Medical Image Classification Using Light-weight CNN with Spiking Cortical Model Based Attention Module.

In the field of disease diagnosis where only a small dataset of medical images may be accessible, the light-weight convolutional neural network (CNN) has become popular because it can help to avoid the over-fitting problem and improve computational efficiency. However, the feature extraction capability of the light-weight CNN is inferior to that of the heavy-weight counterpart. Although the attention mechanism provides a feasible solution to this problem, the existing attention modules, such as the squeeze and excitation module and the convolutional block attention module, have insufficient non-linearity, thereby influencing the ability of the light-weight CNN to discover the key features. To address this issue, we have proposed a spiking cortical model based global and local (SCM-GL) attention module. The SCM-GL module analyzes the input feature maps in parallel and decomposes each map into several components according to the relation between pixels and their neighbors. The components are weighted summed to obtain a local mask. Besides, a global mask is produced by discovering the correlation between the distant pixels in the feature map. The final attention mask is generated by combining the local and global masks, and it is multiplied by the original map so that the important components can be highlighted to facilitate accurate disease diagnosis. To appreciate the performance of the SCM-GL module, this module and some mainstream attention modules have been embedded into the popular light-weight CNN models for comparison. Experiments on the classification of brain MR, chest X-ray, and osteosarcoma image datasets demonstrate that the SCM-GL module can significantly improve the classification performance of the evaluated light-weight CNN models by enhancing the ability of discovering the suspected lesions and it is generally superior to state-of-the-art attention modules in terms of accuracy, recall, specificity and F1 score.

The epidemiological analysis of influenza before and after the outbreak of COVID-19 in Fuzhou

Objective: To analyze the epidemiological characteristics of influenza before and after the outbreak of coronavirus disease 2019(COVID-19)in Fuzhou from 2019 to 2020, and provide the scientific basis for the control and prevention. Methods: The influenza epidemic data was obtained from the Infectious Disease Surveillance Information Management System. The incidence data of influenza before and after the outbreak of COVID-19 from 2019 to 2020 was analyzed statistically by using the descriptive epidemiology, and the influencing factors of influenza epidemic characteristics in Fuzhou were in-depth explored. Results: A total of 3 516 cases of influenza were reported in Fuzhou in 2019 with an incidence rate of 48.30/100 thousand, while 1 522 cases of influenza were reported in Fuzhou in 2020 with an incidence rate of 20.74/100 thousand. The number of reported cases decreased by 56.7%. The peak of influenza in Fuzhou was in December in 2019, with the incidence rate of 12.79/100 thousand. However, there was no obvious peak of influenza in December in 2020, showing a low incidence level, and the incidence rate was 1.02/100 thousand. Compared to 2019, the incidence rate significantly decreased in all cities/countries in 2020 (P< 0.05). The proportion of male among the influenza cases in 2020 was lower than that in 2019(X2=4.096, P< 0.05). The constituent ratio of young age group(< 15 years old)in2020 was significantly lower than that in 2019, and the older age group(> 60 years)was higher than that in 2019(X2=202.094, P< 0.05). Among the occupations of influenza cases, although they are mainly diaspora, nursery children and students, the difference between 2019 and 2020 was statistically significant(X2=338.190, P< 0.05). The dominant influenza strains in 2019 and 2020 was H3N2 subtype, but the positive detection rate of influenza in 2020 was significantly lower than that in 2019(X2=364.845, P< 0.05). Conclusions: After the COVID-19 epidemic occurred in Fuzhou, the epidemic control and prevention was carried out in key public places especially at schools. The prevention knowledge propaganda and the influenza vaccination were strengthened, which significantly reduced the incidence of influenza.

Bibliometric evaluation of 2020-2022 publications on COVID-19-related cardiovascular disease.

