Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration

Improving deep learning U-Net++ by discrete wavelet and attention gate mechanisms for effective pathological lung segmentation in chest X-ray imaging

Since its introduction in 2015, the U-Net architecture used in Deep Learning has played a crucial role in medical imaging. Recognized for its ability to accurately discriminate small structures, the U-Net has received more than 2600 citations in academic literature, which motivated continuous enhancements to its architecture. In hospitals, chest radiography is the primary diagnostic method for pulmonary disorders, however, accurate lung segmentation in chest X-ray images remains a challenging task, primarily due to the significant variations in lung shapes and the presence of intense opacities caused by various diseases. This article introduces a new approach for the segmentation of lung X-ray images. Traditional max-pooling operations, commonly employed in conventional U-Net++ models, were replaced with the discrete wavelet transform (DWT), offering a more accurate down-sampling technique that potentially captures detailed features of lung structures. Additionally, we used attention gate (AG) mechanisms that enable the model to focus on specific regions in the input image, which improves the accuracy of the segmentation process. When compared with current techniques like Atrous Convolutions, Improved FCN, Improved SegNet, U-Net, and U-Net++, our method (U-Net++-DWT) showed remarkable efficacy, particularly on the Japanese Society of Radiological Technology dataset, achieving an accuracy of 99.1%, specificity of 98.9%, sensitivity of 97.8%, Dice Coefficient of 97.2%, and Jaccard Index of 96.3%. Its performance on the Montgomery County dataset further demonstrated its consistent effectiveness. Moreover, when applied to additional datasets of Chest X-ray Masks and Labels and COVID-19, our method maintained high performance levels, achieving up to 99.3% accuracy, thereby underscoring its adaptability and potential for broad applications in medical imaging diagnostics.

Efficient Generative-Adversarial U-Net for Multi-Organ Medical Image Segmentation

Manual labeling of lesions in medical image analysis presents a significant challenge due to its labor-intensive and inefficient nature, which ultimately strains essential medical resources and impedes the advancement of computer-aided diagnosis. This paper introduces a novel medical image-segmentation framework named Efficient Generative-Adversarial U-Net (EGAUNet), designed to facilitate rapid and accurate multi-organ labeling. To enhance the model's capability to comprehend spatial information, we propose the Global Spatial-Channel Attention Mechanism (GSCA). This mechanism enables the model to concentrate more effectively on regions of interest. Additionally, we have integrated Efficient Mapping Convolutional Blocks (EMCB) into the feature-learning process, allowing for the extraction of multi-scale spatial information and the adjustment of feature map channels through optimized weight values. Moreover, the proposed framework progressively enhances its performance by utilizing a generative-adversarial learning strategy, which contributes to improvements in segmentation accuracy. Consequently, EGAUNet demonstrates exemplary segmentation performance on public multi-organ datasets while maintaining high efficiency. For instance, in evaluations on the CHAOS T2SPIR dataset, EGAUNet achieves approximately 2% higher performance on the Jaccard metric, 1% higher on the Dice metric, and nearly 3% higher on the precision metric in comparison to advanced networks such as Swin-Unet and TransUnet.

Leveraging anatomical constraints with uncertainty for pneumothorax segmentation

Background

Pneumothorax is a medical emergency caused by the abnormal accumulation of air in the pleural space-the potential space between the lungs and chest wall. On 2D chest radiographs, pneumothorax occurs within the thoracic cavity and outside of the mediastinum, and we refer to this area as "lung + space." While deep learning (DL) has increasingly been utilized to segment pneumothorax lesions in chest radiographs, many existing DL models employ an end-to-end approach. These models directly map chest radiographs to clinician-annotated lesion areas, often neglecting the vital domain knowledge that pneumothorax is inherently location-sensitive.

Methods

We propose a novel approach that incorporates the lung + space as a constraint during DL model training for pneumothorax segmentation on 2D chest radiographs. To circumvent the need for additional annotations and to prevent potential label leakage on the target task, our method utilizes external datasets and an auxiliary task of lung segmentation. This approach generates a specific constraint of lung + space for each chest radiograph. Furthermore, we have incorporated a discriminator to eliminate unreliable constraints caused by the domain shift between the auxiliary and target datasets.

Results

Our results demonstrated considerable improvements, with average performance gains of 4.6%, 3.6%, and 3.3% regarding intersection over union, dice similarity coefficient, and Hausdorff distance. These results were consistent across six baseline models built on three architectures (U-Net, LinkNet, or PSPNet) and two backbones (VGG-11 or MobileOne-S0). We further conducted an ablation study to evaluate the contribution of each component in the proposed method and undertook several robustness studies on hyper-parameter selection to validate the stability of our method.

Conclusions

The integration of domain knowledge in DL models for medical applications has often been underemphasized. Our research underscores the significance of incorporating medical domain knowledge about the location-specific nature of pneumothorax to enhance DL-based lesion segmentation and further bolster clinicians' trust in DL tools. Beyond pneumothorax, our approach is promising for other thoracic conditions that possess location-relevant characteristics.

Development and Validation of Deep Learning-Based Infectivity Prediction in Pulmonary Tuberculosis Through Chest Radiography: Retrospective Study

BACKGROUND

Pulmonary tuberculosis (PTB) poses a global health challenge owing to the time-intensive nature of traditional diagnostic tests such as smear and culture tests, which can require hours to weeks to yield results.

OBJECTIVE

This study aimed to use artificial intelligence (AI)-based chest radiography (CXR) to evaluate the infectivity of patients with PTB more quickly and accurately compared with traditional methods such as smear and culture tests.

METHODS

We used DenseNet121 and visualization techniques such as gradient-weighted class activation mapping and local interpretable model-agnostic explanations to demonstrate the decision-making process of the model. We analyzed 36,142 CXR images of 4492 patients with PTB obtained from Severance Hospital, focusing specifically on the lung region through segmentation and cropping with TransUNet. We used data from 2004 to 2020 to train the model, data from 2021 for testing, and data from 2022 to 2023 for internal validation. In addition, we used 1978 CXR images of 299 patients with PTB obtained from Yongin Severance Hospital for external validation.

RESULTS

In the internal validation, the model achieved an accuracy of 73.27%, an area under the receiver operating characteristic curve of 0.79, and an area under the precision-recall curve of 0.77. In the external validation, it exhibited an accuracy of 70.29%, an area under the receiver operating characteristic curve of 0.77, and an area under the precision-recall curve of 0.8. In addition, gradient-weighted class activation mapping and local interpretable model-agnostic explanations provided insights into the decision-making process of the AI model.

CONCLUSIONS

This proposed AI tool offers a rapid and accurate alternative for evaluating PTB infectivity through CXR, with significant implications for enhancing screening efficiency by evaluating infectivity before sputum test results in clinical settings, compared with traditional smear and culture tests.

A full-scale lung image segmentation algorithm based on hybrid skip connection and attention mechanism

The segmentation accuracy of the lung images is affected by the occlusion of the front background objects. To address this problem, we propose a full-scale lung image segmentation algorithm based on hybrid skip connection and attention mechanism (HAFS). The algorithm uses yolov8 as the underlying network and enhancement of multi-layer feature fusion by incorporating dense and sparse skip connections into the network structure, and increased weighting of important features through attention gates. Finally the proposed algorithm was applied to the lung datasets Montgomery County chest X-ray and Shenzhen chest X-ray. The experimental results show that the proposed algorithm improves the precision, recall, pixel accuracy, Dice, mIoU, mAP and GFLOPs metrics compared to the comparison algorithms, which proves the advancement and effectiveness of the proposed algorithm.

