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.

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.

HPLC fingerprint of analgesic ingredients in Cangbaiqutong capsules / 国际药学研究杂志

Objective To establish fingerprint of analgesic ingredients in Cangbaiqutong capsules by HPLC, and control different production batches of Cangbaiqutong capsules′ quality. Methods Waters XSELECT CSH-C18 (4.6 mm×150 mm, 5.0μm) chromatographic column was used and eluted with acetonitrile -0.1% phosphoric acid solution gradiently in the flow rate of 1.0 ml/min. The detection wavelength was 284 nm with column temperature of 30℃. rrith phellodendrine chloride, gentiopicroside, paeoniflorin, tetrandrine and berberine hydrochloride as the object references, ten batches of Cangbaiqutong capsules were tested and analyzed by similarity comparison. Results fingerprint spectrum in Cangbaiqutong capsules had 20 common peaks in total, and characteristic spectra of Cortex Phellodendri, Gentiana, Radix Paeoniae Rubra and Radix Stephaniae Tetrandrae were found, while similarity of HPLC fingerprint was more than 0.9 among those batches of samples. Conclusion Using HPLC fingerprint can be used to evaluate the Cangbaiqutong capsules′quality in the round, which could improve the quality control standard in productive process of Cangbaiqutong capsules.

Long-term reproductive consequences of no-scalpel vasectomy in beagles / 华中科技大学学报（医学）（英德文版）

The effects of vasectomy on the reproductive organs in various species are controversial. This study investigated the morphological change and apoptosis of the testis, epididymis, and vas deferens in beagle dogs 12 months after vasectomy. The male beagles were divided into two groups: vasectomized and sham-operated groups (n=5 in each). Histopathological, ultrastructural, and TUNEL evaluation of the changes in the testis, epididymis, and ductus deferens of each animal were conducted 12 months after surgery. The mean lumen diameter, cellular thickness, mean interstitial distance, and lumen area fraction of each seminiferous tubule and ductus epididymis were measured by stereological analysis. The results showed that, compared with the sham-operated group, the seminiferous tubular epithelial cells of the testes in the vasectomized group were disorderly arranged and scattered. Significant atrophy and apoptosis were found in the endothelial cells, and a range of ultrastructural variations were observed in the cells of testes, epididymis, and vas deferens in vasectomized group. It was concluded that complete obstruction of the vas deferens as a traditional contraception method is not absolutely safe in terms of the reversal of fertility in the long run. Techniques of relieving the inner pressure in the vas deferens while maintaining the efficacy of male contraception need to be explored.

Long-term reproductive consequences of no-scalpel vasectomy in beagles / 华中科技大学学报（医学）（英德文版）

The effects of vasectomy on the reproductive organs in various species are controversial. This study investigated the morphological change and apoptosis of the testis, epididymis, and vas deferens in beagle dogs 12 months after vasectomy. The male beagles were divided into two groups: vasectomized and sham-operated groups (n=5 in each). Histopathological, ultrastructural, and TUNEL evaluation of the changes in the testis, epididymis, and ductus deferens of each animal were conducted 12 months after surgery. The mean lumen diameter, cellular thickness, mean interstitial distance, and lumen area fraction of each seminiferous tubule and ductus epididymis were measured by stereological analysis. The results showed that, compared with the sham-operated group, the seminiferous tubular epithelial cells of the testes in the vasectomized group were disorderly arranged and scattered. Significant atrophy and apoptosis were found in the endothelial cells, and a range of ultrastructural variations were observed in the cells of testes, epididymis, and vas deferens in vasectomized group. It was concluded that complete obstruction of the vas deferens as a traditional contraception method is not absolutely safe in terms of the reversal of fertility in the long run. Techniques of relieving the inner pressure in the vas deferens while maintaining the efficacy of male contraception need to be explored.