The value of radiomics-based CT combined with machine learning in the diagnosis of occult vertebral fractures.

PURPOSE: To develop and evaluate the performance of radiomics-based computed tomography (CT) combined with machine learning algorithms in detecting occult vertebral fractures (OVFs). MATERIALS AND METHODS: 128 vertebrae including 64 with OVF confirmed by magnetic resonance imaging and 64 corresponding control vertebrae from 57 patients who underwent chest/abdominal CT scans, were included. The CT radiomics features on mid-axial and mid-sagittal plane of each vertebra were extracted. The fractured and normal vertebrae were randomly divided into training set and validation set at a ratio of 8:2. Pearson correlation analyses and least absolute shrinkage and selection operator were used for selecting sagittal and axial features, respectively. Three machine-learning algorithms were used to construct the radiomics models based on the residual features. Receiver operating characteristic (ROC) analysis was used to verify the performance of model. RESULTS: For mid-axial CT imaging, 6 radiomics parameters were obtained and used for building the models. The logistic regression (LR) algorithm showed the best performance with area under the ROC curves (AUC) of training and validation sets of 0.682 and 0.775. For mid-sagittal CT imaging, 5 parameters were selected, and LR algorithms showed the best performance with AUC of training and validation sets of 0.832 and 0.882. The LR model based on sagittal CT yielded the best performance, with an accuracy of 0.846, sensitivity of 0.846, and specificity of 0.846. CONCLUSION: Machine learning based on CT radiomics features allows for the detection of OVFs, especially the LR model based on the radiomics of sagittal imaging, which indicates it is promising to further combine with deep learning to achieve automatic recognition of OVFs to reduce the associated secondary injury.

CARMA3/NF-κB signaling contributes to tumorigenesis of hepatocellular carcinoma and is inhibited by sodium aescinate.

BACKGROUND: Primary hepatocellular carcinoma (HCC) is a very malignant tumor in the world. CARMA3 plays an oncogenic role in the pathogenesis of various tumors. However, the function of CARMA3 in HCC has not been fully clarified. AIM: To study the biological function of CAEMA3 in HCC. METHODS: Tissue microarray slides including tissues form 100 HCC patients were applied to access the expression of CARMA3 in HCC and its clinical relevance. Knockdown and overexpression of CARMA3 were conducted with plasmid transfection. MTT, colony formation, and apoptosis assays were performed to check the biological activity of cells. RESULTS: Higher expression of CARMA3 in HCC was relevant to poor prognostic survival (P < 0.05). Down-regulation of CARMA3 inhibited proliferation and colony formation and induced apoptosis in HCC cell lines, while increasing its expression promoted tumorigenesis. We also found that sodium aescinate (SA), a natural herb extract, exerted anti-proliferation effects in HCC cells by suppressing the CARMA3/nuclear factor kappa-B (NF-κB) pathway. CONCLUSION: Overexpression of CARMA3 in HCC tissues correlates with a poor prognosis in HCC patients. CARMA3 acts pro-tumorigenic effects partly through activation of CARMA3/NF-κB. SA inhibits HCC growth by targeting CARMA3/NF-κB.

[Frequencies distribution of GSTT1 and GSTM1 null genotypes in 24 Yunnan populations].

OBJECTIVE: To investigate the frequencies distribution of GSTT1 and GSTM1 null genotypes in 24 Yunnan populations. METHODS: GSTT1 and GSTM1 genotypes were analyzed by PCR procedure. RESULTS: The range of frequencies for GSTT1 and GSTM1 null genotypes in the populations were 0.188-0.633 and 0.400-0.745, respectively, and in the districts were 0.286-0.583, 0.433-0.745 respectively. There was significant relationship between GSTT1 frequencies and populations. CONCLUSION: The frequencies of GSTT1 and GSTM1 null genotypes in 24 Yunnan populations were different, but they were almost the same in different districts of Yunnan.