Fuzzy lattices assisted EJAYA Q-learning for automated pulmonary diseases classification

This work proposes a novel technique called Enhanced JAYA (EJAYA) assisted Q-Learning for the classification of pulmonary diseases, such as pneumonia and tuberculosis (TB) sub-classes using chest x-ray images. The work introduces Fuzzy lattices formation to handle real time (non-linear and non-stationary) data based feature extraction using Schrödinger equation. Features based adaptive classification is made possible through the Q-learning algorithm wherein optimal Q-values selection is done via EJAYA optimization algorithm. Fuzzy lattice is formed using x-ray image pixels and lattice Kinetic Energy (K.E.) is calculated using the Schrödinger equation. Feature vector lattices having highest K.E. have been used as an input features for the classifier. The classifier has been employed for pneumonia classification (normal, mild and severe) and Tuberculosis detection (presence or absence). A total of 3000 images have been used for pneumonia classification yielding an accuracy, sensitivity, specificity, precision and F-scores of 97.90%, 98.43%, 97.25%, 97.78% and 98.10%, respectively. For Tuberculosis 600 samples have been used. The achived accuracy, sensitivity, specificity, precision and F-score are 95.50%, 96.39%, 94.40% 95.52% and 95.95%, respectively. Computational time are 40.96 and 39.98 s for pneumonia and TB classification. Classifier learning rate (training accuracy) for pneumonia classes (normal, mild and severe) are 97.907%, 95.375% and 96.391%, respectively and for tuberculosis (present and absent) are 96.928% and 95.905%, respectively. The results have been compared with contemporary classification techniques which shows superiority of the proposed approach in terms of accuracy and speed of classification. The technique could serve as a fast and accurate tool for automated pneumonia and tuberculosis classification.

Neural Networks Based Smart E-Health Application for the Prediction of Tuberculosis Using Serverless Computing

The convergence of the Internet of Things (IoT) with e-health records is creating a new era of advancements in the diagnosis and treatment of disease, which is reshaping the modern landscape of healthcare. In this paper, we propose a neural networks-based smart e-health application for the prediction of Tuberculosis (TB) using serverless computing. The performance of various Convolution Neural Network (CNN) architectures using transfer learning is evaluated to prove that this technique holds promise for enhancing the capabilities of IoT and e-health systems in the future for predicting the manifestation of TB in the lungs. The work involves training, validating, and comparing Densenet-201, VGG-19, and Mobilenet-V3-Small architectures based on performance metrics such as test binary accuracy, test loss, intersection over union, precision, recall, and F1 score. The findings hint at the potential of integrating these advanced Machine Learning (ML) models within IoT and e-health frameworks, thereby paving the way for more comprehensive and data-driven approaches to enable smart healthcare. The best-performing model, VGG-19, is selected for different deployment strategies using server and serless-based environments. We used JMeter to measure the performance of the deployed model, including the average response rate, throughput, and error rate. This study provides valuable insights into the selection and deployment of ML models in healthcare, highlighting the advantages and challenges of different deployment options. Furthermore, it also allows future studies to integrate such models into IoT and e-health systems, which could enhance healthcare outcomes through more informed and timely treatments.

COVID-19 severity detection using chest X-ray segmentation and deep learning

COVID-19 has resulted in a significant global impact on health, the economy, education, and daily life. The disease can range from mild to severe, with individuals over 65 or those with underlying medical conditions being more susceptible to severe illness. Early testing and isolation are vital due to the virus's variable incubation period. Chest radiographs (CXR) have gained importance as a diagnostic tool due to their efficiency and reduced radiation exposure compared to CT scans. However, the sensitivity of CXR in detecting COVID-19 may be lower. This paper introduces a deep learning framework for accurate COVID-19 classification and severity prediction using CXR images. U-Net is used for lung segmentation, achieving a precision of 0.9924. Classification is performed using a Convulation-capsule network, with high true positive rates of 86% for COVID-19, 93% for pneumonia, and 85% for normal cases. Severity assessment employs ResNet50, VGG-16, and DenseNet201, with DenseNet201 showing superior accuracy. Empirical results, validated with 95% confidence intervals, confirm the framework's reliability and robustness. This integration of advanced deep learning techniques with radiological imaging enhances early detection and severity assessment, improving patient management and resource allocation in clinical settings.

Boundary-Aware Gradient Operator Network for Medical Image Segmentation

Medical image segmentation is a crucial task in computer-aided diagnosis. Although convolutional neural networks (CNNs) have made significant progress in the field of medical image segmentation, the convolution kernels of CNNs are optimized from random initialization without explicitly encoding gradient information, leading to a lack of specificity for certain features, such as blurred boundary features. Furthermore, the frequently applied down-sampling operation also loses the fine structural features in shallow layers. Therefore, we propose a boundary-aware gradient operator network (BG-Net) for medical image segmentation, in which the gradient convolution (GConv) and the boundary-aware mechanism (BAM) modules are developed to simulate image boundary features and the remote dependencies between channels. The GConv module transforms the gradient operator into a convolutional operation that can extract gradient features; it attempts to extract more features such as images boundaries and textures, thereby fully utilizing limited input to capture more features representing boundaries. In addition, the BAM can increase the amount of global contextual information while suppressing invalid information by focusing on feature dependencies and the weight ratios between channels. Thus, the boundary perception ability of BG-Net is improved. Finally, we use a multi-modal fusion mechanism to effectively fuse lightweight gradient convolution and U-shaped branch features into a multilevel feature, enabling global dependencies and low-level spatial details to be effectively captured in a shallower manner. We conduct extensive experiments on eight datasets that broadly cover medical images to evaluate the effectiveness of the proposed BG-Net. The experimental results demonstrate that BG-Net outperforms the state-of-the-art methods, particularly those focused on boundary segmentation.

A deep learning-based algorithm for pulmonary tuberculosis detection in chest radiography

In tuberculosis (TB), chest radiography (CXR) patterns are highly variable, mimicking pneumonia and many other diseases. This study aims to evaluate the efficacy of Google teachable machine, a deep neural network-based image classification tool, to develop algorithm for predicting TB probability of CXRs. The training dataset included 348 TB CXRs and 3806 normal CXRs for training TB detection. We also collected 1150 abnormal CXRs and 627 normal CXRs for training abnormality detection. For external validation, we collected 250 CXRs from our hospital. We also compared the accuracy of the algorithm to five pulmonologists and radiological reports. In external validation, the AI algorithm showed areas under the curve (AUC) of 0.951 and 0.975 in validation dataset 1 and 2. The accuracy of the pulmonologists on validation dataset 2 showed AUC range of 0.936-0.995. When abnormal CXRs other than TB were added, AUC decreased in both human readers (0.843-0.888) and AI algorithm (0.828). When combine human readers with AI algorithm, the AUC further increased to 0.862-0.885. The TB CXR AI algorithm developed by using Google teachable machine in this study is effective, with the accuracy close to experienced clinical physicians, and may be helpful for detecting tuberculosis by CXR.

CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images

The development of successful artificial intelligence models for chest X-ray analysis relies on large, diverse datasets with high-quality annotations. While several databases of chest X-ray images have been released, most include disease diagnosis labels but lack detailed pixel-level anatomical segmentation labels. To address this gap, we introduce an extensive chest X-ray multi-center segmentation dataset with uniform and fine-grain anatomical annotations for images coming from five well-known publicly available databases: ChestX-ray8, CheXpert, MIMIC-CXR-JPG, Padchest, and VinDr-CXR, resulting in 657,566 segmentation masks. Our methodology utilizes the HybridGNet model to ensure consistent and high-quality segmentations across all datasets. Rigorous validation, including expert physician evaluation and automatic quality control, was conducted to validate the resulting masks. Additionally, we provide individualized quality indices per mask and an overall quality estimation per dataset. This dataset serves as a valuable resource for the broader scientific community, streamlining the development and assessment of innovative methodologies in chest X-ray analysis.

DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation

Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional U-Net architectures and their transformer-integrated variants excel in automated segmentation tasks. Existing models also struggle with parameter efficiency and computational complexity, often due to the extensive use of Transformers. However, they lack the ability to harness the image's intrinsic position and channel features. Research employing Dual Attention mechanisms of position and channel have not been specifically optimized for the high-detail demands of medical images. To address these issues, this study proposes a novel deep medical image segmentation framework, called DA-TransUNet, aiming to integrate the Transformer and dual attention block (DA-Block) into the traditional U-shaped architecture. Also, DA-TransUNet tailored for the high-detail requirements of medical images, optimizes the intermittent channels of Dual Attention (DA) and employs DA in each skip-connection to effectively filter out irrelevant information. This integration significantly enhances the model's capability to extract features, thereby improving the performance of medical image segmentation. DA-TransUNet is validated in medical image segmentation tasks, consistently outperforming state-of-the-art techniques across 5 datasets. In summary, DA-TransUNet has made significant strides in medical image segmentation, offering new insights into existing techniques. It strengthens model performance from the perspective of image features, thereby advancing the development of high-precision automated medical image diagnosis. The codes and parameters of our model will be publicly available at https://github.com/SUN-1024/DA-TransUnet.

Revisiting Computer-Aided Tuberculosis Diagnosis

Tuberculosis (TB) is a major global health threat, causing millions of deaths annually. Although early diagnosis and treatment can greatly improve the chances of survival, it remains a major challenge, especially in developing countries. Recently, computer-aided tuberculosis diagnosis (CTD) using deep learning has shown promise, but progress is hindered by limited training data. To address this, we establish a large-scale dataset, namely the Tuberculosis X-ray (TBX11 K) dataset, which contains 11 200 chest X-ray (CXR) images with corresponding bounding box annotations for TB areas. This dataset enables the training of sophisticated detectors for high-quality CTD. Furthermore, we propose a strong baseline, SymFormer, for simultaneous CXR image classification and TB infection area detection. SymFormer incorporates Symmetric Search Attention (SymAttention) to tackle the bilateral symmetry property of CXR images for learning discriminative features. Since CXR images may not strictly adhere to the bilateral symmetry property, we also propose Symmetric Positional Encoding (SPE) to facilitate SymAttention through feature recalibration. To promote future research on CTD, we build a benchmark by introducing evaluation metrics, evaluating baseline models reformed from existing detectors, and running an online challenge. Experiments show that SymFormer achieves state-of-the-art performance on the TBX11 K dataset.

Enhancing medical image segmentation with a multi-transformer U-Net

Various segmentation networks based on Swin Transformer have shown promise in medical segmentation tasks. Nonetheless, challenges such as lower accuracy and slower training convergence have persisted. To tackle these issues, we introduce a novel approach that combines the Swin Transformer and Deformable Transformer to enhance overall model performance. We leverage the Swin Transformer's window attention mechanism to capture local feature information and employ the Deformable Transformer to adjust sampling positions dynamically, accelerating model convergence and aligning it more closely with object shapes and sizes. By amalgamating both Transformer modules and incorporating additional skip connections to minimize information loss, our proposed model excels at rapidly and accurately segmenting CT or X-ray lung images. Experimental results demonstrate the remarkable, showcasing the significant prowess of our model. It surpasses the performance of the standalone Swin Transformer's Swin Unet and converges more rapidly under identical conditions, yielding accuracy improvements of 0.7% (resulting in 88.18%) and 2.7% (resulting in 98.01%) on the COVID-19 CT scan lesion segmentation dataset and Chest X-ray Masks and Labels dataset, respectively. This advancement has the potential to aid medical practitioners in early diagnosis and treatment decision-making.

Feature Extraction Based on Local Histogram with Unequal Bins and a Recurrent Neural Network for the Diagnosis of Kidney Diseases from CT Images

Kidney disease remains one of the most common ailments worldwide, with cancer being one of its most common forms. Early diagnosis can significantly increase the good prognosis for the patient. The development of an artificial intelligence-based system to assist in kidney cancer diagnosis is crucial because kidney illness is a global health concern, and there are limited nephrologists qualified to evaluate kidney cancer. Diagnosing and categorising different forms of renal failure presents the biggest treatment hurdle for kidney cancer. Thus, this article presents a novel method for detecting and classifying kidney cancer subgroups in Computed Tomography (CT) images based on an asymmetric local statistical pixel distribution. In the first step, the input image is non-overlapping windowed, and a statistical distribution of its pixels in each cancer type is built. Then, the method builds the asymmetric statistical distribution of the image's gradient pixels. Finally, the cancer type is identified by applying the two built statistical distributions to a Deep Neural Network (DNN). The proposed method was evaluated using a dataset collected and authorised by the Dhaka Central International Medical Hospital in Bangladesh, which includes 12,446 CT images of the whole abdomen and urogram, acquired with and without contrast. Based on the results, it is possible to confirm that the proposed method outperformed state-of-the-art methods in terms of the usual correctness criteria. The accuracy of the proposed method for all kidney cancer subtypes presented in the dataset was 99.89%, which is promising.

In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning

Accurately estimating the breast muscle weight of broilers is important for poultry production. However, existing related methods are plagued by cumbersome processes and limited automation. To address these issues, this study proposed an efficient method for predicting the breast muscle weight of broilers. First, because existing deep learning models struggle to strike a balance between accuracy and memory consumption, this study designed a multistage attention enhancement fusion segmentation network (MAEFNet) to automatically acquire pectoral muscle mask images from X-ray images. MAEFNet employs the pruned MobileNetV3 as the encoder to efficiently capture features and adopts a novel decoder to enhance and fuse the effective features at various stages. Next, the selected shape features were automatically extracted from the mask images. Finally, these features, including live weight, were input to the SVR (Support Vector Regression) model to predict breast muscle weight. MAEFNet achieved the highest intersection over union (96.35%) with the lowest parameter count (1.51 M) compared to the other segmentation models. The SVR model performed best (R2 = 0.8810) compared to the other prediction models in the five-fold cross-validation. The research findings can be applied to broiler production and breeding, reducing measurement costs, and enhancing breeding efficiency.

Towards AI-augmented radiology education: a web-based application for perception training in chest X-ray nodule detection

OBJECTIVES

Artificial intelligence (AI)-based applications for augmenting radiological education are underexplored. Prior studies have demonstrated the effectiveness of simulation in radiological perception training. This study aimed to develop and make available a pure web-based application called Perception Trainer for perception training in lung nodule detection in chest X-rays.

