Explore the vast range of titles available.

Pulmonary nodules are the main manifestation of early lung cancer. Therefore, accurate detection of nodules in CT images is vital for lung cancer diagnosis. A 3D automatic detection system of pulmonary nodules based on multi-scale attention networks is proposed in this paper to use multi-scale features of nodules and avoid network over-fitting problems. The system consists of two parts, nodule candidate detection (determining the locations of candidate nodules), false positive reduction (minimizing the number of false positive nodules). Specifically, with Res2Net structure, using pre-activation operation and convolutional quadruplet attention module, the 3D multi-scale attention block is designed. It makes full use of multi-scale information of pulmonary nodules by extracting multi-scale features at a granular level and alleviates over-fitting by pre-activation. The U-Net-like encoder-decoder structure is combined with multi-scale attention blocks as the backbone network of Faster R-CNN for detection of candidate nodules. Then a 3D deep convolutional neural network based on multi-scale attention blocks is designed for false positive reduction. The extensive experiments on LUNA16 and TianChi competition datasets demonstrate that the proposed approach can effectively improve the detection sensitivity and control the number of false positive nodules, which has clinical application value.

With the rapid development of big data and artificial intelligence technology, computer-aided pulmonary nodule detection based on deep learning has achieved some successes. However, the sizes of pulmonary nodules vary greatly, and the pulmonary nodules have visual similarity with structures such as blood vessels and shadows around pulmonary nodules, which make the quick and accurate detection of pulmonary nodules in CT image still a challenging task. In this paper, we propose two kinds of 3D multi-scale deep convolution neural networks for nodule candidate detection and false positive reduction respectively. Among them, the nodule candidate detection network consists of two parts: 1) the backbone network part Res2SENet, which is used to extract multi-scale feature information of pulmonary nodules, it is composed of the multi-scale Res2Net modules of multiple available receptive fields at a granular level and the squeeze-and-excitation units; 2) the detection part, which uses a region proposal network structure to determine region candidates, and introduces context enhancement module and spatial attention module to improve detection performance. The false positive reduction network, also composed of the multi-scale Res2Net modules and the squeeze-and-excitation units, can further classify the nodule candidates generated by the nodule candidate detection network and screen out the ground truth positive nodules. Finally, the prediction probability generated by the nodule candidate detection network is weighted average with the prediction probability generated by the false positive reduction network to obtain the final results. The experimental results on the publicly available LUNA16 dataset showed that the proposed method has a superior ability to detect pulmonary nodules in CT images.

Diabetic retinopathy is the leading cause of blindness in working population. Lesion segmentation from fundus images helps ophthalmologists accurately diagnose and grade of diabetic retinopathy. However, the task of lesion segmentation is full of challenges due to the complex structure, the various sizes and the interclass similarity with other fundus tissues. To address the issue, this paper proposes a cascade attentive RefineNet (CARNet) for automatic and accurate multi-lesion segmentation of diabetic retinopathy. It can make full use of the fine local details and coarse global information from the fundus image. CARNet is composed of global image encoder, local image encoder and attention refinement decoder. We take the whole image and the patch image as the dual input, and feed them to ResNet50 and ResNet101, respectively, for downsampling to extract lesion features. The high-level refinement decoder uses dual attention mechanism to integrate the same-level features in the two encoders with the output of the low-level attention refinement module for multiscale information fusion, which focus the model on the lesion area to generate accurate predictions. We evaluated the segmentation performance of the proposed CARNet on the IDRiD, E-ophtha and DDR data sets. Extensive comparison experiments and ablation studies on various data sets demonstrate the proposed framework outperforms the state-of-the-art approaches and has better accuracy and robustness. It not only overcomes the interference of similar tissues and noises to achieve accurate multi-lesion segmentation, but also preserves the contour details and shape features of small lesions without overloading GPU memory usage.

