Objective The purpose of this study was to assess the value of prenatal ultrasound diagnosis for fetal ear auricle malformations.Methods The coronal and sagittal planes of fetuses ears were obtained prospectively in 6239 singleton fetuses in the First Affiliated Hospital of Shantou University Medical College for the period from 2012 February to 2015 December,the ultrasound images and pregnancy outcomes were analyzed in 11 cases of fetuses ear auricle malformations diagnosed prenatally.Results Eleven Cases of fetuses ear auricle malformations include with 7 cases of microtia,3 cases of low-set ears and 1 case of anotia.Eleven cases were combined with other structural malformations were as followings,3cases with craniocerebral congenital malformation,5 cases with dentofacial deformity,5 cases with malformation of heart,3 cases with limb deformity.Cordocentesis was performed in 7 cases among which 6 with abnormal karyotype,including 2 cases of trisomy 21,2 cases of trisomy 13,2 cases of trisomy 18,1 case of 22ql 1 abnormalities.Compared with the postpartum facial examination,prenatal ultrasound correctly diagnosed 10 cases of fetal ear auricle malformations,missed diagnosis 1 case of microtia.Conlusions Fetus with ear auricle abnormalities have characteristic prenatal ultrasound imaging;prenatal ultrasonography can provide reliable information in the diagnosis of this disease.This study suggests that antenatal ear auricle length measurements might be a promising sonographic screening method for the detection of abnormal karyotype in pregnancy.

BACKGROUND:Preoperative walking ability and activities are good predictors of functional recovery of patients after hip replacement. But these objective assessment tools are invalid to predict postoperative function of patients with no preoperative walking ability.
OBJECTIVE:To assess the effect of preoperative subjective physical activity questionnaire to predict the 6-month postoperative physical functioning outcomes in elder patients receiving hip arthroplasty, and to determine which aspects of patient’s characteristics influence 6-month postoperative physical activity.
METHODS:A two-center prospective audit was carried out in elder patients who underwent hip arthroplasty between November 2010 and February 2013. These patients were divided into three groups, including the group of total hip arthroplasty for fractures of the femoral neck, the group of total hip arthroplasty for osteoarthritis and the group of hemiarthroplasty for fractures of the femoral neck. Al patients had fulfil ed Longitudinal Aging Study Amsterdam-Physical Activity Questionnaire (LAPAQ) and Short Form 36 (SF-36) recal ing their physical activity at 2 weeks before the fal accident (for fractures of the femoral neck) or admission (for hip osteoarthritis). Preoperative demographic data were also col ected. Postoperative assessment regarding subjective physical activity assessment including LAPAQ and SF-36, and objective physical activity assessment including timed up and go test and six-minute walk test were evaluated at the time of 6-month postoperation.
RESULTS AND CONCLUSION:Total y 115 patients finished the study. Both preoperative LAPAQ and SF-36 can play a predictor to probe 6-month postoperative function of objective and subjective activity in patients with femoral neck fractures or hip osteoarthritis undergoing hip arthroplasty. Preoperative LAPAQ seems better than preoperative SF-36 to predict postoperative physical activity. For hip fracture patients, because preoperative objective function cannot be assessed, preoperative LAPAQ can play an effective and subjective index to predict postoperative function of objective activity, and physical functions can recover 70%-80%at 6 months postoperatively. For hip osteoarthritis patients, postoperative physical function can be increased by approximately 27%compared with before hip arthroplasty. Patient’s characteristics also affect the postoperative physical activity, and the occurrence of preoperative complications is a most important factor.

Objective:To investigate the diagnostic performance of a new artificial intelligence (AI) model incorporating SAM-YOLOV 5 deep learning network and image processing techniques for Breast Imaging Reporting and Data System (BI-RADS) 4 category breast masses in dynamic ultrasound classification.Methods:A total of 530 pathologically proven breast lesions of BI-RADS category 4 in 458 patients were retrospectively collected from May 2019 to June 2023 at the First Affiliated Hospital of Shantou University Medical College. The model was trained and tested at ratio of 7∶3, the area under the ROC curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value of the model were determined. Firstly, the test results of the model were compared with a single static image, then, compared with the three conventional deep learning networks as well as senior and junior radiologists. The diagnostic efficiency of the new model in BI-RADS categories 4a, 4b, and 4c masses were analyzed.Results:The AUC, sensitivity, specificity, positive predictive value and negative predictive value of the new model based on dynamic ultrasound video were higher than those using a single ultrasound static imaging (all P<0.05). Based on dynamic ultrasound video, the AUC, sensitivity, specificity, positive predictive value and negative predictive value of the new model were significantly higher than those of YOLOV 5, VGG 16, Resnet 50 and the junior group (all P<0.05), lower than the senior group (just specificity and negative predictive value, P<0.05). The diagnostic efficiency of new model for BI-RADS category 4b masses was the lowest. Conclusions:Based on the SAM-YOLOV 5 deep learning network and image processing techniques, the new model has a high diagnostic value for breast mass dynamic ultrasound classification and is expected to be used in assisting clinical diagnosis.