Crowdsourcing pneumothorax annotations using machine learning annotations on the NIH chest X-ray dataset

Diagnostic evaluation of blunt chest trauma by imaging-based application of artificial intelligence: A review

Artificial intelligence (AI) is becoming increasingly integral in clinical practice, such as during imaging tasks associated with the diagnosis and evaluation of blunt chest trauma (BCT). Due to significant advances in imaging-based deep learning, recent studies have demonstrated the efficacy of AI in the diagnosis of BCT, with a focus on rib fractures, pulmonary contusion, hemopneumothorax and others, demonstrating significant clinical progress. However, the complicated nature of BCT presents challenges in providing a comprehensive diagnosis and prognostic evaluation, and current deep learning research concentrates on specific clinical contexts, limiting its utility in addressing BCT intricacies. Here, we provide a review of the available evidence surrounding the potential utility of AI in BCT, and additionally identify the challenges impeding its development. This review offers insights on how to optimize the role of AI in the diagnostic evaluation of BCT, which can ultimately enhance patient care and outcomes in this critical clinical domain.

Classification of Lung Diseases Using an Attention-Based Modified DenseNet Model

Lung diseases represent a significant global health threat, impacting both well-being and mortality rates. Diagnostic procedures such as Computed Tomography (CT) scans and X-ray imaging play a pivotal role in identifying these conditions. X-rays, due to their easy accessibility and affordability, serve as a convenient and cost-effective option for diagnosing lung diseases. Our proposed method utilized the Contrast-Limited Adaptive Histogram Equalization (CLAHE) enhancement technique on X-ray images to highlight the key feature maps related to lung diseases using DenseNet201. We have augmented the existing Densenet201 model with a hybrid pooling and channel attention mechanism. The experimental results demonstrate the superiority of our model over well-known pre-trained models, such as VGG16, VGG19, InceptionV3, Xception, ResNet50, ResNet152, ResNet50V2, ResNet152V2, MobileNetV2, DenseNet121, DenseNet169, and DenseNet201. Our model achieves impressive accuracy, precision, recall, and F1-scores of 95.34%, 97%, 96%, and 96%, respectively. We also provide visual insights into our model's decision-making process using Gradient-weighted Class Activation Mapping (Grad-CAM) to identify normal, pneumothorax, and atelectasis cases. The experimental results of our model in terms of heatmap may help radiologists improve their diagnostic abilities and labelling processes.

Clinical Applications, Challenges, and Recommendations for Artificial Intelligence in Musculoskeletal and Soft-Tissue Ultrasound: AJR Expert Panel Narrative Review

Artificial intelligence (AI) is increasingly used in clinical practice for musculoskeletal imaging tasks, such as disease diagnosis and image reconstruction. AI applications in musculoskeletal imaging have focused primarily on radiography, CT, and MRI. Although musculoskeletal ultrasound stands to benefit from AI in similar ways, such applications have been relatively underdeveloped. In comparison with other modalities, ultrasound has unique advantages and disadvantages that must be considered in AI algorithm development and clinical translation. Challenges in developing AI for musculoskeletal ultrasound involve both clinical aspects of image acquisition and practical limitations in image processing and annotation. Solutions from other radiology subspecialties (e.g., crowdsourced annotations coordinated by professional societies), along with use cases (most commonly rotator cuff tendon tears and palpable soft-tissue masses), can be applied to musculoskeletal ultrasound to help develop AI. To facilitate creation of high-quality imaging datasets for AI model development, technologists and radiologists should focus on increasing uniformity in musculoskeletal ultrasound performance and increasing annotations of images for specific anatomic regions. This Expert Panel Narrative Review summarizes available evidence regarding AI's potential utility in musculoskeletal ultrasound and challenges facing its development. Recommendations for future AI advancement and clinical translation in musculoskeletal ultrasound are discussed.

Deep Learning-based Diagnosis and Localization of Pneumothorax on Portable Supine Chest X-ray in Intensive and Emergency Medicine: A Retrospective Study

PURPOSE

To develop two deep learning-based systems for diagnosing and localizing pneumothorax on portable supine chest X-rays (SCXRs).