23% of the total global burden of disease is attributable to disorders in people aged 60 years and older. Although the proportion of the burden arising from older people (≥60 years) is highest in high-income regions, disability-adjusted life years (DALYs) per head are 40% higher in low-income and middle-income regions, accounted for by the increased burden per head of population arising from cardiovascular diseases, and sensory, respiratory, and infectious disorders. The leading contributors to disease burden in older people are cardiovascular diseases (30·3% of the total burden in people aged 60 years and older), malignant neoplasms (15·1%), chronic respiratory diseases (9·5%), musculoskeletal diseases (7·5%), and neurological and mental disorders (6·6%). A substantial and increased proportion of morbidity and mortality due to chronic disease occurs in older people. Primary prevention in adults aged younger than 60 years will improve health in successive cohorts of older people, but much of the potential to reduce disease burden will come from more effective primary, secondary, and tertiary prevention targeting older people. Obstacles include misplaced global health priorities, ageism, the poor preparedness of health systems to deliver age-appropriate care for chronic diseases, and the complexity of integrating care for complex multimorbidities. Although population ageing is driving the worldwide epidemic of chronic diseases, substantial untapped potential exists to modify the relation between chronological age and health. This objective is especially important for the most age-dependent disorders (ie, dementia, stroke, chronic obstructive pulmonary disease, and vision impairment), for which the burden of disease arises more from disability than from mortality, and for which long-term care costs outweigh health expenditure. The societal cost of these disorders is enormous.

Background Cardiovascular disease (CVD) is one of the leading causes of death worldwide. Our study aimed to investigate the prevalence of two conditions, angina and stroke, and relevant risk factors among older adults in six low- and middle- income countries(LMICs). Methods The data was from World Health Organization (WHO) Study on global AGEing and adult Health (SAGE) Wave 1 in China, Ghana, India, Mexico, Russian Federation and South Africa. Presence of CVD was based on self-report of angina and stroke. Multivariate logistic regression was performed to examine the relationship between CVD and selected variables, including age, sex, urban/rural setting, household wealth, and risk factors such as smoking, alcohol drinking, fruit/vegetable intake, physical activity and BMI. Results The age standardized prevalence of angina ranged from 9.5 % (South Africa) to 47.5 % (Russian Federation), and for stoke from 2.0% (India) to 6.1 % (Russia). Hypertension was associated with angina in China, India and Russian Federation after adjustment for age, sex, urban/rural setting, education and marital status (OR ranging from 1.3 [1.1-1.6] in India to 3.8 [2.9-5.0] in Russian Federation), furthermore it was a risk factor of stroke in five countries except Mexico. Low or moderate physical activity were also associated with angina in China, and were also strongly associated with stroke in all countries except Ghana and India. Obesity had a stronger association with angina in Russian Federation and China(ORs were 1.5[1.1-2.0] and 1.2 [1.0-1.5] respectively), and increased the risk of stroke in China. Smoking was associated with angina in India and South Africa(ORs were 1.6[1.0-2.4] and 2.1 [1.2-3.6] respectively ), and was also a risk factor of stroke in South Africa. We observed a stronger association between frequent heavy drinking and stroke in India. Household income was associated with reduced odds of angina in China, India and Russian Federation, however higher household income was a risk factor of angina in South Africa. Conclusion While the specific mix of risk factors contribute to disease prevalence in different ways in these six countries – they should all be targeted in multi-sectoral efforts to reduce the high burden of CVD in today’s society.

