• AI
• PRISMA
• Preferred Reporting Items for Systematic Reviews and Meta-Analysis
• QUADAS-2
• Quality Assessment of Diagnostic Accuracy Studies version 2
• artificial intelligence
• deep learning
• diagnostic performance
• machine learning
• systematic literature review
• tuberculosis detection

• Humans
• Artificial Intelligence
• Tuberculosis/diagnosis
• Algorithms
• Neural Networks, Computer
• Deep Learning

• class activation map
• classification
• clinical variables
• discriminant analysis
• medical imaging

• chest x-ray
• deep learning
• explainable artificial intelligence
• fairness
• interpretability
• thoracic pathology

• Humans
• Radiography, Thoracic/methods
• Male
• Female
• Neural Networks, Computer
• ROC Curve
• Algorithms
• Deep Learning
• Middle Aged
• Adult
• Aged
• Area Under Curve
• Decision Trees

• Anatomical characteristics
• Convolutional neural network
• Machine learning
• Primary angle closure suspect
• Screening

• Humans
• Deep Learning
• Glaucoma, Angle-Closure/diagnostic imaging
• Glaucoma, Angle-Closure/diagnosis
• Cross-Sectional Studies
• Female
• Middle Aged
• Male
• Tomography, Optical Coherence
• Aged
• Anterior Eye Segment/diagnostic imaging
• Algorithms

• 82070964 National Natural Science Foundation of China
• 2022JC-60 Shaanxi Provincial Outstanding Youth Science Foundation Project
• 23JP151 Education Department of Shaanxi Provincial Government for Youth Innovation Team Research Program Project
• 2024GH-YBXM-20 International Scientific and Technological Cooperation Projects
• 83000-32030002 The Open Research Funds of the State Key Laboratory of Ophthalmology
• 2023-YBSF-304 Key R&D Plan of Shaanxi Province

• chest radiography
• deep learning
• ensemble learning
• modality-specific knowledge transfer
• pediatric
• pretext learning
• statistical significance

• Deep learning
• Medical imaging approaches
• Multi-organ cancer diagnosis

• Humans
• Deep Learning
• Image Interpretation, Computer-Assisted/methods
• Neoplasms/diagnosis

• artificial intelligence
• deep learning
• diagnostic accuracy
• medical imaging
• model interpretability
• pulmonary radiography

• grant number G2021171024L The Ministry of Science and Technology of China
• grant number 300203110029 The High-Level Talent Project of Chang'an University

• Chest X-ray
• Deep learning
• Lung nodules
• Stable diffusion
• Tuberculosis

• Humans
• Algorithms
• Radiography, Thoracic/methods
• Deep Learning
• Lung/diagnostic imaging
• Lung/pathology
• Tuberculosis/diagnostic imaging
• Tuberculosis/diagnosis
• Tuberculosis, Pulmonary/diagnostic imaging
• Lung Neoplasms/diagnostic imaging
• Lung Neoplasms/pathology
• Image Processing, Computer-Assisted/methods
• Diagnosis, Computer-Assisted/methods

• PID2019-108435RB-I00 Ministerio de Ciencia e Innovación
• TED2021-131201B-I00 Ministerio de Ciencia e Innovación
• PDC2022-133132-I00 Ministerio de Ciencia e Innovación
• ED431C 2020/24 Xunta de Galicia
• D481A 2021/196 Xunta de Galicia
• ED431G 2019/01 Xunta de Galicia

• U-Net
• artificial intelligence
• chest X-ray
• deep learning
• ensemble classifier
• semantic segmentation
• tuberculosis lesion

• A-ER-112-247 National Cheng Kung University Hospital
• 112-N04-2; 【109H500307】; 【111-1067-2】 National Yunlin University of Science and Technology

• combinatorial fusion
• convolutional neural network (CNN)
• deep learning
• lung X-ray images
• respiratory infections

