Establishment of a deep feature-based classification model for distinguishing benign and malignant breast tumors on full-filed digital mammography / 南方医科大学学报

OBJECTIVE@#To develop a deep features-based model to classify benign and malignant breast lesions on full- filed digital mammography.@*METHODS@#The data of full-filed digital mammography in both craniocaudal view and mediolateral oblique view from 106 patients with breast neoplasms were analyzed. Twenty-three handcrafted features (HCF) were extracted from the images of the breast tumors and a suitable feature set of HCF was selected using -test. The deep features (DF) were extracted from the 3 pre-trained deep learning models, namely AlexNet, VGG16 and GoogLeNet. With abundant breast tumor information from the craniocaudal view and mediolateral oblique view, we combined the two extracted features (DF and HCF) as the two-view features. A multi-classifier model was finally constructed based on the combined HCF and DF sets. The classification ability of different deep learning networks was evaluated.@*RESULTS@#Quantitative evaluation results showed that the proposed HCF+DF model outperformed HCF model, and AlexNet produced the best performances among the 3 deep learning models.@*CONCLUSIONS@#The proposed model that combines DF and HCF sets of breast tumors can effectively distinguish benign and malignant breast lesions on full-filed digital mammography.

Comparison of Clinical Efficacy and Safety of Amiodarone and Propafenone in the Treatment of Chronic Atri-al Fibrillation Cardioversion / 中国药房

OBJECTIVE:To compare the clinical efficacy and safety of amiodarone and propafenone in the treatment of chron-ic atrial fibrillation cardioversion. METHODS:60 patients with chronic atrial fibrillation cardioversion were randomly divided into propafenone group and amiodarone group. All patients were given conventional treatment,including treating primary disease,con-trolling symptoms,orally giving aspirin,intravenous infusion of GIK,monitoring heart rate,QT interval,P-R interval,QRS time,serum potassium and serum magnesium,etc. On this basis,propafenone group was orally given propafenone 450 mg for con-tinuous 3 months,3 times a day,and then the dose was decreased to 300 mg to maintain the sinus rhythm;amiodarone group was orally given amiodarone 200 mg for continuous 7 d a month,twice a day,and then the dose was decreased to 200 mg or 100 mg to maintain the sinus rhythm. The clinic data in 2 groups was observed,including clinical efficacy,simple drug cardioversion,elec-trical cardioversion,electrical cardioversion power,hospitalization time and incidence of adverse reactions,and the recurrence rate in 48 months was followed up. RESULTS:There were no significant differences in the clinical efficacy,simple drug cardiover-sion,electrical cardioversion,electrical cardioversion power,hospitalization time,incidence of adverse reactions and recurrence rate between 2 groups(P>0.05). CONCLUSIONS:Based on the conventinal treatment,amiodarone and propafenone have similar clinical efficacy and safety in the treatment of chronic atrial fibrillation cardioversion,and both of them can be used as the conven-tional drugs for treating chronic atrial fibrillation cardioversion.