Chest Radiographic Images Research Articles

An effective approach for CT lung segmentation using region growing

X-ray is an important means of detecting lung diseases. With the increasing incidence of lung diseases, computer-aided diagnosis technology is of great significance in clinical treatment. It has become a hot research direction to use computer-aided diagnosis to recognize chest radiography images, which can alleviate the uneven status of regional medical level. For clinical diagnosis, medical image segmentation can enable users to timely obtain the target region they are interested in and analyze it, which is significant to be used as an important basis for auxiliary research and judgment. In this case, a region growing algorithm based on threshold presegmentation is selected for lung segmentation, which integrates image enhancement, threshold segmentation, seed point selection and morphological post-processing, etc., to improve the segmentation effect, which also has certain reference value for other medical image processing.

COVID-19 infection localization and severity grading from chest X-ray images

The immense spread of coronavirus disease 2019 (COVID-19) has left healthcare systems incapable to diagnose and test patients at the required rate. Given the effects of COVID-19 on pulmonary tissues, chest radiographic imaging has become a necessity for screening and monitoring the disease. Numerous studies have proposed Deep Learning approaches for the automatic diagnosis of COVID-19. Although these methods achieved outstanding performance in detection, they have used limited chest X-ray (CXR) repositories for evaluation, usually with a few hundred COVID-19 CXR images only. Thus, such data scarcity prevents reliable evaluation of Deep Learning models with the potential of overfitting. In addition, most studies showed no or limited capability in infection localization and severity grading of COVID-19 pneumonia. In this study, we address this urgent need by proposing a systematic and unified approach for lung segmentation and COVID-19 localization with infection quantification from CXR images. To accomplish this, we have constructed the largest benchmark dataset with 33,920 CXR images, including 11,956 COVID-19 samples, where the annotation of ground-truth lung segmentation masks is performed on CXRs by an elegant human-machine collaborative approach. An extensive set of experiments was performed using the state-of-the-art segmentation networks, U-Net, U-Net++, and Feature Pyramid Networks (FPN). The developed network, after an iterative process, reached a superior performance for lung region segmentation with Intersection over Union (IoU) of 96.11% and Dice Similarity Coefficient (DSC) of 97.99%. Furthermore, COVID-19 infections of various shapes and types were reliably localized with 83.05% IoU and 88.21% DSC. Finally, the proposed approach has achieved an outstanding COVID-19 detection performance with both sensitivity and specificity values above 99%.

AIDCOV: An Interpretable Artificial Intelligence Model for Detection of COVID-19 from Chest Radiography Images

As the Coronavirus Disease 2019 (COVID-19) pandemic continues to grow globally, testing to detect COVID-19 and isolating individuals who test positive remains the primary strategy for preventing community spread of the disease. Therefore, automatic and accurate detection of COVID-19 using medical imaging modalities, which are more widely available and accessible, can be beneficial as an alternative diagnostic tool. In this study, an Artificial Intelligence model for Detection of COVID-19 (AIDCOV) is developed to classify chest radiography images as belonging to a person with either COVID-19, other infections, or no pneumonia (i.e., normal). The hierarchical structure in AIDCOV captures the dependencies among features and improves model performance while an attention mechanism makes the model interpretable and transparent. We used several publicly available datasets of both computed tomography (CT) and X-ray modalities. The main public dataset for chest X-ray images contains 475 COVID-19 samples, 3949 samples from other viral/bacterial infections, and 1583 normal samples. Our model achieves a mean cross-validation accuracy of 98.4%. AIDCOV has a sensitivity of 99.8%, a specificity of 100%, and an F1-score of 99.8% in detecting COVID-19 from X-ray images on that dataset. Using a large dataset of CT images, our model obtained mean cross-validation accuracy and sensitivity of 98.8% and 99.4%, respectively. Additionally, our interpretable model can distinguish subtle signs of infection within each radiography image. Assuming these results hold up in larger datasets obtained from a variety of patients over the world, AIDCOV can be used in conjunction with or instead of RT-PCR testing (where RT-PCR testing is unavailable) to detect and isolate individuals with COVID-19, prevent onward transmission to the general population and healthcare workers, and highlight the areas in the lungs that show signs of COVID-related damage.

