Dual-Ray Net: Automatic Diagnosis of Thoracic Diseases Using Frontal and Lateral Chest X-rays

2020 ◽  
Vol 10 (2) ◽  
pp. 348-355
Author(s):  
Xin Huang ◽  
Yu Fang ◽  
Mingming Lu ◽  
Fengqi Yan ◽  
Jun Yang ◽  
...  
Keyword(s):  
Chest Radiography ◽  
Feature Fusion ◽  
Small Data ◽  
Data Sets ◽  
X Rays ◽  
X Ray ◽  
Comparison Results ◽  
Chest Disease ◽  
Chest X Ray ◽  
Lateral Chest

Computer-aided diagnosis (CAD) is an important work which can improve the working efficiency of physicians. With the availability of large-scale data sets, several methods have been proposed to classify pathology on chest X-ray images. However, most methods report performance based on a frontal chest radiograph, ignoring the effect of the lateral chest radiography on the diagnosis. This paper puts forward a kind of model, Dual-Ray Net, of a deep convolutional neural network which can deal with the front and lateral chest radiography at the same time by referring the method of using lateral chest radiography to assist diagnose during the diagnosis used by radiologists. Firstly, we evaluated the performance of parameter migration to small data after pre-training for large datasets. The data sets for pre-training are chest X-ray 14 and ImageNet respectively. The results showed that pre-training with chest X-ray 14 performed better than with the generic dataset ImageNet. Secondly, We evaluated the performance of the Frontal and lateral chest radiographs in different modes of input model for the diagnosis of assisted chest disease. Finally, by comparing different feature fusion methods of addition and concatenation, we found that the fusion effect of concatenation is better, which average AUC reached 0.778. The comparison results show that whether it is a public or a non-public dataset, our Dual-Ray Net (concatenation) architecture shows improved performance in recognizing findings in CXR images when compared to applying separate baseline frontal and lateral classes.

scholarly journals Deep Learning for Screening COVID-19 using Chest X-Ray Images

2020 ◽  
Author(s):  
Sanhita Basu ◽  
Sushmita Mitra ◽  
Nilanjan Saha
Keyword(s):  
Deep Learning ◽  
Lung Parenchyma ◽  
Clinical Findings ◽  
Data Sets ◽  
X Rays ◽  
X Ray ◽  
Chest X Ray ◽  
Increasing Demand ◽  
Novel Coronavirus ◽  
Diverse Data

AbstractWith the ever increasing demand for screening millions of prospective “novel coronavirus” or COVID-19 cases, and due to the emergence of high false negatives in the commonly used PCR tests, the necessity for probing an alternative simple screening mechanism of COVID-19 using radiological images (like chest X-Rays) assumes importance. In this scenario, machine learning (ML) and deep learning (DL) offer fast, automated, effective strategies to detect abnormalities and extract key features of the altered lung parenchyma, which may be related to specific signatures of the COVID-19 virus. However, the available COVID-19 datasets are inadequate to train deep neural networks. Therefore, we propose a new concept called domain extension transfer learning (DETL). We employ DETL, with pre-trained deep convolutional neural network, on a related large chest X-Ray dataset that is tuned for classifying between four classes viz. normal, other_disease, pneumonia and Covid — 19. A 5-fold cross validation is performed to estimate the feasibility of using chest X-Rays to diagnose COVID-19. The initial results show promise, with the possibility of replication on bigger and more diverse data sets. The overall accuracy was measured as 95.3% ± 0.02. In order to get an idea about the COVID-19 detection transparency, we employed the concept of Gradient Class Activation Map (Grad-CAM) for detecting the regions where the model paid more attention during the classification. This was found to strongly correlate with clinical findings, as validated by experts.

scholarly journals COVID-Transformer: Interpretable COVID-19 Detection Using Vision Transformer for Healthcare

2021 ◽  
Vol 18 (21) ◽  
pp. 11086
Author(s):  
Debaditya Shome ◽  
T. Kar ◽  
Sachi Nandan Mohanty ◽  
Prayag Tiwari ◽  
Khan Muhammad ◽  
...  
Keyword(s):  
Data Science ◽  
Disease Spread ◽  
Classification Task ◽  
Data Sets ◽  
Sudden Increase ◽  
X Rays ◽  
Data Set ◽  
X Ray ◽  
Chest X Ray ◽  
Transformer Model

