Standardized treatment of chronic radiation-induced bowel injury / 中华胃肠外科杂志

Radiation-induced bowel injury is a common complication of radiation therapy for pelvic malignancy. Given the huge number of patients diagnosed with pelvic malignancy, the number of patients diagnosed with radiation-induced bowel injury increased year by year, which put a great burden on the clinical diagnosis and treatment of radiation-induced bowel injury. In particular, chronic radiation-induced bowel injury, which is manifested in the process of prolonged, repeated and progressive aggravation, seriously affects the physical and mental health of patients and makes clinical diagnosis and treatment difficult. However, due to insufficient attention and understanding from doctors and patients, standardized diagnosis and treatment of radiation-induced bowel injury still have a long way to go. Radiation-induced bowel injury is self-limited but irreversible. During diagnosis, we should pay attention to overall evaluation of the stage of disease based on clinical symptoms, endoscopic examination, imaging examination, pathology and nutritional risk. The treatment methods include health education, drug therapy, enema therapy, formalin local treatment, endoscopic treatment and surgical treatment, etc. The treatment decision-making should be based on clinical symptoms, endoscopic or imaging findings to alleviate the clinical symptoms of patients as the primary goal and to improve the long-term quality of life of patients as the ultimate goal.

New Approach of Fundus Image Segmentation Evaluation Based on Topology Structure / 生物医学工程学杂志

In view of the evaluation of fundus image segmentation, a new evaluation method was proposed to make up insufficiency of the traditional evaluation method which only considers the overlap of pixels and neglects topology structure of the retinal vessel. Mathematical morphology and thinning algorithm were used to obtain the retinal vascular topology structure. Then three features of retinal vessel, including mutual information, correlation coefficient and ratio of nodes, were calculated. The features of the thinned images taken as topology structure of blood vessel were used to evaluate retinal image segmentation. The manually-labeled images and their eroded ones of STARE database were used in the experiment. The result showed that these features, including mutual information, correlation coefficient and ratio of nodes, could be used to evaluate the segmentation quality of retinal vessel on fundus image through topology structure, and the algorithm was simple. The method is of significance to the supplement of traditional segmentation evaluation of retinal vessel on fundus image.