OLEOTHORAX: PULMONARY PLOMBAGE

TOPIC: Imaging TYPE: Medical Student/Resident Case Reports INTRODUCTION: Plombage (extra-pleural pneumonolysis) is a surgical treatment method used to treat cavitary lesions of the lung in patients with pulmonary tuberculosis (TB) during 1930–50s before the introduction of anti-TB chemotherapy by creating a cavity surgically under the ribs in the chest wall and filling the space with inert material [1]. The materials used in this procedure are acrylic balls, fat, wax, rubber, and mineral oil (Oleothorax). Rarely, Plombage is used to seal a large bronchopleural fistula that causes refractory pneumothorax, with only one reported case in the literature [2]. We present another case of Pulmonary Plombage (Oleothorax) used in successfully treating refractory pneumothorax. CASE PRESENTATION: A 62-year-old man with a history of hypertension and symptomatic bradycardia requiring a permanent pacemaker came in with worsening shortness of breath associated with decreased exercise tolerance and orthopnea. The examination was remarkable for pan systolic murmur at the apex, jugular venous distention, and decreased breath sounds in the right lung base. Chest radiograph (Image 1) revealed cardiomegaly and a pleural-based rounded mass in the right pleural space inferiorly. Computed tomography (Image 2) showed a loculated cystic mass (label A) (13x9x10 cm) measuring slightly above water density and apical bullae. An echocardiogram revealed severe left atrial and left ventricular dilation with an ejection fraction of 55% and prolapse of the anterior leaflet of the mitral valve (MV) with severe mitral regurgitation (MR). Pulmonary service was consulted for loculated cystic mass in the lung, upon further questioning, the patient mentioned he had lung surgery in 1993 due to recurrent pneumothorax, which was found to be Pulmonary Plombage. He was started on intravenous loop diuretics for congestive heart failure secondary to MR with improvement in symptoms. DISCUSSION: We presented the modern imaging description of a Plombage thoracoplasty performed to treat refractory pneumothorax with an uncomplicated outcome 28 years after surgery. A new method to treat pneumothorax due to a large cavity with a bronchopleural fistula. The utility of Pulmonary Plombage to seal a large bronchopleural fistula causing refractory pneumothorax has not been studied, with only one case report [2] in the literature where they used pericardial fat pad as Plombage to successfully treat refractory pneumothorax without complications after 48 years. This technique involves complications like hemorrhage, infection, fistulization to the skin. Radiographic characters depend on the material used in the Plombage treatment. The cystic mass measuring slightly above water density seen in our patient was filled with mineral oil (Oleothorax). CONCLUSIONS: Pulmonary Plombage, a historical treatment used to treat cavitary lesions in tuberculosis patients, can be used effectively in treating refractory pneumothorax. REFERENCE #1: Namana V, Gupta SS, Sarasam R, Mathur P: Historical TB treatment—Plombage. QJM An Int J Med. 2017, 110:191. 10.1093/qjmed/hcw213 REFERENCE #2: Nakano T, Tsubochi H, Minegishi K, Endo S: Pericardial fat pad plombage for pulmonary cavity causing massive air leakage. Surg Case Reports. 2020, 6:156. 10.1186/s40792-020-00917-7 DISCLOSURES: No relevant relationships by Akshay Avula, source=Web Response No relevant relationships by Elias Chuki, source=Web Response No relevant relationships by Raja Jadav, source=Web Response No relevant relationships by Harry Sequeira gross, source=Web Response

