Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization.
Ontology highlight
ABSTRACT:
SUBMITTER: Pasa F
PROVIDER: S-EPMC6472370 | biostudies-literature | 2019 Apr
REPOSITORIES: biostudies-literature
Publications
Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization.
Pasa F F Golkov V V Pfeiffer F F Cremers D D Pfeiffer D D
Scientific reports 20190418 1
Automated diagnosis of tuberculosis (TB) from chest X-Rays (CXR) has been tackled with either hand-crafted algorithms or machine learning approaches such as support vector machines (SVMs) and convolutional neural networks (CNNs). Most deep neural network applied to the task of tuberculosis diagnosis have been adapted from natural image classification. These models have a large number of parameters as well as high hardware requirements, which makes them prone to overfitting and harder to deploy i ...[more]
Similar Datasets
Project description:BackgroundEarly detection and management of sarcopenia is of clinical importance. We aimed to develop a chest X-ray-based deep learning model to predict presence of sarcopenia.MethodsData of participants who visited osteoporosis clinic at Severance Hospital, Seoul, South Korea, between January 2020 and June 2021 were used as derivation cohort as split to train, validation and test set (65:15:20). A community-based older adults cohort (KURE) was used as external test set. Sarcopenia was defined based on Asian Working Group 2019 guideline. A deep learning model was trained to predict appendicular lean mass (ALM), handgrip strength (HGS) and chair rise test performance from chest X-ray images; then the machine learning model (SARC-CXR score) was built using the age, sex, body mass index and chest X-ray predicted muscle parameters along with estimation uncertainty values.ResultsMean age of the derivation cohort (n = 926; women n = 700, 76%; sarcopenia n = 141, 15%) and the external test (n = 149; women n = 95, 64%; sarcopenia n = 18, 12%) cohort was 61.4 and 71.6 years, respectively. In the internal test set (a hold-out set, n = 189, from the derivation cohort) and the external test set (n = 149), the concordance correlation coefficient for ALM prediction was 0.80 and 0.76, with an average difference of 0.18 ± 2.71 and 0.21 ± 2.28, respectively. Gradient-weight class activation mapping for deep neural network models to predict ALM and HGS commonly showed highly weight pixel values at bilateral lung fields and part of the cardiac contour. SARC-CXR score showed good discriminatory performance for sarcopenia in both internal test set [area under the receiver-operating characteristics curve (AUROC) 0.813, area under the precision-recall curve (AUPRC) 0.380, sensitivity 0.844, specificity 0.739, F1-score 0.540] and external test set (AUROC 0.780, AUPRC 0.440, sensitivity 0.611, specificity 0.855, F1-score 0.458). Among SARC-CXR model features, predicted low ALM from chest X-ray was the most important predictor of sarcopenia based on SHapley Additive exPlanations values. Higher estimation uncertainty of HGS contributed to elevate the predicted risk of sarcopenia. In internal test set, SARC-CXR score showed better discriminatory performance than SARC-F score (AUROC 0.813 vs. 0.691, P = 0.029).ConclusionsChest X-ray-based deep leaning model improved detection of sarcopenia, which merits further investigation.
| S-EPMC9891971 | biostudies-literature
Project description:In today's world, we find ourselves struggling to fight one of the worst pandemics in the history of humanity known as COVID-2019 caused by a coronavirus. When the virus reaches the lungs, we observe ground-glass opacity in the chest X-ray due to fibrosis in the lungs. Due to the significant differences between X-ray images of an infected and non-infected person, artificial intelligence techniques can be used to identify the presence and severity of the infection. We propose a classification model that can analyze the chest X-rays and help in the accurate diagnosis of COVID-19. Our methodology classifies the chest X-rays into four classes viz. normal, pneumonia, tuberculosis (TB), and COVID-19. Further, the X-rays indicating COVID-19 are classified on a severity-basis into mild, medium, and severe. The deep learning model used for the classification of pneumonia, TB, and normal is VGG-16 with a test accuracy of 95.9 %. For the segregation of normal pneumonia and COVID-19, the DenseNet-161 was used with a test accuracy of 98.9 %, whereas the ResNet-18 worked best for severity classification achieving a test accuracy up to 76 %. Our approach allows mass screening of the people using X-rays as a primary validation for COVID-19.Supplementary informationThe online version contains supplementary material available at 10.1007/s42979-021-00695-5.
