Diagnostic Yield of Fiberoptic Bronchoscopy for the Evaluation of Chronic Cough in Patients with Normal Chest X-Ray

It has recently been shown that the interpretation by partial differential equations (PDEs) of a class of convolutional neural networks (CNNs) supports definition of architectures such as parabolic and hyperbolic networks. These networks have provable properties regarding the stability against the perturbations of the input features. Aiming for robustness, we tackle the problem of detecting changes in chest X-ray images that may be suggestive of COVID-19 with parabolic and hyperbolic CNNs and with domain-specific transfer learning. To this end, we compile public data on patients diagnosed with COVID-19, pneumonia, and tuberculosis, along with normal chest X-ray images. The negative impact of the small number of COVID-19 images is reduced by applying transfer learning in several ways. For the parabolic and hyperbolic networks, we pretrain the networks on normal and pneumonia images and further use the obtained weights as the initializers for the networks to discriminate between COVID-19, pneumonia, tuberculosis, and normal aspects. For DenseNets, we apply transfer learning twice. First, the ImageNet pretrained weights are used to train on the CheXpert dataset, which includes 14 common radiological observations (e.g., lung opacity, cardiomegaly, fracture, support devices). Then, the weights are used to initialize the network which detects COVID-19 and the three other classes. The resulting networks are compared in terms of how well they adapt to the small number of COVID-19 images. According to our quantitative and qualitative analysis, the resulting networks are more reliable compared to those obtained by direct training on the targeted dataset.

Download Full-text

Przewlekły kaszel jako główna manifestacja chłoniaka Hodgkina – opis przypadku

Nowa Pediatria ◽

10.25121/np.2019.23.3.107 ◽

2019 ◽

Vol 23 (3) ◽

Author(s):

Katarzyna Wójcicka ◽

Andrzej Pogorzelski

Keyword(s):

Chronic Cough ◽

Correct Diagnosis ◽

Diagnostic Methods ◽

Radiographic Examination ◽

Older Children ◽

X Ray ◽

Volume Curve ◽

Flow Volume Curve ◽

Mediastinal Widening ◽

Chest X Ray

A cough lasting longer than 4-8 weeks, defined as chronic cough, always requires thorough diagnostic evaluation. In addition to detailed history-taking and physical examination, simple and available diagnostic methods, such as chest x-ray and spirometry, should be performed. They may be helpful tool to establish the underlying cause of cough. Many younger children may have difficulties in performing the forced expiratory maneuvers and fulfilling repeatability criteria for spirometry. The disturbances resulting from insufficient cooperation should be considered in interpratation of the obtained results. The shape of the flow-volume curve, which suggests upper or central airways obstruction, can not be ignored and always requires further investigation for diagnosis of respiratory pathology. The chest x-ray is the most frequently performed radiographic examination in children. Accurate interpretation is essential in reaching a correct diagnosis. Mediastinal widening on the chest x-ray in children can occur due to a large variety of causes. The normal thymus can take on a variety of sizes and shapes and still be considered normal in the first few years of life. In older children mediastinal widening should be differentiated from mediastinal masses. Lymph node enlargement represents a frequent cause, usually as a result of infection or malignancy. The article reports a case of a 12-year-old boy with chronic cough, mediastinal widening on the chest X-ray and abnormal spirometry results, who was finally diagnosed with stage III Hodgkin’s lymphoma.

Download Full-text

The normal chest X-ray

Radiology for Medical Finals ◽

10.1201/9781315155395-3 ◽

2017 ◽

pp. 15-34

Author(s):

Thomas Kurka

Keyword(s):

X Ray ◽

Normal Chest ◽

Chest X Ray

Download Full-text

Detection of COVID-19 Using Transfer Learning and Grad-CAM Visualization on Indigenously Collected X-ray Dataset

Sensors ◽

10.3390/s21175813 ◽

2021 ◽

Vol 21 (17) ◽

pp. 5813

Author(s):

Muhammad Umair ◽

Muhammad Shahbaz Khan ◽

Fawad Ahmed ◽

Fatmah Baothman ◽

Fehaid Alqahtani ◽

...

Keyword(s):

Transfer Learning ◽

Input Image ◽

Fine Tuning ◽

Feature Maps ◽

Virus Family ◽

X Ray ◽

Normal Chest ◽

Chest X Ray ◽

Confusion Matrices

The COVID-19 outbreak began in December 2019 and has dreadfully affected our lives since then. More than three million lives have been engulfed by this newest member of the corona virus family. With the emergence of continuously mutating variants of this virus, it is still indispensable to successfully diagnose the virus at early stages. Although the primary technique for the diagnosis is the PCR test, the non-contact methods utilizing the chest radiographs and CT scans are always preferred. Artificial intelligence, in this regard, plays an essential role in the early and accurate detection of COVID-19 using pulmonary images. In this research, a transfer learning technique with fine tuning was utilized for the detection and classification of COVID-19. Four pre-trained models i.e., VGG16, DenseNet-121, ResNet-50, and MobileNet were used. The aforementioned deep neural networks were trained using the dataset (available on Kaggle) of 7232 (COVID-19 and normal) chest X-ray images. An indigenous dataset of 450 chest X-ray images of Pakistani patients was collected and used for testing and prediction purposes. Various important parameters, e.g., recall, specificity, F1-score, precision, loss graphs, and confusion matrices were calculated to validate the accuracy of the models. The achieved accuracies of VGG16, ResNet-50, DenseNet-121, and MobileNet are 83.27%, 92.48%, 96.49%, and 96.48%, respectively. In order to display feature maps that depict the decomposition process of an input image into various filters, a visualization of the intermediate activations is performed. Finally, the Grad-CAM technique was applied to create class-specific heatmap images in order to highlight the features extracted in the X-ray images. Various optimizers were used for error minimization purposes. DenseNet-121 outperformed the other three models in terms of both accuracy and prediction.

Download Full-text

Subcutaneous Emphysema in Pregnancy

Journal of Nepal Medical Association ◽

10.31729/jnma.39 ◽

2011 ◽

Vol 51 (183) ◽

Author(s):

A Shrestha ◽

S Acharya

Keyword(s):

Subcutaneous Emphysema ◽

Late Pregnancy ◽

X Ray ◽

Close Observation ◽

The Face ◽

Normal Chest ◽

Chest X Ray ◽

Keywords Pregnancy ◽

Systemic Examination ◽

The Right

Spontaneous pneumomediastinum and subcutaneous emphysema are rare complications of labor, especially in the late pregnancy period, but they are usually self-limiting. Management includes avoidance of exacerbative factors and close observation with supportive treatment. A 19-year-old primi gravida at 36 weeks pregnancy presented with swelling over the right side of the face, neck and chest. Her general examination was normal. Systemic examination revealed swelling with palpatory crepitation over the right side of chest, neck and face, and other examination findings were normal. Chest X-ray revealed subcutaneous emphysema without pneumothorax. The patient left hospital against medical advice. Keywords: Pregnancy; subcutaneous emphysema; pneumomediastinum.

Download Full-text