scholarly journals Development and Validation of a Deep Learning–based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs

2018 ◽  
Vol 69 (5) ◽  
pp. 739-747 ◽  
Author(s):  
Eui Jin Hwang ◽  
Sunggyun Park ◽  
Kwang-Nam Jin ◽  
Jung Im Kim ◽  
So Young Choi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Pulmonary Tuberculosis ◽  
Performance Test ◽  
Automatic Detection ◽  
High Sensitivity ◽  
High Specificity ◽  
Roc Curves ◽  
Chest Radiographs ◽  
Automated System ◽  
Active Pulmonary Tuberculosis

Abstract Background Detection of active pulmonary tuberculosis on chest radiographs (CRs) is critical for the diagnosis and screening of tuberculosis. An automated system may help streamline the tuberculosis screening process and improve diagnostic performance. Methods We developed a deep learning–based automatic detection (DLAD) algorithm using 54c221 normal CRs and 6768 CRs with active pulmonary tuberculosis that were labeled and annotated by 13 board-certified radiologists. The performance of DLAD was validated using 6 external multicenter, multinational datasets. To compare the performances of DLAD with physicians, an observer performance test was conducted by 15 physicians including nonradiology physicians, board-certified radiologists, and thoracic radiologists. Image-wise classification and lesion-wise localization performances were measured using area under the receiver operating characteristic (ROC) curves and area under the alternative free-response ROC curves, respectively. Sensitivities and specificities of DLAD were calculated using 2 cutoffs (high sensitivity [98%] and high specificity [98%]) obtained through in-house validation. Results DLAD demonstrated classification performance of 0.977–1.000 and localization performance of 0.973–1.000. Sensitivities and specificities for classification were 94.3%–100% and 91.1%–100% using the high-sensitivity cutoff and 84.1%–99.0% and 99.1%–100% using the high-specificity cutoff. DLAD showed significantly higher performance in both classification (0.993 vs 0.746–0.971) and localization (0.993 vs 0.664–0.925) compared to all groups of physicians. Conclusions Our DLAD demonstrated excellent and consistent performance in the detection of active pulmonary tuberculosis on CR, outperforming physicians, including thoracic radiologists.

scholarly journals The Accuracy of Emergency Physicians’ Suspicions of Active Pulmonary Tuberculosis

2021 ◽  
Vol 10 (4) ◽  
pp. 860
Author(s):  
Shiang-Jin Chen ◽  
Chun-Yu Lin ◽  
Tzu-Ling Huang ◽  
Ying-Chi Hsu ◽  
Kuan-Ting Liu
Keyword(s):  
Chronic Kidney Disease ◽  
Weight Loss ◽  
Kidney Disease ◽  
Pulmonary Tuberculosis ◽  
General Ward ◽  
Chest Radiographs ◽  
Emergency Physicians ◽  
Active Pulmonary Tuberculosis ◽  
Factors Associated ◽  
History Of

Objective: To investigate factors associated with recognition and delayed isolation of pulmonary tuberculosis (PTB). Background: Precise identification of PTB in the emergency department (ED) remains challenging. Methods: Retrospectively reviewed PTB suspects admitted via the ED were divided into three groups based on the acid-fast bacilli culture report and whether they were isolated initially in the ED or general ward. Factors related to recognition and delayed isolation were statistically compared. Results: Only 24.94% (100/401) of PTB suspects were truly active PTB and 33.77% (51/151) of active PTB were unrecognized in the ED. Weight loss (p = 0.022), absence of dyspnea (p = 0.021), and left upper lobe field (p = 0.024) lesions on chest radiographs were related to truly active PTB. Malignancy (p = 0.015), chronic kidney disease (p = 0.047), absence of a history of PTB (p = 0.013), and lack of right upper lung (p ≤ 0.001) and left upper lung (p = 0.020) lesions were associated with PTB being missed in the ED. Conclusions: Weight loss, absence of dyspnea, and left upper lobe field lesions on chest radiographs were related to truly active PTB. Malignancy, chronic kidney disease, absence of a history of PTB, and absence of right and/or left upper lung lesions on chest radiography were associated with isolation delay.

