Thorax Diseases Research Articles

Semi-Supervised Medical Image Classification With Relation-Driven Self-Ensembling Model

Training deep neural networks usually requires a large amount of labeled data to obtain good performance. However, in medical image analysis, obtaining high-quality labels for the data is laborious and expensive, as accurately annotating medical images demands expertise knowledge of the clinicians. In this paper, we present a novel relation-driven semi-supervised framework for medical image classification. It is a consistency-based method which exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations, and leverages a self-ensembling model to produce high-quality consistency targets for the unlabeled data. Considering that human diagnosis often refers to previous analogous cases to make reliable decisions, we introduce a novel sample relation consistency (SRC) paradigm to effectively exploit unlabeled data by modeling the relationship information among different samples. Superior to existing consistency-based methods which simply enforce consistency of individual predictions, our framework explicitly enforces the consistency of semantic relation among different samples under perturbations, encouraging the model to explore extra semantic information from unlabeled data. We have conducted extensive experiments to evaluate our method on two public benchmark medical image classification datasets, i.e., skin lesion diagnosis with ISIC 2018 challenge and thorax disease classification with ChestX-ray14. Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.

Classification and retrieval of thoracic diseases using patch-based visual words: a study on chest x-rays

This research work explores the Content-Based Medical Image Retrieval system (CBMIR) to categorization and retrieval of different types of common thoracic diseases such as Atelectasis, cardiomegaly, Effusion, Infiltration etc, based on local patch representation of ‘Bag of Visual Words’ approach, when performing patch-based image representation, the selected patch size has significant impact on image categorization and retrieval process. It is a challenging task in selecting the appropriate patch size to the current experimental dataset. Chest Xray8 medical image database is used, to analyze the impact of different patch size to categorize and retrieval of eight common thorax diseases. 1000 frontal view x-ray images is obtained (100 images from each category and 200 images combination of more than one disease) from the database. Different sizes of image patches (16 × 16 and 32 × 32) and different codebook sizes (500, 1000, 1500, 2000) created to identify best precision and recall values. From the excremental result, 32 × 32 patch size and 1500 codebook size gives the good precision and recall value using Radial Basis Function SVM kernel.

Deep learning model for thorax diseases detection

Despite the availability of radiology devices in some health care centers, thorax diseases are considered as one of the most common health problems, especially in rural areas. By exploiting the power of the Internet of things and specific platforms to analyze a large volume of medical data, the health of a patient could be improved earlier. In this paper, the proposed model is based on pre-trained ResNet-50 for diagnosing thorax diseases. Chest x-ray images are cropped to extract the rib cage part from the chest radiographs. ResNet-50 was re-train on Chest x-ray14 dataset where a chest radiograph images are inserted into the model to determine if the person is healthy or not. In the case of an unhealthy patient, the model can classify the disease into one of the fourteen chest diseases. The results show the ability of ResNet-50 in achieving impressive performance in classifying thorax diseases.

Fusion High-Resolution Network for Diagnosing ChestX-ray Images

The application of deep convolutional neural networks (CNN) in the field of medical image processing has attracted extensive attention and demonstrated remarkable progress. An increasing number of deep learning methods have been devoted to classifying ChestX-ray (CXR) images, and most of the existing deep learning methods are based on classic pretrained models, trained by global ChestX-ray images. In this paper, we are interested in diagnosing ChestX-ray images using our proposed Fusion High-Resolution Network (FHRNet). The FHRNet concatenates the global average pooling layers of the global and local feature extractors—it consists of three branch convolutional neural networks and is fine-tuned for thorax disease classification. Compared with the results of other available methods, our experimental results showed that the proposed model yields a better disease classification performance for the ChestX-ray 14 dataset, according to the receiver operating characteristic curve and area-under-the-curve score. An ablation study further confirmed the effectiveness of the global and local branch networks in improving the classification accuracy of thorax diseases.

