CEUS-based classification of liver tumors with deep canonical correlation analysis and multi-kernel learning.

The contrast-enhanced ultrasound (CEUS) has been a widely accepted imaging modality for diagnosis of liver cancers. In clinical practice, several typical images selected from enhancement patterns of the arterial, portal venous and late phases can provide reliable information basis for diagnosis. In this work, we propose to develop a CEUS-based computer-aided diagnosis (CAD) for liver cancers with only three typical CEUS images selected from three phases, which simulates the clinical diagnosis mode of radiologists. In the proposed CAD, the deep canonical correlation analysis (DCCA) is first performed on three CEUS pairs between arterial and portal venous phases, arterial and late phases, respectively, due to the effectiveness of multi-view fusion of DCCA. The generated six-view features are then fed to a multiple kernel learning (MKL) classifier to further promote the predictive diagnosis result. The experimental results indicate that the proposed DCCA-MKL algorithm achieves best performance for discriminating benign liver tumors from malignant liver cancers.

Multimodal Ultrasound imaging based diagnosis of liver cancers with a two-stage multi-view learning framework.

Computer-aided diagnosis (CAD) of liver cancers on contrast-enhanced ultrasound (CEUS) has attracted considerable attention in recent years. The enhancement patterns on CEUS for liver lesions consist of the arterial, portal venous and late phases. Several typical images selected from these three phases can provide reliable information basis for diagnosis of liver lesions. Therefore, we propose to develop a CAD framework for liver cancers with only one B-mode image and three typical CEUS images selected from three enhancement patterns, which simulates the clinical diagnosis mode of radiologists. Moreover, a framework of two-stage multi-view learning (TS-MVL) is proposed to perform both feature-level and classifier-level MVL for the diagnosis of liver cancers with multimodal ultrasound images. We propose to apply the nonlinear kernel matrix (NKM) algorithm to effectively fuse the features of multimodal ultrasound images, and then perform the multiple kernel boosting (MKB) algorithm to promote the predictive performance of multiple classifiers according to multi-view features. The experimental results indicate that the proposed algorithm outperforms the commonly used multi-view learning algorithms.

Investigation and Analysis of the Application of Key Monitoring Varieties among Adjuvant Drugs in Medical Institutions of Yunnan Province / 中国药房

OBJECTIVE:To investigate the application of key monitoring varieties among adjuvant drugs in medical institu tions of Yunnan province,and to provide reference for the formulation of related policy and the promotion of clinical rational drug use.METHODS:The related data of key monitoring varieties in medical institutions of Yunnan province during Jan.1st-Mar.31st,2015 were investigated and analyzed statistically.RESULTS:The data with highest effective rate were reported by tertiary hospi tals,being 93.94％.Among top 10 drugs in the list of consumption sum,the number of key monitoring varieties was the highest in tertiary hospitals,being (5.50 ± 2.12) varieties averagely.The consumption sum of key monitoring varieties in tertiary hospitals took up the highest proportion in total consumption sum of hospitalization drug,being(31.94 ± 16.99)％ averagely;being(26.13 ± 11.93)％ and (22.14 ± 16.39)％ in second level hospitals and first level hospitals.Among top 10 drugs in the list of consumption sum,the consumption sum of key monitoring varieties in second level hospitals took up the highest proportion in total consumption sum of hospitalization key monitoring varieties,being (50.34 ± 26.87) ％ in average,up to 98.53 ％;being (39.13 ± 22.55) ％ and (27.38 ± 27.75)％ in tertiary hospitals and first level hospital.Among top 5 key monitoring types in the list of hospitalization con sumption sum,safflower yellow pigment and omeprazole were involved in hospitals at various levels.CONCLUSIONS:Adjuvant drug use are widespread in medical institutions of Yunnan province.Key monitoring varieties are given priority to TCM injection and proton pump inhibitors.It is necessary to take effective measures,formulate and implement the corresponding supervision sys tem so as to promote rational clinical drug use.

Investigation of the Construction Situation for Pharmacist Team in Medical and Health Institutions in Yun-nan Provence and Legislative Suggestions / 中国药房

OBJECTIVE:To provide data and reference for pharmacist legislation. METHODS:Questionnaire survey was de-signed investigate and analyze the staffing situation,education level,professional composition,age composition,professional titles composition,continuing education and wage of pharmacists who worked in medical and health institutions from 16 states (cities) in Yunnan province,and suggestions were put forward for relevant legislation. RESULTS:Totally 10 questionnaires were received from provincial medical and health institutions,and 16 from state (city) Health and Family Planning Commission,with effective recovery of 100%;data covered 1 561 medical and health institutions,involving 7 409 pharmacists. The numbers of pharmacy per-sonnel/hospital beds in tertiary hospitals,secondary hospitals and class-1 hospitals were 1∶15.49,1∶17.50,1∶20.68,numbers of pharmacy personnel/health professional and technical personnel in hospital accounted for 5.62%,6.18%,5.30%,respectively;most pharmacists in tertiary hospitals were mainly undergraduate degree(35.21%),doctor degree accounted for 0.15%,the high-est ratio of education was junior college degree in secondary hospitals(41.60%)and class-1 hospitals(57.51%);most pharmacists graduated in pharmacy in tertiary hospitals(94.14%),70.22% in secondary hospitals and only 10.50% in class-1 hospitals;phar-macy personnel mainly held the pharmacist professional titles in tertiary,secondary and class-1 hospitals (33.83%,37.89% and 63.55%),senior professional titles accounted for 5.88%,2.71% and 0.21%,respectively;only a few have learning experience and almost less than 6 months (9.17%,5.84% and 21.32%),and 80 pharmacists were certificated as clinical pharmacists in the whole province;generally,all wage was concentrated in 2 000-2 999 per month (27.72%,41.80% and 55.90%,respectively). CONCLUSIONS:Shortage of hospital pharmacists and lack of senior personnel are the main problems in Yunnan province,and wage is not high,especially in primary hospital,this situation is more obvious. The current situation of pharmacists in the hospital should be more taken into consideration during the legislative process in aspects of clearing and guaranteeing access qualifications, responsibilities,status,rights and interests,and pharmaceutical technology and service charges should be established.