This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

GALNT14 genotypes were significantly associated with clinical outcomes of transcatheter arterial chemoembolization. The differential status of extrinsic apoptotic signaling between cancerous and non-cancerous tissues might underlie the clinical association.

Liver cirrhotic patients suffer from a seemingly unpredictable risk of hepatocellular carcinoma (HCC). Here, an HCC risk score R (0 ≦ R ≦ 1) was derived from commonly tested haematological and biochemical parameters. In the score-derivation Taiwanese cohort (144 cirrhosis versus 48 HCC-remission patients), the score had an area-under-the-curve (AUC) of 0.70 (95% confidence interval [CI], 0.61–0.78, P < 0.001). When validated in a Korean cohort (78 cirrhosis versus 23 HCC-remission patients), the AUC was 0.68 (CI, 0.56–0.80, P = 0.009). In a multicentre prospective cohort (478 cirrhotic patients prospectively followed for HCC occurrence), the hazard ratio with respect to R was 2.344 (CI = 1.183–4.646, P = 0.015). The cumulative incidences of HCC at two years after patient enrolment were 9.6% and 1.7% for the high-risk (R ≧ 0.5) and low-risk (R < 0.5) groups, respectively (P < 0.001). At the end of the study, the incidences were 10.9% and 5.0%, respectively (P = 0.012). The majority of HCCs (23/26) in the high-risk group emerged within the first two years of follow-up. In conclusion, an HCC risk score was developed for cirrhotic patients that effectively predicted HCC in a prospective cohort study.

An approach to improve the regions of interesting (ROIs) selection accuracy automatically for medical images is proposed. The aim of the study is to select the most interesting regions of image features that good for diffuse objects detection or classification. We use the AHP (Analytic Hierarchy Process) to obtain physicians high-level diagnosis vectors and are clustered using the well-known K-Means clustering algorithm. The system also automatically extracts low-level image features for improving to detect liver diseases from ultrasound images. The weights of low-level features are adaptively updated according the feature variances in the class. Finally, the high-level diagnosis decision is made based on the high-level diagnosis vectors for the top K near neighbors from the medical experts classified database. Experimental results show the effectiveness of the system.