METHODS

Based on open-access data, we trained a deep-learning model for lung segmentation in chest X-rays. Subsequently, an algorithm for artificial lung nodule generation was implemented and combined with the segmentation model to allow on-the-fly procedural insertion of lung nodules in chest X-rays. This functionality was integrated into an existing zero-footprint web-based DICOM viewer, and a dynamic HTML page was created to specify case generation parameters.

RESULTS

The result is an easily accessible platform-agnostic web application available at: https://castlemountain.dk/mulrecon/perceptionTrainer.html.The application allows the user to specify the characteristics of lung nodules to be inserted into chest X-rays, and it produces automated feedback regarding nodule detection performance. Generated cases can be shared through a uniform resource locator.

CONCLUSION

We anticipate that the description and availability of our developed solution with open-sourced codes may help facilitate radiological education and stimulate the development of similar AI-augmented educational tools.

ADVANCES IN KNOWLEDGE

A web-based application applying AI-based techniques for radiological perception training was developed. The application demonstrates a novel approach for on-the-fly generation of cases in chest X-ray lung nodule detection employing deep-learning-based segmentation and lung nodule simulation.

Early Detection of Lung Nodules Using a Revolutionized Deep Learning Model

According to the WHO (World Health Organization), lung cancer is the leading cause of cancer deaths globally. In the future, more than 2.2 million people will be diagnosed with lung cancer worldwide, making up 11.4% of every primary cause of cancer. Furthermore, lung cancer is expected to be the biggest driver of cancer-related mortality worldwide in 2020, with an estimated 1.8 million fatalities. Statistics on lung cancer rates are not uniform among geographic areas, demographic subgroups, or age groups. The chance of an effective treatment outcome and the likelihood of patient survival can be greatly improved with the early identification of lung cancer. Lung cancer identification in medical pictures like CT scans and MRIs is an area where deep learning (DL) algorithms have shown a lot of potential. This study uses the Hybridized Faster R-CNN (HFRCNN) to identify lung cancer at an early stage. Among the numerous uses for which faster R-CNN has been put to good use is identifying critical entities in medical imagery, such as MRIs and CT scans. Many research investigations in recent years have examined the use of various techniques to detect lung nodules (possible indicators of lung cancer) in scanned images, which may help in the early identification of lung cancer. One such model is HFRCNN, a two-stage, region-based entity detector. It begins by generating a collection of proposed regions, which are subsequently classified and refined with the aid of a convolutional neural network (CNN). A distinct dataset is used in the model's training process, producing valuable outcomes. More than a 97% detection accuracy was achieved with the suggested model, making it far more accurate than several previously announced methods.

Intelligent contour extraction approach for accurate segmentation of medical ultrasound images

Introduction: Accurate contour extraction in ultrasound images is of great interest for image-guided organ interventions and disease diagnosis. Nevertheless, it remains a problematic issue owing to the missing or ambiguous outline between organs (i.e., prostate and kidney) and surrounding tissues, the appearance of shadow artifacts, and the large variability in the shape of organs. Methods: To address these issues, we devised a method that includes four stages. In the first stage, the data sequence is acquired using an improved adaptive selection principal curve method, in which a limited number of radiologist defined data points are adopted as the prior. The second stage then uses an enhanced quantum evolution network to help acquire the optimal neural network. The third stage involves increasing the precision of the experimental outcomes after training the neural network, while using the data sequence as the input. In the final stage, the contour is smoothed using an explicable mathematical formula explained by the model parameters of the neural network. Results: Our experiments showed that our approach outperformed other current methods, including hybrid and Transformer-based deep-learning methods, achieving an average Dice similarity coefficient, Jaccard similarity coefficient, and accuracy of 95.7 ± 2.4%, 94.6 ± 2.6%, and 95.3 ± 2.6%, respectively. Discussion: This work develops an intelligent contour extraction approach on ultrasound images. Our approach obtained more satisfactory outcome compared with recent state-of-the-art approaches . The knowledge of precise boundaries of the organ is significant for the conservation of risk structures. Our developed approach has the potential to enhance disease diagnosis and therapeutic outcomes.

Optimization of U-shaped pure transformer medical image segmentation network

In recent years, neural networks have made pioneering achievements in the field of medical imaging. In particular, deep neural networks based on U-shaped structures are widely used in different medical image segmentation tasks. In order to improve the early diagnosis and clinical decision-making system of lung diseases, it has become a key step to use the neural network for lung segmentation to assist in positioning and observing the shape. There is still the problem of low precision. For the sake of achieving better segmentation accuracy, an optimized pure Transformer U-shaped segmentation is proposed in this article. The optimization segmentation network adopts the method of adding skip connections and performing special splicing processing, which reduces the information loss in the encoding process and increases the information in the decoding process, so as to achieve the purpose of improving the segmentation accuracy. The final experiment shows that our improved network achieves 97.86% accuracy in segmentation of the "Chest Xray Masks and Labels" dataset, which is better than the full convolutional network or the combination of Transformer and convolution.

HAL-IA: A Hybrid Active Learning framework using Interactive Annotation for medical image segmentation

High performance of deep learning models on medical image segmentation greatly relies on large amount of pixel-wise annotated data, yet annotations are costly to collect. How to obtain high accuracy segmentation labels of medical images with limited cost (e.g. time) becomes an urgent problem. Active learning can reduce the annotation cost of image segmentation, but it faces three challenges: the cold start problem, an effective sample selection strategy for segmentation task and the burden of manual annotation. In this work, we propose a Hybrid Active Learning framework using Interactive Annotation (HAL-IA) for medical image segmentation, which reduces the annotation cost both in decreasing the amount of the annotated images and simplifying the annotation process. Specifically, we propose a novel hybrid sample selection strategy to select the most valuable samples for segmentation model performance improvement. This strategy combines pixel entropy, regional consistency and image diversity to ensure that the selected samples have high uncertainty and diversity. In addition, we propose a warm-start initialization strategy to build the initial annotated dataset to avoid the cold-start problem. To simplify the manual annotation process, we propose an interactive annotation module with suggested superpixels to obtain pixel-wise label with several clicks. We validate our proposed framework with extensive segmentation experiments on four medical image datasets. Experimental results showed that the proposed framework achieves high accuracy pixel-wise annotations and models with less labeled data and fewer interactions, outperforming other state-of-the-art methods. Our method can help physicians efficiently obtain accurate medical image segmentation results for clinical analysis and diagnosis.

MTMC-AUR2CNet: Multi-textural multi-class attention recurrent residual convolutional neural network for COVID-19 classification using chest X-ray images

Coronavirus disease (COVID-19) has infected over 603 million confirmed cases as of September 2022, and its rapid spread has raised concerns worldwide. More than 6.4 million fatalities in confirmed patients have been reported. According to reports, the COVID-19 virus causes lung damage and rapidly mutates before the patient receives any diagnosis-specific medicine. Daily increasing COVID-19 cases and the limited number of diagnosis tool kits encourage the use of deep learning (DL) models to assist health care practitioners using chest X-ray (CXR) images. The CXR is a low radiation radiography tool available in hospitals to diagnose COVID-19 and combat this spread. We propose a Multi-Textural Multi-Class (MTMC) UNet-based Recurrent Residual Convolutional Neural Network (MTMC-UR2CNet) and MTMC-UR2CNet with attention mechanism (MTMC-AUR2CNet) for multi-class lung lobe segmentation of CXR images. The lung lobe segmentation output of MTMC-UR2CNet and MTMC-AUR2CNet are mapped individually with their input CXRs to generate the region of interest (ROI). The multi-textural features are extracted from the ROI of each proposed MTMC network. The extracted multi-textural features from ROI are fused and are trained to the Whale optimization algorithm (WOA) based DeepCNN classifier on classifying the CXR images into normal (healthy), COVID-19, viral pneumonia, and lung opacity. The experimental result shows that the MTMC-AUR2CNet has superior performance in multi-class lung lobe segmentation of CXR images with an accuracy of 99.47%, followed by MTMC-UR2CNet with an accuracy of 98.39%. Also, MTMC-AUR2CNet improves the multi-textural multi-class classification accuracy of the WOA-based DeepCNN classifier to 97.60% compared to MTMC-UR2CNet.

Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation

Medical image analysis plays an important role in clinical diagnosis. In this paper, we examine the recent Segment Anything Model (SAM) on medical images, and report both quantitative and qualitative zero-shot segmentation results on nine medical image segmentation benchmarks, covering various imaging modalities, such as optical coherence tomography (OCT), magnetic resonance imaging (MRI), and computed tomography (CT), as well as different applications including dermatology, ophthalmology, and radiology. Those benchmarks are representative and commonly used in model development. Our experimental results indicate that while SAM presents remarkable segmentation performance on images from the general domain, its zero-shot segmentation ability remains restricted for out-of-distribution images, e.g., medical images. In addition, SAM exhibits inconsistent zero-shot segmentation performance across different unseen medical domains. For certain structured targets, e.g., blood vessels, the zero-shot segmentation of SAM completely failed. In contrast, a simple fine-tuning of it with a small amount of data could lead to remarkable improvement of the segmentation quality, showing the great potential and feasibility of using fine-tuned SAM to achieve accurate medical image segmentation for a precision diagnostics. Our study indicates the versatility of generalist vision foundation models on medical imaging, and their great potential to achieve desired performance through fine-turning and eventually address the challenges associated with accessing large and diverse medical datasets in support of clinical diagnostics.

Experimental analysis of machine learning methods to detect Covid-19 from x-rays

To automate the detection of covid-19 patients most have proposed deep learning neural networks to classify patients using large databases of chest x-rays. Very few used classical machine learning methods. Machine learning methods may require less computational power and perform well if the data set is small. We experiment with classical machine learning methods on three different data sources varying in size from 55 to almost 4000 samples. We experiment with four feature extraction methods of Gabor, SURF, LBP, and HOG. Backpropagation neural networks and k-nearest neighbor classifiers are combined using one of the four combining methods of bagging, RSM, ARCx4 boosting and Ada-boosting. Results show that using the proper feature extraction and feature selection methods very high performance can be reached using simple backpropagation neural network classifiers. Regardless of combiner method used, the best classification rate achieved was 99.06% for the largest data set, and 100% for the smallest data set.

Classification of chest X-ray images by incorporation of medical domain knowledge into operation branch networks

BACKGROUND

This study was conducted to alleviate a common difficulty in chest X-ray image diagnosis: The attention region in a convolutional neural network (CNN) does not often match the doctor's point of focus. The method presented herein, which guides the area of attention in CNN to a medically plausible region, can thereby improve diagnostic capabilities.

METHODS

The model is based on an attention branch network, which has excellent interpretability of the classification model. This model has an additional new operation branch that guides the attention region to the lung field and heart in chest X-ray images. We also used three chest X-ray image datasets (Teikyo, Tokushima, and ChestX-ray14) to evaluate the CNN attention area of interest in these fields. Additionally, after devising a quantitative method of evaluating improvement of a CNN's region of interest, we applied it to evaluation of the proposed model.

RESULTS

Operation branch networks maintain or improve the area under the curve to a greater degree than conventional CNNs do. Furthermore, the network better emphasizes reasonable anatomical parts in chest X-ray images.

CONCLUSIONS

The proposed network better emphasizes the reasonable anatomical parts in chest X-ray images. This method can enhance capabilities for image interpretation based on judgment.

COVID-ConvNet: A Convolutional Neural Network Classifier for Diagnosing COVID-19 Infection

The novel coronavirus (COVID-19) pandemic still has a significant impact on the worldwide population's health and well-being. Effective patient screening, including radiological examination employing chest radiography as one of the main screening modalities, is an important step in the battle against the disease. Indeed, the earliest studies on COVID-19 found that patients infected with COVID-19 present with characteristic anomalies in chest radiography. In this paper, we introduce COVID-ConvNet, a deep convolutional neural network (DCNN) design suitable for detecting COVID-19 symptoms from chest X-ray (CXR) scans. The proposed deep learning (DL) model was trained and evaluated using 21,165 CXR images from the COVID-19 Database, a publicly available dataset. The experimental results demonstrate that our COVID-ConvNet model has a high prediction accuracy at 97.43% and outperforms recent related works by up to 5.9% in terms of prediction accuracy.

A Convolutional Neural Network Architecture for Segmentation of Lung Diseases Using Chest X-ray Images

The segmentation of lungs from medical images is a critical step in the diagnosis and treatment of lung diseases. Deep learning techniques have shown great promise in automating this task, eliminating the need for manual annotation by radiologists. In this research, a convolution neural network architecture is proposed for lung segmentation using chest X-ray images. In the proposed model, concatenate block is embedded to learn a series of filters or features used to extract meaningful information from the image. Moreover, a transpose layer is employed in the concatenate block to improve the spatial resolution of feature maps generated by a prior convolutional layer. The proposed model is trained using k-fold validation as it is a powerful and flexible tool for evaluating the performance of deep learning models. The proposed model is evaluated on five different subsets of the data by taking the value of k as 5 to obtain the optimized model to obtain more accurate results. The performance of the proposed model is analyzed for different hyper-parameters such as the batch size as 32, optimizer as Adam and 40 epochs. The dataset used for the segmentation of disease is taken from the Kaggle repository. The various performance parameters such as accuracy, IoU, and dice coefficient are calculated, and the values obtained are 0.97, 0.93, and 0.96, respectively.

BIO-CXRNET: a robust multimodal stacking machine learning technique for mortality risk prediction of COVID-19 patients using chest X-ray images and clinical data

Nowadays, quick, and accurate diagnosis of COVID-19 is a pressing need. This study presents a multimodal system to meet this need. The presented system employs a machine learning module that learns the required knowledge from the datasets collected from 930 COVID-19 patients hospitalized in Italy during the first wave of COVID-19 (March-June 2020). The dataset consists of twenty-five biomarkers from electronic health record and Chest X-ray (CXR) images. It is found that the system can diagnose low- or high-risk patients with an accuracy, sensitivity, and F1-score of 89.03%, 90.44%, and 89.03%, respectively. The system exhibits 6% higher accuracy than the systems that employ either CXR images or biomarker data. In addition, the system can calculate the mortality risk of high-risk patients using multivariate logistic regression-based nomogram scoring technique. Interested physicians can use the presented system to predict the early mortality risks of COVID-19 patients using the web-link: Covid-severity-grading-AI. In this case, a physician needs to input the following information: CXR image file, Lactate Dehydrogenase (LDH), Oxygen Saturation (O2%), White Blood Cells Count, C-reactive protein, and Age. This way, this study contributes to the management of COVID-19 patients by predicting early mortality risk.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00521-023-08606-w.

