Background: Overweight and obesity have become a major health issue in the past 30 years. Several studies have already shown that obesity is significantly associated with a higher risk of developing breast cancer.However, few studies have assessed the prognostic value of the body mass index (BMI) in Asian populations.The purpose of this study was to retrospectively analyze the impact of BMI on the prognosis of breast cancer in overweight, under 160 cm tall patients from southern China.Methods: We retrospectively analyzed data from 525 breast cancer patients diagnosed between 2003 to 2010 in a multi-center of China. After applying the exclusion criteria, 315 patients with complete data were retained. Their clinical and pathological characteristics were compared using the chi-square test. Survival analysis was performed with the Kaplan-Meier method. Univariate and multivariate analyses were performed using Cox regression to calculate hormone receptor status, HER-2 status, lymph node status, age, BMI and tumor size hazard ratio (HR), and 95% confidence intervals (95% CI).Results: There was a strong correlation between BMI and age in the baseline feature analysis (P=0.001).After grouping the patients according to the molecular type of cancer, we found that in Luminal A and B, the BMI was related to age (P=0.002, P=0.010). The disease-free survival (DFS) and overall survival (OS) of patients with different BMI were not significantly different. This conclusion was also reached by pairwise comparison of subgroups. There was no significant difference in recurrence in patients from different BMI groups. We did not find a critical weight threshold associated with higher risk of recurrence. There were no statistically significant differences in treatment among the three BMI groups of overweight patients. Conclusions:We found that the BMI of Chinese breast cancer patients is related to age but not prognosis.
With the massive use of computers, the growth and explosion of data has greatly promoted the development of artificial intelligence (AI). The rise of deep learning (DL) algorithms, such as convolutional neural networks (CNN), has provided radiation oncologists with many promising tools that can simplify the complex radiotherapy process in the clinical work of radiation oncology, improve the accuracy and objectivity of diagnosis, and reduce the workload, thus enabling clinicians to spend more time on advanced decision-making tasks. As the development of DL gets closer to clinical practice, radiation oncologists will need to be more familiar with its principles to properly evaluate and use this powerful tool. In this paper, we explain the development and basic concepts of AI and discuss its application in radiation oncology based on different task categories of DL algorithms. This work clarifies the possibility of further development of DL in radiation oncology.
Purpose: This study aimed to evaluate (1) the performance of the Auto-Planning module embedded in the Pinnacle treatment planning system (TPS) with 30 left-side breast cancer plans and (2) the dose-distance correlations between dose-based patients and overlap volume histogram-based (OVH) patients. Method: A total of 30 patients with left-side breast cancer after breast-conserving surgery were enrolled in this study. The clinical manual-planning (MP) and the Auto-Planning (AP) plans were generated by Monaco and by the Auto-Planning module in Pinnacle respectively. The geometric information between organ at risk (OAR) and planning target volume (PTV) of each patient was described by the OVH. The AP and MP plans were ranked to compare with the geometry-based patients from OVH. The Pearson product-moment correlation coefficient (R) was used to describe the correlations between dose-based patients (APs and MPs) and geometry-based patients (OVH). Dosimetric differences between MP and AP plans were evaluated with statistical analysis. Result: The correlation coefficient (mean R = 0.71) indicated that the AP plans have a high correlation with geometry-based patients from OVH, whereas the correlation coefficient (mean R = 0.48) shows a weak correlation between MP plans and geometry-based patients. The dosimetric comparison revealed a statistically significant improvement in the ipsilateral lung V5Gy and V10Gy, and in the heart V5Gy of AP plans compared to MP plans, while statistical reduction was seen in PTV V107% for MP plans compared to AP plans. Conclusion: The overall results of AP plans were superior to MP plans. The dose distribution in AP plans was more consistent with the distance-dose relationship described by OVH. After eliminating the interference of human factors, the AP was able to provide more stable and objective plans for radiotherapy patients.
Background: We aimed to compare the segmentation accuracy of heart substructure on contrast enhanced CT by deep neural network combined with different loss functions.Methods: We collected 35 thoracic tumor patients admitted to the Department of Radiation Oncology of Yunnan Cancer Hospital. Organ-at-risks (OARs) were defined as 10 organs of cardiac substructures (pericardium, heart, left atrium, left ventricle, right atrium, right ventricle, left main stem, left anterior descending Branch, left circumflex branch, right coronary artery), and use the OARs manually outlined by radiation oncologists on enhanced localization CT as the gold standard. The automatic segmentation results of GDL U-Net, WCEGDL U-Net, ELL U-Net, and GDL V-Net are compared with the gold standard. DSC, JC, HD, VD are used as quantitative evaluation indicators. Results: The segmentation DSC of the pericardium, heart, atrium, and ventricle of the DCNN with different loss functions all reached above 0.87. WCEGDL U-Net segmented the pericardium with DSC of 0.961 and 95% HD of 3.449mm; The segmentation DSC of the heart by ELL U-Net reached 0.965, and the 95% HD was 3.477mm; GDL U-Net segmentation of left atrium and right ventricle is better, DSC is 0.896 (95% HD: 3.429mm), 0.912 (95% HD: 4.242mm);GDL V-Net has better segmentation performance for right atrium and left ventricle, with DSC of 0.881 (95% HD: 3.904mm) and 0.940 (95% HD: 2.821mm). Conclusions: The DCNN proposed in this study have achieved better segmentation effects on the pericardium, heart and four chambers in cardiac substructure segmentation.
BackgroundThis study aimed to evaluate (1) the performance of Auto-Planning module embedded in Pinnnacle treatment planning system (TPS) with 30 left-side breast cancer plans; (2) the dose-distance relations based on overlap volume histogram (OVH) curve.Method30 patients with left-side breast cancer after breast-serving surgery were enrolled in this study. The clinical manual plan (MP) and the automatic plan (AP) were generated by Monaco and Auto-planning module respectively. The geometric relations between organ at risk (OAR) and planning target volume (PTV) of each patient were described by the overlap volume histogram (OVH). The patients were ranked according to the extension distance from PTV at a specific volume on the OVH curve. The MP and AP plans then were ranked to compare with the ranking of the OVH curves. Dosimetric difference between MP and AP plans were evaluated with statistical analysis.ResultThe comparative result shows a higher degree of correlation between AP and OVH curve. For different indicators, the dose distribution of , , in ipsilateral lung is more consistent with the distance-dose relation compared to the dose distribution of in heart. Dosimetric comparison shows a statistically significant improvement in ipsilateral lung and , and in heart of AP plans compared to MP plans. However, the result of ipsilateral lung of MP plans are better than that of AP plans.ConclusionThe overall results of AP plans are superior to MP plans. The dose distribution in AP plans are more consistent with the distance-dose relationship, which was described by OVH. After eliminating the interference of human factors, the AP is able to provide more stable and objective plans for radiotherapy patients.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.