Objective: This study aimed to investigate the international scientific output regarding the relationship between COVID-19 and cardiovascular diseases (CVDs) through a bibliometric analysis and explore research hotspots in this field. Methods: We searched the Web of Science Core Collection for publications and used different types of software, such as R, CiteSpace, and VOSviewer, to analyze and visualize the data. Results: A total of 10,055 publications were retrieved as of the 13 December 2022, based on the inclusion criteria after screening. The USA and China lead in the quantity and quality of publications in this field. Based on Bradford's law, 63 journals were considered core journals in the field. Co-cited references and keywords analysis indicated that researchers paid particular attention to cardiovascular comorbidities, outcomes, and COVID-19 regenerative medicine. In summary, with increasing COVID-19 research related to CVD, more attention might be drawn to the relationship between these two diseases. Conclusion: The hotspots in this field may continue to revolve around cardiovascular comorbidities, outcomes, and COVID-19 regenerative medicine. Owing to the different situations faced by different groups with COVID-19, further exploration of the related factors specific to each of these groups, e.g., history or no history of heart failure, is needed, with a view to providing a reference for intervention measures in COVID-19 research.

Tea Culture Tourism Perception: A Study on the Harmony of Importance and Performance

Tea culture tourism is a product of the combination of agricultural tourism and ecotourism. After the COVID-19 period, this product is more and more popular. Tourism performance is an important index for measuring the development level of tourist destinations, and research on the influencing factors of tourism performance is an important way to promote the high-quality development of tea culture tourism. Using the tea tourism town of Wushan as a case study, 452 valid questionnaires were used as research data, and exploratory factor analysis, paired sample t-test and IPA analysis were applied. The results indicate that: (1) tourism performance is mainly divided into 5 dimensions and 22 specific indicators, including service quality, resource environment, tourism transportation, tourism-supporting facilities and tea tourism products;(2) there is a significant difference between the degree of importance and performance of visitors to each indicator, and the overall tourism performance of the case sites at an average level;(3) convenient service, professional service, business management, park traffic, parking conditions, environmental design, shopping environment, tea quality, and tea culture characteristics are potential advantageous factors, and 'service with a smile', accessibility, trail layout, overall image, air quality, natural scenery, landscape vignettes, network communication, public toilets, sanitation facilities, tourist service centers, tea travel activities, and tourism souvenirs are areas in need of improvement.

Anxiety and depression among medical staff facing SARS-CoV-2 vaccination in China.

BACKGROUND: SARS-COV-2 vaccination is being carried out worldwide. However, little is known about the effect of SARS-COV-2 vaccination on psychological problems faced by the medical staff. This study aimed to examine the prevalence and factors contributing to anxiety and depression among medical staff facing SARS-COV-2 vaccination. METHODS: The GAD-7 and the PHQ-9 scales were used to investigate the anxiety and depression among participants involved in SARS-CoV-2 vaccination. Multivariate logistics regression analysis method was used to assess the risk factors related to anxiety or depression. RESULTS: A total of 6984 people responded to all the surveyed questions in our study, including 2707 medical staff and 4277 nonmedical staff. Of the participants, 680 reported anxiety, while 1354 reported depression. Higher anxiety levels were observed among medical staff (13.1 % vs. 7.6 % among the non-medical staff). Participants suffered from depression with higher numbers among medical staff (24.7 % vs. 16.0 % among the non-medical staff). Multivariate logistic regression analysis showed that female medical staff was at higher risk of anxiety and depression compared to their male counterparts (OR = 1.497; OR = 1.417). Pregnancy intention increased the risk of anxiety and depression among medical staff (OR = 1.601; OR = 1.724). LIMITATIONS: Our findings may not be extrapolated to other countries. CONCLUSION: Medical staff facing SARS-CoV-2 vaccination were more likely to suffer from anxiety or depression, especially the females planning for pregnancy. These results should assist in updating intervention guidelines for the mental health of medical staff facing vaccination.

Prevalence and risk factors of depression and anxiety among Chinese adults who received SARS-CoV-2 vaccine - A cross-sectional survey.

BACKGROUND: Direct data reflecting the psychological problems during the nationwide SARS-CoV-2 vaccination campaign are scarce in China. The aim of this study was to assess the prevalence of depression and anxiety and investigate the associated risk factors after vaccination against SARS-CoV-2 among Chinese adults. METHODS: We conducted a web-based cross-sectional survey from June to July 2021. A structured questionnaire including the Patient Health Questionnaire-9(PHQ-9) and Generalized Anxiety Disorder-7(GAD-7) was used to investigated depression and anxiety symptoms. After excluding 223 ineligible records, a total of 6984 participants were included in our final analysis. Multivariable logistic regression analysis was used to examined the potential factors associated with depression or anxiety. RESULTS: Our data indicated that the overall prevalence of depression and anxiety was assessed at 19.39 % and 9.74 %, respectively. Participants who had vaccinated the second dose were more likely to have depressive symptoms (20.95 % vs.16.40 %) and anxiety symptoms (10.38 % vs. 8.51 %) than who had vaccinated the first dose. Multivariable logistic regression analysis indicated female gender, being healthcare worker, college or above and planning a pregnancy were all independently linked to depression or anxiety. LIMITATIONS: The present study was based on an online survey. CONCLUSION: The present study confirmed the presence of depression and anxiety among Chinese adults who received SARS-COV-2 vaccine, as well as the potential influencing factors. Additional attention and psychological support should be directed at these high-risk groups during SARS-CoV-2 vaccination campaign.

