AMFP-net: Adaptive multi-scale feature pyramid network for diagnosis of pneumoconiosis from chest X-ray images.

Early detection of pneumoconiosis by routine health screening of workers in the mining industry is critical for preventing the progression of this incurable disease. Automated pneumoconiosis classification in chest X-ray images is challenging due to the low contrast of opacities, inter-class similarity, intra-class variation and the existence of artifacts. Compared to traditional methods, convolutional neural networks have shown significant improvement in pneumoconiosis classification tasks, however, accurate classification remains challenging due to mainly the inability to focus on semantically meaningful lesion opacities. Most existing networks focus on high level abstract information and ignore low level detailed object information. Different from natural images where an object occupies large space, the classification of pneumoconiosis depends on the density of small opacities inside the lung. To address this issue, we propose a novel two-stage adaptive multi-scale feature pyramid network called AMFP-Net for the diagnosis of pneumoconiosis from chest X-rays. The proposed model consists of 1) an adaptive multi-scale context block to extract rich contextual and discriminative information and 2) a weighted feature fusion module to effectively combine low level detailed and high level global semantic information. This two-stage network first segments the lungs to focus more on relevant regions by excluding irrelevant parts of the image, and then utilises the segmented lungs to classify pneumoconiosis into different categories. Extensive experiments on public and private datasets demonstrate that the proposed approach can outperform state-of-the-art methods for both segmentation and classification.

DLA-Net: dual lesion attention network for classification of pneumoconiosis using chest X-ray images.

Accurate and early detection of pneumoconiosis using chest X-rays (CXR) is important for preventing the progression of this incurable disease. It is also a challenging task due to large variations in appearance, size and location of lesions in the lung regions as well as inter-class similarity and intra-class variance. Compared to traditional methods, Convolutional Neural Networks-based methods have shown improved results; however, these methods are still not applicable in clinical practice due to limited performance. In some cases, limited computing resources make it impractical to develop a model using whole CXR images. To address this problem, the lung fields are divided into six zones, each zone is classified separately and the zone classification results are then aggregated into an image classification score, based on state-of-the-art. In this study, we propose a dual lesion attention network (DLA-Net) for the classification of pneumoconiosis that can extract features from affected regions in a lung. This network consists of two main components: feature extraction and feature refinement. Feature extraction uses the pre-trained Xception model as the backbone to extract semantic information. To emphasise the lesion regions and improve the feature representation capability, the feature refinement component uses a DLA module that consists of two sub modules: channel attention (CA) and spatial attention (SA). The CA module focuses on the most important channels in the feature maps extracted by the backbone model, and the SA module highlights the spatial details of the affected regions. Thus, both attention modules combine to extract discriminative and rich contextual features to improve classification performance on pneumoconiosis. Experimental results show that the proposed DLA-Net outperforms state-of-the-art methods for pneumoconiosis classification.

Circular value creation: business models and supply chain strategies.

This paper aims to advance research on the circular economy, sustainable innovation through adopting a circular business model (CBM), and circular supply chain management (CSCM). The circular economy is gradually acknowledged as promising to attain ecological growth by minimising resource input, waste, emissions and energy loss. This article investigates the environmental efficacy of circular value creation and its implications for business models and supply chain strategies. It intends to incorporate CBM and CSCM for sustainable innovation and ecological growth, relying on a review of the literature and four case analyses. The context identifies five distinct CBM propelling supply chain strategies and sustainable innovation, supply chain loops, which differ in intricacy and worth. The study demonstrates that circular business models (CBM) and circular CSCM models can facilitate organisations in accomplishing ecological objectives. The companies examined in the study have different characteristics, but all face comparable challenges in persuading consumers and suppliers to adopt circular business models and supply chain management. A significant challenge is that customers perceive products made from recycled or remanufactured materials as inferior to traditional products, leading to lower prices despite meeting comparable quality standards. Therefore, we review the current literature on the business model background to technological, organisational and social innovation. Since the existing literature does not provide a general conceptual definition of sustainable innovation and circular business mode for circular supply chain management, we present normative examples of requirements that circular business models should meet to support sustainable innovation. Finally, we outline the research agenda by asking some guiding questions.

A Multi-Scale Context Aware Attention Model for Medical Image Segmentation.

Medical image segmentation is critical for efficient diagnosis of diseases and treatment planning. In recent years, convolutional neural networks (CNN)-based methods, particularly U-Net and its variants, have achieved remarkable results on medical image segmentation tasks. However, they do not always work consistently on images with complex structures and large variations in regions of interest (ROI). This could be due to the fixed geometric structure of the receptive fields used for feature extraction and repetitive down-sampling operations that lead to information loss. To overcome these problems, the standard U-Net architecture is modified in this work by replacing the convolution block with a dilated convolution block to extract multi-scale context features with varying sizes of receptive fields, and adding a dilated inception block between the encoder and decoder paths to alleviate the problem of information recession and the semantic gap between features. Furthermore, the input of each dilated convolution block is added to the output through a squeeze and excitation unit, which alleviates the vanishing gradient problem and improves overall feature representation by re-weighting the channel-wise feature responses. The original inception block is modified by reducing the size of the spatial filter and introducing dilated convolution to obtain a larger receptive field. The proposed network was validated on three challenging medical image segmentation tasks with varying size ROIs: lung segmentation on chest X-ray (CXR) images, skin lesion segmentation on dermoscopy images and nucleus segmentation on microscopy cell images. Improved performance compared to state-of-the-art techniques demonstrates the effectiveness and generalisability of the proposed Dilated Convolution and Inception blocks-based U-Net (DCI-UNet).

