Frontal Chest X-ray Research Articles

Automated quantification of SARS-CoV-2 pneumonia with large vision model knowledge adaptation

BackgroundLarge vision models (LVM) pretrained by large datasets have demonstrated their enormous capacity to understand visual patterns and capture semantic information from images. We proposed a novel method of knowledge domain adaptation with pretrained LVM for a low-cost artificial intelligence (AI) model to quantify the severity of SARS-CoV-2 pneumonia based on frontal chest X-ray (CXR) images. MethodsOur method used the pretrained LVMs as the primary feature extractor and self-supervised contrastive learning for domain adaptation. An encoder with a 2048-dimensional feature vector output was first trained by self-supervised learning for knowledge domain adaptation. Then a multi-layer perceptron (MLP) was trained for the final severity prediction. A dataset with 2599 CXR images was used for model training and evaluation. ResultsThe model based on the pretrained vision transformer (ViT) and self-supervised learning achieved the best performance in cross validation, with mean squared error (MSE) of 23.83 (95 % CI 22.67–25.00) and mean absolute error (MAE) of 3.64 (95 % CI 3.54–3.73). Its prediction correlation has the R2 of 0.81 (95 % CI 0.79–0.82) and Spearman ρ of 0.80 (95 % CI 0.77–0.81), which are comparable to the current state-of-the-art (SOTA) methods trained by much larger CXR datasets. ConclusionThe proposed new method has achieved the SOTA performance to quantify the severity of SARS-CoV-2 pneumonia at a significantly lower cost. The method can be extended to other infectious disease detection or quantification to expedite the application of AI in medical research.

Screening and staging of chronic obstructive pulmonary disease with deep learning based on chest X-ray images and clinical parameters

BackgroundChronic obstructive pulmonary disease (COPD) is underdiagnosed with the current gold standard measure pulmonary function test (PFT). A more sensitive and simple option for early detection and severity evaluation of COPD could benefit practitioners and patients.MethodsIn this multicenter retrospective study, frontal chest X-ray (CXR) images and related clinical information of 1055 participants were collected and processed. Different deep learning algorithms and transfer learning models were trained to classify COPD based on clinical data and CXR images from 666 subjects, and validated in internal test set based on 284 participants. External test including 105 participants was also performed to verify the generalization ability of the learning algorithms in diagnosing COPD. Meanwhile, the model was further used to evaluate disease severity of COPD by predicting different grads.ResultsThe Ensemble model showed an AUC of 0.969 in distinguishing COPD by simultaneously extracting fusion features of clinical parameters and CXR images in internal test, better than models that used clinical parameters (AUC = 0.963) or images (AUC = 0.946) only. For the external test set, the AUC slightly declined to 0.934 in predicting COPD based on clinical parameters and CXR images. When applying the Ensemble model to determine disease severity of COPD, the AUC reached 0.894 for three-classification and 0.852 for five-classification respectively.ConclusionThe present study used DL algorithms to screen COPD and predict disease severity based on CXR imaging and clinical parameters. The models showed good performance and the approach might be an effective case-finding tool with low radiation dose for COPD diagnosis and staging.

AI Models for Chest Radiograph Analysis: Internal Clinical Trial vs. Gold Standards

Our vision is to develop an AI-based software which is capable of analyzing frontal PA chest X-rays for disease diagnosis, detection, and prediction through the analysis of several different X-ray manifestations and findings which are inter-correlated to arrive to a final result. We utilize state of-the-art AI, thereby facilitating in empowering of the world through our med-tech ecosystem. It is being developed with the intention of enhanced cardiopulmonary care, bridging the gaps in healthcare, by giving conclusive and comprehensive diagnosis at lower costs and reducing the number of unnecessary diagnostic tests which, often, serve as the main cause of the delay between diagnosis and treatment. Why X-rays? X-rays have been chosen as the input because it is Non-invasive mode of diagnostic test, affordable, accessible and has much lesser radiation exposure compared to other imaging methods of CT, MRI, PET.

Diagnostic Strategy for Suspected Unilateral Absence of the Pulmonary Artery.

