N = 509) was administered. Overall, pCR was 22.3% (N = 468 patients). The proportion of patients achieving pCR with respect to time interval was, as follows: 12.6% (1st group), 23% (2nd group) and 31.1% (3rd group) (p < 0.001), respectively. The pCR relative risk comparison of 2nd to 1st group was 1.8, while 3rd to 2nd group was 1.3. Moreover, between the 3rd and 1st group, a pCR relative risk of 2.4 (p < 0.01) was noted. At univariate analysis, clinical stage III (p < 0.001), radiotherapy dose >5040 cGy (p = 0.002) and longer interval (p < 0.001) were significantly correlated to pCR. The positive impact of interval (p < 0.001) was confirmed at multivariate analysis as the only correlated factor. We confirmed on a population-level that lengthening the interval (>13 weeks) from CRT to surgery improves the pathological response (pCR and pathologic partial response; pPR) in comparison to historic data. Furthermore, radiotherapy dose >5040 cGy and two drugs chemotherapy correlated with pPR rate.

Purpose: When autocontouring based on artificial intelligence (AI) is used in the radiotherapy (RT) workflow, the contours are reviewed and eventually adjusted by a radiation oncologist before an RT treatment plan is generated, with the purpose of improving dosimetry and reducing both interobserver variability and time for contouring. The purpose of this study was to evaluate the results of application of a commercial AI-based autocontouring for RT, assessing both geometric accuracies and the influence on optimized dose from automatically generated contours after review by human operator. Materials and Methods: A commercial autocontouring system was applied to a retrospective database of 40 patients, of which 20 were treated with radiotherapy for prostate cancer (PCa) and 20 for head and neck cancer (HNC). Contours resulting from AI were compared against AI contours reviewed by human operator and human-only contours using Dice similarity coefficient (DSC), Hausdorff distance (HD), and relative volume difference (RVD). Dosimetric indices such as D_mean, D_0.03cc, and normalized plan quality metrics were used to compare dose distributions from RT plans generated from structure sets contoured by humans assisted by AI against plans from manual contours. The reduction in contouring time obtained by using automated tools was also assessed. A Wilcoxon rank sum test was computed to assess the significance of differences. Interobserver variability of the comparison of manual vs. AI-assisted contours was also assessed among two radiation oncologists for PCa. Results: For PCa, AI-assisted segmentation showed good agreement with expert radiation oncologist structures with average DSC among patients ≥ 0.7 for all structures, and minimal radiation oncology adjustment of structures (DSC of adjusted versus AI structures ≥ 0.91). For HNC, results of comparison between manual and AI contouring varied considerably e.g., 0.77 for oral cavity and 0.11–0.13 for brachial plexus, but again, adjustment was generally minimal (DSC of adjusted against AI contours 0.97 for oral cavity, 0.92–0.93 for brachial plexus). The difference in dose for the target and organs at risk were not statistically significant between human and AI-assisted, with the only exceptions of D_0.03cc to the anal canal and D_mean to the brachial plexus. The observed average differences in plan quality for PCa and HNC cases were 8% and 6.7%, respectively. The dose parameter changes due to interobserver variability in PCa were small, with the exception of the anal canal, where large dose variations were observed. The reduction in time required for contouring was 72% for PCa and 84% for HNC. Conclusions: When an autocontouring system is used in combination with human review, the time of the RT workflow is significantly reduced without affecting dose distribution and plan quality.