METHODS

For this retrospective study, images meeting the following inclusion criteria were included: (1) patient age ≥ 20 years; (2) portable SCXR; (3) imaging obtained in the emergency department or intensive care unit. Included images were temporally split into training (1571 images, between January 2015 and December 2019) and testing (1071 images, between January 2020 to December 2020) datasets. All images were annotated using pixel-level labels. Object detection and image segmentation were adopted to develop separate systems. For the detection-based system, EfficientNet-B2, DneseNet-121, and Inception-v3 were the architecture for the classification model; Deformable DETR, TOOD, and VFNet were the architecture for the localization model. Both classification and localization models of the segmentation-based system shared the UNet architecture.

RESULTS

In diagnosing pneumothorax, performance was excellent for both detection-based (Area under receiver operating characteristics curve [AUC]: 0.940, 95% confidence interval [CI]: 0.907-0.967) and segmentation-based (AUC: 0.979, 95% CI: 0.963-0.991) systems. For images with both predicted and ground-truth pneumothorax, lesion localization was highly accurate (detection-based Dice coefficient: 0.758, 95% CI: 0.707-0.806; segmentation-based Dice coefficient: 0.681, 95% CI: 0.642-0.721). The performance of the two deep learning-based systems declined as pneumothorax size diminished. Nonetheless, both systems were similar or better than human readers in diagnosis or localization performance across all sizes of pneumothorax.

CONCLUSIONS

Both deep learning-based systems excelled when tested in a temporally different dataset with differing patient or image characteristics, showing favourable potential for external generalizability.

Recent progress in transformer-based medical image analysis

The transformer is primarily used in the field of natural language processing. Recently, it has been adopted and shows promise in the computer vision (CV) field. Medical image analysis (MIA), as a critical branch of CV, also greatly benefits from this state-of-the-art technique. In this review, we first recap the core component of the transformer, the attention mechanism, and the detailed structures of the transformer. After that, we depict the recent progress of the transformer in the field of MIA. We organize the applications in a sequence of different tasks, including classification, segmentation, captioning, registration, detection, enhancement, localization, and synthesis. The mainstream classification and segmentation tasks are further divided into eleven medical image modalities. A large number of experiments studied in this review illustrate that the transformer-based method outperforms existing methods through comparisons with multiple evaluation metrics. Finally, we discuss the open challenges and future opportunities in this field. This task-modality review with the latest contents, detailed information, and comprehensive comparison may greatly benefit the broad MIA community.

“Quo Vadis Diagnosis”: Application of Informatics in Early Detection of Pneumothorax

A pneumothorax is a condition that occurs in the lung region when air enters the pleural space—the area between the lung and chest wall—causing the lung to collapse and making it difficult to breathe. This can happen spontaneously or as a result of an injury. The symptoms of a pneumothorax may include chest pain, shortness of breath, and rapid breathing. Although chest X-rays are commonly used to detect a pneumothorax, locating the affected area visually in X-ray images can be time-consuming and prone to errors. Existing computer technology for detecting this disease from X-rays is limited by three major issues, including class disparity, which causes overfitting, difficulty in detecting dark portions of the images, and vanishing gradient. To address these issues, we propose an ensemble deep learning model called PneumoNet, which uses synthetic images from data augmentation to address the class disparity issue and a segmentation system to identify dark areas. Finally, the issue of the vanishing gradient, which becomes very small during back propagation, can be addressed by hyperparameter optimization techniques that prevent the model from slowly converging and poorly performing. Our model achieved an accuracy of 98.41% on the Society for Imaging Informatics in Medicine pneumothorax dataset, outperforming other deep learning models and reducing the computation complexities in detecting the disease.

The 2021 SIIM-FISABIO-RSNA Machine Learning COVID-19 Challenge: Annotation and Standard Exam Classification of COVID-19 Chest Radiographs

We describe the curation, annotation methodology, and characteristics of the dataset used in an artificial intelligence challenge for detection and localization of COVID-19 on chest radiographs. The chest radiographs were annotated by an international group of radiologists into four mutually exclusive categories, including "typical," "indeterminate," and "atypical appearance" for COVID-19, or "negative for pneumonia," adapted from previously published guidelines, and bounding boxes were placed on airspace opacities. This dataset and respective annotations are available to researchers for academic and noncommercial use.