To analyze the diagnostic strategy applied to seven patients with UAPA who were examined and subsequently treated at the National Lung Hospital, Hanoi, Vietnam. All seven patients, including three pediatric cases (1, 2, and 14 years old) and four adult cases (21, 26, 44, and 53 years old), had a history of recurrent pneumonia, and the clinical symptoms on admission included cough, progressive dyspnea, chest pain, and fatigue. The patients were initially examined clinically, followed by hematological testing, blood biochemistry testing, and chest X-ray radiology. The results suggested UAPA, so echocardiography and contrast-enhanced chest computed tomography (CT) were performed as soon as practical. The echocardiographic and CT imaging findings confirmed the suspected diagnosis of UAPA in all seven patients, which was accompanied by congenital heart disease in three patients. Three of the seven patients had mild and medium pulmonary hypertension. All seven patients were treated with drugs, which led to improvement in symptoms. Frontal chest X-ray provided the initial signs suggesting a diagnosis of UAPA. Subsequent echocardiography and contrast-enhanced chest CT were effective diagnostic tools for fast and accurate confirmation of UAPA.</p>.

Chest CT at X-Ray Dose Using a Noise-Mitigating Weighted Projection: The Thoracic Tomogram. Diagnostic Performance for Pneumonia Detection in Hemato-Oncology Patients.

To compare the diagnostic performance of a thick-slab reconstruction obtained from an ultra-low-dose CT (termed thoracic tomogram) with standard-of-care low-dose CT (SOC-CT) for rapid interpretation and detection of pneumonia in hemato-oncology patients. Hemato-oncology patients with a working diagnosis of pneumonia underwent an SOC-CT followed by an ultra-low-dose CT, from which the thoracic tomogram (TT) was reconstructed. Three radiologists evaluated the TT and SOC-CT in the following categories: (I) infectious/inflammatory opacities, (II) small airways infectious/inflammatory changes, (III) atelectasis, (IV) pleural effusions, and (V) interstitial abnormalities. The TT interpretation time and radiation dose were recorded. Sensitivity, specificity, diagnostic accuracy, ROC, and AUC were calculated with the corresponding power analyses. The agreement between TT and SOC-CT was calculated by Correlation Coefficient for Repeated Measures (CCRM), and the Shrout-Fleiss intra-class correlations test was used to calculate interrater agreement. Forty-seven patients (mean age 58.7 ± 14.9 years; 29 male) were prospectively enrolled. Sensitivity, specificity, accuracy, AUC, and Power for categories I/II/III/IV/V were: 94.9/99/97.9/0.971/100, 78/91.2/86.5/0.906/100, 88.6/100/97.2/0.941/100, 100/99.2/99.3/0.995/100, and 47.6/100/92.2/0.746/87.3. CCRM between TT and SOC-CT for the same categories were .97/.81/.92/.96/.62 with an interobserver agreement of .93/.88/.82/.96/.61. Mean interpretation time was 18.6 ± 5.4 seconds. The average effective radiation dose of TT was similar to a frontal and lateral chest X-ray (0.27 ± 0.08 vs 1.46 ± 0.64 mSv for SOC-CT; P < .01). Thoracic tomograms provide comparable diagnostic information to SOC-CT for the detection of pneumonia in immunocompromised patients at one-fifth of the radiation dose with high interobserver agreement.

Diagnosis of a Case of Achalasia of the Cardiac at the Somine Dolo Hospital in Mopti

We report through this observation the diagnosis of a case of achalasia of the cardia in a 14-year-old adolescent at the Sominé Dolo hospital in Mopti. This was the first case of Achalasia of the cardia out of the 2650 gastroscopies carried out in Mopti from 2018 to 2022. The patient had no particular personal or family medical/surgical history. According to the symptoms, it was classified as Stage 3 of the Eckardt Score. The esogastroduodenal fibroscopy performed revealed a narrowing of the cardia and a jump when passing the endoscope. It was stage II at the time of diagnosis, according to the distension of the body of the esophagus during esophagogastric transit and a Radish tail image at the level of the esophagogastric junction. Frontal chest x-ray showed significant mediastinal widening. However, monomerism (essential examination) inaccessible in our context could not be achieved. The diagnosis of achalasia of the cardia was retained based on clinical, endoscopic and radiological arguments.

