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.

A review on multi-modal human motion representation recognition and its application in orthopedic rehabilitation training / 生物医学工程学杂志

Human motion recognition (HAR) is the technological base of intelligent medical treatment, sports training, video monitoring and many other fields, and it has been widely concerned by all walks of life. This paper summarized the progress and significance of HAR research, which includes two processes: action capture and action classification based on deep learning. Firstly, the paper introduced in detail three mainstream methods of action capture: video-based, depth camera-based and inertial sensor-based. The commonly used action data sets were also listed. Secondly, the realization of HAR based on deep learning was described in two aspects, including automatic feature extraction and multi-modal feature fusion. The realization of training monitoring and simulative training with HAR in orthopedic rehabilitation training was also introduced. Finally, it discussed precise motion capture and multi-modal feature fusion of HAR, as well as the key points and difficulties of HAR application in orthopedic rehabilitation training. This article summarized the above contents to quickly guide researchers to understand the current status of HAR research and its application in orthopedic rehabilitation training.

Diagnosis and treatment of cholesterol granuloma of the middle ear / 中国耳鼻咽喉头颈外科

OBJECTIVE To discuss the diagnosis and treatment of cholesterol granuloma of the middle ear and the choice and effect of surgical methods. METHODS A retrospective analysis was conducted on 18 cases of cholesterol granuloma of the middle ear confirmed by surgery and pathology. Different choices of surgical methods were made according to the lesion extension of this disease. RESULTS All patients were followed up for at least 6 months. Two cases with eustachian tube obstruction had ventilation tube inserted for a long time. One case who had recurrence and metastasis of nasopharyngeal carcinoma in the middle ear was transferred to oncology department for further treatment. Post-operative dry ears were obtained in the other cases whose pure tone thresholds were improved to different degrees. CONCLUSION Etiology of cholesterol granuloma of middle ear remains controversial. It's supposed to result from the bleeding, occlusion of ventilation and disturbance of drainage of the air cavity because of the middle ear inflammation, and bone marrow exposure. The middle ear and mastoid surgery can completely remove the disease tissues, and establish ventilation system of mastoid-tympani-eustachian, which is the key point of the middle ear surgery.

Clinical analysis of 23 primary sinonasal malignant melanoma / 临床耳鼻咽喉头颈外科杂志

OBJECTIVE@#To review the pathological and clinical features and treatment of sinonasal malignant melanoma.@*METHOD@#A retrospective analysis of 23 cases of sinonasal malignant melanoma. All the patients were conformed by histopathology, the most common symptoms were nasal obstruction and epistexis. Eight cases were treated with surgery, 8 with surgery and radiotherapy, 5 with surgery and chemotherapy, 2 with surgery and ra- diotherapy plus chemotherapy.@*RESULT@#Twenty patients were followed up, the survival rates of 3 and 5 years were 50% (10/20) and 35% (7/20), respectively.@*CONCLUSION@#Sinonasal malignant melanoma has an aggressive behavior and easy recurrence and poor prognosis. Early diagnosis and reasonable treatment can increase the survival rate of the disease.

The treatment of trigeminal neuralgia by resecting maxillary nerve and infraorbital nerve under the endoscopy at the pterygopalatofossa through approach to the maxillary sinus / 临床耳鼻咽喉头颈外科杂志

OBJECTIVE@#This paper presents a method for treating maxillary neuralgia, the second division of trigeminal nerve.@*METHOD@#One hundred and thirty six cases with 136 trigeminal neuralgia were treated from 2004 to 2011. All patients were treated with endoscopic surgery at the pterygopalatofossa through approach to the maxillary sinus for resecting maxillary nerve and infraorbital nerve.@*RESULT@#One hundred and eighteen patients were relieved after operation and no recurrence of neuralgia was occurred after 2 to 8 years of follow-up.@*CONCLUSION@#This method had the advantages of avoiding to operate craniotomy with no complications, which was performed easily with valid efficacy.

Molecular etiology analysis among students with profound hearing loss in a special education school in Yangzhou / 临床耳鼻咽喉头颈外科杂志

OBJECTIVE@#To study molecular epidemiological basis of non-syndromic hearing loss in Yangzhou area.@*METHOD@#The selected objects were 90 severe non-syndrome deafness students in special education schools in Yangzhou city, Jiangsu province. The deafness gene chip diagnostic kit was used for screening the nine hot spots mutations in four common deafness-related genes in Medical Testing Center of Northern Jiangsu People's Hospital. These nine hot spots gene mutations included GJB2 (35 delG, 176 del16, 235 delC and 299 delAT) GJB3 (538C > T), SLC26A4 (IVS7-2A > G, 2168A > G) and mtDNA 12S rRNA (A > G,1494C > T) mutation detection by line.@*RESULT@#In 90 patients, 64 patients were found to carry deafness mutations by using gene chip diagnostic kit (the rate of mutation was 71.7%) GJB2 gene mutation in 40 cases (44.4%)which included 235 delC homozygous in 20 (22.2%) cases, 235 delC single heterozygous mutation in 4 cases (4.4%)and 235 delC and 299 delAT compound heterozygous mutations in 2 case (2.2%) separately. 299 delAT single heterozygous mutation in 2 case (2.2%), 299 delAT simple mutation in 2 case (2.2%). 176 del16 heterozygous mutations in 2 case, 176 del16 homozygous mutation in 2 case (2.2%). 176 del16 heterozygous mutations, and 235 del C heterozygous mutation in 6 cases (6.7%). SLC26A4 gene mutations in 22 cases (24.4%),which included IVS7-2A > G homozygous in 2 (2.22%) cases, IVS7-2A > G and 2168A > G compound heterozygous mutations in 2 cases (2.2%), IVS7-2A > G single heterozygous mutation in 18 cases (20.2%), and mtDNA 12S rRNA A > G mutation in 2 cases (2.2%), GJB3 mutations were not detected.@*CONCLUSION@#The deafness gene diagnostic techniques is worth applying for screening and diagnosis.