Learning to diagnose common thorax diseases on chest radiographs from radiology reports in Vietnamese

Deep learning, in recent times, has made remarkable strides when it comes to impressive performance for many tasks, including medical image processing. One of the contributing factors to these advancements is the emergence of large medical image datasets. However, it is exceedingly expensive and time-consuming to construct a large and trustworthy medical dataset; hence, there has been multiple research leveraging medical reports to automatically extract labels for data. The majority of this labor, however, is performed in English. In this work, we propose a data collecting and annotation pipeline that extracts information from Vietnamese radiology reports to provide accurate labels for chest X-ray (CXR) images. This can benefit Vietnamese radiologists and clinicians by annotating data that closely match their endemic diagnosis categories which may vary from country to country. To assess the efficacy of the proposed labeling technique, we built a CXR dataset containing 9,752 studies and evaluated our pipeline using a subset of this dataset. With an F1-score of at least 0.9923, the evaluation demonstrates that our labeling tool performs precisely and consistently across all classes. After building the dataset, we train deep learning models that leverage knowledge transferred from large public CXR datasets. We employ a variety of loss functions to overcome the curse of imbalanced multi-label datasets and conduct experiments with various model architectures to select the one that delivers the best performance. Our best model (CheXpert-pretrained EfficientNet-B2) yields an F1-score of 0.6989 (95% CI 0.6740, 0.7240), AUC of 0.7912, sensitivity of 0.7064 and specificity of 0.8760 for the abnormal diagnosis in general. Finally, we demonstrate that our coarse classification (based on five specific locations of abnormalities) yields comparable results to fine classification (twelve pathologies) on the benchmark CheXpert dataset for general anomaly detection while delivering better performance in terms of the average performance of all classes.

Chest L-Transformer: Local Features With Position Attention for Weakly Supervised Chest Radiograph Segmentation and Classification

We consider the problem of weakly supervised segmentation on chest radiographs. The chest radiograph is the most common means of screening and diagnosing thoracic diseases. Weakly supervised deep learning models have gained increasing popularity in medical image segmentation. However, these models are not suitable for the critical characteristics presented in chest radiographs: the global symmetry of chest radiographs and dependencies between lesions and their positions. These models extract global features from the whole image to make the image-level decision. The global symmetry can lead these models to misclassification of symmetrical positions of the lesions. Thoracic diseases often have special disease prone areas in chest radiographs. There is a relationship between the lesions and their positions. In this study, we propose a weakly supervised model, called Chest L-Transformer, to take these characteristics into account. Chest L-Transformer classifies an image based on local features to avoid the misclassification caused by the global symmetry. Moreover, associated with Transformer attention mechanism, Chest L-Transformer models the dependencies between the lesions and their positions and pays more attention to the disease prone areas. Chest L-Transformer is only trained with image-level annotations for lesion segmentation. Thus, Log-Sum-Exp voting and its variant are proposed to unify the pixel-level prediction with the image-level prediction. We demonstrate a significant segmentation performance improvement over the current state-of-the-art while achieving competitive classification performance.

Review on COVID-19 diagnosis models based on machine learning and deep learning approaches

COVID-19 is the disease evoked by a new breed of coronavirus called the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Recently, COVID-19 has become a pandemic by infecting more than 152 million people in over 216 countries and territories. The exponential increase in the number of infections has rendered traditional diagnosis techniques inefficient. Therefore, many researchers have developed several intelligent techniques, such as deep learning (DL) and machine learning (ML), which can assist the healthcare sector in providing quick and precise COVID-19 diagnosis. Therefore, this paper provides a comprehensive review of the most recent DL and ML techniques for COVID-19 diagnosis. The studies are published from December 2019 until April 2021. In general, this paper includes more than 200 studies that have been carefully selected from several publishers, such as IEEE, Springer and Elsevier. We classify the research tracks into two categories: DL and ML and present COVID-19 public datasets established and extracted from different countries. The measures used to evaluate diagnosis methods are comparatively analysed and proper discussion is provided. In conclusion, for COVID-19 diagnosing and outbreak prediction, SVM is the most widely used machine learning mechanism, and CNN is the most widely used deep learning mechanism. Accuracy, sensitivity, and specificity are the most widely used measurements in previous studies. Finally, this review paper will guide the research community on the upcoming development of machine learning for COVID-19 and inspire their works for future development. This review paper will guide the research community on the upcoming development of ML and DL for COVID-19 and inspire their works for future development.