Accuracy of an artificial intelligence-enabled diagnostic assistance device in recognizing normal chest radiographs: a service evaluation.

Artificial intelligence (AI) enabled devices may be able to optimize radiologists' productivity by identifying normal and abnormal chest X-rays (CXRs) for triaging. In this service evaluation, we investigated the accuracy of one such AI device (qXR). A randomly sampled subset of general practice and outpatient-referred frontal CXRs from a National Health Service Trust was collected retrospectively from examinations conducted during November 2022 to January 2023. Ground truth was established by consensus between 2 radiologists. The main objective was to estimate negative predictive value (NPV) of AI. A total of 522 CXRs (458 [87.74%] normal CXRs) from 522 patients (median age, 64 years [IQR, 49-77]; 305 [58.43%] female) were analysed. AI predicted 348 CXRs as normal, of which 346 were truly normal (NPV: 99.43% [95% CI, 97.94-99.93]). The sensitivity, specificity, positive predictive value, and area under the ROC curve of AI were found to be 96.88% (95% CI, 89.16-99.62), 75.55% (95% CI, 71.34-79.42), 35.63% (95% CI, 28.53-43.23), and 91.92% (95% CI, 89.38-94.45), respectively. A sensitivity analysis was conducted to estimate NPV by varying assumptions of the prevalence of normal CXRs. The NPV ranged from 88.96% to 99.54% as prevalence increased. The AI device recognized normal CXRs with high NPV and has the potential to increase radiologists' productivity. There is a need for more evidence on the utility of AI-enabled devices in identifying normal CXRs. This work adds to such limited evidence and enables researchers to plan studies to further evaluate the impact of such devices.

Bone suppression of lateral chest x-rays with imperfect and limited dual-energy subtraction images.

Bone suppression is to suppress the superimposed bone components over the soft tissues within the lung area of Chest X-ray (CXR), which is potentially useful for the subsequent lung disease diagnosis for radiologists, as well as computer-aided systems. Despite bone suppression methods for frontal CXRs being well studied, it remains challenging for lateral CXRs due to the limited and imperfect DES dataset containing paired lateral CXR and soft-tissue/bone images and more complex anatomical structures in the lateral view. In this work, we propose a bone suppression method for lateral CXRs by leveraging a two-stage distillation learning strategy and a specific data correction method. Specifically, a primary model is first trained on a real DES dataset with limited samples. The bone-suppressed results on a relatively large lateral CXR dataset produced by the primary model are improved by a designed gradient correction method. Secondly, the corrected results serve as training samples to train the distillated model. By automatically learning knowledge from both the primary model and the extra correction procedure, our distillated model is expected to promote the performance of the primary model while omitting the tedious correction procedure. We adopt an ensemble model named MsDd-MAP for the primary and distillated models, which learns the complementary information of Multi-scale and Dual-domain (i.e., intensity and gradient) and fuses them in a maximum-a-posteriori (MAP) framework. Our method is evaluated on a two-exposure lateral DES dataset consisting of 46 subjects and a lateral CXR dataset consisting of 240 subjects. The experimental results suggest that our method is superior to other competing methods regarding the quantitative evaluation metrics. Furthermore, the subjective evaluation by three experienced radiologists also indicates that the distillated model can produce more visually appealing soft-tissue images than the primary model, even comparable to real DES imaging for lateral CXRs.

Retrocardiac Pneumomediastinum: Description of an Unusual Case and Review of Literature

Retrocardiac pneumomediastinum (RP) is the consequence of air trapping in the inferior and posterior mediastinum. It is characterized by the presence of a right or left para-sagittal infrahilar oval or pyramidal air collection on a chest X-ray. It is usually detected in neonates because of alveolar rupture after invasive ventilation or invasive manoeuvres applied on airways or the digestive tract. A healthy child came to the emergency department (ED) for acute respiratory failure due to viral bronchiolitis when he was 2 months old. Because of his clinical condition, he underwent helmet continuous positive airway pressure (HCPAP). When the condition allowed, he was discharged and sent home. He was re-admitted into the hospital for asthmatic bronchitis 3 months later. A frontal chest X-ray taken during the second hospitalization showed an oval-shaped retrocardiac air lucency not previously detected. Differential diagnosis including digestive and lung malformations was made. Finally, the diagnosis of RP was made. We report an unusual case of retrocardiac pneumomediastinum in a 5-month-old male infant after the application of continuous positive pressure via a helmet. RP presentation after the administration of non-invasive ventilatory support beyond the neonatal age is unusual. Although surgical drainage is curative, conservative treatment can be considered in hemodynamically stable patients.

