[A preliminary investigation on a deep learning convolutional neural networks based pulmonary tuberculosis CT diagnostic model].

Objective: To evaluate the clinical value of a pulmonary tuberculosis CT diagnostic model based on deep learning convolutional neural networks (CNN). Methods: From March 2017 to March 2018,a total of 1 764 patients with positive sputum for tuberculous bacterium and had received high-resolution chest CT scan in radiology department of Hebei province chest hospital were enrolled. Among them, 937 were male, and 827 were female, aging from 17-73 years (average 38.4). A total of 20 139 CT images (17 kinds of image features) classified by 4 radiologists were used as training dataset to create a tuberculosis CT CNN diagnostic model. The top 5 image features in training set were: infiltrative pulmonary tuberculosis, cavitary pulmonary tuberculosis, pleural thickening, caseous pneumonia and pleural effusion. A total of 302 images were randomly selected from the marked images as testing dataset. The diagnosis of 2 senior radiologists was taken as "golden standard". The differences of sensitivity and accuracy in CT diagnosis between the CNN diagnostic model and the radiologists were compared. The classification error types and numbers of the CNN diagnostic model were recorded. FROC(free response operating characteristic curve)curve was drawn and the highest diagnostic efficiency of the model was measured. Results: The diagnostic accuracy of infiltrative pulmonary tuberculosis, cavitary pulmonary tuberculosis, pleural thickening, caseous pneumonia and pleural effusion by the CNN diagnostic model were 95.33%(10 982/11 520), 73.68%(2 151/2 920), 73.07%(1 128/1544), 83.33%(1 020/1225)and 94.11%(814/865), respectively. The overall diagnostic sensitivity and accuracy of the CNN model were 95.49%(339/355)and 90.40%(339/375), respectively, and the corresponding values ​​of radiologists were 93.80%(348/371)and 92.80%(348/375), respectively, and there was no statistical difference between the CNN model and the radiologists(sensitivity χ2=1.022,P=0.312;accuracy χ2=1.404,P=0.236). FROC curve showed that when sensitivity of the CNN model was 78% and FPI value was 2.48, it reached the highest diagnostic efficiency. The classification error of CNN diagnostic models was mainly confusion of fiber stripe components, cavitary pulmonary tuberculosis, caseous pneumonia and infiltrative pulmonary tuberculosis. Conclusions: The CNN-based pulmonary tuberculosis CT diagnostic model exhibited high sensitivity and accuracy (95.49% and 90.40% respectively). It could assist radiologists in CT diagnosis of pulmonary tuberculosis and deserve further clinical application.

Application of Multiple Genetic Markers in Determination of Full and Half Sibling Relationship： A Case Report.

ABSTRACT: Objective To investigate the application of the comprehensive use of multiple genetic markers in full and half sibling relationship testing through the identification of a case of suspected sibling relationship. Methods Genomic DNA were extracted from bloodstain samples from 4 subjects （ZHANG-1, ZHANG-2, male; ZHANG-3, ZHANG-4, female）. Autosomal STR loci, X-STR, Y-STR loci and polymorphisms of mtDNA HV-Ⅰ and Ⅱwere genotyped by EX20 STR kit, X19 kit, Data Y24 STR kit, and Sanger sequencing, respectively. Results According to autosomal STR based IBS scoring results, full sibling relationships were indicated among ZHANG-2, ZHANG-3 and ZHANG-4, but those were not indicated between ZHANG-1 and ZHANG-2 or ZHANG-3 or ZHANG-4. According to autosomal STR based FSI and HSI, with ITO method and discriminant function method, full sibling relationships among ZHANG-2, ZHANG-3 and ZHANG-4 were indicated, and half sibling relationships between ZHANG-1 and ZHANG-2 or ZHANG-3 or ZHANG-4 were also indicated. X-STR and mtDNA sequencing results showed that all the 4 samples came from a same maternal line, and Y-STR results showed that ZHANG-1 and ZHANG-2 did not come from a same paternal line, which supported the half sibling relationship between ZHANG-1 and ZHANG-2 or ZHANG-3 or ZHANG-4, verified by parental genotype reconstruction based on autosomal STR genotyping. Conclusion For the identification of sibling relationships, it is effective to have reliable results with the mutual verification and support of multiple genetic markers （autosomal STR, sex chromosomal STR and mtDNA sequence） and calculations （IBS, ITO, discriminant function method and family reconstruction）.