Utilizing Knowledge Distillation in Deep Learning for Classification of Chest X-Ray Abnormalities

Automatic screening and diagnosis of lung abnormalities from chest X-ray images has been recently drawing attention from the computer vision and medical imaging communities. Previous studies of deep neural networks have predominantly demonstrated the effectiveness of lung disease binary classification procedures. However, large numbers of medical images-which can be labeled with a variety of existing or suspected pathologies-are required to be interpreted and reported upon daily by an individual radiologist; this poses a challenge in maintaining a consistently high diagnosis accuracy. In this paper, we present a competitive study of knowledge distillation (KD) in deep learning for classification of abnormalities in chest X-ray images. This method aims to either distill knowledge from cumbersome teacher models into lightweight student models or to self-train these student models, to generate weakly supervised multi-label lung disease classifications. Our approach was based on multi-task deep learning architectures that, in addition to multi-class classification, supported the visualizations utilized in saliency maps of the pathological regions where an abnormality was located. A self-training KD framework, in which the model learned from itself, was shown to outperform both the well-established baseline training procedure and the normal KD, achieving the AUC improvements of up to 6.39% and 3.89%, respectively. Through application to the publicly available ChestX-ray14 dataset, we demonstrated that our approach efficiently overcame the interdependency of 14 weakly annotated thorax diseases and facilitated the state-of-the-art classification compared with the current deep learning baselines.

Attention Mechanism in Radiologist-Level Thorax Diseases Detection

Abstract Chest X-ray images play an important role in diagnosing thorax diseases. They can show the complete state of the human chest, including the heart, lungs, ribs, etc. However, the diagnosis of diseases is mainly based on the location and morphology of diseased tissues, which requires our model to pay more attention to the lesion, so we choose to introduce the attention mechanism. In recent years, the development of deep neural networks has gradually shifted from increasing the depth of the network to increasing the complexity of the network, which is to improve the capacity of the network by introducing attention mechanism with almost no parameter increase. Multiple attention mechanisms have been proposed for visual tasks to augment convolutions. They have been proved to be powerful in the public datasets but which kind of attention is more effective on X-ray images has not been studied. This paper explores effectiveness of spatial attention and channel attention mechanisms on Chest X-ray 14 dataset and combines them together to improve the disease recognition capability of model. Our AUROC beat the benchmark by 7.7%.

Learning to Recognize Thoracic Disease in Chest X-Rays With Knowledge-Guided Deep Zoom Neural Networks

Automatic and accurate thorax disease diagnosis in Chest X-ray (CXR) image plays an essential role in clinical assist analysis. However, due to its imaging noise regions and the similarity of visual features between diseases and their surroundings, the precise analysis of thoracic disease becomes a challenging problem. In this study, we propose a novel knowledge-guided deep zoom neural network (KGZNet) which is a data-driven model. Our approach leverage prior medical knowledge to guide its training process, due to thoracic diseases typically limit within the lung regions. Also, we utilized weakly-supervised learning (WSL) to search for finer regions without using annotated samples. Learning on each scale consists of a classification sub-network. The KGZNet starts from global images, and iteratively generates discriminative part from coarse to fine; while a finer scale sub-network takes as input an amplified attended discriminative region from previous scales in a recurrent way. Specifically, we first train a robust modified U-Net model of lung segmentation and capture the lung area from the original CXR image through the Lung Region Generator. Then, guided by the attention heatmap, we obtain a finer discriminative lesion region from the lung region images by the Lesion Region Generator. Lastly, the most discriminative features knowledge is fused, and the complementary features information is learned for final disease prediction. Extensive experiments demonstrate that our method can effectively leverage discriminative region information, and significantly outperforms the other state-of-the-art methods in the thoracic disease recognition task. Furthermore, the proposed KGZNet can gradually learn the discriminative region from coarse to fine in a mutually reinforced way. The code is will available at: https://github.com/ISSE-AILab/KGZNet.

Morphological diagnostics of pathology of the thorax organs in HIV-infected patients of a phthisiopulmonology hospital.

