Discriminating low grade from high grade prostate cancer based on MR apparent diffusion coefficient map texture analysis / 中华放射学杂志

Objective@#To investigate the value of texture analysis based on MR ADC map of prostate in differentiating between low-grade and high-grade prostate cancer (PCa).@*Methods@#PCa confirmed by pathology after radical prostatectomy were analyzed retrospectively, all patients underwent multiparametric MRI before radical prostatectomy, including T1WI,T2WI and DWI. On the ADC map, ROI was drawn manually to encompass the whole tumor by ITK-SNAP software. The python-based pyradiomics package was used to extract 105 texture features. The intraclass correlation coefficient was used to evaluate the repeatability of the texture features. The independent sample t test or Mann-Whitney U test was used to exclude features that had no significant difference between low grade and high grade PCa. Lasso regression model and 5 fold cross validation method were used to obtain texture feature combination of the highest performance and develop a classification modelfor discriminating low from high grade PCa. ROC curve was used to evaluate the diagnostic efficiency of the model.@*Result@#Ninety patients with PCa confirmed by pathology after radical prostatectomywere analyzed retrospectively,including 36 patients with low-level PCa (GS≤3+4) and 54 patients with high-level PCa (GS≥4+3). The area under curve of the model was 0.841, with sensitivity 69.6% and specificity 91.2%, which was significantly higher than single texture feature or traditional mean ADC value.@*Conclusion@#Texture analysis based on MRI-ADC map of prostate could be used to discriminate low grade PCa from high grade PCa.

Deep learning for classification of multi-sequence MR images of the prostate / 中华放射学杂志

Objective@#To develop a convolution neural network (CNN) model to classify multi-sequence MR images of the prostate.@*Methods@#ResNet18 convolution neural network (CNN) model was developed to classify multi-sequence MR images of the prostate. A deep residual network was used to improve training accuracy and test accuracy. The dataset used in this experiment included 19 146 7-sequence prostate MR images (transverse T1WI, transverse T2WI, coronal T2WI, sagittal T2WI, transverse DWI, transverse ADC, transverse PWI), from which a total of 2 800 7-sequence MR images was selected as a training set. Three hundred and eighty eight 7-sequence MR images were selected as test sets. Accuracy was used to evaluate the effectiveness of ResNet18 CNN model.@*Results@#The classification accuracy of the model for transverse DWI, sagittal T2WI, transverse ADC, transverse T1WI, and transverse T2WI was as high as 100.0% (44/44,52/52), and the accuracy for transverse PWI was also as high as 96.7% (116/120). The accuracy for coronal T2WI was 77.5% (31/40). 0.8% (1/120) of transverse PWI was incorrectly assigned to transverse T2WI, and 2.5% (3/120) incorrectly assigned to sagittal T2WI. 15.0% (6/40) of coronal T2WI was incorrectly assigned to transverse T2WI, and 7.5% (3/40) to sagittal T2WI.@*Conclusion@#The experimental results show the effectiveness of our deep learning method regarding accuracy in the prostate multi-sequence MR images detection.

Discriminating low grade from high grade prostate cancer based on MR apparent diffusion coefficient map texture analysis / 中华放射学杂志

Objective To investigate the value of texture analysis based on MR ADC map of prostate in differentiating between low?grade and high?grade prostate cancer (PCa). Methods PCa confirmed by pathology after radical prostatectomy were analyzed retrospectively, all patients underwent multiparametric MRI before radical prostatectomy, including T1WI,T2WI and DWI. On the ADC map, ROI was drawn manually to encompass the whole tumor by ITK?SNAP software. The python?based pyradiomics package was used to extract 105 texture features. The intraclass correlation coefficient was used to evaluate the repeatability of the texture features. The independent sample t test or Mann?Whitney U test was used to exclude features that had no significant difference between low grade and high grade PCa. Lasso regression model and 5 fold cross validation method were used to obtain texture feature combination of the highest performance and develop a classification modelfor discriminating low from high grade PCa. ROC curve was used to evaluate the diagnostic efficiency of the model. Result Ninety patients with PCa confirmed by pathology after radical prostatectomywere analyzed retrospectively,including 36 patients with low?level PCa (GS≤3+4) and 54 patients with high?level PCa (GS≥4+3). The area under curve of the model was 0.841, with sensitivity 69.6% and specificity 91.2%, which was significantly higher than single texture feature or traditional mean ADC value. Conclusion Texture analysis based on MRI?ADC map of prostate could be used to discriminate low grade PCa from high grade PCa.