RESPECTING PATIENT PRIVACY WITH FEDERATED ARTIFICIAL INTELLIGENCE

Multiple research has shown that deep artificial neural networks (ANN) can assist physicians in diagnosing a patient with greater accuracy and sensitivity. ANN applications are not limited to just the classification of diseases but also include image segmentation, tumor localization, and mortality rate predictions. Nonetheless, the great march of success by ANN is only possible by the availability of an open medical dataset. Only with such open datasets can developers build, train and test ANN models to obtain higher accuracy. However, there is yet an open medical dataset in Malaysia that can be used to validate ANN performance on local patients. This may be due to local medical institution's hesitance to release any medical images and records to respect patient's confidentiality. One way around this is to adopt the Ensemble or Federated Learning system. In federated learning, medical institutes share their locally trained ANN model's weight and bias to create a single federated level ANN model. While in ensemble learning, multiple ANN models are used to vote on the most probable class for each data. In both systems, no sharing of patient's data is required. In our experiment, we tested the capability of 25 ANN models to classify chest radiograph images into three classes; normal, bacterial pneumonia, and viral pneumonia. Each ANN model is given a training dataset that is random in size and class ratio. The result obtained from the experiment shows that the federated system obtains the highest score in all measured metrics. It obtains a score of 0.76, 0.72, and 0.72 for average weighted precision, weight sensitivity, and F1, respectively. It also has the lowest standard deviation in all performance metrics compare to other learning systems. The result obtains here further strengthens the notion that if Malaysia wants to adopt a national-level artificial intelligent system for medical purposes, it should utilize the federated learning system at its core. It ensures Malaysia has an artificial intelligence system that respects patient's privacy while maintains its robustness.

Role of standard and soft tissue chest radiography images in deep-learning-based early diagnosis of COVID-19.

.Purpose: We propose a deep learning method for the automatic diagnosis of COVID-19 at patient presentation on chest radiography (CXR) images and investigates the role of standard and soft tissue CXR in this task.Approach: The dataset consisted of the first CXR exams of 9860 patients acquired within 2 days after their initial reverse transcription polymerase chain reaction tests for the SARS-CoV-2 virus, 1523 (15.5%) of whom tested positive and 8337 (84.5%) of whom tested negative for COVID-19. A sequential transfer learning strategy was employed to fine-tune a convolutional neural network in phases on increasingly specific and complex tasks. The COVID-19 positive/negative classification was performed on standard images, soft tissue images, and both combined via feature fusion. A U-Net variant was used to segment and crop the lung region from each image prior to performing classification. Classification performances were evaluated and compared on a held-out test set of 1972 patients using the area under the receiver operating characteristic curve (AUC) and the DeLong test.Results: Using full standard, cropped standard, cropped, soft tissue, and both types of cropped CXR yielded AUC values of 0.74 [0.70, 0.77], 0.76 [0.73, 0.79], 0.73 [0.70, 0.76], and 0.78 [0.74, 0.81], respectively. Using soft tissue images significantly underperformed standard images, and using both types of CXR failed to significantly outperform using standard images alone.Conclusions: The proposed method was able to automatically diagnose COVID-19 at patient presentation with promising performance, and the inclusion of soft tissue images did not result in a significant performance improvement.

A Fine-tuned deep convolutional neural network for chest radiography image classification on COVID-19 cases.

The outbreak of coronavirus disease 2019 (COVID-19) continues to have a catastrophic impact on the living standard of people worldwide. To fight against COVID-19, many countries are using a combination of containment and mitigation activities. Effective screening of contaminated patients is a critical step in the battle against COVID-19. During the early medical examination, it was observed that patient having abnormalities in chest radiography images shows the symptoms of COVID-19 infection. Motivated by this, in this article, we proposed a unique framework to diagnose the COVID-19 infection. Here, we removed the fully connected layers of an already proven model VGG-16 and placed a new simplified fully connected layer set that is initialized with some random weights on top of this deep convolutional neural network, which has already learned discriminative features, namely, edges, colors, geometric changes,shapes, and objects. To avoid the risk of destroying the rich features, we warm up our FC head by seizing all layers in the body of our network and then unfreeze all the layers in the network body to be fine-tuned.The suggested classification model achieved an accuracy of 97.12% with 99.2% sensitivity and 99.6% specificity for COVID-19 identification. This classification model is superior to the other classification model used to classify COVID-19 infected patients.