Quarantine and the Transformation of Power Dynamics during China's War of Resistance against Japan

Zou and Quan discuss quarantine and the transformation of power dynamics during China's war of resistance against Japan. In the novel Cold Nights (1947), the modern Chinese writer Ba Jin (1904-2005) uses representations of quarantine rather than the frequently used themes of heroic resistance and nationalism to show how China's war of resistance against Japan brought about changes in power relations within the nation. Cold Nights describes how this military engagement in the wartime capital of Chongqing China influences and transforms labor, government, social community, and individuality during an epidemic. In a time when COVID-19 sweeps across the world and also points to the important role quarantine plays in revealing the change and formation of new forms of socio-political power dynamics, more thorough studies of how the enforcement of quarantine can impact different societies and what the consequences of these decisions are for the people are clearly necessary.

Correction: The inactivation mechanism of chemical disinfection against SARS-CoV-2: from MD and DFT perspectives.

[This corrects the article DOI: 10.1039/D0RA06730J.].

Multi-omics of the expression and clinical outcomes of TMPRSS2 in human various cancers: A potential therapeutic target for COVID-19.

Growing evidence has shown that Transmembrane Serine Protease 2 (TMPRSS2) not only contributes to the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, but is also closely associated with the incidence and progression of tumours. However, the correlation of coronavirus disease (COVID-19) and cancers, and the prognostic value and molecular function of TMPRSS2 in various cancers have not been fully understood. In this study, the expression, genetic variations, correlated genes, immune infiltration and prognostic value of TMPRSS2 were analysed in many cancers using different bioinformatics platforms. The observed findings revealed that the expression of TMPRSS2 was considerably decreased in many tumour tissues. In the prognostic analysis, the expression of TMPRSS2 was considerably linked with the clinical consequences of the brain, blood, colorectal, breast, ovarian, lung and soft tissue cancer. In protein network analysis, we determined 27 proteins as protein partners of TMPRSS2, which can regulate the progression and prognosis of cancer mediated by TMPRSS2. Besides, a high level of TMPRSS2 was linked with immune cell infiltration in various cancers. Furthermore, according to the pathway analysis of differently expressed genes (DEGs) with TMPRSS2 in lung, breast, ovarian and colorectal cancer, 160 DEGs genes were found and were significantly enriched in respiratory system infection and tumour progression pathways. In conclusion, the findings of this study demonstrate that TMPRSS2 may be an effective biomarker and therapeutic target in various cancers in humans, and may also provide new directions for specific tumour patients to prevent SARS-CoV-2 infection during the COVID-19 outbreak.

Disease, Desire, and Devotion: Mobilities and Becoming-(M)other in Jen Sookfong Lee's The Better Mother

The Better Mother tells the story of how Danny Lim, a gay Chinese Canadian man, negotiates the tensions between his sexual orientation and his patriarchal family, between his pursuit of art and beauty and the banality and monotony that permeate Vancouver's Chinatown, and between his desire for a glamorous mother and dissatisfaction with his homely and dowdy mother. Peter Merriman, in his call for an expansion of mobility studies in Micro-Mobilities in Lockdown" further draws scholarly attention to embodied micro-mobilities, which are defined as the myriad bodily movements and mobile embodied practices involved in all manner of actions, events, and systems, from the bodily movements involved in walking, driving, and flying, to the embodied movements involved in virus transmission and infection control (54). Bringing the frameworks of becoming and embodied micro-mobilities into dialogue as a critical lens through which to address the issue of AIDS in The Better Mother, this article argues that interracial and queer forms of care have the potential to mitigate the impact of AIDS upon queer mobilities, both physical and metaphysical, and trouble heteronormativity. [...]those infected, as Danny has noticed, show different symptoms and suffer from different diseases that result from HIV.

