Research on coronavirus disease 2019 (COVID-19) detection method based on depthwise separable DenseNet in chest X-ray images / 生物医学工程学杂志

Coronavirus disease 2019 (COVID-19) has spread rapidly around the world. In order to diagnose COVID-19 more quickly, in this paper, a depthwise separable DenseNet was proposed. The paper constructed a deep learning model with 2 905 chest X-ray images as experimental dataset. In order to enhance the contrast, the contrast limited adaptive histogram equalization (CLAHE) algorithm was used to preprocess the X-ray image before network training, then the images were put into the training network and the parameters of the network were adjusted to the optimal. Meanwhile, Leaky ReLU was selected as the activation function. VGG16, ResNet18, ResNet34, DenseNet121 and SDenseNet models were used to compare with the model proposed in this paper. Compared with ResNet34, the proposed classification model of pneumonia had improved 2.0%, 2.3% and 1.5% in accuracy, sensitivity and specificity respectively. Compared with the SDenseNet network without depthwise separable convolution, number of parameters of the proposed model was reduced by 43.9%, but the classification effect did not decrease. It can be found that the proposed DWSDenseNet has a good classification effect on the COVID-19 chest X-ray images dataset. Under the condition of ensuring the accuracy as much as possible, the depthwise separable convolution can effectively reduce number of parameters of the model.

Efficacy and safety of pancreas freezing / 中华胰腺病杂志

Objective To observe the blood biochemical and histological changes before and after pancreas freezing, to provide evidence for cryosurgery for pancreatic cancer. Methods Fifteen healthy pigs were divided into deep frozen group (n = 5), shallow frozen group (n = 5), non-frozen group (n = 3) and normal group (n = 2). After anesthesia and Iaparotomy, a probe of the Argon-Helium Surgical System was inserted into the pancreas, 100% and 10% argon output power were used in deep and shallow frozen group, respectively;and the temperature were - 130 ～ - 140℃ and - 110 ～ - 120℃, respectively;which results in an ice-ball with 15 ～ 20 mm in diameter. Then helium gas was inputted to increase the temperature to 10 ～ 20℃ for three minutes;then the whole process was repeated. A probe was inserted into the pancreas in the non-frozen group only and only laparotomy was performed in non-grozen group normal group and normal group. Serum amylase, IL-6, CRP levels before and after the experiment was determined;the pigs were sacrificed at day 7 and the pancreas was harvested for light microscope and electron microscope examination. Results The frozen pancreatic tissue became pitchy necrosis zone, and it could be distinguished from non-frozen tissue;there were obvious tissue necrosis in the center and para-center of frozen area, and the ultra-structure were destroyed and disappeared, mitochondria degranulation and rough endoplasmic reticulum degrannlation were observed. Serum amylase was elevated in 13 (86.7%) pigs and most returned to normal at 6th day. Serum IL-6 was slightly elevated in 5 (33.3%) pigs. There was no significant difference among all the groups in term of serum CRP. All the pigs were alive until the time of sacrifice. Conclusions Cryosurgery has affirmative fatal ablative effects on pancreatic tissue, and it is safe with no serious complications.