Collimation border with U-Net segmentation on chest radiographs compared to radiologists

INTRODUCTION

Chest Radiography (CXR) is a common radiographic procedure. Radiation exposure to patients should be kept as low as reasonably achievable (ALARA), and monitored continuously as part of quality assurance (QA) programs. One of the most effective dose reduction tools is proper collimation practice. The purpose of this study is to determine whether a U-Net convolutional neural networks (U-CNN) can be trained to automatically segment the lungs and calculate an optimized collimation border on a limited CXR dataset.

METHODS

662 CXRs with manual lung segmentations were obtained from an open-source dataset. These were used to train and validate three different U-CNNs for automatic lung segmentation and optimal collimation. The U-CNN dimensions were 128 × 128, 256 × 256, and 512 × 512 pixels and validated with five-fold cross validation. The U-CNN with the highest area under the curve (AUC) was tested externally, using a dataset of 50 CXRs. Dice scores (DS) were used to compare U-CNN segmentations with manual segmentations by three radiographers and two junior radiologists.

RESULTS

DS for the three U-CNN dimensions with segmentation of the lungs ranged from 0.93 to 0.96, respectively. DS of the collimation border for each U-CNN was 0.95 compared to the ground truth labels. DS for lung segmentation and collimation border between the junior radiologists was 0.97 and 0.97. One radiographer differed significantly from the U-CNN (p = 0.016).

CONCLUSION

We demonstrated that a U-CNN could reliably segment the lungs and suggest a collimation border with great accuracy compared to junior radiologists. This algorithm has the potential to automate collimation auditing of CXRs.

IMPLICATIONS FOR PRACTICE

Creating an automatic segmentation model of the lungs can produce a collimation border, which can be used in CXR QA programs.

Test-time bi-directional adaptation between image and model for robust segmentation

BACKGROUND AND OBJECTIVE

Deep learning models often suffer from performance degradations when deployed in real clinical environments due to appearance shifts between training and testing images. Most extant methods use training-time adaptation, which almost require target domain samples in the training phase. However, these solutions are limited by the training process and cannot guarantee the accurate prediction of test samples with unforeseen appearance shifts. Further, it is impractical to collect target samples in advance. In this paper, we provide a general method of making existing segmentation models robust to samples with unknown appearance shifts when deployed in daily clinical practice.

METHODS

Our proposed test-time bi-directional adaptation framework combines two complementary strategies. First, our image-to-model (I2M) adaptation strategy adapts appearance-agnostic test images to the learned segmentation model using a novel plug-and-play statistical alignment style transfer module during testing. Second, our model-to-image (M2I) adaptation strategy adapts the learned segmentation model to test images with unknown appearance shifts. This strategy applies an augmented self-supervised learning module to fine-tune the learned model with proxy labels that it generates. This innovative procedure can be adaptively constrained using our novel proxy consistency criterion. This complementary I2M and M2I framework demonstrably achieves robust segmentation against unknown appearance shifts using existing deep-learning models.

RESULTS

Extensive experiments on 10 datasets containing fetal ultrasound, chest X-ray, and retinal fundus images demonstrate that our proposed method achieves promising robustness and efficiency in segmenting images with unknown appearance shifts.

CONCLUSIONS

To address the appearance shift problem in clinically acquired medical images, we provide robust segmentation by using two complementary strategies. Our solution is general and amenable for deployment in clinical settings.

Enhancing physicians' radiology diagnostics of COVID-19's effects on lung health by leveraging artificial intelligence

Introduction: This study aimed to develop an individualized artificial intelligence model to help radiologists assess the severity of COVID-19's effects on patients' lung health. Methods: Data was collected from medical records of 1103 patients diagnosed with COVID-19 using RT- qPCR between March and June 2020, in Hospital Madrid-Group (HM-Group, Spain). By using Convolutional Neural Networks, we determine the effects of COVID-19 in terms of lung area, opacities, and pulmonary air density. We then combine these variables with age and sex in a regression model to assess the severity of these conditions with respect to fatality risk (death or ICU). Results: Our model can predict high effect with an AUC of 0.736. Finally, we compare the performance of the model with respect to six physicians' diagnosis, and test for improvements on physicians' performance when using the prediction algorithm. Discussion: We find that the algorithm outperforms physicians (39.5% less error), and thus, physicians can significantly benefit from the information provided by the algorithm by reducing error by almost 30%.

A stereo spatial decoupling network for medical image classification

Deep convolutional neural network (CNN) has made great progress in medical image classification. However, it is difficult to establish effective spatial associations, and always extracts similar low-level features, resulting in redundancy of information. To solve these limitations, we propose a stereo spatial discoupling network (TSDNets), which can leverage the multi-dimensional spatial details of medical images. Then, we use an attention mechanism to progressively extract the most discriminative features from three directions: horizontal, vertical, and depth. Moreover, a cross feature screening strategy is used to divide the original feature maps into three levels: important, secondary and redundant. Specifically, we design a cross feature screening module (CFSM) and a semantic guided decoupling module (SGDM) to model multi-dimension spatial relationships, thereby enhancing the feature representation capabilities. The extensive experiments conducted on multiple open source baseline datasets demonstrate that our TSDNets outperforms previous state-of-the-art models.

Cross Dataset Analysis of Domain Shift in CXR Lung Region Detection

Domain shift is one of the key challenges affecting reliability in medical imaging-based machine learning predictions. It is of significant importance to investigate this issue to gain insights into its characteristics toward determining controllable parameters to minimize its impact. In this paper, we report our efforts on studying and analyzing domain shift in lung region detection in chest radiographs. We used five chest X-ray datasets, collected from different sources, which have manual markings of lung boundaries in order to conduct extensive experiments toward this goal. We compared the characteristics of these datasets from three aspects: information obtained from metadata or an image header, image appearance, and features extracted from a pretrained model. We carried out experiments to evaluate and compare model performances within each dataset and across datasets in four scenarios using different combinations of datasets. We proposed a new feature visualization method to provide explanations for the applied object detection network on the obtained quantitative results. We also examined chest X-ray modality-specific initialization, catastrophic forgetting, and model repeatability. We believe the observations and discussions presented in this work could help to shed some light on the importance of the analysis of training data for medical imaging machine learning research, and could provide valuable guidance for domain shift analysis.

A survey on recent trends in deep learning for nucleus segmentation from histopathology images

Nucleus segmentation is an imperative step in the qualitative study of imaging datasets, considered as an intricate task in histopathology image analysis. Segmenting a nucleus is an important part of diagnosing, staging, and grading cancer, but overlapping regions make it hard to separate and tell apart independent nuclei. Deep Learning is swiftly paving its way in the arena of nucleus segmentation, attracting quite a few researchers with its numerous published research articles indicating its efficacy in the field. This paper presents a systematic survey on nucleus segmentation using deep learning in the last five years (2017-2021), highlighting various segmentation models (U-Net, SCPP-Net, Sharp U-Net, and LiverNet) and exploring their similarities, strengths, datasets utilized, and unfolding research areas.