In the recent pandemic, accurate and rapid testing of patients remained a critical task in the diagnosis and control of COVID-19 disease spread in the healthcare industry. Because of the sudden increase in cases, most countries have faced scarcity and a low rate of testing. Chest X-rays have been shown in the literature to be a potential source of testing for COVID-19 patients, but manually checking X-ray reports is time-consuming and error-prone. Considering these limitations and the advancements in data science, we proposed a Vision Transformer-based deep learning pipeline for COVID-19 detection from chest X-ray-based imaging. Due to the lack of large data sets, we collected data from three open-source data sets of chest X-ray images and aggregated them to form a 30 K image data set, which is the largest publicly available collection of chest X-ray images in this domain to our knowledge. Our proposed transformer model effectively differentiates COVID-19 from normal chest X-rays with an accuracy of 98% along with an AUC score of 99% in the binary classification task. It distinguishes COVID-19, normal, and pneumonia patient’s X-rays with an accuracy of 92% and AUC score of 98% in the Multi-class classification task. For evaluation on our data set, we fine-tuned some of the widely used models in literature, namely, EfficientNetB0, InceptionV3, Resnet50, MobileNetV3, Xception, and DenseNet-121, as baselines. Our proposed transformer model outperformed them in terms of all metrics. In addition, a Grad-CAM based visualization is created which makes our approach interpretable by radiologists and can be used to monitor the progression of the disease in the affected lungs, assisting healthcare.

scholarly journals Finding COVID-19 from Chest X-rays using Deep Learning on a Small Dataset

2020 ◽  
Author(s):  
Lawrence Hall ◽  
Dmitry Goldgof ◽  
Rahul Paul ◽  
Gregory M. Goldgof
Keyword(s):  
False Negative ◽  
False Negative Rate ◽  
Disease Process ◽  
Small Data ◽  
X Rays ◽  
Data Set ◽  
X Ray ◽  
Set Size ◽  
Lack Of Information ◽  
Chest X Ray

<p>Testing for COVID-19 has been unable to keep up with the demand. Further, the false negative rate is projected to be as high as 30% and test results can take some time to obtain. X-ray machines are widely available and provide images for diagnosis quickly. This paper explores how useful chest X-ray images can be in diagnosing COVID-19 disease. We have obtained 122 chest X-rays of COVID-19 and over 4,000 chest X-rays of viral and bacterial pneumonia. A pre-trained deep convolutional neural network has been tuned on 102 COVID-19 cases and 102 other pneumonia cases in a 10-fold cross validation. The results were all 102 COVID-19 cases were correctly classified and there were 8 false positives resulting in an AUC of 0.997. On a test set of 20 unseen COVID-19 cases all were correctly classified and more than 95% of 4,171 other pneumonia examples were correctly classified. This study has flaws, most critically a lack of information about where in the disease process the COVID-19 cases were and the small data set size. More COVID-19 case images will enable a better answer to the question of how useful chest X-rays can be for diagnosing COVID-19 (so please send them). </p>

scholarly journals D2-CovidNet: A Deep Learning Model for COVID-19 Detection in Chest X-Ray Images

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Xin Wang ◽  
Yiyang Hu ◽  
Yanhong Luo ◽  
Wei Wang
Keyword(s):  
Feature Fusion ◽  
Detection Accuracy ◽  
Data Sets ◽  
X Ray ◽  
Public Data ◽  
Chest X Ray ◽  
Feature Information ◽  
Novel Coronavirus ◽  
Sensitivity Specificity ◽  
Deep Learning Model

Since the outbreak of Coronavirus disease 2019 (COVID-19), it has been spreading rapidly worldwide and has not yet been effectively controlled. Many researchers are studying novel Coronavirus pneumonia from chest X-ray images. In order to improve the detection accuracy, two modules sensitive to feature information, dual-path multiscale feature fusion module and dense depthwise separable convolution module, are proposed. Based on these two modules, a lightweight convolutional neural network model, D2-CovidNet, is designed to assist experts in diagnosing COVID-19 by identifying chest X-ray images. D2-CovidNet is tested on two public data sets, and its classification accuracy, precision, sensitivity, specificity, and F1-score are 94.56%, 95.14%, 94.02%, 96.61%, and 95.30%, respectively. Specifically, the precision, sensitivity, and specificity of the network for COVID-19 are 98.97%, 94.12%, and 99.84%, respectively. D2-CovidNet has fewer computation number and parameter number. Compared with other methods, D2-CovidNet can help diagnose COVID-19 more quickly and accurately.