PTXNet: An extended UNet model based segmentation of pneumothorax from chest radiography images

AbstractIn the respiratory analysis of human beings, lungs play an important role and can be used to find several associated diseases. One of such conditions is called pneumothorax which occurs due to leaking of air into pleural space and results in lungs collapse. The traditional methodology uses chest radiography with the manual intervention of radiologists for the detection and segmentation of the affected areas. This paper introduces a deep neural network based methodology for the automatic localization and segmentation of the proper region‐of‐interest (RoI). The proposed approach is based on transfer learning where the existing UNet model is extended and redesigned to a new architecture named PTXNet for RoI segmentation. In PTXNet, the traditional encoder is redesigned with the use of EfficientNet, SE‐ResNeXt50 and Xception convolutional neural network (CNN) architectures. Furthermore, residual blocks are introduced in the decoder phase and concatenation of the previous decoder stage feature maps in addition to standard global skip connections is performed. The PTXNet is trained on a dataset of more than 15,000 chest radiography and resulted in the mean dice coefficient of 84.89%. It is found that the proposed approach provides superior results than the UNet model with an increase in the mean dice coefficient of 18.76%.

Optimal number of strong labels for curriculum learning with convolutional neural network to classify pulmonary abnormalities in chest radiographs.

It is important to alleviate annotation efforts and costs by efficiently training on medical images. We performed a stress test on several strong labels for curriculum learning with a convolutional neural network to differentiate normal and five types of pulmonary abnormalities in chest radiograph images. The numbers of CXR images of healthy subjects and patients, acquired at Asan Medical Center (AMC), were 6069 and 3465, respectively. The numbers of CXR images of patients with nodules, consolidation, interstitial opacity, pleural effusion, and pneumothorax were 944, 550, 280, 1360, and 331, respectively. The AMC dataset was split into training, tuning, and test, with a ratio of 7:1:2. All lesions were strongly labeled by thoracic expert radiologists, with confirmation of the corresponding CT. For curriculum learning, normal and abnormal patches (N=26658) were randomly extracted around the normal lung and strongly labeled abnormal lesions, respectively. In addition, 1%, 5%, 20%, 50%, and 100% of strong labels were used to determine an optimal number for them. Each patch dataset was trained with the ResNet-50 architecture, and all CXRs with weak labels were used for fine-tuning them in a transfer-learning manner. A dataset acquired from the Seoul National University Bundang Hospital (SNUBH) was used for external validation. The detection accuracies of the 1%, 5%, 20%, 50%, and 100% datasets were 90.51, 92.15, 93.90, 94.54, and 95.39, respectively, in the AMC dataset and 90.01, 90.14, 90.97, 91.92, and 93.00 in the SNUBH dataset. Our results showed that curriculum learning with over 20% sampling rate for strong labels are sufficient to train a model with relatively high performance, which can be easily and efficiently developed in an actual clinical setting.

A bagging dynamic deep learning network for diagnosing COVID-19

COVID-19 is a serious ongoing worldwide pandemic. Using X-ray chest radiography images for automatically diagnosing COVID-19 is an effective and convenient means of providing diagnostic assistance to clinicians in practice. This paper proposes a bagging dynamic deep learning network (B-DDLN) for diagnosing COVID-19 by intelligently recognizing its symptoms in X-ray chest radiography images. After a series of preprocessing steps for images, we pre-train convolution blocks as a feature extractor. For the extracted features, a bagging dynamic learning network classifier is trained based on neural dynamic learning algorithm and bagging algorithm. B-DDLN connects the feature extractor and bagging classifier in series. Experimental results verify that the proposed B-DDLN achieves 98.8889% testing accuracy, which shows the best diagnosis performance among the existing state-of-the-art methods on the open image set. It also provides evidence for further detection and treatment.

Federated Semi-Supervised Multi-Task Learning to Detect COVID-19 and Lungs Segmentation Marking Using Chest Radiography Images and Raspberry Pi Devices: An Internet of Medical Things Application.