| S-EPMC8152712 | biostudies-literature
Project description:The world is suffering from an existential global health crisis known as the COVID-19 pandemic. Countries like India, Bangladesh, and other developing countries are still having a slow pace in the detection of COVID-19 cases. Therefore, there is an urgent need for fast detection with clear visualization of infection is required using which a suspected patient of COVID-19 could be saved. In the recent technological advancements, the fusion of deep learning classifiers and medical images provides more promising results corresponding to traditional RT-PCR testing while making detection and predictions about COVID-19 cases with increased accuracy. In this paper, we have proposed a deep transfer learning algorithm that accelerates the detection of COVID-19 cases by using X-ray and CT-Scan images of the chest. It is because, in COVID-19, initial screening of chest X-ray (CXR) may provide significant information in the detection of suspected COVID-19 cases. We have considered three datasets known as 1) COVID-chest X-ray, 2) SARS-COV-2 CT-scan, and 3) Chest X-Ray Images (Pneumonia). In the obtained results, the proposed deep learning model can detect the COVID-19 positive cases in ≤ 2 seconds which is faster than RT-PCR tests currently being used for detection of COVID-19 cases. We have also established a relationship between COVID-19 patients along with the Pneumonia patients which explores the pattern between Pneumonia and COVID-19 radiology images. In all the experiments, we have used the Grad-CAM based color visualization approach in order to clearly interpretate the detection of radiology images and taking further course of action.
| S-EPMC7413068 | biostudies-literature
Project description:Tuberculosis affects various tissues, including the lungs, kidneys, and brain. According to the medical report published by the World Health Organization (WHO) in 2020, approximately ten million people have been infected with tuberculosis. U-NET, a preferred method for detecting tuberculosis-like cases, is a convolutional neural network developed for segmentation in biomedical image processing. The proposed RNGU-NET architecture is a new segmentation technique combining the ResNet, Non-Local Block, and Gate Attention Block architectures. In the RNGU-NET design, the encoder phase is strengthened with ResNet, and the decoder phase incorporates the Gate Attention Block. The key innovation lies in the proposed Local Non-Local Block architecture, overcoming the bottleneck issue in U-Net models. In this study, the effectiveness of the proposed model in tuberculosis segmentation is compared to the U-NET, U-NET+ResNet, and RNGU-NET algorithms using the Shenzhen dataset. According to the results, the RNGU-NET architecture achieves the highest accuracy rate of 98.56%, Dice coefficient of 97.21%, and Jaccard index of 96.87% in tuberculosis segmentation. Conversely, the U-NET model exhibits the lowest accuracy and Jaccard index scores, while U-NET+ResNet has the poorest Dice coefficient. These findings underscore the success of the proposed RNGU-NET method in tuberculosis segmentation.
| S-EPMC10909175 | biostudies-literature
Project description:IntroductionChest ultrasound is increasingly used to radiologically diagnose childhood pneumonia, but there are limited data on its use for pulmonary tuberculosis (PTB).AimCompare chest ultrasound with a chest X-ray (CXR) findings.MethodsChildren (up to 13 years) with suspected PTB were enrolled. Bedside chest ultrasound findings were compared to CXR. The analysis was stratified by PTB category: confirmed PTB (microbiologically confirmed), unconfirmed PTB (clinical diagnosis with negative microbiological tests), or unlikely PTB (other respiratory diseases with improvement without tuberculosis treatment).ResultsOne hundred fifty-nine children were enrolled (57% boys, median age 26.6 months [interquartile range 15.1-59.3]). Ultrasound detected abnormalities in 72% (n?=?114), CXR in 56% (n?=?89), P?<?.001. Pleural effusion was detected on ultrasound in 15% (n?=?24) compared 9% (n?=?14) on CXR, P?=?.004, more in confirmed PTB (33%, n?=?12 vs 8%, n?=?4 unlikely PTB, P?=?.013). Ultrasound detected enlarged mediastinal lymph nodes more commonly (22%, n?=?25) than CXR (6%, n?=?10, P?=?.001); the size of lymph nodes in the unlikely category (1.0?cm) was smaller than the other two PTB categories (1.4 and 1.5?cm, P?=?.001). Inter-reader agreement (kappa Cohen) was higher for ultrasound than CXR for several findings (consolidation 0.67 vs 0.47, pleural effusion 0.86 vs 0.56, enlarged lymph nodes 0.56 vs 0.27).ConclusionUltrasound detected abnormalities more frequently than CXR with the higher inter-reader agreement; ultrasound abnormalities were most common in children with confirmed PTB. Ultrasound is a promising modality for detecting abnormalities in PTB. Further studies should evaluate the diagnostic accuracy of ultrasound against a gold standard.