Reflections on the Cluster Epidemic of COVID-19; Lessons Learned from Wuhan's Experience: A Brief Review.

At present, new coronavirus pneumonia (COVID-19) is circulating worldwide. The pathogen of this coronavirus pneumonia is named SARS-CoV-2. The virus has a long incubation period and is highly contagious. There is currently no specific targeted drug treatment. The focus of anti-epidemic work should be more on prevention and control while cutting off the virus transmission route while treating infected patients, and protecting healthy people. In order to protect the safety and health of the Chinese citizens and to maintain the safety of world public health, the Chinese government and people have made unprecedented efforts to control the epidemic. Many people in the international community have joined in limiting the spread of COVID-19. This article combines the development of COVID-19 epidemic situation in Wuhan, the relevant prevention and control measures of the Wuhan government and local health authorities to share Wuhan's experience on control the cluster epidemic and provide new suggestions and ideas for epidemic prevention and control.

Additional Value of Non-contrast Chest CT in the Prediction of Adverse Cardiovascular Events in Patients With Novel Coronavirus Disease 2019 (COVID-19).

Background: Coronavirus disease 2019 (COVID-19) has outbroken in China and subsequently spread worldwide since the end of 2019. Chest computed tomography (CT) plays an important role in the diagnosis of lung diseases, but its value in the diagnosis of cardiac injury remains unknown. Methods: We enrolled 241 consecutive hospitalized patients (aged 61 ± 16 years, 115 males) with laboratory-confirmed COVID-19 at Renmin Hospital of Wuhan University from January 11 to March 2, 2020. They were divided into two groups according to whether major adverse cardiovascular events (MACEs) occurred during the follow-up. The anteroposterior diameter of the left atrium (LAD), the length of the left ventricle (LV), and cardiothoracic ratio (CTR) were measured. The values of myocardial CT were also recorded. Results: Of 241 patients, 115 patients (47.7%) had adverse cardiovascular events. Compared with no MACEs, patients with MACEs were more likely to have bilateral lesions (95.7% vs. 86.5%, p = 0.01). In multivariable analysis, bronchial wall thickening would increase the odds of MACEs by 13.42 (p = 0.01). LAD + LV and CTR was the best predictor for MACEs (area under the curve = 0.88, p < 0.001) with a sensitivity of 82.6% and a specificity of 80.2%. Plasma high-sensitivity troponin I levels in patients with cardiac injury showed a moderate negative correlation with minimum CT value (R 2 = -0.636, p < 0.001). Conclusions: Non-contrast chest CT can be a useful modality for detection cardiac injury and provide additional value to predict MACEs in COVID-19 patients.

Chinese Color Nest Project : An accelerated longitudinal brain-mind cohort.

The ongoing Chinese Color Nest Project (CCNP) was established to create normative charts for brain structure and function across the human lifespan, and link age-related changes in brain imaging measures to psychological assessments of behavior, cognition, and emotion using an accelerated longitudinal design. In the initial stage, CCNP aims to recruit 1520 healthy individuals (6-90 years), which comprises three phases: developing (devCCNP: 6-18 years, N = 480), maturing (matCCNP: 20-60 years, N = 560) and aging (ageCCNP: 60-84 years, N = 480). In this paper, we present an overview of the devCCNP, including study design, participants, data collection and preliminary findings. The devCCNP has acquired data with three repeated measurements from 2013 to 2017 in Southwest University, Chongqing, China (CCNP-SWU, N = 201). It has been accumulating baseline data since July 2018 and the second wave data since September 2020 in Chinese Academy of Sciences, Beijing, China (CCNP-CAS, N = 168). Each participant in devCCNP was followed up for 2.5 years at 1.25-year intervals. The devCCNP obtained longitudinal neuroimaging, biophysical, social, behavioral and cognitive data via MRI, parent- and self-reported questionnaires, behavioral assessments, and computer tasks. Additionally, data were collected on children's learning, daily life and emotional states during the COVID-19 pandemic in 2020. We address data harmonization across the two sites and demonstrated its promise of characterizing the growth curves for the overall brain morphometry using multi-center longitudinal data. CCNP data will be shared via the National Science Data Bank and requests for further information on collaboration and data sharing are encouraged.