Machine Learning: Using Xception, a Deep Convolutional Neural Network Architecture, to Implement Pectus Excavatum Diagnostic Tool from Frontal-View Chest X-rays.

Pectus excavatum (PE), a chest-wall deformity that can compromise cardiopulmonary function, cannot be detected by a radiologist through frontal chest radiography without a lateral view or chest computed tomography. This study aims to train a convolutional neural network (CNN), a deep learning architecture with powerful image processing ability, for PE screening through frontal chest radiography, which is the most common imaging test in current hospital practice. Posteroanterior-view chest images of PE and normal patients were collected from our hospital to build the database. Among them, 80% were used as the training set used to train the established CNN algorithm, Xception, whereas the remaining 20% were a test set for model performance evaluation. The performance of our diagnostic artificial intelligence model ranged between 0.976-1 under the receiver operating characteristic curve. The test accuracy of the model reached 0.989, and the sensitivity and specificity were 96.66 and 96.64, respectively. Our study is the first to prove that a CNN can be trained as a diagnostic tool for PE using frontal chest X-rays, which is not possible by the human eye. It offers a convenient way to screen potential candidates for the surgical repair of PE, primarily using available image examinations.

COVID-19 chest X-ray image analysis by threshold-based segmentation

COVID-19 is a severe acute respiratory syndrome that has caused a major ongoing pandemic worldwide. Imaging systems such as conventional chest X-ray (CXR) and computed tomography (CT) were proven essential for patients due to the lack of information about the complications that could result from this disease. In this study, the aim was to develop and evaluate a method for automatic diagnosis of COVID-19 using binary segmentation of chest X-ray images. The study used frontal chest X-ray images of 27 infected and 19 uninfected individuals from Kaggle COVID-19 Radiography Database, and applied binary segmentation and quartering in MATLAB to analyze the images. The binary images of the lung were split into four quarters; Q1 = right upper quarter, Q2 = left upper quarter, Q3 = right lower, and Q4 = left lower. The results showed that COVID-19 patients had a higher percentage of attenuation in the lower lobes of the lungs (p-value < 0.00001) compared to healthy individuals, which is likely due to ground-glass opacities and consolidations caused by the infection. The ratios of white pixels in the four quarters of the X-ray images were calculated, and it was found that the left lower quarter had the highest number of white pixels but without a statistical significance compared to right lower quarter (p-value = 0.102792). This supports the theory that COVID-19 primarily affects the lower and lateral fields of the lungs, and suggests that the virus is accumulated mostly in the lower left quarter of the lungs. Overall, this study contributes to the understanding of the impact of COVID-19 on the respiratory system and can help in the development of accurate diagnostic methods.

Assessing the Impact of Image Resolution on Deep Learning for TB Lesion Segmentation on Frontal Chest X-rays.

Deep learning (DL) models are state-of-the-art in segmenting anatomical and disease regions of interest (ROIs) in medical images. Particularly, a large number of DL-based techniques have been reported using chest X-rays (CXRs). However, these models are reportedly trained on reduced image resolutions for reasons related to the lack of computational resources. Literature is sparse in discussing the optimal image resolution to train these models for segmenting the tuberculosis (TB)-consistent lesions in CXRs. In this study, we investigated the performance variations with an Inception-V3 UNet model using various image resolutions with/without lung ROI cropping and aspect ratio adjustments and identified the optimal image resolution through extensive empirical evaluations to improve TB-consistent lesion segmentation performance. We used the Shenzhen CXR dataset for the study, which includes 326 normal patients and 336 TB patients. We proposed a combinatorial approach consisting of storing model snapshots, optimizing segmentation threshold and test-time augmentation (TTA), and averaging the snapshot predictions, to further improve performance with the optimal resolution. Our experimental results demonstrate that higher image resolutions are not always necessary; however, identifying the optimal image resolution is critical to achieving superior performance.