Rapid diagnosis of Covid-19 infections by a progressively growing GAN and CNN optimisation

BACKGROUND AND OBJECTIVE

Covid-19 infections are spreading around the globe since December 2019. Several diagnostic methods were developed based on biological investigations and the success of each method depends on the accuracy of identifying Covid infections. However, access to diagnostic tools can be limited, depending on geographic region and the diagnosis duration plays an important role in treating Covid-19. Since the virus causes pneumonia, its presence can also be detected using medical imaging by Radiologists. Hospitals with X-ray capabilities are widely distributed all over the world, so a method for diagnosing Covid-19 from chest X-rays would present itself. Studies have shown promising results in automatically detecting Covid-19 from medical images using supervised Artificial neural network (ANN) algorithms. The major drawback of supervised learning algorithms is that they require huge amounts of data to train. Also, the radiology equipment is not computationally efficient for deep neural networks. Therefore, we aim to develop a Generative Adversarial Network (GAN) based image augmentation to optimize the performance of custom, light, Convolutional networks used for the classification of Chest X-rays (CXR).

METHODS

A Progressively Growing Generative Adversarial Network (PGGAN) is used to generate synthetic and augmented data to supplement the dataset. We propose two novel CNN architectures to perform the Multi-class classification of Covid-19, healthy and pneumonia affected Chest X-rays. Comparisons have been drawn to the state of the art models and transfer learning methods to evaluate the superiority of the networks. All the models are trained using enhanced and augmented X-ray images and are compared based on classification metrics.

RESULTS

The proposed models had extremely high classification metrics with proposed Architectures having test accuracy of 98.78% and 99.2% respectively while having 40% lesser training parameters than their state of the art counterpart.

CONCLUSION

In the present study, a method based on artificial intelligence is proposed, leading to a rapid diagnostic tool for Covid infections based on Generative Adversarial Network (GAN) and Convolutional Neural Networks (CNN). The benefit will be a high accuracy of detection with up to 99% hit rate, a rapid diagnosis, and an accessible Covid identification method by chest X-ray images.

Improving Anatomical Plausibility in Medical Image Segmentation via Hybrid Graph Neural Networks: Applications to Chest X-Ray Analysis

Anatomical segmentation is a fundamental task in medical image computing, generally tackled with fully convolutional neural networks which produce dense segmentation masks. These models are often trained with loss functions such as cross-entropy or Dice, which assume pixels to be independent of each other, thus ignoring topological errors and anatomical inconsistencies. We address this limitation by moving from pixel-level to graph representations, which allow to naturally incorporate anatomical constraints by construction. To this end, we introduce HybridGNet, an encoder-decoder neural architecture that leverages standard convolutions for image feature encoding and graph convolutional neural networks (GCNNs) to decode plausible representations of anatomical structures. We also propose a novel image-to-graph skip connection layer which allows localized features to flow from standard convolutional blocks to GCNN blocks, and show that it improves segmentation accuracy. The proposed architecture is extensively evaluated in a variety of domain shift and image occlusion scenarios, and audited considering different types of demographic domain shift. Our comprehensive experimental setup compares HybridGNet with other landmark and pixel-based models for anatomical segmentation in chest x-ray images, and shows that it produces anatomically plausible results in challenging scenarios where other models tend to fail.

Efficient contour-based annotation by iterative deep learning for organ segmentation from volumetric medical images

PURPOSE

Training deep neural networks usually require a large number of human-annotated data. For organ segmentation from volumetric medical images, human annotation is tedious and inefficient. To save human labour and to accelerate the training process, the strategy of annotation by iterative deep learning recently becomes popular in the research community. However, due to the lack of domain knowledge or efficient human-interaction tools, the current AID methods still suffer from long training time and high annotation burden.

METHODS

We develop a contour-based annotation by iterative deep learning (AID) algorithm which uses boundary representation instead of voxel labels to incorporate high-level organ shape knowledge. We propose a contour segmentation network with a multi-scale feature extraction backbone to improve the boundary detection accuracy. We also developed a contour-based human-intervention method to facilitate easy adjustments of organ boundaries. By combining the contour-based segmentation network and the contour-adjustment intervention method, our algorithm achieves fast few-shot learning and efficient human proofreading.

RESULTS

For validation, two human operators independently annotated four abdominal organs in computed tomography (CT) images using our method and two compared methods, i.e. a traditional contour-interpolation method and a state-of-the-art (SOTA) convolutional network (CNN) method based on voxel label representation. Compared to these methods, our approach considerably saved annotation time and reduced inter-rater variabilities. Our contour detection network also outperforms the SOTA nnU-Net in producing anatomically plausible organ shape with only a small training set.

CONCLUSION

Taking advantage of the boundary shape prior and the contour representation, our method is more efficient, more accurate and less prone to inter-operator variability than the SOTA AID methods for organ segmentation from volumetric medical images. The good shape learning ability and flexible boundary adjustment function make it suitable for fast annotation of organ structures with regular shape.

A deep learning architecture for multi-class lung diseases classification using chest X-ray (CXR) images

In 2019, the world experienced the rapid outbreak of the Covid-19 pandemic creating an alarming situation worldwide. The virus targets the respiratory system causing pneumonia with other symptoms such as fatigue, dry cough, and fever which can be mistakenly diagnosed as pneumonia, lung cancer, or TB. Thus, the early diagnosis of COVID-19 is critical since the disease can provoke patients’ mortality. Chest X-ray (CXR) is commonly employed in healthcare sector where both quick and precise diagnosis can be supplied. Deep learning algorithms have proved extraordinary capabilities in terms of lung diseases detection and classification. They facilitate and expedite the diagnosis process and save time for the medical practitioners. In this paper, a deep learning (DL) architecture for multi-class classification of Pneumonia, Lung Cancer, tuberculosis (TB), Lung Opacity, and most recently COVID-19 is proposed. Tremendous CXR images of 3615 COVID-19, 6012 Lung opacity, 5870 Pneumonia, 20,000 lung cancer, 1400 tuberculosis, and 10,192 normal images were resized, normalized, and randomly split to fit the DL requirements. In terms of classification, we utilized a pre-trained model, VGG19 followed by three blocks of convolutional neural network (CNN) as a feature extraction and fully connected network at the classification stage. The experimental results revealed that our proposed VGG19 + CNN outperformed other existing work with 96.48 % accuracy, 93.75 % recall, 97.56 % precision, 95.62 % F1 score, and 99.82 % area under the curve (AUC). The proposed model delivered superior performance allowing healthcare practitioners to diagnose and treat patients more quickly and efficiently.

COVID-19 Classification on Chest X-ray Images Using Deep Learning Methods

Since December 2019, the coronavirus disease has significantly affected millions of people. Given the effect this disease has on the pulmonary systems of humans, there is a need for chest radiographic imaging (CXR) for monitoring the disease and preventing further deaths. Several studies have been shown that Deep Learning models can achieve promising results for COVID-19 diagnosis towards the CXR perspective. In this study, five deep learning models were analyzed and evaluated with the aim of identifying COVID-19 from chest X-ray images. The scope of this study is to highlight the significance and potential of individual deep learning models in COVID-19 CXR images. More specifically, we utilized the ResNet50, ResNet101, DenseNet121, DenseNet169 and InceptionV3 using Transfer Learning. All models were trained and validated on the largest publicly available repository for COVID-19 CXR images. Furthermore, they were evaluated on unknown data that was not used for training or validation, authenticating their performance and clarifying their usage in a medical scenario. All models achieved satisfactory performance where ResNet101 was the superior model achieving 96% in Precision, Recall and Accuracy, respectively. Our outcomes show the potential of deep learning models on COVID-19 medical offering a promising way for the deeper understanding of COVID-19.