• KAFGH_A_111005 Armed Forces General Hospital Kaohsiung Taiwan

• Multiple lung abnormalities
• artificial intelligence
• case report conclusion level
• chest X-ray imaging
• observer performance study

• Humans
• Artificial Intelligence
• Retrospective Studies
• Radiography, Thoracic/methods
• Radiologists
• Sensitivity and Specificity
• Observer Variation
• Female
• Male
• Lung/diagnostic imaging
• Middle Aged
• Adult
• Lung Diseases/diagnostic imaging
• Aged
• Adolescent
• Young Adult
• Radiographic Image Interpretation, Computer-Assisted/methods

• Domain translation
• Explainable artificial intelligence
• Generative adversarial networks
• Medical imaging
• Visual attribution

• Humans
• Alzheimer Disease/diagnostic imaging
• Databases, Factual
• Image Interpretation, Computer-Assisted/methods
• Neuroimaging/methods
• Algorithms

• active tuberculosis
• deep learning
• efficientnet
• kappa
• observer performance test

• computer-aided detection (CAD)
• convolutional neural network algorithm
• deep learning
• diagnosis
• radiography
• screening
• tuberculosis

• chest X-ray
• localization
• pulmonary tuberculosis
• visualization
• weakly supervised

• Humans
• X-Rays
• Radiography, Thoracic/methods
• Tuberculosis, Pulmonary/diagnostic imaging
• Radiography
• Tuberculosis

• Artificial Neural Network
• CNN
• Densenet201
• EfficientnetB0
• Tuberculosis

• Chest pathologies
• Chest radiography
• Classification
• Datasets
• Deep learning
• Feature extraction
• Image acquisition

• CT
• deep learning
• lung cancer
• uncertainty quantification

• Chest X-ray diagnosis
• Counterfactual reasoning
• Explainable AI
• Interpretable machine learning

• Humans
• Benchmarking
• Radiology
• Semantics

• R01 HL141813 NHLBI NIH HHS

• tuberculosis
• computational science

• COVID-19
• Pneumoconiosis
• chest X-ray
• interpretable deep learning
• pneumonia
• trusted AI
• tuberculosis

• artificial intelligence
• diagnostic accuracy
• medical imaging
• pulmonary tuberculosis
• sensitivity
• specificity

• deep learning
• ensemble learning
• lung segmentation
• medical image analysis
• transfer learning
• tuberculosis detection

• Chest radiography
• Deep learning
• Image classification
• Vision transformer
• X-Rays

• Humans
• COVID-19/diagnostic imaging
• Deep Learning
• Pneumonia/diagnostic imaging
• SARS-CoV-2
• X-Rays

In recent years, coronavirus (Covid-19) has evolved into one of the world’s leading life-threatening severe viral illnesses. A self-executing accord system might be a better option to stop Covid-19 from spreading due to its quick diagnostic option. Many researches have already investigated various deep learning techniques, which have a significant impact on the quick and precise early detection of Covid-19. Most of the existing techniques, though, have not been trained and tested using a significant amount of data. In this paper, we purpose a deep learning technique enabled Convolutional Neural Network (CNN) to automatically diagnose Covid-19 from chest x-rays. To train and test our model, 10,293 x-rays, including 2875 x-rays of Covid-19, were collected as a data set. The applied dataset consists of three groups of chest x-rays: Covid-19, pneumonia, and normal patients. The proposed approach achieved 98.5% accuracy, 98.9% specificity, 99.2% sensitivity, 99.2% precision, and 98.3% F1-score. Distinguishing Covid-19 patients from pneumonia patients using chest x-ray, particularly for human eyes is crucial since both diseases have nearly identical characteristics. To address this issue, we have categorized Covid-19 and pneumonia using x-rays, achieving a 99.60% accuracy rate. Our findings show that the proposed model might aid clinicians and researchers in rapidly detecting Covid-19 patients, hence facilitating the treatment of Covid-19 patients.