Background. Intravital differential diagnostics of HIV-associated of the thorax pathology is complex. Currently in the diagnostic algorithm various mini-invasive diagnostic procedures with morphological examination of biopsy material are widely used. Objective – to evaluate the effectiveness of the morphological diagnostics of the thorax diseases in HIV-infected patients. Methods. A retrospective analysis of 205 cases of a morphological study of a biopsy and surgical material from hospitalized HIV-infected patients of a phthisiopulmonological profile over a 5-year period was carried out. Comparison of the histological conclusion with the final clinical diagnosis was made. Results. Among all hospitalized HIV patients in 45,5 % of cases in the diagnostic algorithm of the thorax pathology there was a need for a morphological study. Endoscopic procedures with a biopsy were performed in 93,6 % of cases; typical surgeries – in 5,8 % of cases. In 60,0 % of cases the material was obtained in video assisted thoracoscopy. Histological examination of the lungs was carried out in 23,4 %, lymph nodes in 25,4 % and parietal pleura in 50,7 % of cases. Conclusion. In 77,1 % of cases of all histological studies the final clinical diagnosis and histological conclusion coincided. In 12,7 % of the histological examination there was a clarification of the preliminary clinical diagnosis. The effectiveness of histological diagnostics of thorax diseases in HIV-infected patients was: lung pathology – 81,3 %, lymphatic system pathology – 84,6 % and pleural pathology – 95,2 %. The overall effectiveness of histological examination of biopsy and surgical material among hospitalized HIV-infected patients was 89,8 %.

Thorax disease classification with attention guided convolutional neural network

This paper considers the task of thorax disease diagnosis on chest X-ray (CXR) images. Most existing methods generally learn a network with global images as input. However, thorax diseases usually happen in (small) localized areas which are disease specific. Thus training CNNs using global images may be affected by the (excessive) irrelevant noisy areas. Besides, due to the poor alignment of some CXR images, the existence of irregular borders hinders the network performance. For addressing the above problems, we propose to integrate the global and local cues into a three-branch attention guided convolution neural network (AG-CNN) to identify thorax diseases. An attention guided mask inference based cropping strategy is proposed to avoid noise and improve alignment in the global branch. AG-CNN also integrates the global cues to compensate the lost discriminative cues by the local branch. Specifically, we first learn a global CNN branch using global images. Then, guided by the attention heatmap generated from the global branch, we infer a mask to crop a discriminative region from the global image. The local region is used for training a local CNN branch. Lastly, we concatenate the last pooling layers of both the global and local branches for fine-tuning the fusion branch. Experiments on the ChestX-ray14 dataset demonstrate that after integrating the local cues with the global information, the average AUC scores are improved by AG-CNN.

Chest X-Ray Image Classification on Common Thorax Diseases using GLCM and AlexNet Deep Features

Image processing has been progressing far in medical as it is one of the main techniques used in the development of medical imaging diagnosis system. Some of the medical imaging modalities are the Magnetic Resonance Imaging (MRI), Computed Tomography (CT) Scan, X-Ray and Ultrasound. The output from all of these modalities would later be reviewed by the expert for an accurate result. Ensemble methods in machine learning are able to provide an automatic detection that can be used in the development of computer aided diagnosis system which can aid the experts in making their diagnosis. This paper presents the investigation on the classification of fourteen thorax diseases using chest x-ray image from ChestX-Ray8 database using Grey Level Co-occurrence Matrix (GLCM) and AlexNet feature extraction which are process using supervised classifiers: Zero R, k-NN, Naive Bayes, PART, and J48 Tree. The classification accuracy result indicates that k-NN classifier gave the highest accuracy compare to the other classifiers with 47.51% accuracy for GLCM feature extraction method and 47.18% for AlexNet feature extraction method. The result shows that number of data by class and multilabelled data will influence the classifcation method. Data using GLCM feature extraction method has higher classification accuracy compared to AlexNet and required less processing step.