| S-EPMC6899616 | biostudies-literature
Project description:Medical imaging refers to visualization techniques to provide valuable information about the internal structures of the human body for clinical applications, diagnosis, treatment, and scientific research. Segmentation is one of the primary methods for analyzing and processing medical images, which helps doctors diagnose accurately by providing detailed information on the body's required part. However, segmenting medical images faces several challenges, such as requiring trained medical experts and being time-consuming and error-prone. Thus, it appears necessary for an automatic medical image segmentation system. Deep learning algorithms have recently shown outstanding performance for segmentation tasks, especially semantic segmentation networks that provide pixel-level image understanding. By introducing the first fully convolutional network (FCN) for semantic image segmentation, several segmentation networks have been proposed on its basis. One of the state-of-the-art convolutional networks in the medical image field is U-Net. This paper presents a novel end-to-end semantic segmentation model, named Ens4B-UNet, for medical images that ensembles four U-Net architectures with pre-trained backbone networks. Ens4B-UNet utilizes U-Net's success with several significant improvements by adapting powerful and robust convolutional neural networks (CNNs) as backbones for U-Nets encoders and using the nearest-neighbor up-sampling in the decoders. Ens4B-UNet is designed based on the weighted average ensemble of four encoder-decoder segmentation models. The backbone networks of all ensembled models are pre-trained on the ImageNet dataset to exploit the benefit of transfer learning. For improving our models, we apply several techniques for training and predicting, including stochastic weight averaging (SWA), data augmentation, test-time augmentation (TTA), and different types of optimal thresholds. We evaluate and test our models on the 2019 Pneumothorax Challenge dataset, which contains 12,047 training images with 12,954 masks and 3,205 test images. Our proposed segmentation network achieves a 0.8608 mean Dice similarity coefficient (DSC) on the test set, which is among the top one-percent systems in the Kaggle competition.
| S-EPMC8279140 | biostudies-literature
Project description:BackgroundThe health crisis resulting from the global COVID-19 pandemic highlighted more than ever the need for rapid, reliable and safe methods of diagnosis and monitoring of respiratory diseases. To study pulmonary involvement in detail, one of the most common resources is the use of different lung imaging modalities (like chest radiography) to explore the possible affected areas.MethodsThe study of patient characteristics like sex and age in pathologies of this type is crucial for gaining knowledge of the disease and for avoiding biases due to the clear scarcity of data when developing representative systems. In this work, we performed an analysis of these factors in chest X-ray images to identify biases. Specifically, 11 imbalance scenarios were defined with female and male COVID-19 patients present in different proportions for the sex analysis, and 6 scenarios where only one specific age range was used for training for the age factor. In each study, 3 different approaches for automatic COVID-19 screening were used: Normal vs COVID-19, Pneumonia vs COVID-19 and Non-COVID-19 vs COVID-19. The study was validated using two public chest X-ray datasets, allowing a reliable analysis to support the clinical decision-making process.ResultsThe results for the sex-related analysis indicate this factor slightly affects the system in the Normal VS COVID-19 and Pneumonia VS COVID-19 approaches, although the identified differences are not relevant enough to worsen considerably the system. Regarding the age-related analysis, this factor was observed to be influencing the system in a more consistent way than the sex factor, as it was present in all considered scenarios. However, this worsening does not represent a major factor, as it is not of great magnitude.ConclusionsMultiple studies have been conducted in other fields in order to determine if certain patient characteristics such as sex or age influenced these deep learning systems. However, to the best of our knowledge, this study has not been done for COVID-19 despite the urgency and lack of COVID-19 chest x-ray images. The presented results evidenced that the proposed methodology and tested approaches allow a robust and reliable analysis to support the clinical decision-making process in this pandemic scenario.
