Search

A deep learning-based automatic bone age identification system (ABAIs) was introduced in medical imaging. This ABAIs enhanced accurate, consistent, and timely clinical diagnostics and enlightened research fields of deep learning and artificial intelligence (AI) in medical imaging.The goal of this study was to use the Deep Neural Network (DNN) model to assess bone age in months based on a database of pediatric left-hand radiographs.The Inception Resnet V2 model with a Global Average Pooling layer to connect to a single fully connected layer with one neuron using the Rectified Linear Unit (ReLU) activation function consisted of the DNN model for bone age assessment (BAA) in this study. The medical data in each case contained posterior view of X-ray image of left hand, information of age, gender and weight, and clinical skeletal bone assessment.A database consisting of 8,061 hand radiographs with their gender and age (0-18 years) as the reference standard was used. The DNN model's accuracies on the testing set were 77.4%, 95.3%, 99.1% and 99.7% within 0.5, 1, 1.5 and 2 years of the ground truth respectively. The MAE for the study subjects was 0.33 and 0.25 year for male and female models, respectively.In this study, Inception Resnet V2 model was used for automatic interpretation of bone age. The convolutional neural network based on feature extraction has good performance in the bone age regression model, and further improves the accuracy and efficiency of image-based bone age evaluation. This system helps to greatly reduce the burden on clinical personnel.

We hypothesized that sorafenib plus transarterial chemoembolization (TACE) would confer survival benefits over sorafenib alone for advanced hepatocellular carcinoma (aHCC). We investigated this while using the population-based All-Cancer Dataset to assemble a cohort (n = 3674, median age, 60, 83% men) of patients receiving sorafenib for aHCC (Child-Pugh A) with macro-vascular invasion or nodal/distant metastases. The patients were classified into the sorafenib-TACE group (n = 426) or the propensity score-matched sorafenib-alone group (n = 1686). All of the participants were followed up until death or the end of the study. Time-dependent Cox model and the Mantel&ndash, Byar test were used for survival analysis. During the median follow-ups of 221 and 133 days for the sorafenib-TACE and sorafenib-alone groups, 164 (39%) and 916 (54%) deaths occurred, respectively, the corresponding median overall survivals (OS) were 381 and 204 days, respectively (hazard ratio, HR: 0.74, 95% confidence interval, CI, 0.63&ndash, 0.88, p = 0.021). The one-year and six-month OS were 53.5% and 80.3% in the sorafenib-TACE group and 32.4% and 54.4% in the sorafenib-alone group, respectively. The major complications were comparable between the two groups. The addition of TACE to sorafenib improves survival, with a 26% reduction in mortality. These findings provide strong real-world evidence that supports this combination strategy for eligible Child-Pugh A aHCC patients.

Background The currently recommended treatment algorithm for patients with advanced renal cell carcinoma who fail the first-line targeted therapy does not normally include pazopanib as a second-line treatment option. It would therefore be of interest to determine the efficiency of pazopanib in this setting in terms of the partial response rate (PRR), disease control rate (DCR), and progression-free survival (PFS). Methods Peer-reviewed clinical reports without language restriction, both full papers and conference abstracts, which assessed the second-line use of pazopanib following failure of first-line non-cytokine-targeted therapy, were included. After the literature retrieval, we conducted a Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA)-compliant systematic review of the literature and meta-analysis of the size of the effect of each outcome measure (PRR, DCR, and PFS). The effect size and 95 % confidence interval (CI) were calculated using fixed-effect or random-effects models based on the heterogeneity represented by I2 of selected studies. Meta-analysis forest plots with a fixed-effect model showing the PRR and DCR were created. Results Our results show that there are no available comparative studies on pazopanib second-line treatment. Only phase II trials or retrospective analysis reports were retrievable. Six studies (comprising 217 patients) were included in the qualitative and quantitative analysis. Pazopanib as a second-line treatment resulted in a PRR of 23 % (95 % CI, 17–31 %; I2 = 52.6 %) and a DCR of 73 % (95 % CI, 65–80 %; I2 = 0.00 %). The meta-analysis with fixed-effect model revealed that PFS was 6.5 months (95 % CI, 5.6–7.5 months; I2 = 86.2 %). Conclusions In conclusion, the effectiveness and indication of pazopanib for use in the second-line setting has not yet been examined in-depth; however, this meta-analysis has shown that the treatment effects in terms of PRR, DCR, and PFS may be similar to other well-studied second-line targeted therapies. Rigorous comparative phase III trials testing this hypothesis are required.