Internet of Medical Things (IoMT) provides an excellent opportunity to investigate better automatic medical decision support tools with the effective integration of various medical equipment and associated data. This study explores two such medical decision-making tasks, namely COVID-19 detection and lung area segmentation detection, using chest radiography images. We also explore different cutting-edge machine learning techniques, such as federated learning, semi-supervised learning, transfer learning, and multi-task learning to explore the issue. To analyze the applicability of computationally less capable edge devices in the IoMT system, we report the results using Raspberry Pi devices as accuracy, precision, recall, for COVID-19 detection, and average dice score for lung segmentation detection tasks. We also publish the results obtained through server-centric simulation for comparison. The results show that Raspberry Pi-centric devices provide better performance in lung segmentation detection, and server-centric experiments provide better results in COVID-19 detection. We also discuss the IoMT application-centric settings, utilizing medical data and decision support systems, and posit that such a system could benefit all the stakeholders in the IoMT domain.

An Expert-Assisted Chest Radiograph Classification Tool To Differentiate Between Active Tuberculosis and Healed Tuberculosis Sequelae

Tuberculosis (TB) heals with a scarring response in the lung and chest radiographic abnormalities termed as tuberculosis sequelae are often observed in patients with healed pulmonary TB. Patients with healed TB can also have frequent chest infections, breathlessness and fever, which are also seen in active pulmonary TB. This leads to frequent mismanagement of these patients where they are treated as active TB cases. In this paper, we present a method to differentiate between active and healed pulmonary TB patients using their chest radiograph images. Our method requires the clinician to acquire the image of the chest radiograph using a hand-held cellular smartphone, and then mark points along the boundary of the lungs in the image. We then use these point markings in an iterative Otsu-based thresholding method, parameterized optimally using a discrete simulation optimization technique, to segment the lungs from the rest of the image. Clinically relevant morphological features such as the lung areas, lung base curvatures and tracheal shift, and textural features such as average intensity within the lung, are extracted from the segmented image. We then train multiple standard machine learning methods on the extracted features, and convolutional neural networks on the segmented images themselves to classify the radiograph images. We achieve area under the receiver operating characteristic curve scores of up to 0.83. We also present results from preliminary experiments conducted to estimate the extent of inter-doctor variability in marking points on the lung boundaries.

Artificial Intelligence Framework for Efficient Detection and Classification of Pneumonia Using Chest Radiography Images

BackgroundChest diseases are serious health problems that threaten the lives of people. The early and accurate diagnosis of such diseases is very crucial in the success of their treatment and cure. Pneumonia is one of the most widely occurred chest diseases responsible for a high percentage of deaths especially among children. So, detection and classification of pneumonia using the non-invasive chest x-ray imaging would have a great advantage of reducing the mortality rates.ResultsThe results showed that the best input image size in this framework was 64 × 64 based on comparison between different sizes. Using CNN as a deep features extractor and utilizing the tenfold methodology the propose artificial intelligence framework achieved an accuracy of 94% for SVM and 93.9% for KNN, a sensitivity of 93.33% for SVM and 93.19% for KNN and a specificity of 96.68% for SVM and 96.60% for KNN.ConclusionsIn this study, an artificial intelligence framework has been proposed for the detection and classification of pneumonia based on chest x-ray imaging with different sizes of input images. The proposed methodology used CNN for features extraction that were fed to two different types of classifiers, namely, SVM and KNN; in addition to the SoftMax classifier which is the default CNN classifier. The proposed CNN has been trained, validated, and tested using a large dataset of chest x-ray images contains in total 5852 images.

Automated detection of Covid-19 disease using deep fused features from chest radiography images

The health systems of many countries are desperate in the face of Covid-19, which has become a pandemic worldwide and caused the death of hundreds of thousands of people. In order to keep Covid-19, which has a very high propagation rate, under control, it is necessary to develop faster, low-cost and highly accurate methods, rather than a costly Polymerase Chain Reaction test that can yield results in a few hours. In this study, a deep learning-based approach that can detect Covid-19 quickly and with high accuracy on X-ray images, which are common in every hospital and can be obtained at low cost, was proposed. Deep features were extracted from X-Ray images in RGB, CIE Lab and RGB CIE color spaces using DenseNet121 and EfficientNet B0 pre-trained deep learning architectures and then obtained features were fed into a two-stage classifier approach. Each of the classifiers in the proposed approach performed binary classification. In the first stage, healthy and infected samples were separated, and in the second stage, infected samples were detected as Covid-19 or pneumonia. In the experiments, Bi-LSTM network and well-known ensemble approaches such as Gradient Boosting, Random Forest and Extreme Gradient Boosting were used as the classifier model and it was seen that the Bi-LSTM network had a superior performance than other classifiers with 92.489% accuracy.