A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis

In 2020, an experiment testing AI solutions for lung X-ray analysis on a multi-hospital network was conducted. The multi-hospital network linked 178 Moscow state healthcare centers, where all chest X-rays from the network were redirected to a research facility, analyzed with AI, and returned to the centers. The experiment was formulated as a public competition with monetary awards for participating industrial and research teams. The task was to perform the binary detection of abnormalities from chest X-rays. For the objective real-life evaluation, no training X-rays were provided to the participants. This paper presents one of the top-performing AI frameworks from this experiment. First, the framework used two EfficientNets, histograms of gradients, Haar feature ensembles, and local binary patterns to recognize whether an input image represents an acceptable lung X-ray sample, meaning the X-ray is not grayscale inverted, is a frontal chest X-ray, and completely captures both lung fields. Second, the framework extracted the region with lung fields and then passed them to a multi-head DenseNet, where the heads recognized the patient’s gender, age and the potential presence of abnormalities, and generated the heatmap with the abnormality regions highlighted. During one month of the experiment from 11.23.2020 to 12.25.2020, 17,888 cases have been analyzed by the framework with 11,902 cases having radiological reports with the reference diagnoses that were unequivocally parsed by the experiment organizers. The performance measured in terms of the area under receiving operator curve (AUC) was 0.77. The AUC for individual diseases ranged from 0.55 for herniation to 0.90 for pneumothorax.

Etiological and Radiological Profile of Acute Lower Respiratory Infections during the Pre-COVID Period in the Paediatric Ward of the Teaching Hospital of Mali and in the Community Health Centre of Yirimadio in Bamako

Introduction: Every year, nearly 4 million people pass away from acute respiratory infections. 98% of such deaths are due to lower respiratory tract infections. Even though studies have been carried on lower respiratory infections x-ray aspects in Mali, very few studies have been done to reveal bacteriological and virological evidence of this disease. Materials and methods: It is about a descriptive prospective study carried out from January to December 2018 having involved patients of all ages, coming for medical consultation at the Yirimadio Community-based health center as well as children from 6 months to 15 years old coming at the pediatric department of UHC Hôpital du Mali for a lower respiratory infection. They had all undergone chest X-ray and a PCR. The purpose: of this work is to study etiological and x-ray aspects of acute lower respiratory infections at the Yirimadio Community-based Health Center and at the UHC pediatric department of Hôpital du Mali. Findings: From January to December 2018, we recorded a frequency of 1.19%. The age group 0 - 5 years was the most represented (64.5%) with a sex ratio of 0.97 for women. Cough was the most common clinical sign (98.7%) followed by fever (58.9%). Standard frontal chest X-ray was pathological in 70% of our patients. It was bronchitis in 75.4% of cases, pneumonia (13.5%), and bronchopneumonia (12.3%). PCR positive was in 83.9% of patients. It revealed a co-infection in more than half of the patients (52.5%), bacterial infection (16.1%) and viral infection (15.2%). Pathogens isolated ranked by frequency were Streptococcus pneumoniaa (87.6%) followed by Staphylococcus aureus (24.9%) and human rhinovirus (17%). The most common viral causes were human rhinovirus (17%), followed by influenza A and B virus (7%) and human parainfluenza virus (7%). Conclusion: It stemed from the study that lower respiratory infections were mainly due to Streptococcus pneumonea and human rhinovirus during pre-COVID at the Yirimadio Community-based health center and UHC Hôpital du Mali.

Pre-deployment assessment of an AI model to assist radiologists in chest X-ray detection and identification of lead-less implanted electronic devices for pre-MRI safety screening: realized implementation needs and proposed operational solutions.

