Strategies to develop radiomics and machine learning models for lung cancer stage and histology prediction using small data samples.

Predictive models based on radiomics and machine-learning (ML) need large and annotated datasets for training, often difficult to collect. We designed an operative pipeline for model training to exploit data already available to the scientific community. The aim of this work was to explore the capability of radiomic features in predicting tumor histology and stage in patients with non-small cell lung cancer (NSCLC). We analyzed the radiotherapy planning thoracic CT scans of a proprietary sample of 47 subjects (L-RT) and integrated this dataset with a publicly available set of 130 patients from the MAASTRO NSCLC collection (Lung1). We implemented intra- and inter-sample cross-validation strategies (CV) for evaluating the ML predictive model performances with not so large datasets. We carried out two classification tasks: histology classification (3 classes) and overall stage classification (two classes: stage I and II). In the first task, the best performance was obtained by a Random Forest classifier, once the analysis has been restricted to stage I and II tumors of the Lung1 and L-RT merged dataset (AUC = 0.72 ± 0.11). For the overall stage classification, the best results were obtained when training on Lung1 and testing of L-RT dataset (AUC = 0.72 ± 0.04 for Random Forest and AUC = 0.84 ± 0.03 for linear-kernel Support Vector Machine). According to the classification task to be accomplished and to the heterogeneity of the available dataset(s), different CV strategies have to be explored and compared to make a robust assessment of the potential of a predictive model based on radiomics and ML.

Moderate hypofractionated helical tomotherapy for prostate cancer in a cohort of older patients: a mono-institutional report of toxicity and clinical outcomes.

PURPOSE OR OBJECTIVE: To evaluate toxicity and outcomes of moderately hypofractionated helical tomotherapy for the curative treatment of a cohort of patients aged ≥ 75 years with localized prostate cancer (PC). MATERIALS AND METHODS: From January 2013 to February 2017, 95 patients with median age 77 years (range 75-88) were treated for PC. 39% were low risk, 33% intermediate risk (IR), 28% high risk (HR). Median iPSA was 9.42 ng/ml (1.6-107). Androgen deprivation was prescribed according to NCCN recommendations. All patients received 70 Gy in 28 fractions to the prostate; 61.6 Gy were delivered to the seminal vesicles for IR; whole pelvis irradiation with a total dose of 50.4 Gy was added in the HR group. Toxicity evaluation was based on CTCAE V4.0 criteria, biochemical failure was defined following Phoenix criteria. Quality of Life was assessed with the EPIC-26 index. Overall survival and biochemical failure-free survival were analysed with Kaplan-Meier method. RESULTS: With a median follow-up of 36 months (range 24-73), acute and late toxicity were acceptable. No correlation between toxicity patterns and clinical or dosimetric parameter was registered. EPIC-26 showed a negligible difference in urinary and bowel function post-treatment that did not reach statistical significance. The 2- and 3-years OS were 93% and 87% with cancer specific survival of 97.9% and 96.2%. CONCLUSION: Moderate hypofractionated RT reported excellent outcomes in our cohort of older patients. Shorter schedules may be proposed regardless of chronological age facilitating the treatment compliance in the older population.

Histopathology of the muscle in rheumatic diseases.

The presence of muscular symptoms is common in rheumatological clinical practice, but often the differential diagnosis between muscular involvement in connective tissue diseases, vasculitis and drug-induced myopathy may be difficult. In addition to clinical assessment, laboratory analysis and instrumental examinations, muscle biopsy may help to clarify the diagnosis in patients with muscular involvement. The purpose of this review is to provide a critical analysis of the current medical literature on muscular histopathology, to help clinicians to identify when to perform muscular biopsy and to provide a practical guide to a better understanding of the pathology report. Moreover, we provide an overview of the muscular involvement and the most common histopathological findings in rheumatic diseases.

The use of rituximab in idiopathic inflammatory myopathies: description of a monocentric cohort and review of the literature.

Rituximab (RTX), a chimeric monoclonal antibody targeted against CD20, has been used to treat refractory inflammatory myopathies (IIM). The primary objective of this study was to retrospectively assess the efficacy of RTX in reducing disease activity in patients with IIM refractory to conventional therapy. Secondary aim was the evaluation of adverse events (AE) during the treatment period. We examined 26 patients with a diagnosis of IIM, referred to our Rheumatology Unit and treated with RTX for active refractory disease. Patients were treated with RTX 1000 mg i.v., twice, with a 2-week interval. RTX treatment was associated with a significant reduction of creatine kinase (p=0.001) after six months compared to the baseline, an improved muscular strength measured with MMT8 (p<0.001) and a reduction of the extramuscular activity of the disease measured with MYOACT (p<0.001). In particular, RTX improved DM skin rash, arthritis and pulmonary manifestations. Autoantibody positivity (in particular antisynthetase, anti- SRP and antiRo/SSA), and a disease duration <36 months at the moment of the treatment are associated with a better response rate. Treatment with RTX was also associated with a reduction of the mean daily dose of steroids needed to control disease activity (p=0.002). Our results have confirmed that RTX is efficacious in the treatment of refractory IIM. Ad hoc controlled trials are needed to better clarify the specific subset of patients who may better respond to the treatment and the optimal therapeutic schedule.