Anomaly Detection Approach to Identify Early Cases in a Pandemic using Chest X-rays

The current COVID-19 pandemic is now getting contained, albeit at the cost of more than 2.3 million human lives. A critical phase in any pandemic is the early detection of cases to develop preventive treatments and strategies. In the case of COVID-19, several studies have indicated that chest radiography images of the infected patients show characteristic abnormalities. However, at the onset of a given pandemic, such as COVID-19, there may not be sufficient data for the affected cases to train models for their robust detection. Hence, supervised classification is ill-posed for this problem because the time spent in collecting large amounts of data from infected persons could lead to the loss of human lives and delays in preventive interventions. Therefore, we formulate the problem of identifying early cases in a pandemic as an anomaly detection problem, in which the data for healthy patients is abundantly available, whereas no training data is present for the class of interest (COVID-19 in our case). To solve this problem, we present several unsupervised deep learning approaches, including convolutional and adversarially trained autoencoder. We tested two settings on a publicly available dataset (COVIDx) by training the model on chest X-rays from (i) only healthy adults, and (ii) healthy and other non-COVID-19 pneumonia, and detected COVID-19 as an anomaly. After performing 3-fold cross validation, we obtain a ROC-AUC of 0.765. These results are very encouraging and pave the way towards research for ensuring emergency preparedness in future pandemics, especially the ones that could be detected from chest X-rays.

MO170“SWEET HYPOXIA” WITH ACUTE KIDNEY INJURY: THE UNPREDICTABILITY OF ACUTE HYPOXIC RESPIRATORY FAILURE IN COVID-19 INFECTION - A COMMUNITY HOSPITAL EXPERIENCE