| S-EPMC9046709 | biostudies-literature
Project description:A newly emerged coronavirus (COVID-19) seriously threatens human life and health worldwide. In coping and fighting against COVID-19, the most critical step is to effectively screen and diagnose infected patients. Among them, chest X-ray imaging technology is a valuable imaging diagnosis method. The use of computer-aided diagnosis to screen X-ray images of COVID-19 cases can provide experts with auxiliary diagnosis suggestions, which can reduce the burden of experts to a certain extent. In this study, we first used conventional transfer learning methods, using five pre-trained deep learning models, which the Xception model showed a relatively ideal effect, and the diagnostic accuracy reached 96.75%. In order to further improve the diagnostic accuracy, we propose an efficient diagnostic method that uses a combination of deep features and machine learning classification. It implements an end-to-end diagnostic model. The proposed method was tested on two datasets and performed exceptionally well on both of them. We first evaluated the model on 1102 chest X-ray images. The experimental results show that the diagnostic accuracy of Xception + SVM is as high as 99.33%. Compared with the baseline Xception model, the diagnostic accuracy is improved by 2.58%. The sensitivity, specificity and AUC of this model reached 99.27%, 99.38% and 99.32%, respectively. To further illustrate the robustness of our method, we also tested our proposed model on another dataset. Finally also achieved good results. Compared with related research, our proposed method has higher classification accuracy and efficient diagnostic performance. Overall, the proposed method substantially advances the current radiology based methodology, it can be very helpful tool for clinical practitioners and radiologists to aid them in diagnosis and follow-up of COVID-19 cases.
| S-EPMC7671547 | biostudies-literature
Project description:The Coronavirus (COVID-19) pandemic has created havoc on humanity by causing millions of deaths and adverse physical and mental health effects. To prepare humankind for the fast and efficient detection of the virus and its variants shortly, COVID-19 detection using Artificial Intelligence and Computer-Aided Diagnosis has been the subject of several studies. To detect COVID-19, there are numerous publicly accessible datasets of Chest X-rays that the researchers have combined to solve the problem of inadequate data. The cause for concern here is that in combining two or more datasets, some of the images might be duplicates, so a curated dataset has been used in this study, taken from an author's paper. This dataset consists of 1281 COVID-19, 3270 Normal X-rays, and 1656 viral-pneumonia infected Chest X-ray images. Dataset has been pre-processed and divided carefully to ensure that there are no duplicate images. A comparative study on many traditional pre-trained models was performed, analyzing top-performing models. Fine-tuned InceptionV3, Modified EfficientNet B0&B1 produced an accuracy of 99.78% on binary classification, i.e., covid-19 infected and normal Chest X-ray image. ResNetV2 had a classification accuracy of 97.90% for 3-class classification i.e., covid-19 infected, normal, and pneumonia. Furthermore, a trailblazing custom CNN-based model, CoviXNet, has been proposed consisting of 15 layers that take efficiency into account. The proposed model CoviXNet exhibited a 10-fold accuracy of 99.47% on binary classification and 96.61% on 3-class. CoviXNet has shown phenomenal performance with exceptional accuracy and minimum computational cost. We anticipate that this comparative study, along with the proposed model CoviXNet, can assist medical centers with the efficient real-life detection of Coronavirus.
| S-EPMC9174225 | biostudies-literature
Project description:Background and objectiveThe novel Coronavirus also called COVID-19 originated in Wuhan, China in December 2019 and has now spread across the world. It has so far infected around 1.8 million people and claimed approximately 114,698 lives overall. As the number of cases are rapidly increasing, most of the countries are facing shortage of testing kits and resources. The limited quantity of testing kits and increasing number of daily cases encouraged us to come up with a Deep Learning model that can aid radiologists and clinicians in detecting COVID-19 cases using chest X-rays.MethodsIn this study, we propose CoroNet, a Deep Convolutional Neural Network model to automatically detect COVID-19 infection from chest X-ray images. The proposed model is based on Xception architecture pre-trained on ImageNet dataset and trained end-to-end on a dataset prepared by collecting COVID-19 and other chest pneumonia X-ray images from two different publically available databases.ResultsCoroNet has been trained and tested on the prepared dataset and the experimental results show that our proposed model achieved an overall accuracy of 89.6%, and more importantly the precision and recall rate for COVID-19 cases are 93% and 98.2% for 4-class cases (COVID vs Pneumonia bacterial vs pneumonia viral vs normal). For 3-class classification (COVID vs Pneumonia vs normal), the proposed model produced a classification accuracy of 95%. The preliminary results of this study look promising which can be further improved as more training data becomes available.ConclusionCoroNet achieved promising results on a small prepared dataset which indicates that given more data, the proposed model can achieve better results with minimum pre-processing of data. Overall, the proposed model substantially advances the current radiology based methodology and during COVID-19 pandemic, it can be very helpful tool for clinical practitioners and radiologists to aid them in diagnosis, quantification and follow-up of COVID-19 cases.
| S-EPMC7274128 | biostudies-literature