الملخص
Objective To develop and validate a deep learning model for automatic identification of liver CT contrast-enhanced phases.Methods A total of 766 patients with liver CT contrast-enhanced images were retrospectively collected.A three-phase classification model and an arterial phase(AP)classification model were developed,so as to automatically identify liver CT contrast-enhanced phases as early arterial phase(EAP)or late arterial phase(LAP),portal venous phase(PVP),and equilibrium phase(EP).In addition,221 patients with liver CT contrast-enhanced images in 5 different hospitals were used for external validation.The annotation results of radiologists were used as a reference standard to evaluate the model performances.Results In the external validation datasets,the accuracy in identifying each enhanced phase reached to 90.50%-99.70%.Conclusion The automatic identification model of liver CT contrast-enhanced phases based on residual network may provide an efficient,objective,and unified image quality control tool.
الملخص
Objective:To classify the symptom characteristics of young and middle-aged peritoneal dialysis patients and to explore the differences of demographic functional status and social function of patients with different symptom categories.Methods:A total of 179 peritoneal dialysis patients from 3 peritoneal dialysis centers in Shanghai were investigated from December 2019 to August 2020 by General Information Questionnaire, Peritoneal Dialysis Symptom Distress Scale. Latent class analysis was used to classify young and middle-aged peritoneal dialysis patients according to symptom characteristics. Multiple Logistic regression was used to explore the differences of demographic and disease characteristics of different categories of patients.Results:Peritoneal dialysis patients could be divided into three potential categories according to symptom characteristics ( P<0.05). According to the conditional probability of each category, they were named "low symptom group" (111 cases,62.0%), "high psychological-moderate physical symptom group" (22 cases, 12.3%), "high symptom group" (46 cases,25.7%). There were differences in working status ( OR=0.029, P<0.01), education level ( OR=152.799, P<0.01), duration ( OR=81.307, P<0.05), diabetic nephropathy ( OR=80.619, P<0.01) and CCI score ( OR=91.188, P<0.01) distribution among different potential categories of young and middle-aged peritoneal dialysis patients. Conclusions:There are three types of potential symptoms in young and middle-aged patients undergoing peritoneal dialysis. In clinical practice, medical staff should focus on the psychological status of young and middle-aged patients with low educational background and early stage of dialysis, and encourage them to return to work; at the same time, they should regularly evaluate the symptom burden of patients with diabetic nephropathy and high complication index peritoneal dialysis patients, in order to provide targeted intervention measures to prevent the progression of the disease.
الملخص
<p><b>OBJECTIVE</b>To explore the value of rectal mucosa stripping and pull-through from rectal muscle sheath of blind pouch in the treatment of congenital high anal atresia in the newborn.</p><p><b>METHODS</b>Clinical data of 232 newborns diagnosed as congenital high anal atresia undergoing operation from January 2001 to December 2010 were retrospectively analyzed. Among these patients, 168 underwent rectal mucosa stripping and pull-through from rectal muscle sheath of blind pouch through the previous of sagittal approach (intrathecal pull-through group), and 64 cases underwent the Pena procedure (Pena group). Patients were followed up for two years. Kelly score was used to estimate postoperative anorectal function. Defecography was used to examine the morphology of anorectum. Rectal pressure was measured as well.</p><p><b>RESULTS</b>Two years after operation, Kelly score revealed that 126 (75.0%) cases in the intrathecal pull-through group and 54 cases (84.4%) in the Pena group had good control defecation (P>0.05), while constipation rate was significantly lower in intrathecal pull-through group [8.3% (14/168) vs. 21.9% (14/64), P<0.05]. Postoperative barium defecography showed that defecation rectum maximum diameter was (2.2±0.3) cm in intrathecal pull-through group and (2.3±0.8) cm in the Pena group (P>0.05). Anorectal manometry showed rectal maximum capacity threshold value was (91.4±15.2) ml in the intrathecal pull-through group and (95.1±18.6) ml in the Pena group (P>0.05). There were no significant differences in defecography, anal bowel function and anorectal manometry between the two groups postoperatively (all P>0.05).</p><p><b>CONCLUSIONS</b>Rectal mucosa stripping and pull-through from rectal muscle sheath of blind pouch through the former sagittal can be completed with one-stage operation in newborn for the treatment of congenital high anal atresia, the efficacy of which is similar to the classic Pena operation. This procedure can avoid other operations, ameliorate the pains of newborns, decrease the burden of family, and has lower constipation rate, therefore it is a valid surgical option.</p>