Spontaneous Pneumomediastinum: Uncommon Cause of Air Leak in Late Preterm Neonate

2021 ◽  
Vol 35 (2) ◽  
pp. 93-94
Author(s):  
Jyotsna Bhushan ◽  
Shagufta Iqbal ◽  
Abhishek Chopra
Keyword(s):  
Respiratory Distress ◽  
Conservative Management ◽  
Preterm Neonate ◽  
Late Preterm ◽  
Intravenous Fluids ◽  
X Rays ◽  
Blood Gas ◽  
X Ray ◽  
Spontaneous Pneumomediastinum ◽  
Chest X Ray

A clinical case report of spontaneous pneumomediastinum in a late-preterm neonate, chest x-ray showing classical “spinnaker sail sign,” which was managed conservatively and had excellent prognosis on conservative management. Respiratory distress in a preterm neonate is a common clinical finding. Common causes include respiratory distress syndrome, transient tachypnea of the newborn, pneumonia, and pneumothorax. Pneumomediastinum is not very common cause of respiratory distress and more so spontaneous pneumomediastinum. We report here a preterm neonate with spontaneous pneumomediastinum who had excellent clinical recovery with conservative management. A male baby was delivered to G3P1A1 mother at 34 + 6 weeks through caesarean section done due to abruptio placenta. Apgar scores were 8 and 9. Maternal antenatal history was uneventful and there were no risk factors for early onset sepsis. Baby had respiratory distress soon after birth with Silverman score being 2/10. Baby was started on oxygen (O2) by nasal prongs through blender 0.5 l/min, FiO2 25%, and intravenous fluids. Blood gas done was normal. Possibility of transient tachypnea of newborn or mild hyaline membrane disease was kept. Respiratory distress increased at 20 h of life (Silverman score: 5), urgent chest x-ray done revealed “spinnaker sign” suggestive of pneumomediastinum, so baby was shifted to O2 by hood with FiO2 being 70%. Blood gas repeated was normal. Baby was managed conservatively on intravenous fluids and O2 by hood. Baby was gradually weaned off from O2 over next 5 days. As respiratory distress decreased, baby was started on orogastric feed, which baby tolerated well and then was switched to oral feeds. Serial x-rays showed resolution of pneumomediastinum. Baby was discharged on day 7 of life in stable condition on breast feeds and room air.

scholarly journals Accessory pathway analysis using a multimodal deep learning model

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Makoto Nishimori ◽  
Kunihiko Kiuchi ◽  
Kunihiro Nishimura ◽  
Kengo Kusano ◽  
Akihiro Yoshida ◽  
...  
Keyword(s):  
Deep Learning ◽  
Electrophysiological Study ◽  
Accessory Pathway ◽  
Learning Model ◽  
X Rays ◽  
X Ray ◽  
Wpw Syndrome ◽  
Chest X Ray ◽  
Deep Learning Model ◽  
Ecg Data

AbstractCardiac accessory pathways (APs) in Wolff–Parkinson–White (WPW) syndrome are conventionally diagnosed with decision tree algorithms; however, there are problems with clinical usage. We assessed the efficacy of the artificial intelligence model using electrocardiography (ECG) and chest X-rays to identify the location of APs. We retrospectively used ECG and chest X-rays to analyse 206 patients with WPW syndrome. Each AP location was defined by an electrophysiological study and divided into four classifications. We developed a deep learning model to classify AP locations and compared the accuracy with that of conventional algorithms. Moreover, 1519 chest X-ray samples from other datasets were used for prior learning, and the combined chest X-ray image and ECG data were put into the previous model to evaluate whether the accuracy improved. The convolutional neural network (CNN) model using ECG data was significantly more accurate than the conventional tree algorithm. In the multimodal model, which implemented input from the combined ECG and chest X-ray data, the accuracy was significantly improved. Deep learning with a combination of ECG and chest X-ray data could effectively identify the AP location, which may be a novel deep learning model for a multimodal model.

scholarly journals 3D Imaging in Unilateral Primary Pulmonary Hypoplasia in an Adult: A Case Report

2011 ◽  
Vol 2011 ◽  
pp. 1-6
Author(s):  
Aristida Georgescu ◽  
Crinu Nuta ◽  
Simona Bondari
Keyword(s):  
3D Imaging ◽  
Pulmonary Hypoplasia ◽  
Left Lung ◽  
Left Lobe ◽  
X Rays ◽  
X Ray ◽  
Female Smoker ◽  
Multidetector Computer Tomography ◽  
Biological Tests ◽  
Chest X Ray

Unilateral primary pulmonary hypoplasia is rare in adulthood (UPHA); it is characterized by a decreased number of bronchial segmentation and decreased/absent alveolar air space. Classical chest X-ray may be confusing, and the biological tests are unspecific. We present a case of UPHA in a 60-year-old female, smoker, with 3 term normal deliveries, who presented with late recurrent pneumonias and bronchiectasis-type symptomathology, arterial hypertension, and obesity. Chest X-rays revealed opacity in the left lower pulmonary zone, an apparent hypoaerated upper left lobe and left deviation of the mediastinum. Preoperatory multidetector computer tomography (MDCT) presented a small retrocardiac left lung with 5-6 bronchial segmentation range and cystic appearance. After pneumonectomy the gross specimen showed a small lung with multiple bronchiectasis and small cysts, lined by hyperplasic epithelium, surrounded by stromal fibrosclerosis. We concluded that this UPHA occurred in the 4–7 embryonic weeks, and the 3D MDCT reconstructions offered the best noninvasive diagnosis.