Chest X-ray (CXR) use in pre-MRI safety screening, such as for lead-less implanted electronic device (LLIED) recognition, is common. To assist CXR interpretation, we "pre-deployed" an artificial intelligence (AI) model to assess (1)accuracies in LLIED-type (and consequently safety-level) identification, (2)safety implications of LLIED nondetections or misidentifications, (3)infrastructural or workflow requirements, and (4)demands related to model adaptation to real-world conditions. A two-tier cascading methodology for LLIED detection/localization and identification on a frontal CXR was applied to evaluate the performance of the original nine-class AI model. With the unexpected early appearance of LLIED types during simulated real-world trialing, retraining of a newer 12-class version preceded retrialing. A zero footprint (ZF) graphical user interface (GUI)/viewer with DICOM-based output was developed for inference-result display and adjudication, supporting end-user engagement and model continuous learning and/or modernization. During model testing or trialing using both the nine-class and 12-class models, robust detection/localization was consistently 100%, with mAP 0.99 from fivefold cross-validation. Safety-level categorization was high during both testing ( and , respectively) and trialing (accuracy 98% and 97%, respectively). LLIED-type identifications by the two models during testing (1)were 98.9% and 99.5% overall correct and (2)consistently showed (1.00 for 8/9 and 9/12 LLIED-types, respectively). Pre-deployment trialing of both models demonstrated overall type-identification accuracies of 94.5% and 95%, respectively. Of the small number of misidentifications, none involved MRI-stringently conditional or MRI-unsafe types of LLIEDs. Optimized ZF GUI/viewer operations led to greater user-friendliness for radiologist engagement. Our LLIED-related AI methodology supports (1)100% detection sensitivity, (2)high identification (including MRI-safety) accuracy, and (3)future model deployment with facilitated inference-result display and adjudication for ongoing model adaptation to future real-world experiences.

Deep learning-based classification for lung opacities in chest x-ray radiographs through batch control and sensitivity regulation

In this study, we implemented a system to classify lung opacities from frontal chest x-ray radiographs. We also proposed a training method to address the class imbalance problem presented in the dataset. We participated in the Radiological Society of America (RSNA) 2018 Pneumonia Detection Challenge and used the datasets provided by the RSNA for further research. Using convolutional neural networks, we implemented a training procedure termed batch control to manipulate the data distribution of positive and negative cases in each training batch. The batch control method regulated and stabilized the performance of the deep-learning models, allowing the adaptive sensitivity of the network models to meet the specific application. The convolutional neural network is practical for classifying lung opacities on chest x-ray radiographs. The batch control method is advantageous for sensitivity regulation and optimization for class-unbalanced datasets.

A novel abnormality annotation database for COVID-19 affected frontal lung X-rays.

Consistent clinical observations of characteristic findings of COVID-19 pneumonia on chest X-rays have attracted the research community to strive to provide a fast and reliable method for screening suspected patients. Several machine learning algorithms have been proposed to find the abnormalities in the lungs using chest X-rays specific to COVID-19 pneumonia and distinguish them from other etiologies of pneumonia. However, despite the enormous magnitude of the pandemic, there are very few instances of public databases of COVID-19 pneumonia, and to the best of our knowledge, there is no database with annotation of abnormalities on the chest X-rays of COVID-19 affected patients. Annotated databases of X-rays can be of significant value in the design and development of algorithms for disease prediction. Further, explainability analysis for the performance of existing or new deep learning algorithms will be enhanced significantly with access to ground-truth abnormality annotations. The proposed COVID Abnormality Annotation for X-Rays (CAAXR) database is built upon the BIMCV-COVID19+ database which is a large-scale dataset containing COVID-19+ chest X-rays. The primary contribution of this study is the annotation of the abnormalities in over 1700 frontal chest X-rays. Further, we define protocols for semantic segmentation as well as classification for robust evaluation of algorithms. We provide benchmark results on the defined protocols using popular deep learning models such as DenseNet, ResNet, MobileNet, and VGG for classification, and UNet, SegNet, and Mask-RCNN for semantic segmentation. The classwise accuracy, sensitivity, and AUC-ROC scores are reported for the classification models, and the IoU and DICE scores are reported for the segmentation models.