• coronavirus (covid-19)
• classification
• deep learning
• chest x-ray
• convolutional neural network (cnn)

• COVID-19
• Deep learning
• Grad-CAM
• LIME
• Pneumonia
• SHAP
• Tuberculosis
• eXplainable AI

• Humans
• COVID-19/diagnostic imaging
• Artificial Intelligence
• Deep Learning
• Pneumonia/diagnostic imaging
• Tuberculosis

• Deep Learning
• Machine Learning
• Rare Disease

• Humans
• Deep Learning
• Rare Diseases
• Quality of Life
• Neural Networks, Computer
• Nervous System Diseases

• R01 LM012895 NLM NIH HHS

Tuberculosis (TB) is an airborne disease caused by Mycobacterium tuberculosis. It is imperative to detect cases of TB as early as possible because if left untreated, there is a 70% chance of a patient dying within 10 years. The necessity for supplementary tools has increased in mid to low-income countries due to the rise of automation in healthcare sectors. The already limited resources are being heavily allocated towards controlling other dangerous diseases. Modern digital radiography (DR) machines, used for screening chest X-rays of potential TB victims are very practical. Coupled with computer-aided detection (CAD) with the aid of artificial intelligence, radiologists working in this field can really help potential patients. In this study, progressive resizing is introduced for training models to perform automatic inference of TB using chest X-ray images. ImageNet fine-tuned Normalization-Free Networks (NFNets) are trained for classification and the Score-Cam algorithm is utilized to highlight the regions in the chest X-Rays for detailed inference on the diagnosis. The proposed method is engineered to provide accurate diagnostics for both binary and multiclass classification. The models trained with this method have achieved 96.91% accuracy, 99.38% AUC, 91.81% sensitivity, and 98.42% specificity on a multiclass classification dataset. Moreover, models have also achieved top-1 inference metrics of 96% accuracy and 98% AUC for binary classification. The results obtained demonstrate that the proposed method can be used as a secondary decision tool in a clinical setting for assisting radiologists.

• CheXNet
• Grad-CAM
• chest X-ray radiographs
• coal worker pneumoconiosis
• computer-aided diagnosis
• deep learning
• ensemble learning
• machine learning classifiers
• occupational lung diseases
• pneumoconiosis

• Algorithms
• Dust
• Humans
• Lung Diseases
• Pneumoconiosis/diagnostic imaging
• X-Rays

We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong’s test is used to compare with the black-box model ROC and McNemar’s test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity (p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 (p = 0.407) and 0.935 (p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 (p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at https://doi.org/10.5281/zenodo.6373392.

• Deep Learning
• Emphysema/diagnostic imaging
• Humans
• Pulmonary Emphysema/diagnostic imaging
• Radiography
• Radiography, Thoracic/methods
• Radiologists
• Retrospective Studies

With the increasing incidence and mortality of pulmonary tuberculosis, in addition to tough and controversial disease management, time-wasting and resource-limited conventional approaches to the diagnosis and differential diagnosis of tuberculosis are still awkward issues, especially in countries with high tuberculosis burden and backwardness. In the meantime, the climbing proportion of drug-resistant tuberculosis poses a significant hazard to public health. Thus, auxiliary diagnostic tools with higher efficiency and accuracy are urgently required. Artificial intelligence (AI), which is not new but has recently grown in popularity, provides researchers with opportunities and technical underpinnings to develop novel, precise, rapid, and automated implements for pulmonary tuberculosis care, including but not limited to tuberculosis detection. In this review, we aimed to introduce representative AI methods, focusing on deep learning and radiomics, followed by definite descriptions of the state-of-the-art AI models developed using medical images and genetic data to detect pulmonary tuberculosis, distinguish the infection from other pulmonary diseases, and identify drug resistance of tuberculosis, with the purpose of assisting physicians in deciding the appropriate therapeutic schedule in the early stage of the disease. We also enumerated the challenges in maximizing the impact of AI in this field such as generalization and clinical utility of the deep learning models.