Asthma is a common chronic airway disease worldwide. Despite its large population size, China has had no comprehensive study of the national prevalence, risk factors, and management of asthma. We therefore aimed to estimate the national prevalence of asthma in a representative sample of the Chinese population. A representative sample of 57 779 adults aged 20 years or older was recruited for the national cross-sectional China Pulmonary Health (CPH) study using a multi-stage stratified sampling method with parameters derived from the 2010 census. Ten Chinese provinces, representative of all socioeconomic settings, from six geographical regions were selected, and all assessments were done in local health centres. Exclusion criteria were temporary residence, inability to take a spirometry test, hospital treatment of cardiovascular conditions or tuberculosis, and pregnancy and breastfeeding. Asthma was determined on the basis of a self-reported history of diagnosis by a physician or by wheezing symptoms in the preceding 12 months. All participants were assessed with a standard asthma questionnaire and were classed as having or not having airflow limitation through pulmonary function tests before and after the use of a bronchodilator (400 μg of salbutamol). Risk factors for asthma were examined by multivariable-adjusted analyses done in all participants for whom data on the variables of interest were available. Disease management was assessed by the self-reported history of physician diagnosis, treatments, and hospital visits in people with asthma. Between June 22, 2012, and May 25, 2015, 57 779 participants were recruited into the CPH study. 50 991 (21 446 men and 29 545 women) completed the questionnaire survey and had reliable post-bronchodilator pulmonary function test results and were thus included in the final analysis. The overall prevalence of asthma in our sample was 4·2% (95% CI 3·1–5·6), representing 45·7 million Chinese adults. The prevalence of asthma with airflow limitation was 1·1% (0·9–1·4), representing 13·1 million adults. Cigarette smoking (odds ratio [OR] 1·89, 95% CI 1·26–2·84; p=0·004), allergic rhinitis (3·06, 2·26–4·15; p<0·0001), childhood pneumonia or bronchitis (2·43, 1·44–4·10; p=0·002), parental history of respiratory disease (1·44, 1·02–2·04; p=0·040), and low education attainment (p=0·045) were associated with prevalent asthma. In 2032 people with asthma, only 28·8% (95% CI 19·7–40·0) reported ever being diagnosed by a physician, 23·4% (13·9–36·6) had a previous pulmonary function test, and 5·6% (3·1–9·9) had been treated with inhaled corticosteroids. Furthermore, 15·5% (11·4–20·8) people with asthma reported at least one emergency room visit and 7·2% (4·9–10·5) at least one hospital admission due to exacerbation of respiratory symptoms within the preceding year. Asthma is prevalent but largely undiagnosed and undertreated in China. It is crucial to increase the awareness of asthma and disseminate standardised treatment in clinical settings to reduce the disease burden. National Key R&D Program of China, Ministry of Science and Technology of China; the Special Research Foundation for Public Welfare of Health, Ministry of Health of China; the Chinese National Research Program for Key Issues in Air Pollution Control; and the National Natural Science Foundation of China.

Glaucoma is a leading cause of blindness. Accurate and efficient segmentation of the optic disc and cup from fundus images is important for glaucoma screening. However, using off-the-shelf networks against new datasets may lead to degraded performances due to domain shift. To address this issue, in this paper, we propose a coarse-to-fine adaptive Faster R-CNN framework for cross-domain joint optic disc and cup segmentation. The proposed CAFR-CNN consists of the Faster R-CNN detector, a spatial attention-based region alignment module, a pyramid ROI alignment module and a prototype-based semantic alignment module. The Faster R-CNN detector extracts features from fundus images using a VGG16 network as a backbone. The spatial attention-based region alignment module extracts the region of interest through a spatial mechanism and aligns the feature distribution from different domains via multilayer adversarial learning to achieve a coarse-grained adaptation. The pyramid ROI alignment module learns multilevel contextual features to prevent misclassifications due to the similar appearances of the optic disc and cup. The prototype-based semantic alignment module minimizes the distance of global prototypes with the same category between the target domain and source domain to achieve a fine-grained adaptation. We evaluated the proposed CAFR-CNN framework under different scenarios constructed from four public retinal fundus image datasets (REFUGE2, DRISHTI-GS, DRIONS-DB and RIM-ONE-r3). The experimental results show that the proposed method outperforms the current state-of-the-art methods and has good accuracy and robustness: it not only avoids the adverse effects of low contrast and noise interference but also preserves the shape priors and generates more accurate contours.

