Search

The aim of the study was to use a previously proposed mask region–based convolutional neural network (Mask R-CNN) for automatic abnormal liver density detection and segmentation based on hepatocellular carcinoma (HCC) computed tomography (CT) datasets from a radiological perspective. Training and testing datasets were acquired retrospectively from two hospitals of Taiwan. The training dataset contained 10,130 images of liver tumor densities of 11,258 regions of interest (ROIs). The positive testing dataset contained 1,833 images of liver tumor densities with 1,874 ROIs, and negative testing data comprised 20,283 images without abnormal densities in liver parenchyma. The Mask R-CNN was used to generate a medical model, and areas under the curve, true positive rates, false positive rates, and Dice coefficients were evaluated. For abnormal liver CT density detection, in each image, we identified the mean area under the curve, true positive rate, and false positive rate, which were 0.9490, 91.99%, and 13.68%, respectively. For segmentation ability, the highest mean Dice coefficient obtained was 0.8041. This study trained a Mask R-CNN on various HCC images to construct a medical model that serves as an auxiliary tool for alerting radiologists to abnormal CT density in liver scans; this model can simultaneously detect liver lesions and perform automatic instance segmentation. [ABSTRACT FROM AUTHOR]

Huang Y-H, Chen C-H, Chang T-T, Chen S-C, Wang S-Y, Lee P-C, Lee H-S, Lin P-W, Huang G-T, Sheu J-C, Tsai H-M, Chau G-Y, Chiang J-H, Lui W-Y, Lee S-D, Wu J-C. The role of transcatheter arterial embolization in patients with resectable hepatocellular carcinoma: a nation-wide, multi-center study.Liver International 2004: DOI: 10.1111/j.1478-3231.2004.0941.x.© Blackwell Munksgaard 2004The role of transcatheter arterial embolization (TAE) for patients with resectable hepatocellular carcinoma (HCC) is controversial. Analyzing a cohort of nation-wide data can delineate the beneficial effect of TAE for those patients.From 1991 to 1995, 818 patients who had potentially resectable HCC from four medical centers in Taiwan were enrolled. Among them, 599 underwent curative resection, 157 received TAE and 62 received supportive treatment alone. The survivals among the three groups were compared.The 5-year survival rates for patients who underwent surgery, TAE and supportive treatment were 43.6%, 25.6% and 3.7%, respectively. Surgery offered the best survival for those patients. TAE could also prolong survival as compared with supportive treatment (P=0.0001). However, among patients who were in advanced tumor stage (Cancer and the Liver Italian Program (CLIP) score≥2), no statistical difference in survival was noted between patients who underwent TAE or supportive treatment. In multivariate analysis, single tumor, serum albumin≥3.5 g/dl, tumor size less than 5 cm, early-stage tumor (CLIP score=0–1) and aggressive treatment including surgery and TAE were independent factors associated with a better survival.Surgery is superior to TAE for patients with resectable HCC. In patients who refuse surgery, TAE can be considered for selected patients whose tumors are in early stage. [ABSTRACT FROM AUTHOR]