Double Cardiac Silhouette on Lateral Chest X-Ray Graphy

2011 ◽  
Vol 29 (2) ◽  
pp. E52-E53 ◽  
Author(s):  
Ozcan Basaran ◽  
Ahmet Guler ◽  
Can Y. Karabay ◽  
Soe M. Aung ◽  
Arzu Kalayci ◽  
...  
Keyword(s):  
X Ray ◽  
Chest X Ray ◽  
Lateral Chest ◽  
Cardiac Silhouette

scholarly journals Lower resolution Laue neutron data yield correct nanocluster formulations

2014 ◽  
Vol 70 (a1) ◽  
pp. C187-C187
Author(s):  
Alison Edwards
Keyword(s):  
Neutron Diffraction ◽  
Single Crystal ◽  
Diffraction Pattern ◽  
Precise Determination ◽  
Data Sets ◽  
X Rays ◽  
Low Resolution ◽  
Neutron Data ◽  
X Ray ◽  
Product Formulation

"The renaissance in Laue studies - at neutron sources - provides us with access to single crystal neutron diffraction data for synthetic compounds without requiring synthesis of prohibitively large amounts of compound or improbably large crystals. Such neutron diffraction studies provide vital data where proof of the presence or absence of hydrogen in particular locations is required and which cannot validly be proved by X-ray studies. Since the commissioning of KOALA at OPAL in 2009[1] we have obtained numerous data sets which demonstrate the vital importance of measuring data even where the extent of the diffraction pattern is at relatively low resolution - especially when compared to that obtainable for the same compound with X-rays. In the Laue experiment performed with a fixed radius detector, data reduction is only feasible for crystals in the ""goldilocks"" zone – where the unit cell is relatively large for the detector, a correspondingly low resolution diffraction pattern in which adjacent spots are less affected by overlap will yield more data against which a structure can be refined than a pattern of higher resolution – one where neighbouring spots overlap rendering both unusable (in our current methodology). Analogous application of powder neutron diffraction in such determinations is also considered. Single crystal neutron diffraction studies of several important compounds (up to 5KDa see figure below)[2] in which precise determination of hydride content by neutron diffraction was pivotal to the final formulation will be presented. The neutron data sets typically possess 20% or fewer unique data at substantially "lower resolution" than the corresponding X-ray data sets. Careful refinement clearly reveals chemical detail which is typically unexplored in related X-ray diffraction studies reporting high profile chemistry despite the synthetic route being one which hydride ought to be considered/excluded in product formulation."

CHEST X RAY SCORE AND CLINICAL SEVERITY IN COVID-19 PATIENTS

2021 ◽  
pp. 31-32
Author(s):  
Sheeba Rana ◽  
Vicky Bakshi ◽  
Yavini Rawat ◽  
Zaid Bin Afroz
Keyword(s):  
Retrospective Study ◽  
Medical Records ◽  
Scoring Systems ◽  
Clinical Severity ◽  
X Rays ◽  
Antigen Test ◽  
X Ray ◽  
Classi Cation ◽  
Chest X Ray ◽  
Male Subjects

INTRODUCTION: Various chest X-ray scoring systems have been discovered and are employed to correlate with clinical severity, outcome and progression of diseases. With, the coronavirus outbreak, few chest radiograph classication were formulated, like the BSTI classication and the Brixia chest X-ray score. Brixia CXR scoring is used for assessing the clinical severity and outcome of COVID-19. This study aims to compare the Brixia CXR score with clinical severity of COVID-19 patients. MATERIAL& METHODS:This was a retrospective study in which medical records of patients aged 18 years or above, who tested for RTPCR or st st Rapid Antigen Test (RAT) for COVID positive from 1 February 2021 to 31 July 2021 (6 months) were taken. These subjects were stratied into mild, moderate and severe patients according to the ICMR guidelines. Chest X Rays were obtained and lesions were classied according to Brixia scoring system. RESULTS: Out of these 375 patients, 123 (32.8%) were female and 252 (67.2%) were male subjects. The average brixia score was 11.12. Average Brixia CXR score for mild, moderate and severe diseased subjects were 5.23, 11.20, and 14.43 respectively. DISCUSSION:The extent of chest x-ray involvement is proportional to the clinical severity of the patient. Although, a perplexing nding was that the average Brixia score of the female subjects were slightly higher than their male counterparts in the same clinical groups. CONCLUSION: Brixia CXR score correlates well with the clinical severity of the COVID-19.

Sign in / Sign up

Export Citation Format

Share Document