ABSTRACT
OBJECTIVE@#To explore the integration method and technical realization of artificial intelligence bone age assessment system with the hospital RIS-PACS network and workflow.@*METHODS@#Two sets of artificial intelligence based on bone age assessment systems (CHBoneAI 1.0/2.0) were developed. The intelligent system was further integrated with RIS-PACS based on the http protocol in Python flask web framework.@*RESULTS@#The two sets of systems were successfully integrated into the local network and RIS-PACS in hospital. The deployment has been smoothly running for nearly 3 years. Within the current network setting, it takes less than 3 s to complete bone age assessment for a single patient.@*CONCLUSIONS@#The artificial intelligence based bone age assessment system has been deployed in clinical RIS-PACS platform and the "running in parallel", which is marking a success of Stage-I and paving the way to Stage-II where the intelligent systems can evolve to become more powerful in particular of the system self-evolution and the "running alternatively".
Subject(s)
Humans , Age Determination by Skeleton , Artificial Intelligence , Bone and Bones , Hospital Information Systems , Hospitals , Radiology Information Systems , Systems IntegrationABSTRACT
Objective To investigate the value of conventional MRI,MR cholangiopancreatography(MRCP) and diffusion weighted imaging(DWI) in T-staging of gallbladder cancer(GBC).Methods 56 patients with histologically proven GBCs were analyzed retrospectively.Staging was performed according to MR findings and compared with pathological findings.The accuracy of the two methods with or without DWI sequence was also compared.Results The accuracy of staging of conventional MRI and MRCP was 87.5％ (49/56).The sensitivity,specificity and accuracy of conventional MRI and MRCP in the stage of lesions as T1 vs ≥T2,≤T2 vs ≥T3 and ≤T3 vs T4 were 83.3 ％/98.0 ％/96.4 ％,92.3 ％/97.7 ％/96.4 ％ and 93.1％/88.8 ％/91.1％,respectively.The accuracy of staging of conventional MRI and MRCP combined with DWI was 91.1％ (51/56).The sensitivity,specificity and accuracy of conventional MRI and MRCP combined with DWI in the stage of lesions as T1 vs ≥T2,≤T2 vs ≥T3 and ≤T3 vs T4 were 83.3％/98.0％/96.4％,92.3％/97.7％/96.4％ and 93.8％/100％/96.4％,respectively.There was no statistical difference between the two groups(P＞0.05).Conclusion Conventional MRI and MRCP provides excellent T-staging accuracy for GBC.The accuracy of T-staging can be improved by conventional MRI and MRCP combining with DWI,especially for T4 stage.
ABSTRACT
<p><b>OBJECTIVES</b>To investigate the influencing factors of nonalcoholic fatty liver disease (NAFLD).</p><p><b>METHODS</b>A hospital-based case-control study was conducted in patients with NAFLD and controls without NAFLD in a hospital from January to August in 2007. All data were analyzed by SPSS 13.0 software.</p><p><b>RESULTS</b>One-way analysis of variance found that the two groups were significantly different in cigarette smoking, alcohol and tea comsumption, movement index, speed of food intake, frequency of social engagement, kinds of edible oil, marine products, family history of NAFLD, hypertension, higher blood sugar, abnormality of blood fat, higher level of ALT, higher level of AST, hyperuricemia, obesity, decrease of high density lipoprotein (HDL), and increase of low density lipoprotein. By non-conditional logistic stepwise regression analysis, 12 of 18 factors were used to construct a model, ten of which were the risk factors and two were protective factors of NAFLD. Risk factors included obesity (OR=6.35), hypertension(OR=3.82), dyslipidemia (OR=2.95), decrease of HDL (OR=2.85), hyperglycemia (OR=2.82), increase of ALT (OR=2.80), hyperuricemia (OR=2.35), HBsAg positive (OR=1.99), family history of fatty liver (OR=1.79) and frequently intake of marine products (OR=1.58), and protective factors included tea drinking (OR=0.72) and exercise (OR=0.90).</p><p><b>CONCLUSIONS</b>There are many influencing factors of NAFLD, and life styles are the key factors. Genetic background may also play some roles in NAFLD.</p>