• Computer-Aided Diagnosis
• Picture Archiving and Communication System (PACS)
• chest X-ray (CXR)
• clinical validation
• deep learning

• COVID-19
• Chest X-ray
• Deep learning
• Lung disease
• Multichannel
• Pneumonia
• Stacking
• Transfer learning
• Tuberculosis

Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust model requires large, high-quality data with annotations that are expensive to obtain. This situation poses a conundrum that annually-collected chest x-rays cannot be utilized due to the absence of labels, especially in deprived areas. In this study, we present a framework named distillation for self-supervision and self-train learning (DISTL) inspired by the learning process of the radiologists, which can improve the performance of vision transformer simultaneously with self-supervision and self-training through knowledge distillation. In external validation from three hospitals for diagnosis of tuberculosis, pneumothorax, and COVID-19, DISTL offers gradually improved performance as the amount of unlabeled data increase, even better than the fully supervised model with the same amount of labeled data. We additionally show that the model obtained with DISTL is robust to various real-world nuisances, offering better applicability in clinical setting.

Although deep learning-based computer-aided diagnosis systems have recently achieved expert level performance, developing a robust model requires large, high-quality data with annotations. Here, the authors present a framework which can improve the performance of vision transformer simultaneously with self-supervision and self-training.

• Chest X-Ray
• Disease Localization
• Multi-Stage Classification
• Severity Assessment
• Superpixels

• COVID-19/diagnostic imaging
• Diagnosis, Computer-Assisted/methods
• Humans
• Lung Diseases
• Thorax
• X-Rays

• Deep learning
• Image analysis
• Image classification
• Sputum smear images
• Tuberculosis detection

• Humans
• Mycobacterium tuberculosis
• Sensitivity and Specificity
• Sputum/microbiology
• Tuberculosis/diagnosis
• Tuberculosis, Pulmonary/diagnosis

• Monte–Carlo Dropout
• chest X-ray
• confidence intervals
• deep learning
• mean average precision
• medical image segmentation
• tuberculosis
• uncertainty
• uncertainty quantification

• EfficientNets
• chest X-rays
• pulmonary sarcoidosis
• sarcoidosis detection
• stain normalization
• tuberculosis

• Humans
• Radiography
• Sarcoidosis/diagnostic imaging
• Staining and Labeling
• Tuberculosis
• Tuberculosis, Pulmonary/diagnostic imaging
• X-Rays

• PNURSP2022R293 Princess Nourah bint Abdulrahman University

Our objective was to develop deep learning models with chest radiograph data to predict healthcare costs and classify top-50% spenders. 21,872 frontal chest radiographs were retrospectively collected from 19,524 patients with at least 1-year spending data. Among the patients, 11,003 patients had 3 years of cost data, and 1678 patients had 5 years of cost data. Model performances were measured with area under the receiver operating characteristic curve (ROC-AUC) for classification of top-50% spenders and Spearman ρ for prediction of healthcare cost. The best model predicting 1-year (N = 21,872) expenditure achieved ROC-AUC of 0.806 [95% CI 0.793–0.819] for top-50% spender classification and ρ of 0.561 [0.536–0.586] for regression. Similarly, for predicting 3-year (N = 12,395) expenditure, ROC-AUC of 0.771 [0.750–0.794] and ρ of 0.524 [0.489–0.559]; for predicting 5-year (N = 1779) expenditure ROC-AUC of 0.729 [0.667–0.729] and ρ of 0.424 [0.324–0.529]. Our deep learning model demonstrated the feasibility of predicting health care expenditure as well as classifying top 50% healthcare spenders at 1, 3, and 5 year(s), implying the feasibility of combining deep learning with information-rich imaging data to uncover hidden associations that may allude to physicians. Such a model can be a starting point of making an accurate budget in reimbursement models in healthcare industries.

• convolutional
• efficient
• neural network
• radiology
• self-attention
• tuberculosis