Medical image is a powerful tool to assist doctors in the diagnosis and treatment planning.Nowadays,the segmentation of medical images is no longer limited to manual segmentation methods.Traditional methods and deep learning methods have been used to achieve more accurate results in medical image segmentation.Herein some innovative medical image segmentation methods in recent years are reviewed.By elaborating on the innovations of deep learning methods(SAM,SegNet,Mask R-CNN,and U-NET)and traditional methods(active contour model and threshold segmentation model),the differences and similarities between them are compared.The summary of medical image segmentation methods and the prospect is expected to help researchers better grasp and familiarize themselves with research status and development trend.

Brachytherapy is a kind of radiation therapy corresponding to external radiation therapy, i. It has been widely used because it can achieve a higher radiation dose to the lesion area and better protect to the organs at risk. However, tThe workflow of brachytherapy is time-consuming and may lead to patient discomfort, displacement of the applicator or interstitial needle, and organ changes. In recent years, deep learning technology has achieved significant success in the medical field, offering new avenues for the automation of brachytherapy, improvement of radiotherapy precision, and ensuring the safety and effectiveness of radiotherapy plans. This review summarizes the research progress of deep learning in the context of brachytherapy segmentation, image registration, applicator reconstruction, dose prediction and planning optimization, and quality assurance for clinical research reference.

OBJECTIVETo analyze the associations between birth weight and overweight/obesity among children.

METHODSA total of 8 267 twin pairs younger than 18 years old from the Chinese National Twin Registry were included in the study. Associations between birth weight, childhood BMI and overweight/obesity were explored by this co-twin control study.

RESULTSAfter adjusting for sex and zygosity, when birth weight had an increase of 0.5 kg per fold, the OR values for overweight and obesity were 1.87(95%CI: 1.40-2.48) for 2-6 year olds, 1.69 (95%CI: 1.16-2.46) for 6-12 year olds and 1.28 (95%CI: 0.80-2.07) for 12-18 year olds.

RESULTSfrom the stratified analysis in the 2-6 year-olds, statistically significant differences were seen. When birth weight increased 0.5 kg per fold, the risk of overweight and obesity increased by 0.87 times among the dizygotic twins, more than that of the monozygotic twins (OR=1.86, 95%CI:1.24-2.81). The risk for male twins was 1.12 times higher than that of female twins (OR=1.65, 95%CI:1.11-2.44).

CONCLUSIONSBirth weight seemed associated with overweight and obesity for kids at early childhood or at age for schools. However, guidance on the implementation of public health interventions is still needed on these children.

Adolescent ; Birth Weight ; Child ; Child, Preschool ; China ; epidemiology ; Female ; Humans ; Male ; Obesity ; ethnology ; Overweight ; ethnology ; Registries ; Risk ; Twins, Dizygotic ; Twins, Monozygotic