Identification of common gene networks responsive to radiotherapy in human cancer cells.

Identification of the genes that are differentially expressed between radiosensitive and radioresistant cancers by global gene analysis may help to elucidate the mechanisms underlying tumor radioresistance and improve the efficacy of radiotherapy. An integrated analysis was conducted using publicly available GEO datasets to detect differentially expressed genes (DEGs) between cancer cells exhibiting radioresistance and cancer cells exhibiting radiosensitivity. Gene Ontology (GO) enrichment analyses, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis and protein-protein interaction (PPI) networks analysis were also performed. Five GEO datasets including 16 samples of radiosensitive cancers and radioresistant cancers were obtained. A total of 688 DEGs across these studies were identified, of which 374 were upregulated and 314 were downregulated in radioresistant cancer cell. The most significantly enriched GO terms were regulation of transcription, DNA-dependent (GO: 0006355, P=7.00E-09) for biological processes, while those for molecular functions was protein binding (GO: 0005515, P=1.01E-28), and those for cellular component was cytoplasm (GO: 0005737, P=2.81E-26). The most significantly enriched pathway in our KEGG analysis was Pathways in cancer (P=4.20E-07). PPI network analysis showed that IFIH1 (Degree=33) was selected as the most significant hub protein. This integrated analysis may help to predict responses to radiotherapy and may also provide insights into the development of individualized therapies and novel therapeutic targets.

Prognostic value of the stem cell markers CD133 and ABCG2 expression in esophageal squamous cell carcinoma.

In the light of increasing evidence supporting cancer stem cells (CSCs) theory, the expression of two stem cell markers, CD133 and adenosine triphosphate-binding cassette superfamily G member 2 (ABCG2), in esophageal squamous cell carcinoma (ESCC) was investigated, and their prognostic values were evaluated. Paraffin-embedded tissue sections of 110 ESCC patients were investigated using Immunohistochemistry. The association of CD133 and ABCG2 expression with clinicopathologic characteristics was analyzed by χ(2) test. Survival analysis was carried out using Kaplan-Meier method and Cox proportional hazards model. CD133 and ABCG2 expression were detected in 27.3% and 15.5% of ESCC patients, respectively. The presence of CD133-positive cancer cells was associated with tumor cell differentiation (P= 0.008) but not significantly related to the survival of ESCC patients (P= 0.085). ABCG2 expression was not associated with clinicopathologic characteristics but was a significant prognostic factor for adverse overall survival of ESCC patients (P= 0.005). The median overall survival time for ESCC patients with and without ABCG2 expression were 21.8 and >49.3 months, respectively. A combined analysis of CD133 and ABCG2 expression did not show that ESCC patients with coexpression of these two markers had a worse prognosis than those with only ABCG2 expression (P= 0.934). Moreover, ABCG2 expression was revealed to be an independent prognostic factor along with tumor node metastasis stage in multivariate analysis (hazard ratio of ABCG2, 3.38; 95% confidence interval, 1.61∼7.09; P= 0.001). By survival analysis based on tumor node metastasis stage of ESCC, the association between ABCG2 expression and the patients' prognosis was found significant in the group of relatively early stage (P= 0.005) and marginally significant in the group of relatively late stage (P= 0.058). This is the first time to report the presence of CD133-positive cancer cells in ESCC but not supporting its prognostic value and validity as a CSC marker for ESCC. ABCG2 expression was found to correlate with the survival of ESCC patients, especially those at relatively early stage, suggesting that ABCG2-positive cancer cells may represent a pool of CSCs in ESCC, and relatively early-stage patients with ABCG2 expression may deserve more intensive or targeted therapy.

Magnetic properties in Co and Mn-doped ZnO powders and thin films.

Zn0.86Co0.14O powder and thin films were prepared by standard solid-state reaction processes and radio-frequency (RF) magnetron sputtering. Magnetic measurements indicate that the powder is paramagnetic for temperatures above 3 K, while the thin films annealed in vacuum are ferromagnetic at room temperature. The saturated magnetization was found to be about 0.6 microB/Co, while the coercive force was found to be 200 Oe at room temperature. The very similar results were also obtained in Zn0.96Mn0.04O powder and thin films. Such different results for the powder and thin films indicate that growth conditions and defects play an important role in producing ferromagnetism.