U-shaped GAN for Semi-Supervised Learning and Unsupervised Domain Adaptation in High Resolution Chest Radiograph Segmentation

Deep learning has achieved considerable success in medical image segmentation. However, applying deep learning in clinical environments often involves two problems: (1) scarcity of annotated data as data annotation is time-consuming and (2) varying attributes of different datasets due to domain shift. To address these problems, we propose an improved generative adversarial network (GAN) segmentation model, called U-shaped GAN, for limited-annotated chest radiograph datasets. The semi-supervised learning approach and unsupervised domain adaptation (UDA) approach are modeled into a unified framework for effective segmentation. We improve GAN by replacing the traditional discriminator with a U-shaped net, which predicts each pixel a label. The proposed U-shaped net is designed with high resolution radiographs (1,024 × 1,024) for effective segmentation while taking computational burden into account. The pointwise convolution is applied to U-shaped GAN for dimensionality reduction, which decreases the number of feature maps while retaining their salient features. Moreover, we design the U-shaped net with a pretrained ResNet-50 as an encoder to reduce the computational burden of training the encoder from scratch. A semi-supervised learning approach is proposed learning from limited annotated data while exploiting additional unannotated data with a pixel-level loss. U-shaped GAN is extended to UDA by taking the source and target domain data as the annotated data and the unannotated data in the semi-supervised learning approach, respectively. Compared to the previous models dealing with the aforementioned problems separately, U-shaped GAN is compatible with varying data distributions of multiple medical centers, with efficient training and optimizing performance. U-shaped GAN can be generalized to chest radiograph segmentation for clinical deployment. We evaluate U-shaped GAN with two chest radiograph datasets. U-shaped GAN is shown to significantly outperform the state-of-the-art models.

Curation of the CANDID-PTX Dataset with Free-Text Reports

Supplemental material is available for this article. Keywords: Conventional Radiography, Thorax, Trauma, Ribs, Catheters, Segmentation, Diagnosis, Classification, Supervised Learning, Machine Learning © RSNA, 2021.

Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process

The purpose of this study was to evaluate the diagnostic performance achieved by using fully-connected small artificial neural networks (ANNs) and a simple training process, the Kim-Monte Carlo algorithm, to detect the location of pneumothorax in chest X-rays. A total of 1,000 chest X-ray images with pneumothorax were taken randomly from NIH (the National Institutes of Health) public image database and used as the training and test sets. Each X-ray image with pneumothorax was divided into 49 boxes for pneumothorax localization. For each of the boxes in the chest X-ray images contained in the test set, the area under the receiver operating characteristic (ROC) curve (AUC) was 0.882, and the sensitivity and specificity were 80.6% and 83.0%, respectively. In addition, a common currently used deep-learning method for image recognition, the convolution neural network (CNN), was also applied to the same dataset for comparison purposes. The performance of the fully-connected small ANN was better than that of the CNN. Regarding the diagnostic performances of the CNN with different activation functions, the CNN with a sigmoid activation function for fully-connected hidden nodes was better than the CNN with the rectified linear unit (RELU) activation function. This study showed that our approach can accurately detect the location of pneumothorax in chest X-rays, significantly reduce the time delay incurred when diagnosing urgent diseases such as pneumothorax, and increase the effectiveness of clinical practice and patient care.

Deep Learning for Diagnosis and Segmentation of Pneumothorax: The Results on the Kaggle Competition and Validation Against Radiologists