Thorax-Net: An Attention Regularized Deep Neural Network for Classification of Thoracic Diseases on Chest Radiography.

Deep learning techniques have been increasingly used to provide more accurate and more accessible diagnosis of thorax diseases on chest radiographs. However, due to the lack of dense annotation of large-scale chest radiograph data, this computer-aided diagnosis task is intrinsically a weakly supervised learning problem and remains challenging. In this paper, we propose a novel deep convolutional neural network called Thorax-Net to diagnose 14 thorax diseases using chest radiography. Thorax-Net consists of a classification branch and an attention branch. The classification branch serves as a uniform feature extraction-classification network to free users from the troublesome hand-crafted feature extraction and classifier construction. The attention branch exploits the correlation between class labels and the locations of pathological abnormalities via analyzing the feature maps learned by the classification branch. Feeding a chest radiograph to the trained Thorax-Net, a diagnosis is obtained by averaging and binarizing the outputs of two branches. The proposed Thorax-Net model has been evaluated against three state-of-the-art deep learning models using the patientwise official split of the ChestX-ray14 dataset and against other five deep learning models using the imagewise random data split. Our results show that Thorax-Net achieves an average per-class area under the receiver operating characteristic curve (AUC) of 0.7876 and 0.896 in both experiments, respectively, which are higher than the AUC values obtained by other deep models when they were all trained with no external data.

Dense networks with relative location awareness for thorax disease identification.

Chest X-ray is one of the most common examinations for diagnosing heart and lung diseases. Due to the existing of a large number of clinical cases, many automated diagnosis algorithms based on chest X-ray images have been proposed. To our knowledge, almost none of the previous auto-diagnosis algorithms consider the effect of relative location information on disease incidence. In this study, we propose to use relative location information to assist the identification of thorax diseases. In this work, U-Net is used to segment lung and heart from chest image. The relative location maps are computed through Euclidean distance transformation from segmented masks. By introducing the relative location information into the network, the usual location of disease is combined with the incidence. The proposed network is the fusion of two branches: mask branch and image branch. A mask branch is designed to be a bottom-up and top-down structure to extract relative location information. The structure has a large receptive field, which can extract more information for large lesion and contextual information for small lesion. The features learned from mask branch are fused with image branch, which is a 121-layers DenseNet. We compare our proposed method with four state-of-the-art methods on the largest public chest X-ray dataset: ChestX-ray14. The proposed method achieves the area under a curve of 0.820, which outperforms all the existing models and algorithms. This paper proposed a dense network with relative location information to identify thorax disease. The method combines the usual location of disease with the incidence for the first time and performs good.

A Novel Approach for Multi-Label Chest X-Ray Classification of Common Thorax Diseases

Chest X-ray (CXR) is one of the most common types of radiology examination for the diagnosis of thorax diseases. Computer-aided diagnosis (CAD) was developed to help radiologists to achieve diagnostic excellence in a short period of time and to enhance patient healthcare. In this paper, we seek to improve the performance of the CAD system in the task of thorax diseases diagnosis by providing a new method that combines the advantages of CNN models in image feature extraction with those of the problem transformation methods in the multi-label classification task. The experimental study is tested on two publicly available CXR datasets ChestX-ray14 (frontal view) and CheXpert (frontal and lateral views). The results show that our proposed method outperformed the current state of the art.