Background and AimsSevere COVID-19 infection may result in hypoxemic respiratory failure necessitating invasive mechanical ventilation. We revisit the phenomenon of asymptomatic patients despite very low pulse oximetry readings, the so-called “sweet hypoxia” or “happy hypoxia” or “silent hypoxemia”. We describe for the first time, the sequential chest radiographic images of the progressive radiological trajectory of COVID-19 pneumonia.Method Case Report. ResultsA 62-year old hypertensive obese Caucasian male, an ex-smoker, was diagnosed with mild community-acquired pneumonia in mid-March 2020, following evaluation for low grade fever. He had traveled to Florida and Texas in the previous month. He tested positive for COVID-19 by RT-PCR. A week later, he was admitted to a Community Hospital with one day history of new shortness of breath and loose stools. Vital signs were stable. Pulse oximeter was 96% on room air. He was fatigued with few bibasilar lung crackles. CBC was normal. Creatinine was 1.0 mg/dL. Abnormal laboratory: sodium 131 mmol/L, AST 50 iu/L, ALT 96 iu/L. Chest radiograph revealed new patchy left lower lobe airspace infiltrate (Figure 1B). EKG showed regular sinus rhythm of 96/min, QT interval 445 msec and PVCs. Treatment included nasal cannula oxygen, IV fluids, IV Azithromycin and IV Ceftriaxone. He improved the next day, requested discharge home, vital signs were stable, pulse oximetry was 91% on room air, sodium had normalized at 137 mmol/L and he was discharged home on Azithromycin 500 mg daily x 3 days and Cefdinir 300 mg BID x 5 days.MO170 Figure 1:Sequence of chest radiographs, normal in November 2019 (A), before initial hospital admission - March 20, 2020 @ 02:10:10 (B), and just before intubation in the Emergency Department following the second .admission - March 22, 2020 @ 03:32:01 (C).He cheerfully went home. Later that night he quickly developed worsening dyspnea. He was readmitted about 18 hours post-discharge. Temperature 99.40F, blood pressure 161/101, pulse 100/min. He was tachypneic and pulse oximetry was 82% on room air. This improved to 93% on 4.5 LPM nasal cannula oxygen. Initial EKG was normal. New pertinent laboratory data: Bicarbonate 17 mmol/L, phosphorus 5.5 mg/dL, calcium 7.2 mg/dL, creatinine 1.1 mg/dL, BNP 31 pg/mL and lactic acid 1.2 mmol/L. PTT was 28.3 sec. HIV-1 p24 AG, HIV-1 AB, HIV-2 AB, HbSAG and Hepatitis C AB were negative. Chest radiograph showed worsening bilateral infiltrates (Figure 1C). He very quickly desaturated in the ED down to 81% despite high flow oxygen therapy. He was promptly intubated (Figure 2A). Oxygenation immediately improved. He was transferred to the ICU on IV Vancomycin and IV Cefepime. He developed septic shock and required IV Norepinephrine. With worsening chest radiographs, (Figures 2B & 2C), he was transferred to a tertiary medical center. On transfer, pertinent new data: creatinine 1.38 mg/dL, albumin 2.8 g/dL, Ferritin 2,573 ng/mL, LDH 534 u/L, CRP 6.0 mg/L, INR 1.2, D-Dimer 1.04, procalcitonin 0.38 ng/mL, WBC 13.3 x 109/L. EKG showed sinus bradycardia. Urine Legionnaire AG and Strep. Pneumonia AG were negative. IV Azithromycin 500 mg daily and IV Ceftriaxone 2 gm daily were administered for 8 days. Chloroquine phosphate 500 mg 2x daily was added. IV Norepinephrine was continued. IV fluids were withheld. The head of the bed was elevated to >300. DVT prophylaxis with SQ Enoxaparin and Vitamin C were administered. New blood cultures remained negative. COVID-19 RT-PCR after 3 days remained positive. He was extubated after 4 days and discharged home after 9 days with normalized creatinine of 1.03 mg/dL.ConclusionWe have for the first time demonstrated the sequential chest radiographic images of the progressive radiological trajectory of COVID-19 pneumonia. The place of non-invasive ventilation demands further study. The so-called “sweet hypoxia” or “happy hypoxia” or “silent hypoxemia” in COVID-19 is revisited – indeed, it is not exactly limited to COVID-19 patients. The need to mitigate lung barotrauma is mandatory. Finally, prognostication of pneumonia in COVID-19 is unpredictable. Too early premature discharge from the hospital is strongly discouraged.

Performance of SURF and SIFT Keypoints for the Automated Differentiation of Abnormality in Chest Radiographs.

In this work, automated abnormality detection using keypoint information from Speeded-Up Robust feature (SURF) and Scale Invariant Feature Transform (SIFT) descriptors in chest Radiographic (CR) images is investigated and compared. Computerized image analysis using artificial intelligence is crucial to detect subtle and non-specific alterations of Tuberculosis (TB). For this, the healthy and TB CRs are subjected to lung field segmentation. SURF and SIFT keypoints are extracted from the segmented lung images. Statistical features from keypoints, its scale and orientation are computed. Discrimination of TB from healthy is performed using SVM. Results show that the SURF and SIFT methods are able to extract local keypoint information in CRs. Linear SVM is found to perform better with precision of 88.9% and AUC of 91% in TB detection for combined features. Hence, the application of keypoint techniques is found to have clinical relevance in the automated screening of non-specific TB abnormalities using CRs.

