Deep-learning magnetic resonance imaging-based automatic segmentation for organs-at-risk in the brain: Accuracy and impact on dose distribution.

Background and purpose: Normal tissue sparing in radiotherapy relies on proper delineation. While manual contouring is time consuming and subject to inter-observer variability, auto-contouring could optimize workflows and harmonize practice. We assessed the accuracy of a commercial, deep-learning, MRI-based tool for brain organs-at-risk delineation. Materials and methods: Thirty adult brain tumor patients were retrospectively manually recontoured. Two additional structure sets were obtained: AI (artificial intelligence) and AIedit (manually corrected auto-contours). For 15 selected cases, identical plans were optimized for each structure set. We used Dice Similarity Coefficient (DSC) and mean surface-distance (MSD) for geometric comparison and gamma analysis and dose-volume-histogram comparison for dose metrics evaluation. Wilcoxon signed-ranks test was used for paired data, Spearman coefficient(ρ) for correlations and Bland-Altman plots to assess level of agreement. Results: Auto-contouring was significantly faster than manual (1.1/20 min, p < 0.01). Median DSC and MSD were 0.7/0.9 mm for AI and 0.8/0.5 mm for AIedit. DSC was significantly correlated with structure size (ρ = 0.76, p < 0.01), with higher DSC for large structures. Median gamma pass rate was 74% (71-81%) for Plan_AI and 82% (75-86%) for Plan_AIedit, with no correlation with DSC or MSD. Differences between Dmean_AI and Dmean_Ref were ≤ 0.2 Gy (p < 0.05). The dose difference was moderately correlated with DSC. Bland Altman plot showed minimal discrepancy (0.1/0) between AI and reference Dmean/Dmax. Conclusions: The AI-model showed good accuracy for large structures, but developments are required for smaller ones. Auto-segmentation was significantly faster, with minor differences in dose distribution caused by geometric variations.

Determinants of visfatin in type 2 diabetes patients with diabetic kidney disease: Relationship to inflammation, adiposity and undercarboxylated osteocalcin.

BACKGROUND: Visfatin is a proinflammatory molecule with possible actions on glucose metabolism. Interactions to bone metabolism and undercarboxylated osteocalcin (uOC) in diabetic patients (T2DP) with diabetic kidney disease (DKD) have not been reported. MATERIALS AND METHODS: We included 51 incident T2DP with DKD. History, laboratory evaluation, anthropometry, visfatin, uOC were obtained. Fifteen T2DP without DKD were used as controls. RESULTS: Visfatin was similar in DKD patients and controls: 1.56(0.97-3.03) versus 2.04(1.08-3.21) ng/mL, p = 0.51. In controls, visfatin positively correlated with diabetes duration (r = 0.63, p = 0.01) and negatively with uOC (r = -0.57, p = 0.03). In multivariate regression, diabetes duration remained significant (p = 0.01). In patients with DKD, visfatin was positively linked to C reactive protein (r = 0.27, p = 0.05), tricipital skin fold (TSF) (r = 0.41, p = 0.004) and leukocytes (r = 0.37, p = 0.01); the latter two parameters predicted visfatin in multivariate model (p = 0.001). In normoalbuminuric patients, visfatin was linked to body mass index (r = 0.32, p = 0.04), waist circumference (r = 0.42, p < 0.0001), LDL cholesterol (r = 0.33, p = 0.03), serum glucose (r = 0.36, p = 0.03) and glycated hemoglobin (r = 0.41, p = 0.007); there was a trend towards negative correlation to uOC (r = -0.28, p = 0.07); only glycaemia remained significant in multivariate analysis (p = 0.04). Albuminuric patients displayed a positive correlation of visfatin to waist to hip ratio (r = 0.41, p = 0.04) and leukocytes (r = 0.56, p = 0.04); the latter remained significant in multivariate regression (p = 0.005). CONCLUSION: The main determinant of visfatin in T2D patients with DKD is inflammation; in normoalbuminuric patients, a positive link to adiposity and altered glycemic control and a trend towards a negative correlation to uOC was observable; the latter relationship was evident in patients without DKD.

Brachytherapy next generation: robotic systems.

In a field dominated by external beam radiation therapy (EBRT), both the therapeutic and technical possibilities of brachytherapy (BT) are underrated, shadowed by protons and intensity modulated radiotherapy. Decreasing expertise and indications, as well as increasing lack of specific BT training for radiation therapy (RT) residents led to the real need of shortening its learning curve and making it more popular. Developing robotic BT devices can be a way to mitigate the above issues. There are many teams working at custom-made robotic BT platforms to perfect and overcome the limitations of the existing systems. This paper provides a picture of the current state-of-the-art in robotic assisted BT, as it also conveys the author's solution to the problem, a parallel robot that uses CT-guidance.