Deep learning for classification of multi?sequence MR images of the prostate / 中华放射学杂志

Objective To develop a convolution neural network (CNN) model to classify multi?sequence MR images of the prostate. Methods ResNet18 convolution neural network (CNN) model was developed to classify multi?sequence MR images of the prostate. A deep residual network was used to improve training accuracy and test accuracy. The dataset used in this experiment included 19 146 7?sequence prostate MR images (transverse T1WI, transverse T2WI, coronal T2WI, sagittal T2WI, transverse DWI, transverse ADC, transverse PWI), from which a total of 2 800 7?sequence MR images was selected as a training set. Three hundred and eighty eight 7?sequence MR images were selected as test sets. Accuracy was used to evaluate the effectiveness of ResNet18 CNN model. Results The classification accuracy of the model for transverse DWI, sagittal T2WI, transverse ADC, transverse T1WI, and transverse T2WI was as high as 100.0% (44/44,52/52), and the accuracy for transverse PWI was also as high as 96.7% (116/120). The accuracy for coronal T2WI was 77.5% (31/40). 0.8% (1/120) of transverse PWI was incorrectly assigned to transverse T2WI, and 2.5% (3/120) incorrectly assigned to sagittal T2WI. 15.0% (6/40) of coronal T2WI was incorrectly assigned to transverse T2WI, and 7.5% (3/40) to sagittal T2WI. Conclusion The experimental results show the effectiveness of our deep learning method regarding accuracy in the prostate multi?sequence MR images detection.

A candidate tumor suppressor gene RIZ1 / 国际肿瘤学杂志

The retinoblastoma-protein-interacting zinc finger proteinl (RIZ1),a methyltransferase,contains the characteristic PR zinc finger domain.RIZ1 can methylate H3K9 of the histone,acted as a transcription suppression factor of cancers.Increasing numbers of human cancers are reported to hold decreased or absent RIZ1 expression,which is closely related to the progression of cancer.RIZ1 is defined as a candidate anti-oncogene.The mechanisms of the suppression involved in both oncocytogenetics and epigenetic changes.

P-450-dependent epoxygenase pathway of arachidonic acid is involved in myeloma-induced angiogenesis of endothelial cells / 华中科技大学学报（医学）（英德文版）

P-450-dependent epoxygenase pathway of arachidonic acid and the products of epoxyeicosatrienoic acids (EETs) have been demonstrated to be involved in angiogenesis and tumor progression. This study examined the expression of EETs and the role of the pathway in the angiogenesis of multiple myeloma (MM). MM cell lines of U266 and RPMI8226 were cultured, and the EETs levels (11, 12-EET and 14, 15-EET) in the supernatant were determined by ELISA. Human umbilical vein endothelial cells (HUVECs) were cultured and used for analysis of the angiogenesis activity of the two MM cell lines, which was examined both in vitro and in vivo by employing MTT, chemotaxis, tube formation and matrigel plug assays. 11, 12-EET and 14, 15-EET were found in the supernatant of the cultured MM cells. The levels of the two EETs in the supernatant of U266 cells were significantly higher than those in the RPMI8226 cell supernatant (P<0.05), and the levels paralleled the respective angiogenesis activity of the two different MM cell lines. 17-octadecynoic acid (17-ODYA), as a specific inhibitor of P450 enzyme, suppressed HUVECs proliferation and tube formation induced by MM cells. Furthermore, 17-ODYA decreased the EET levels in the supernatant of MM cells. These results suggest that EETs may play an important role in the angiogenesis of MM, and the inhibitor 17-ODYA suppresses this effect.

Isolation and multilineage differentiation of mesenchymal stem cells from human umbilical cord vein in vitro / 中国病理生理杂志

AIM: To investigate the isolation,purification,expansion and multilineage differentiation of mesenchymal stem cells(MSCs) derived from human umbilical cord vein in vitro.METHODS: By 1% collagenase Ⅱ digestion,endothelial cells were isolated from human umbilical cord vein and cultured in IMDM medium.The morphology of the cells was observed by Wright's staining and electron microscope.Cell cycle and immunophenotype were investigated by flow cytometry.Assays of adipogenic and osteogenic differentiation were performed in vitro.von Kossa staining,Oil Red O staining and mRNA expression of osteopontin and lipoprotein lipase were studied in the induced cells.RESULTS: The cells from the cord vein displayed a fibroblast-like morphology adhering to the culture plate.FACS showed that the cells expressed several MSCs-related antigens such as CD29,CD44 and CD105,while CD13,CD31,CD45,CD34,and HLA-DR were negative.Adipocyte and osteocyte differentiation were induced successfully.CONCLUSION: The morphology,growth characteristics,immunophenotype and pluripotentiality of the MSCs from human umbilical cord vein are similar to the MSCs from bone marrow(BM).They could potentially be an excellent source of MSCs for experiments and clinics.