Pneumothorax is potentially a life-threatening disease that requires urgent diagnosis and treatment. The chest X-ray is the diagnostic modality of choice when pneumothorax is suspected. The computer-aided diagnosis of pneumothorax has received a dramatic boost in the last few years due to deep learning advances and the first public pneumothorax diagnosis competition with 15257 chest X-rays manually annotated by a team of 19 radiologists. This paper describes one of the top frameworks that participated in the competition. The framework investigates the benefits of combining the Unet convolutional neural network with various backbones, namely ResNet34, SE-ResNext50, SE-ResNext101, and DenseNet121. The paper presents a step-by-step instruction for the framework application, including data augmentation, and different pre- and post-processing steps. The performance of the framework was of 0.8574 measured in terms of the Dice coefficient. The second contribution of the paper is the comparison of the deep learning framework against three experienced radiologists on the pneumothorax detection and segmentation on challenging X-rays. We also evaluated how diagnostic confidence of radiologists affects the accuracy of the diagnosis and observed that the deep learning framework and radiologists find the same X-rays to be easy/difficult to analyze (p-value <1e4). Finally, the methodology of all top-performing teams from the competition leaderboard was analyzed to find the consistent methodological patterns of accurate pneumothorax detection and segmentation.

Pneumothorax detection in chest radiographs: optimizing artificial intelligence system for accuracy and confounding bias reduction using in-image annotations in algorithm training

OBJECTIVES

Diagnostic accuracy of artificial intelligence (AI) pneumothorax (PTX) detection in chest radiographs (CXR) is limited by the noisy annotation quality of public training data and confounding thoracic tubes (TT). We hypothesize that in-image annotations of the dehiscent visceral pleura for algorithm training boosts algorithm's performance and suppresses confounders.

METHODS

Our single-center evaluation cohort of 3062 supine CXRs includes 760 PTX-positive cases with radiological annotations of PTX size and inserted TTs. Three step-by-step improved algorithms (differing in algorithm architecture, training data from public datasets/clinical sites, and in-image annotations included in algorithm training) were characterized by area under the receiver operating characteristics (AUROC) in detailed subgroup analyses and referenced to the well-established "CheXNet" algorithm.

RESULTS

Performances of established algorithms exclusively trained on publicly available data without in-image annotations are limited to AUROCs of 0.778 and strongly biased towards TTs that can completely eliminate algorithm's discriminative power in individual subgroups. Contrarily, our final "algorithm 2" which was trained on a lower number of images but additionally with in-image annotations of the dehiscent pleura achieved an overall AUROC of 0.877 for unilateral PTX detection with a significantly reduced TT-related confounding bias.

CONCLUSIONS

We demonstrated strong limitations of an established PTX-detecting AI algorithm that can be significantly reduced by designing an AI system capable of learning to both classify and localize PTX. Our results are aimed at drawing attention to the necessity of high-quality in-image localization in training data to reduce the risks of unintentionally biasing the training process of pathology-detecting AI algorithms.

KEY POINTS

• Established pneumothorax-detecting artificial intelligence algorithms trained on public training data are strongly limited and biased by confounding thoracic tubes. • We used high-quality in-image annotated training data to effectively boost algorithm performance and suppress the impact of confounding thoracic tubes. • Based on our results, we hypothesize that even hidden confounders might be effectively addressed by in-image annotations of pathology-related image features.

Multi-Institutional Assessment and Crowdsourcing Evaluation of Deep Learning for Automated Classification of Breast Density

OBJECTIVE

We developed deep learning algorithms to automatically assess BI-RADS breast density.

METHODS

Using a large multi-institution patient cohort of 108,230 digital screening mammograms from the Digital Mammographic Imaging Screening Trial, we investigated the effect of data, model, and training parameters on overall model performance and provided crowdsourcing evaluation from the attendees of the ACR 2019 Annual Meeting.

RESULTS

Our best-performing algorithm achieved good agreement with radiologists who were qualified interpreters of mammograms, with a four-class κ of 0.667. When training was performed with randomly sampled images from the data set versus sampling equal number of images from each density category, the model predictions were biased away from the low-prevalence categories such as extremely dense breasts. The net result was an increase in sensitivity and a decrease in specificity for predicting dense breasts for equal class compared with random sampling. We also found that the performance of the model degrades when we evaluate on digital mammography data formats that differ from the one that we trained on, emphasizing the importance of multi-institutional training sets. Lastly, we showed that crowdsourced annotations, including those from attendees who routinely read mammograms, had higher agreement with our algorithm than with the original interpreting radiologists.

CONCLUSION

We demonstrated the possible parameters that can influence the performance of the model and how crowdsourcing can be used for evaluation. This study was performed in tandem with the development of the ACR AI-LAB, a platform for democratizing artificial intelligence.