Predicting response to radiotherapy of head and neck squamous cell carcinoma using radiomics from cone-beam CT images.

INTRODUCTION: Radiotherapy (RT) for head and neck cancer is now guided by cone-beam computed tomography (CBCT). We aim to identify a CBCT radiomic signature predictive of progression to RT. MATERIAL AND METHODS: A cohort of 93 patients was split into training (n = 60) and testing (n = 33) sets. A total of 88 features were extracted from the gross tumor volume (GTV) on each CBCT. Receiver operating characteristic (ROC) curves were used to determine the power of each feature at each week of treatment to predict progression to radio(chemo)therapy. Only features with AUC > 0.65 at each week were pre-selected. Absolute differences were calculated between features from each weekly CBCT and baseline CBCT1 images. The smallest detectable change (C = 1.96 × SD, SD being the standard deviation of differences between feature values calculated on CBCT1 and CBCTn) with its confidence interval (95% confidence interval [CI]) was determined for each feature. The features for which the change was larger than C for at least 5% of patients were then selected. A radiomics-based model was built at the time-point that showed the highest AUC and compared with models relying on clinical variables. RESULTS: Seven features had an AUC > 0.65 at each week, and six exhibited a change larger than the predefined CI 95%. After exclusion of inter-correlated features, only one parameter remains, Coarseness. Among clinical variable, only hemoglobin value was significant. AUC for predicting the treatment response were 0.78 (p = .006), 0.85 (p < .001), and 0.99 (p < .001) for clinical, CBCT4-radiomics (Coarseness) and clinical + radiomics based models respectively. The mean AUC of this last model on a 5-fold cross-validation was 0.80 (±0.09). On the testing cohort, the best prediction was given by the combined model (balanced accuracy [BAcc] 0.67 , p < .001). CONCLUSIONS: We described a feature selection methodology for delta-radiomics that is able to select reproducible features which are informative due to their change during treatment. A selected delta radiomics feature may improve clinical-based prediction models.

Association of the RAVER2 gene with increased susceptibility for ulcerative colitis.

Crohn's disease (CD), ulcerative colitis (UC), systemic lupus erythematosus (SLE) and autoimmune polyglandular syndromes (APS) are autoimmune diseases (ADs) that may share common susceptibility pathways. We examined ribonucleo-protein, polypyrimidine tract-binding protein (PTB)-binding 2 (RAVER2) loci for these diseases in a cohort of 39 CD cases, 67 UC cases, 93 SLE cases, 60 APS cases and 162 healthy control subjects of Tunisian origin. We genotyped 3 SNPs of RAVER2 (rs2780814, rs1333739 and rs2780889) and evaluated it genetic association with each ADs, using X2-test. For each association, odds ratio (OR) and 95% CI were calculated. We show that rs2780814 is significantly associated with UC (P = 0.00016, P(corr) = 0.00048, OR = 3.66 (1.82; 7.34)). We also observed a trend of possible association to SLE (P = 0.023, P(corr) = 0.69, OR = 2.19 (1.1; 4.36)). None of these RAVER2 SNPs were associated with CD and APS susceptibility. These findings establish RAVER2 as a new UC genetic susceptibility factor and reveal a genetic heterogeneity of the associated polymorphisms and risk alleles between ADs suggesting different immunopathological roles of RAVER2 in these diseases.

[Dosimetric comparison between the intensity modulated radiotherapy with fixed field and Rapid Arc of cervix cancer]. / Comparaison dosimétrique des radiothérapies conformationnelles avec modulation d'intensité par faisceaux statiques et RapidArc(®) des cancers du col.

PURPOSE: Concurrent radiochemotherapy is the standard treatment for locally advanced cervical cancer. This treatment is responsible for bowel and hematologic toxicities. The use of intensity-modulated radiotherapy (IMRT), in static beams, allows a decrease of this toxicity. The technique of RapidArc(®) IMRT could lower the dose delivered to the organs at risk and improve the homogeneity of the planning target volume coverage, while decreasing the processing time. PATIENTS AND MATERIALS: For 20 patients, treatment plans performed with IMRT and RapidArc(®) were compared. The target volumes were: the clinical target volume (gross tumour volume, uterus, upper third of the vagina, the hypogastric, iliac and presacral nodal regions), and the planning target volume (clinical target volume+1cm). The delineated organs at risk were: rectum, bladder, bowel and bone marrow. The dose was 45 Gy in 25 fractions. IMRT were delivered with five beams and RapidArc(®) with two arcs. The comparisons were made by the non-parametric test of Wilcoxon. RESULTS: Medium coverage of the planning target volume was better with RapidArc(®) (P=0.01). It was also better regarding the sparing of bowel (P=0.01) and IMRT was better regarding the sparing of bladder (P=0.01) and rectum (P=0.05). The total volume receiving 20 Gy was less important with RapidArc(®) (P<0.001). RapidArc(®) allowed to decrease the treatment time (3 versus 12 minutes with IMRT) and the number of monitor units (MU) (376.5 versus 962.2, on average, P=0.0001). CONCLUSION: The technique of RapidArc(®) seems to obtain better dosimetric results compared to RCMI, with fewer MU, and a significant decrease in treatment time.