Dose Reduction Methods in Chest Computed Tomography

Introduction: Computed tomography is one of the most powerful tools for investigating thorax disease, because it shows progression of lung disease much clearer than chest radiography. Technical advances in CT scanners have led to some abilities for CT scanners such as coverage of larger volume, lower noise and ability for acquiring image in one respiratory phase. However, this will be accompanied by more radiation exposure to patient and research shows that CT gives higher exposure dose to patient in comparison with conventional radiography.1 Materials and Methods: In each computed tomography (CT), patient dose is dependent on the scan parameters. Scan parameters are included kV, mA, scan field of view (SFOV), rotation time, focal spot size, slice width and pitch. Also, shielding of sensitive organs such as breast which is not interest organ during chest CT scanning is one of the dose reduction methods. Furthermore, Type of scanner, methods and protocols of scanning, for example in multi-slice scanners there is some more cases like collimation, which effect on patient dose, and therefore all of these options should be adjusted, accurately. It is considerable that scan parameters such as reconstructed matrix and reconstruction algorithms have considered in this paper; however, these parameters do not impact directly on patient dose but they have some affects through changing the characteristics of the image indirectly. In this study twenty methods for radiation dose reduction in thorax CT were explained. Conclusion: According to the principle of ALARA, the aim of applying optimization techniques is to reduce the amount of receiving dose while maintaining image quality.

METHODS TO REDUCE IMPACT OF PAPER DUST ON WORKERS IN BALLER DEPARTMENT AT LITHO-OFFSET PRESSES WITH APPLICATION ON THE GENERAL ORGANIZATION FOR GOVERNMENT PRINTING OFFICES

Paper Dust is defined as fine particles of paper fibres, its fibrils and its powder or it is the particles of paper filler material which is falling during the process of passing paper reel in web litho-offset printing machineor during transfering paper sheets to printing machines or during shredding of scraps of paper resulting from shearing or trimming or Slit or Punching. Paper dust causes many health problems and thorax diseases to be treated to varying degrees according to several variables, including source distance, exposure periods, inhaled quantity, and particle properties such as size, shape, density and chemical composition. Paper dust particles maximum exposure limits in accordance to the Egyptian ministerial act no. (211) of 2003 year equals 10 milligram / m3 every 8 hours. So the aim of this research is to introduce several available engineering solutions to protect workers from the health risks resulting of exposure to paper dust which are as follows: Ventilation , Dust Collectors installation, Water Mist, and Respiratory protective Equipment (RPE), in addition to ensuring the optimal selection of filters used in it and their suitability to the material and its concentration on air surrounding the workers.

Deep Generative Classifiers for Thoracic Disease Diagnosis with Chest X-ray Images.

Thoracic diseases are very serious health problems that plague a large number of people. Chest X-ray is currently one of the most popular methods to diagnose thoracic diseases, playing an important role in the healthcare workflow. However, reading the chest X-ray images and giving an accurate diagnosis remain challenging tasks for expert radiologists. With the success of deep learning in computer vision, a growing number of deep neural network architectures were applied to chest X-ray image classification. However, most of the previous deep neural network classifiers were based on deterministic architectures which are usually very noise-sensitive and are likely to aggravate the overfitting issue. In this paper, to make a deep architecture more robust to noise and to reduce overfitting, we propose using deep generative classifiers to automatically diagnose thorax diseases from the chest X-ray images. Unlike the traditional deterministic classifier, a deep generative classifier has a distribution middle layer in the deep neural network. A sampling layer then draws a random sample from the distribution layer and input it to the following layer for classification. The classifier is generative because the class label is generated from samples of a related distribution. Through training the model with a certain amount of randomness, the deep generative classifiers are expected to be robust to noise and can reduce overfitting and then achieve good performances. We implemented our deep generative classifiers based on a number of well-known deterministic neural network architectures, and tested our models on the chest X-ray14 dataset. The results demonstrated the superiority of deep generative classifiers compared with the corresponding deep deterministic classifiers.

Multi-label chest X-ray image classification via category-wise residual attention learning

This paper considers the problem of multi-label thorax disease classification on chest X-ray images. Identifying one or more pathologies from a chest X-ray image is often hindered by the pathologies unrelated to the targets. In this paper, we address the above problem by proposing a category-wise residual attention learning (CRAL) framework. CRAL predicts the presence of multiple pathologies in a class-specific attentive view. It aims to suppress the obstacles of irrelevant classes by endowing small weights to the corresponding feature representation. Meanwhile, the relevant features would be strengthened by assigning larger weights. Specifically, the proposed framework consists of two modules: feature embedding module and attention learning module. The feature embedding module learns high-level features with a convolutional neural network (CNN) while the attention learning module focuses on exploring the assignment scheme of different categories. The attention module can be flexibly integrated into any feature embedding networks with end-to-end training. The comprehensive experiments are conducted on the Chest X-ray14 dataset. CRAL yields the average AUC score of 0.816 which is a new state of the art.