A deep learning based dual encoder-decoder framework for anatomical structure segmentation in chest X-ray images

Automated multi-organ segmentation plays an essential part in the computer-aided diagnostic (CAD) of chest X-ray fluoroscopy. However, developing a CAD system for the anatomical structure segmentation remains challenging due to several indistinct structures, variations in the anatomical structure shape among different individuals, the presence of medical tools, such as pacemakers and catheters, and various artifacts in the chest radiographic images. In this paper, we propose a robust deep learning segmentation framework for the anatomical structure in chest radiographs that utilizes a dual encoder-decoder convolutional neural network (CNN). The first network in the dual encoder-decoder structure effectively utilizes a pre-trained VGG19 as an encoder for the segmentation task. The pre-trained encoder output is fed into the squeeze-and-excitation (SE) to boost the network's representation power, which enables it to perform dynamic channel-wise feature calibrations. The calibrated features are efficiently passed into the first decoder to generate the mask. We integrated the generated mask with the input image and passed it through a second encoder-decoder network with the recurrent residual blocks and an attention the gate module to capture the additional contextual features and improve the segmentation of the smaller regions. Three public chest X-ray datasets are used to evaluate the proposed method for multi-organs segmentation, such as the heart, lungs, and clavicles, and single-organ segmentation, which include only lungs. The results from the experiment show that our proposed technique outperformed the existing multi-class and single-class segmentation methods.

A multi-output network with U-net enhanced class activation map and robust classification performance for medical imaging analysis

Computer vision in medical diagnosis has achieved a high level of success in diagnosing diseases with high accuracy. However, conventional classifiers that produce an image-to-label result provide insufficient information for medical professionals to judge and raise concerns over the trust and reliability of a model with results that cannot be explained. To gain local insight of cancerous regions, separate tasks such as imaging segmentation needs to be implemented to aid the doctors in treating patients which doubles the training time and costs which renders the diagnosis system inefficient and difficult to be accepted by the public. To tackle this issue and drive the AI-first medical solutions further, this paper proposes a multi-output network which follows a U-Net architecture for image segmentation output and features an additional CNN module for auxiliary classification output. Class Activation Maps or CAMs are a method of providing insight into a convolutional neural network’s feature maps that lead to its classification but in the case of lung diseases, the region of interest is enhanced by U-net assisted Class Activation Mapping (CAM) visualization. Therefore, our proposed model combines image segmentation models and classifiers to crop out only the lung region of a chest X-ray’s class activation map to provide a visualization that improves the explainability and can generate classification results simultaneously which builds trust for AI-led diagnosis system. The proposed U-Net model achieves 97.72% accuracy and a dice coefficient of 0.9691 on a testing data from the COVID-QU-Ex Dataset which includes both diseased and healthy lungs.

Lesion detection of chest X-Ray based on scalable attention residual CNN

Most of the research on disease recognition in chest X-rays is limited to segmentation and classification, but the problem of inaccurate recognition in edges and small parts makes doctors spend more time making judgments. In this paper, we propose a lesion detection method based on a scalable attention residual CNN (SAR-CNN), which uses target detection to identify and locate diseases in chest X-rays and greatly improves work efficiency. We designed a multi-convolution feature fusion block (MFFB), tree-structured aggregation module (TSAM), and scalable channel and spatial attention (SCSA), which can effectively alleviate the difficulties in chest X-ray recognition caused by single resolution, weak communication of features of different layers, and lack of attention fusion, respectively. These three modules are embeddable and can be easily combined with other networks. Through a large number of experiments on the largest public lung chest radiograph detection dataset, VinDr-CXR, the mean average precision (mAP) of the proposed method was improved from 12.83% to 15.75% in the case of the PASCAL VOC 2010 standard, with IoU > 0.4, which exceeds the existing mainstream deep learning model. In addition, the proposed model has a lower complexity and faster reasoning speed, which is conducive to the implementation of computer-aided systems and provides referential solutions for relevant communities.

AI-based radiodiagnosis using chest X-rays: A review

Chest Radiograph or Chest X-ray (CXR) is a common, fast, non-invasive, relatively cheap radiological examination method in medical sciences. CXRs can aid in diagnosing many lung ailments such as Pneumonia, Tuberculosis, Pneumoconiosis, COVID-19, and lung cancer. Apart from other radiological examinations, every year, 2 billion CXRs are performed worldwide. However, the availability of the workforce to handle this amount of workload in hospitals is cumbersome, particularly in developing and low-income nations. Recent advances in AI, particularly in computer vision, have drawn attention to solving challenging medical image analysis problems. Healthcare is one of the areas where AI/ML-based assistive screening/diagnostic aid can play a crucial part in social welfare. However, it faces multiple challenges, such as small sample space, data privacy, poor quality samples, adversarial attacks and most importantly, the model interpretability for reliability on machine intelligence. This paper provides a structured review of the CXR-based analysis for different tasks, lung diseases and, in particular, the challenges faced by AI/ML-based systems for diagnosis. Further, we provide an overview of existing datasets, evaluation metrics for different[][15mm][0mm]Q5 tasks and patents issued. We also present key challenges and open problems in this research domain.

Deep Learning Detection of Active Pulmonary Tuberculosis at Chest Radiography Matched the Clinical Performance of Radiologists

Background The World Health Organization (WHO) recommends chest radiography to facilitate tuberculosis (TB) screening. However, chest radiograph interpretation expertise remains limited in many regions. Purpose To develop a deep learning system (DLS) to detect active pulmonary TB on chest radiographs and compare its performance to that of radiologists. Materials and Methods A DLS was trained and tested using retrospective chest radiographs (acquired between 1996 and 2020) from 10 countries. To improve generalization, large-scale chest radiograph pretraining, attention pooling, and semisupervised learning ("noisy-student") were incorporated. The DLS was evaluated in a four-country test set (China, India, the United States, and Zambia) and in a mining population in South Africa, with positive TB confirmed with microbiological tests or nucleic acid amplification testing (NAAT). The performance of the DLS was compared with that of 14 radiologists. The authors studied the efficacy of the DLS compared with that of nine radiologists using the Obuchowski-Rockette-Hillis procedure. Given WHO targets of 90% sensitivity and 70% specificity, the operating point of the DLS (0.45) was prespecified to favor sensitivity. Results A total of 165 754 images in 22 284 subjects (mean age, 45 years; 21% female) were used for model development and testing. In the four-country test set (1236 subjects, 17% with active TB), the receiver operating characteristic (ROC) curve of the DLS was higher than those for all nine India-based radiologists, with an area under the ROC curve of 0.89 (95% CI: 0.87, 0.91). Compared with these radiologists, at the prespecified operating point, the DLS sensitivity was higher (88% vs 75%, P < .001) and specificity was noninferior (79% vs 84%, P = .004). Trends were similar within other patient subgroups, in the South Africa data set, and across various TB-specific chest radiograph findings. In simulations, the use of the DLS to identify likely TB-positive chest radiographs for NAAT confirmation reduced the cost by 40%-80% per TB-positive patient detected. Conclusion A deep learning method was found to be noninferior to radiologists for the determination of active tuberculosis on digital chest radiographs. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by van Ginneken in this issue.