Remarkable gastrointestinal and liver manifestations of COVID-19: A clinical and radiologic overview.

The coronavirus disease 2019 (COVID-19) raging around the world still has not been effectively controlled in most countries and regions. As a severe acute respiratory syndrome coronavirus, in addition to the most common infectious pneumonia, it can also cause digestive system disease such as diarrhea, nausea, vomiting, liver function damage, etc. In medical imaging, it manifests as thickening of the intestinal wall, intestinal perforation, pneumoperitoneum, ascites and decreased liver density. Angiotensin-converting enzyme 2 has great significance in COVID-19-related digestive tract diseases. In this review, we summarized the data on the clinical and imaging manifestations of gastrointestinal and liver injury caused by COVID-19 so far and explored its possible pathogenesis.

Regional Travel as an Alternative Form of Tourism during the COVID-19 Pandemic: Impacts of a Low-Risk Perception and Perceived Benefits.

Previous COVID-19 tourism research has not considered the positive impact of a low-risk perception and a perception of the benefits of regional travel on taking alternative tourism. This study attempts to fill the research gap and examine the positive effect of these perceptions on tourists' attitudes to regional travel and intentions to undertake regional travel during the COVID-19 pandemic. A survey of 278 respondents confirmed that the perceived benefit positively influences tourists' attitudes and travel intentions, but that a low-risk perception only positively affects their attitudes. This study contributes to tourism risk management research by introducing the concept of a low-risk perception as a positive factor. For tourism recovery, it finds that relaxation, value, and convenience are benefits to drive people to travel.

Effectiveness of chelating agent-assisted Fenton-like processes on remediation of glucocorticoid-contaminated soil using chemical and biological assessment: performance comparison of CaO2 and H2O2.

Glucocorticoids (GCs) have drawn great concern due to widespread contamination in the environment and application in treating COVID-19. Most studies on GC removal mainly focused on aquatic environment, while GC behaviors in soil were less mentioned. In this study, degradation of three selected GCs in soil has been investigated using citric acid (CA)-modified Fenton-like processes (H2O2/Fe(III)/CA and CaO2/Fe(III)/CA treatments). The results showed that GCs in soil can be removed by modified Fenton-like processes (removal efficiency gt; 70% for 24 h). CaO2/Fe(III)/CA was more efficient than H2O2/Fe(III)/CA at low oxidant dosage (< 0.28-0.69 mmol/g) for long treatment time (> 4 h). Besides the chemical assessment with GC removal, effects of Fenton-like processes were also evaluated by biological assessments with bacteria and plants. CaO2/Fe(III)/CA was less harmful to the richness and diversity of microorganisms in soil compared to H2O2/Fe(III)/CA. Weaker phytotoxic effects were observed on GC-contaminated soil treated by CaO2/Fe(III)/CA than H2O2/Fe(III)/CA. This study, therefore, recommends CaO2-based treatments to remediate GC-contaminated soils.

The prognostic value of myocardial injury in COVID-19 patients and associated characteristics.

BACKGROUND: Since December 2019, coronavirus disease 2019 (COVID-19) has emerged as an international pandemic. COVID-19 patients with myocardial injury might need special attention. However, an understanding on this aspect remains unclear. This study aimed to illustrate clinical characteristics and the prognostic value of myocardial injury to COVID-19 patients. METHODS: This retrospective, single-center study finally included 304 hospitalized COVID-19 cases confirmed by real-time reverse-transcriptase polymerase chain reaction from January 11 to March 25, 2020. Myocardial injury was determined by serum high-sensitivity troponin I (Hs-TnI). The primary endpoint was COVID-19-associated mortality. RESULTS: Of 304 COVID-19 patients (median age, 65 years; 52.6% males), 88 patients (27.3%) died (61 patients with myocardial injury, 27 patients without myocardial injury on admission). COVID-19 patients with myocardial injury had more comorbidities (hypertension, chronic obstructive pulmonary disease, cardiovascular disease, and cerebrovascular disease); lower lymphocyte counts, higher C-reactive protein (CRP; median, 84.9 vs. 28.5 mg/L; p < .001), procalcitonin levels (median, 0.29 vs. 0.06 ng/ml; p < .001), inflammatory and immune response markers; more frequent need for noninvasive ventilation, invasive mechanical ventilation; and was associated with higher mortality incidence (hazard ratio [HR] = 7.02; 95% confidence interval [CI], 4.45-11.08; p < .001) than those without myocardial injury. Myocardial injury (HR = 4.55; 95% CI, 2.49-8.31; p < .001), senior age, CRP levels, and novel coronavirus pneumonia types on admission were independent predictors to mortality in COVID-19 patients. CONCLUSIONS: COVID-19 patients with myocardial injury on admission is associated with more severe clinical presentation and biomarkers. Myocardial injury and higher Hs-TnI are both strongest independent predictors to COVID-19-related mortality after adjusting confounding factors.