75 Juvenile systemic sclerodermas: a case report

BackgroundSystemic scleroderma (SSc) is a rare generalized connective tissue disorder of poorly understood aetiology resulting in systemic fibrosis. It affects mainly women, usually in adulthood, but can occur at any age, although it is rare in children. Its prognosis is conditioned by cardiopulmonary involvement, which is the primary cause of mortality. Some innovative therapies have improved the management of this orphan disease.We report an observation of a 14-year-old child with systemic scleroderma.ObservationChild B.Z, 14 years old, without any particular history, consulted for a Raynaud's phenomenon that had appeared 4 months earlier. Clinical examination reveals localized skin sclerosis on the face and extremities of the upper limbs (Rodnan score = 11), associated with inflammatory-type arthralgias. Biologically: SV = 38 mmH1, CRP = 87 mg/l, FAN at 1/320 and positive Anti-Scl70. Periungual capillaroscopy showed megacapillaries with altered capillary architecture. The frontal chest X-ray did not reveal any interstitial syndrome, the cardiac ultrasound was without abnormalities (no PAH). The diagnosis of SSc was retained, the patient was put on calcium channel blockers (Diltiazem at a dose of 120 mg/d) associated with dietary rules and NSAIDs on demand with good improvement.ConclusionVery few cases of juvenile SSc have been reported in the literature. Its diagnosis should be based on the same ACR-EULAR 2013 criteria as those for adults. Its prognosis is conditioned by visceral damage which must be diagnosed and treated early.

An interpretable multi-task system for clinically applicable COVID-19 diagnosis using CXR.

With the emergence of continuously mutating variants of coronavirus, it is urgent to develop a deep learning model for automatic COVID-19 diagnosis at early stages from chest X-ray images. Since laboratory testing is time-consuming and requires trained laboratory personal, diagnosis using chest X-ray (CXR) is a befitting option. In this study, we proposed an interpretable multi-task system for automatic lung detection and COVID-19 screening in chest X-rays to find an alternate method of testing which are reliable, fast and easily accessible, and able to generate interpretable predictions that are strongly correlated with radiological findings. The proposed system consists of image preprocessing and an unsupervised machine learning (UML) algorithm for lung region detection, as well as a truncated CNN model based on deep transfer learning (DTL) to classify chest X-rays into three classes of COVID-19, pneumonia, and normal. The Grad-CAM technique was applied to create class-specific heatmap images in order to establish trust in the medical AI system. Experiments were performed with 15,884 frontal CXR images to show that the proposed system achieves an accuracy of 91.94% in a test dataset with 2,680 images including a sensitivity of 94.48% on COVID-19 cases, a specificity of 88.46% on normal cases, and a precision of 88.01% on pneumonia cases. Our system also produced state-of-the-art outcomes with a sensitivity of 97.40% on public test data and 88.23% on a previously unseen clinical data (1,000 cases) for binary classification of COVID-19-positive and COVID-19-negative films. Our automatic computerized evaluation for grading lung infections exhibited sensitivity comparable to that of radiologist interpretation in clinical applicability. Therefore, the proposed solution can be used as one element of patient evaluation along with gold-standard clinical and laboratory testing.

Deep learning-based patient re-identification is able to exploit the biometric nature of medical chest X-ray data

With the rise and ever-increasing potential of deep learning techniques in recent years, publicly available medical datasets became a key factor to enable reproducible development of diagnostic algorithms in the medical domain. Medical data contains sensitive patient-related information and is therefore usually anonymized by removing patient identifiers, e.g., patient names before publication. To the best of our knowledge, we are the first to show that a well-trained deep learning system is able to recover the patient identity from chest X-ray data. We demonstrate this using the publicly available large-scale ChestX-ray14 dataset, a collection of 112,120 frontal-view chest X-ray images from 30,805 unique patients. Our verification system is able to identify whether two frontal chest X-ray images are from the same person with an AUC of 0.9940 and a classification accuracy of 95.55%. We further highlight that the proposed system is able to reveal the same person even ten and more years after the initial scan. When pursuing a retrieval approach, we observe an mAP@R of 0.9748 and a precision@1 of 0.9963. Furthermore, we achieve an AUC of up to 0.9870 and a precision@1 of up to 0.9444 when evaluating our trained networks on external datasets such as CheXpert and the COVID-19 Image Data Collection. Based on this high identification rate, a potential attacker may leak patient-related information and additionally cross-reference images to obtain more information. Thus, there is a great risk of sensitive content falling into unauthorized hands or being disseminated against the will of the concerned patients. Especially during the COVID-19 pandemic, numerous chest X-ray datasets have been published to advance research. Therefore, such data may be vulnerable to potential attacks by deep learning-based re-identification algorithms.