Employer safety obligations, safety climate, and safety behaviors in the ready-made garment context in Bangladesh.

PURPOSE: The impact of employer safety obligations on safety climate and safety outcomes has become an important area of research in organizational and safety sciences. Evidence shows that employer safety obligations positively impact safety outcomes, including safety climate and safety behaviors. However, these relationships have not been thoroughly explored within the garment settings. This study is one of the first known studies to examine the relationships between employer safety obligations, safety climate, and safety behavior outcomes in a sample of garment employees. METHODS: Two-wave time-lagged data were collected from 347 garment employees and their supervisors in Bangladesh. Hierarchical regression analysis was applied to examine hypothesized relationships using AMOS a SPSS. RESULTS: Employer safety obligations positively influenced safety climate perceptions among garment employees. Safety climate perceptions are positively and significantly associated with safety behaviors, including safety compliance behaviors, prosocial safety behaviors, and proactive safety behaviors. Moreover, the safety climate mediates the influence of employer safety obligations on safety behaviors. CONCLUSIONS: These findings provide important evidence of the relationships between employer safety obligations, safety climate, and safety behaviors in the garment industry of Bangladesh. PRACTICAL APPLICATIONS: Ultimately, these findings guide the government, garment manufacturers, and managers to bolster garment employees' safety outcomes.

Graphic health warnings on tobacco packets and containers: compliance status in Bangladesh.

OBJECTIVE: This study describes and analyses compliance with tobacco product graphic health warning (GHW) legislation introduced in Bangladesh in March 2016. METHODS: A survey based on a structured questionnaire was conducted in April 2016 (immediately following the law coming into force), and 8 months later in November 2016, in eight divisional cities in Bangladesh. Five stores from three categories of retailers of combustible and smokeless tobacco products were surveyed, providing a total of 120 completed questionnaires. The study investigated a range of measures including the image and text of GHW, their ratio and colour use, and prescribed rotation. FINDINGS: Warning labels for 3312 tobacco items were assessed. In April 2016, 75% of tobacco products surveyed did not have GHWs. In November 2016, 19% were still found to not have the prescribed warnings. Even among products which did include GHW, there was significant non-compliance with the full range of requirements, in both survey periods. Compliance was highest for cigarette packets and lowest among smokeless tobacco products. In addition, awareness among tobacco retailers about the range of GHW requirements was low. CONCLUSION: Effective implementation of GHW labels in low-income and middle-income countries requires awareness-raising among key stakeholders, combined with focused monitoring and compliance strategies. This should take into account different product categories and manufacturers, as well as measures targeted at retailers.

Graves' disease presenting as bi-ventricular heart failure with severe pulmonary hypertension and pre-eclampsia in pregnancy--a case report and review of the literature.

BACKGROUND: Graves' disease, a well-known cause of hyperthyroidism, is an autoimmune disease with multi-system involvement. More prevalent among young women, it appears as an uncommon cardiovascular complication during pregnancy, posing a diagnostic challenge, largely owing to difficulty in detecting the complication, as a result of a low index of suspicion of Graves' disease presenting during pregnancy. Globally, cardiovascular disease is an important factor for pregnancy-related morbidity and mortality. Here, we report a case of Graves' disease detected for the first time in pregnancy, in a patient presenting with bi- ventricular heart failure, severe pulmonary hypertension and pre- eclampsia. Emphasis is placed on the spectrum of clinical presentations of Graves' disease, and the importance of considering this thyroid disorder as a possible aetiological factor for such a presentation in pregnancy. CASE PRESENTATION: A 30-year-old Bangladeshi-Bengali woman, in her 28th week of pregnancy presented with severe systemic hypertension, bi-ventricular heart failure and severe pulmonary hypertension with a moderately enlarged thyroid gland. She improved following the administration of high dose intravenous diuretics, and delivered a premature female baby of low birth weight per vaginally, twenty four hours later. Pre-eclampsia was diagnosed on the basis of hypertension first detected in the third trimester, 3+ oedema and mild proteinuria. Electrocardiography revealed sinus tachycardia with incomplete right bundle branch block and echocardiography showed severe pulmonary hypertension with an estimated pulmonary arterial systolic pressure of 73 mm Hg, septal and anterior wall hypokinesia with an ejection fraction of 51%, grade I mitral and tricuspid regurgitation. Thyroid function tests revealed a biochemically hyperthyroid state and positive anti- thyroid peroxidase antibodies was found. (99m)Technetium pertechnetate thyroid scans demonstrated diffuse toxic goiter as evidenced by an enlarged thyroid gland with intense radiotracer concentration all over the gland. The clinical and biochemical findings confirmed the diagnosis of Graves' disease. CONCLUSIONS: Graves' disease is an uncommon cause of bi-ventricular heart failure and severe pulmonary hypertension in pregnancy, and a high index of clinical suspicion is paramount to its effective diagnosis and treatment.