Weighted Focal Loss: An Effective Loss Function to Overcome Unbalance Problem of Chest X-ray14

X-ray film has been applied widely in the elementary diagnosis and screening of thorax diseases. The rapid development of deep learning has improved automatic diagnosis of thorax disease. But different thorax disease in database inevitably exist the problem of unbalanced quantity because of the different morbidity in real life. So, the restricted factor is not just the architecture of the models but the unbalanced problem of database. What’s more, different from the same problem of natural images, this unbalanced problem is not just the unbalanced quantity but also the unbalanced complexity of diagnosis between samples. In this study, we introduced the Focal Loss and proposed the W-FL (weight Focal Loss) function which makes the model pay more attention to the difficult samples and those kinds of diseases which have small quantity and protect the loss and computed gradients from overwhelming by easy negatives. We evaluate the efficiency of W-FL function on the public Chest X-ray14 database using prevailing per-trained models including AlexNet, Inception-v3 and ResNet. We exceed at least 2% average AUC value on 14 different thorax diseases than the W-CEL function which is commonly proposed to solve the unbalanced problem in this database.

Three- dimensional reconstruction of the thorax in the mongoose (Herpestes ichneumon)

Three- dimensional (3D) reconstruction obtained by using multidetector computed tomography (MDCT) images have widely been used in anatomical studies. Thorax is one of the most important body cavities necessary for the protection of lungs and heart in mammals. Two adult mongooses (1 male, 1 female) obtained from traffic accidents were used in this study. The images obtained from MDCT were stacked and 3D reconstruction of thorax was performed by overlaying images using a 3D modeling software (Mimics 13.1). Some measurements of thoracic cavity, lungs and sternum were taken from the reconstructive images of mongoose and indexes were calculated from these measurements. The morphometric parameters were recorded for both sexes. From the study, it could be concluded that the thoracic cavity, lungs and sternum imagings and findings revealed by 3D modeling techniques can be utilized for anatomical training of wild animals. This study is expected to help in the diagnosis and treatment of thorax diseases in wild animals.

FACTORS AFFECTING QUALITY OF LIFE AND LEVEL OF SOCIAL SUPPORT IN CANCER PATIENTS

Background: When people face health problems, their life satisfaction levels and social relations could be ruined. When it comes to an eerie, deadly and chronic disease like cancer, the individual is much more likely to be affected by it.
 Objective: This descriptive study aims to identify quality of life and level of social support and the affecting factors in cancer patients.
 Methods: The sample included 170 patients who applied to internal diseases, radiation oncology, thorax diseases clinics and chemotherapy polyclinic in a university hospital in Turkey between March and August, 2005, who met the research criteria, and who volunteered to participate in the study. The sample represented 20 % of the target population. Data were collected through SF-36 Quality of Life Scale and Multidimensional Scale of perceived social support.
 Results: The patients’ global quality of life mean score was found 38.67 ± 13.64, and mean score for the perceived social support was found 59.19 ± 17.5. Global quality of life score was higher in those who underwent an operation and who received ambulatory health care. Although global quality of life was not influenced by the gender variable, male patients’ level of well-being was found to be higher. Perceived social support total score was found to be higher in those who knew about their disease. Family support was found to be higher in those who were married and who lived in town; it was found to be low in those who had low socio-economic level and who received inpatient treatment. Friend support was found to be high in those who knew about their disease.
 Conclusion: There was a linear relationship between perceived social support and quality of life. It is recommended that more studies with wider groups of participants would shed more light to the issue of identifying quality of life, social support level and the relationships between them in cancer patients.