[18F] fluorodeoxyglucose positron emission tomography/computed tomography ([18F] FDG-PET/CT) may be used for tumor staging and prognosis in several tumors but its role in rectal cancer is still debated. The aim of the present study was to assess the correlation of baseline [18F] FDG-PET parameters with tumor staging, tumor response (tumor regression grade (TRG)), and outcome in a series of patients affected by locally advanced rectal cancer (LARC) treated with neoadjuvant chemoradiotherapy (CRT). One hundred patients treated with neoadjuvant CRT and radical surgery were enrolled in the present study. Maximum standardized uptake value (SUVmax), SUVmean, metabolic tumor volume (MTV), and total lesion glycolysis (TLG) at the baseline [18F] FDG-PET were calculated. These PET parameters were correlated with tumor staging, histopathological data (TRG1 vs. TRG2–5 and TRG1–2 vs. TRG3–5), disease-free survival, and overall survival. SUVmax and SUVmean of primary tumor were statistically associated with T4-stage. SUVmax, SUVmean, and TLG did not result statistically associated with TRG (TRG1 or TRG1–2). MTV resulted statistically associated with TRG1–2 group (OR 2.9; 95% CI 1.2–7.1). Finally, no PET parameter was significantly associated with disease-free or overall survival. Our results showed that baseline [18F] FDG-PET parameters correlated with tumor staging, and only MTV correlated with TRG 1–2. PET parameters failed to predict disease-free and overall survival after treatment completion. The results leave open to further studies the issue of identifying patients suitable for conservative approaches.

Purpose: to predict eligibility for deep inspiration breath-hold (DIBH) radiotherapy (RT) treatment of patients with left breast cancer from analysis of respiratory signal, using Deep Bidirectional Long Short-Term Memory (BLSTM) recurrent neural networks. Methods: The respiratory traces from 36 patients who underwent DIBH RT were collected. The patients’ RT treatment plans were generated for both DIBH and free-breathing (FB) modalities. The patients were divided into two classes (patient eligible or not), based on the decrease of maximum dose to the left anterior descending (LAD) artery achieved with DIBH, compared to that achieved with FB and ΔD_L. Patients with ΔD_L > median value of ΔD_L within the patient cohort were assumed to be those selected for DIBH. A BLSTM-RNN was trained for classification of patients eligible for DIBH by analysis of their respiratory signals, as acquired during acquisition of the pre-treatment computed tomography (CT), for selecting the window for DIBH. The dataset was split into training (60%) and test groups (40%), and the hyper-parameters, including the number of hidden layers, the optimizer, the learning rate, and the number of epochs, were selected for optimising model performance. The BLSTM included 2 layers of 100 neural units, each followed by a dropout layer with 20% dropout, and was trained in 35 epochs using the Adam optimizer, with an initial learning rate of 0.0003. Results: The system achieved accuracy, specificity, and sensitivity of, F1 score and area under the receiving operating characteristic curve (AUC) of 71.4%, 66.7%, 80.1%, 72.4%, and 69.4% in the test dataset, respectively. Conclusions: The proposed BLSTM-RNN classified patients in the test set eligible for DIBH with good accuracy. These results look promising for building an accurate and robust decision system to provide automated assistance to the radiotherapy team in assigning patients to DIBH.

And purpose: Radiation recall dermatitis is an adverse event predominantly due to systemic therapy administration after a previous radiation therapy course. Few case reports describe radiation recall dermatitis in breast cancer patients treated with postoperative radiation therapy following COVID-19 vaccination. In this study we investigated the incidence and severity of radiation recall dermatitis after COVID-19 vaccination in irradiated breast cancer patients. Patients that received at least one COVID-19 vaccination dose during the year after the end of postoperative breast radiation therapy were included in this observational monocentric study. Local symptoms occurring inside the radiation field after vaccination were patient-reported and scored according to the PRO-CTCAE questionnaire. Descriptive data of radiation recall dermatitis incidence and severity, and potential risk factors were evaluated. A cohort of 361 patients with 756 administered COVID-19 vaccinations was analyzed. Breast symptoms were reported by 7.5% of patients, while radiation recall dermatitis was considered for 5.5%. The incidence of radiation recall dermatitis per single dose of vaccine was 2.6%, with a higher risk for the first dose compared to the second/third (4.4% vs 1%, p = 0.003), especially when administered within the first month after the end of irradiation (12.5% vs 2.2%, p = 0.0004). Local symptoms were generally self-limited and a few cases required anti-inflammatory drugs. Radiation recall dermatitis is an uncommon but not rare phenomenon in breast cancer patients that received COVID-19 vaccination within one year after breast irradiation. However, symptoms severity were generally low/mild and reversible. These findings can be useful for patient counseling.