Vulnerability in Deep Transfer Learning Models to Adversarial Fast Gradient Sign Attack for COVID-19 Prediction from Chest Radiography Images

The COVID-19 pandemic requires the rapid isolation of infected patients. Thus, high-sensitivity radiology images could be a key technique to diagnose patients besides the polymerase chain reaction approach. Deep learning algorithms are proposed in several studies to detect COVID-19 symptoms due to the success in chest radiography image classification, cost efficiency, lack of expert radiologists, and the need for faster processing in the pandemic area. Most of the promising algorithms proposed in different studies are based on pre-trained deep learning models. Such open-source models and lack of variation in the radiology image-capturing environment make the diagnosis system vulnerable to adversarial attacks such as fast gradient sign method (FGSM) attack. This study therefore explored the potential vulnerability of pre-trained convolutional neural network algorithms to the FGSM attack in terms of two frequently used models, VGG16 and Inception-v3. Firstly, we developed two transfer learning models for X-ray and CT image-based COVID-19 classification and analyzed the performance extensively in terms of accuracy, precision, recall, and AUC. Secondly, our study illustrates that misclassification can occur with a very minor perturbation magnitude, such as 0.009 and 0.003 for the FGSM attack in these models for X-ray and CT images, respectively, without any effect on the visual perceptibility of the perturbation. In addition, we demonstrated that successful FGSM attack can decrease the classification performance to 16.67% and 55.56% for X-ray images, as well as 36% and 40% in the case of CT images for VGG16 and Inception-v3, respectively, without any human-recognizable perturbation effects in the adversarial images. Finally, we analyzed that correct class probability of any test image which is supposed to be 1, can drop for both considered models and with increased perturbation; it can drop to 0.24 and 0.17 for the VGG16 model in cases of X-ray and CT images, respectively. Thus, despite the need for data sharing and automated diagnosis, practical deployment of such program requires more robustness.

Chest Dynamic-Ventilatory Digital Radiography in Chronic Obstructive or Restrictive Lung Disease.

ObjectiveThe aim of this study was to identify the relationships between parameters obtained from dynamic-ventilatory digital radiography (DR) and ventilatory disorders.MethodsThis study comprised 273 participants with respiratory diseases who underwent spirometry and functional residual capacity measurements (104 with normal findings on spirometry as controls, 139 with an obstructive lung disorder, 30 with a restrictive lung disorder) were assessed by dynamic-ventilatory DR. Sequential chest radiography images of the patient’s slow and maximum breathing were captured at 15 frames per second by a dynamic flat-panel imaging system. The system measured the following parameters: lung area at maximum inspiration divided by height (lung area_in/height), changes in tracheal diameter due to respiratory motions, rate of tracheal narrowing, diaphragmatic motion, and rate of change in lung area due to respiratory motion. Relationships between these parameters and ventilatory disorders were analyzed.ResultsLung area_in/height in patients with restrictive disorders showed significant decreases. Tracheal diameter change and tracheal narrowing rate in patients with obstructive disorders were significantly increased compared to both the control participants and patients with restrictive disorders. Patients with obstructive disorders and patients with restrictive disorders showed decreased diaphragmatic motion and lung area change rate. With the restrictive disorders as references, the area under the curve (AUC), sensitivity and specificity of lung area_in/height were 0.88, 0.77, and 0.88, respectively. With the obstructive disorders as references, the AUC, sensitivity and specificity of tracheal narrowing rate were 0.67, 0.53 and 0.81, respectively.ConclusionDynamic-ventilatory DR shows potential as a method for the detection and evaluation of ventilatory disorders in patients with respiratory diseases.

Classification of Healthy Control and Abnormal Lung Chest Radiography images using CBIR and Atlas-Based Graph cut Segmentation by Transfer Learning CNNs

The prominent aim of systematic lung pathologies detection is to improve health outcomes among people with pulmonary diseases and decrease thorax diseases disseminating among the peoples through improved lung abnormality detection, reduction in diagnostic delays and early treatment. Today technological breakthroughs have led to the discovery of various invasive clinical imaging methods for the analysis of lung diseases. In this work, an integrated Computer-Aided Diagnoses (CAD) based on Deep Learning (DL) to diagnosis of lung diseases on chest radiographs was proposed. In this paper we have used JSRT datasets it contains 247 images are employed atlas-based graph-cut segmentation algorithm for extract the lung regions and segmented regions are input to the Convolutional Neural Network (CNN) with augmentation techniques that are provides the training accuracy is 97% and 89% for testing accuracy.