Although exposure to cigarette smoking and air pollution is common, the current prevalence of chronic obstructive pulmonary disease (COPD) is unknown in the Chinese adult population. We conducted the China Pulmonary Health (CPH) study to assess the prevalence and risk factors of COPD in China. The CPH study is a cross-sectional study in a nationally representative sample of adults aged 20 years or older from ten provinces, autonomous regions, and municipalities in mainland China. All participants underwent a post-bronchodilator pulmonary function test. COPD was diagnosed according to 2017 Global Initiative for Chronic Obstructive Lung Disease (GOLD) criteria. Between June, 2012, and May, 2015, 57 779 individuals were invited to participate, of whom 50 991 (21 446 men and 29 545 women) had reliable post-bronchodilator results and were included in the final analysis. The overall prevalence of spirometry-defined COPD was 8·6% (95% CI 7·5–9·9), accounting for 99·9 (95% CI 76·3–135·7) million people with COPD in China. Prevalence was higher in men (11·9%, 95% CI 10·2–13·8) than in women (5·4%, 4·6–6·2; p<0·0001 for sex difference) and in people aged 40 years or older (13·7%, 12·1–15·5) than in those aged 20–39 years (2·1%, 1·4–3·2; p<0·0001 for age difference). Only 12·0% (95% CI 8·1–17·4) of people with COPD reported a previous pulmonary function test. Risk factors for COPD included smoking exposure of 20 pack-years or more (odds ratio [OR] 1·95, 95% CI 1·53–2·47), exposure to annual mean particulate matter with a diameter less than 2·5 μm of 50–74 μg/m3 (1·85, 1·23–2·77) or 75 μg/m3 or higher (2·00, 1·36–2·92), underweight (body-mass index <18·5 kg/m2; 1·43, 1·03–1·97), sometimes childhood chronic cough (1·48, 1·14–1·93) or frequent cough (2·57, 2·01–3·29), and parental history of respiratory diseases (1·40, 1·23–1·60). A lower risk of COPD was associated with middle or high school education (OR 0·76, 95% CI 0·64–0·90) and college or higher education (0·47, 0·33–0·66). Spirometry-defined COPD is highly prevalent in the Chinese adult population. Cigarette smoking, ambient air pollution, underweight, childhood chronic cough, parental history of respiratory diseases, and low education are major risk factors for COPD. Prevention and early detection of COPD using spirometry should be a public health priority in China to reduce COPD-related morbidity and mortality. Ministry of Health and Ministry of Science and Technology of China.

Quantification of the cardiac function is vital for diagnosing and curing the cardiovascular diseases. Left ventricular function measurement is the most commonly used measure to evaluate the function of cardiac in clinical practice, how to improve the accuracy of left ventricular quantitative assessment results has always been the subject of research by medical researchers. Although considerable efforts have been put forward to measure the left ventricle (LV) automatically using deep learning methods, the accurate quantification is yet a challenge work as a result of the changeable anatomy structure of heart in the systolic diastolic cycle. Besides, most methods used direct regression method which lacks of visual based analysis. In this work, a deep learning segmentation and regression task-unified network with transformer and spatial–temporal convolution is proposed to segment and quantify the LV simultaneously. The segmentation module leverages a U-Net like 3D Transformer model to predict the contour of three anatomy structures, while the regression module learns spatial–temporal representations from the original images and the reconstruct feature map from segmentation path to estimate the finally desired quantification metrics. Furthermore, we employ a joint task loss function to train the two module networks. Our framework is evaluated on the MICCAI 2017 Left Ventricle Full Quantification Challenge dataset. The results of experiments demonstrate the effectiveness of our framework, which achieves competitive cardiac quantification metric results and at the same time produces visualized segmentation results that are conducive to later analysis.

Background Patients with severe acute exacerbations of chronic obstructive pulmonary disease often have a poor prognosis. Biomarkers can help clinicians personalize the assessment of different patients and mitigate mortality. The present study sought to determine if the lymphocyte count could act as a risk factor for mortality in individuals with severe AECOPD. Methods A retrospective study was carried out with 458 cases who had severe AECOPD. For analysis, patients were divided into two groups on the basis of lymphocyte count: < 0.8 × 10 9 /L and ≥ 0.8 × 10 9 /L. Results Patients who fulfilled the criteria for inclusion were enrolled, namely 458 with a mean age of 78.2 ± 8.2 years. Of these patients, 175 had a low lymphocyte count. Compared to patients with normal lymphocyte counts, those with low counts were older (79.2 ± 7.4 vs. 77.5 ± 8.6 years, p  = 0.036), had lower activities of daily living scores on admission (35.9 ± 27.6 vs. 47.5 ± 17.1, p  < 0.001), and had a greater need for home oxygen therapy (84.6 vs. 72.1%, p  = 0.002). Patients with low lymphocytes had higher mortality rates during hospitalization (17.1 vs. 7.1%, p  = 0.001), longer hospital stay (median [IQR] 16 days [12–26] vs. 14 days [10–20], p  = 0.002) and longer time on mechanical ventilation (median [IQR] 11.6 days [5.8–18.7] vs. 10.9 days [3.8–11.6], p  < 0.001). The logistic regression analysis showed lymphocyte count < 0.8 × 10 9 /L was an independent risk factor associated with in-hospital mortality (OR 2.74, 95%CI 1.33–5.66, p  = 0.006). Conclusion Lymphocyte count could act as a predictor of mortality in patients with severe AECOPD.