Cough Recognition Based on Mel-Spectrogram and Convolutional Neural Network.

In daily life, there are a variety of complex sound sources. It is important to effectively detect certain sounds in some situations. With the outbreak of COVID-19, it is necessary to distinguish the sound of coughing, to estimate suspected patients in the population. In this paper, we propose a method for cough recognition based on a Mel-spectrogram and a Convolutional Neural Network called the Cough Recognition Network (CRN), which can effectively distinguish cough sounds.

Clinical Characteristics, Risk Factors and Cardiac Manifestations of Cancer Patients with COVID-19 (preprint)

Background: Coronavirus disease 2019 (COVID-19) has been associated with cardiovascular features, which may be deteriorated in cancer patients.Methods: We retrospectively assessed 1,244 COVID-19 patients from February 1st to August 31st (140 cancer and 1104 non-cancer patients). Clinical data and laboratory findings were obtained and compared between cancer and non-cancer groups. Risk factors for in-hospital mortality were identified by multivariable COX regression models.Findings: The median age of cancer group was older than that in non-cancer patients [61 (57-67) vs. 56 (40-68), p < 0.001]. For cancer group, 56% were in severe and critical status, while the proportion was 10% for non-cancer group. Cancer patients had increased levels of leukocyte, neutrophil count and BUN (all p < 0.01), while lymphocyte count was significantly lower (p < 0.001). The most common solid tumor types were gastrointestinal cancer (26%), lung cancer (21%), breast and reproductive cancer (both 19%). There is a rising for cardiac biomarkers, including Pro-BNP, cTnI, MYO, CK-MB, and D-Dimer in COVID-19 cancer population, especially in deceased cancer subjects. The 30-day in hospital mortality in cancer group was dramatically raised than that in non-cancer group (12.9% vs. 4.0%, p<0.01). In multivariable COX regression models, fever, disease severity status, underlying diseases were risk factors for mortality. The Pro-BNP and D-Dimer levels were significantly increased in cancer subjects with cardiovascular disease.Interpretation: COVID-19 cancer patients relate to deteriorating conditions, increased risk of admission to intensive care units and in-hospital mortality. They display severely impaired myocardium, damaged heart function and imbalanced homeostasis of coagulation, which warrants more aggressive treatment. Funding: The current work was supported by the National Natural Science Foundation Project of China (Grant No. 81670304) and the Fundamental Research Funds for the Central Universities of China (NO.2042019kf0058).Declaration of Interests: All authors report no relationship or conflict of interest to disclose.Ethics Approval Statement: This study was approved by the National Health Commission of China and the institutional review board at Renmin Hospital of Wuhan University (Wuhan, China).

Batch Similarity Based Triplet Loss Assembled into Light-Weighted Convolutional Neural Networks for Medical Image Classification.

In many medical image classification tasks, there is insufficient image data for deep convolutional neural networks (CNNs) to overcome the over-fitting problem. The light-weighted CNNs are easy to train but they usually have relatively poor classification performance. To improve the classification ability of light-weighted CNN models, we have proposed a novel batch similarity-based triplet loss to guide the CNNs to learn the weights. The proposed loss utilizes the similarity among multiple samples in the input batches to evaluate the distribution of training data. Reducing the proposed loss can increase the similarity among images of the same category and reduce the similarity among images of different categories. Besides this, it can be easily assembled into regular CNNs. To appreciate the performance of the proposed loss, some experiments have been done on chest X-ray images and skin rash images to compare it with several losses based on such popular light-weighted CNN models as EfficientNet, MobileNet, ShuffleNet and PeleeNet. The results demonstrate the applicability and effectiveness of our method in terms of classification accuracy, sensitivity and specificity.