Liver cancer is the second leading cause of cancer-related death worldwide,so early detection and prediction for response to treatment is of great benefit to hepatocellular carcinoma (HCC) patients.Currently,needle biopsy and conventional medical imaging play a significant and basic role in HCC patients' management,while those two approaches are limited in sample error and observerdependence.Radiomics can make up for this deficiency because it is an emerging non-invasive technic that is capable of getting comprehensive information relevant to tumor situation across spatial-temporal limitation.The basic procedure for radiomics includes image acquisition,region of interest segmentation and reconstruction,feature extraction,selection and classification,and model building and performance evaluation.The current advances and potential prospect of radiomics in HCC studies are involved in diagnosis,prediction for response to treatment,prognosis evaluation and radiogenomics.

Objective:To summarize the clinical and genetic features of 7 patients with a mild form of Geleophysic dysplasia type 2(GD2)/Acromicric dysplasia(AD) induced by fibrillin 1(FBN1) gene mutation from one Chinese family.Methods:A Chinese pedigree of mild GD2/AD treated at the Pediatric Endocrinology Department at the First Affiliated Hospital of Sun Yat-sen University between August 2017 and May 2022 was collected. Whole-exome genetic sequencing of the FBN1 gene were performed to establish the diagnosis. Additionally, a literature review was further conducted.Results:In this family, among 13 individuals spanning three generations, there were 7 affected cases, including 1 adult female, 1 adult male, and 5 children. All individuals exhibited postnatal growth failure, severe disproportionate short stature, and lacked typical facial features. Exome sequencing and Sanger sequencing confirmed the presence of a heterozygous missense mutation c. 5099A>G(p.Tyr1700Cys) in exon 42 of the FBNI gene in 6 affected individuals(Ⅱ-1, Ⅲ-1 to Ⅲ-5), which was identified as a pathogenic mutation. This mutation was previously reported in a Chinese classical achondroplasia(AD) family. Based on comprehensive genetic analysis, clinical features, and multisystem evaluation, 3 cases were diagnosed with mild type 2 growth hormone deficiency(GD2), and 4 cases were diagnosed with mild AD. Recombinant human growth hormone(rhGH; 1.1-1.4 IU·kg -1·week -1) was applied to all the 5 children, and additional gonadotropin releasing hormone analogue(GnRHa) was administered to the 2 girls in late puberty, resulting in certain growth-promoting effect. Conclusions:The c. 5099A>G(p.Tyr1700Cys) mutation not only leads to the classical type of achondroplasia(AD) as reported in the literature but also causes the non-classical GD2 or AD(mild GD2/AD). Further research is warranted to investigate the long-term therapeutic effects of rhGH treatment.

Objective:To establish a radiomics signature based on CT images of non-small cell lung cancer (NSCLC) to predict the expression of molecular marker P63.Methods:A total of 245 NSCLC patients who underwent CT scans were retrospectively included.All patients were confirmed by histopathological examinations and P63 expression were examined within 2 weeks after CT examination.Radiomics features were extracted by MaZda software and subjective image features were defined from original non-enhanced CT images.The Lasso-logistic regression model was used to select features and develop radiomics signature,subjective image features model,and combined diagnostic model.The predictive performance of each model was evaluated by the receiver operating characteristic (ROC) curve,and compared with Delong test.Results:Of the 245 patients,96 were P63 positive and 149 were P63 negative.The subjective image feature model consisted of 6 image features.Through feature selection,the radiomics signature consisted of 8 radiomics features.The area under the ROC curves of the subjective image feature model and the radiomics signature in predicting P63 expression statue were 0.700 and 0.755,respectively,without a significant difference (P＞0.05).The combined diagnostic model showed the best predictive power (AUC=0.817,P＜0.01).Conclusion:The radiomics-based CT scan images can predict the expression status of NSCLC molecular marker P63.The combination of the radiomics features and subjective image features can significantly improve the predictive performance of the predictive model,which may be helpful to provide a non-invasive way for understanding the molecular information for lung cancer cells.