A deep Residual U-Net algorithm for automatic detection and quantification of ascites on the abdominopelvic computed tomography acquired in the emergency department (Preprint)

2021 ◽  
Author(s):  
Hoon Ko ◽  
Jimi Huh ◽  
Kyung Won Kim ◽  
Heewon Chung ◽  
Yousun Ko ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Automatic Detection ◽  
High Specificity ◽  
Ct Images ◽  
Free Fluid ◽  
Detection Accuracy ◽  
Abdominopelvic Ct ◽  
Segmentation Accuracy ◽  
Detection And Quantification

BACKGROUND Detection and quantification of intraabdominal free fluid (i.e., ascites) on computed tomography (CT) are essential processes to find emergent or urgent conditions in patients. In an emergent department, automatic detection and quantification of ascites will be beneficial. OBJECTIVE We aimed to develop an artificial intelligence (AI) algorithm for the automatic detection and quantification of ascites simultaneously using a single deep learning model (DLM). METHODS 2D deep learning models (DLMs) based on a deep residual U-Net, U-Net, bi-directional U-Net, and recurrent residual U-net were developed to segment areas of ascites on an abdominopelvic CT. Based on segmentation results, the DLMs detected ascites by classifying CT images into ascites images and non-ascites images. The AI algorithms were trained using 6,337 CT images from 160 subjects (80 with ascites and 80 without ascites) and tested using 1,635 CT images from 40 subjects (20 with ascites and 20 without ascites). The performance of AI algorithms was evaluated for diagnostic accuracy of ascites detection and for segmentation accuracy of ascites areas. Of these DLMs, we proposed an AI algorithm with the best performance. RESULTS The segmentation accuracy was the highest in the deep residual U-Net with a mean intersection over union (mIoU) value of 0.87, followed by U-Net, bi-directional U-Net, and recurrent residual U-net (mIoU values 0.80, 0.77, and 0.67, respectively). The detection accuracy was the highest in the deep residual U-net (0.96), followed by U-Net, bi-directional U-net, and recurrent residual U-net (0.90, 0.88, and 0.82, respectively). The deep residual U-net also achieved high sensitivity (0.96) and high specificity (0.96). CONCLUSIONS We propose the deep residual U-net-based AI algorithm for automatic detection and quantification of ascites on abdominopelvic CT scans, which provides excellent performance.

Serum sFlt-1/PlGF ratio has better diagnostic ability in early- compared to late-onset pre-eclampsia

2018 ◽  
Vol 47 (1) ◽  
pp. 35-40 ◽  
Author(s):  
Theng Theng Chuah ◽  
Wan Shi Tey ◽  
Mor Jack Ng ◽  
Edward T.H. Tan ◽  
Bernard Chern ◽  
...  
Keyword(s):  
Diagnostic Tool ◽  
Late Onset ◽  
Asian Population ◽  
High Sensitivity ◽  
High Specificity ◽  
Roc Curves ◽  
Youden Index ◽  
Operating Characteristics ◽  
Gestation Age ◽  
Plgf Ratio

Abstract Background To establish gestational specific cutoffs for the soluble fms-like tyrosine kinase-1 (sFlt-1) and placental growth factor (PlGF) ratio as a diagnostic tool for pre-eclampsia (PE) in an Asian population. Methods 82 subjects (48 PE patients and 34 controls) were recruited. sFlt-1 and PlGF were analysed on the Roche Cobas e411 analyzer and their ratio was calculated. Diagnostic performance was evaluated using receiver-operating characteristics (ROC) curves. Optimal cutoffs for sFlt-1/PlGF ratio were determined for different gestation phases. Results The most optimal cut-off for the study group is 32 with a sensitivity and specificity of 85.1% and 100% and Youden Index (J) of 0.85. Applying this cutoff for early-onset PE (EO-PE), sensitivity increased to 95.8% while specificity remains at 100% (J=0.96). However, for late onset PE (LO-PE), sensitivity decreases to 73.9% while specificity remains at 100% (J=0.74). Two cutoffs were further determined for EO-PE and LO-PE – the first focusing on high sensitivity; the second focusing on high specificity. For EO-PE, cutoff <17 yielded sensitivity of 100% and specificity of 94.4% (J=0.94) while cutoff ≥32 yielded sensitivity of 95.8% and specificity of 100% (J=0.95). For LO-PE, cutoff <22 has a sensitivity of 82.6% and a specificity of 91.7% (J=0.74) while cutoff ≥32 yielded sensitivity of 73.9% and specificity of 100% (J=0.74). Conclusion While our study found an overall cutoff at 32 regardless of gestation age, it has limited diagnostic accuracy for LO-PE in our study. Multiple cutoffs focusing on either high sensitivity or high specificity enhance the performance of the sFlt-1/PlGF ratio as a diagnostic tool for PE and contribute to the identification of women at risk of PE in our Asian region.

scholarly journals A Novel, High-sensitivity, Bacteriophage-based Assay Identifies Low-level Mycobacterium tuberculosis Bacteremia in Immunocompetent Patients With Active and Incipient Tuberculosis

2019 ◽  
Author(s):  
Raman Verma ◽  
Benjamin M C Swift ◽  
Wade Handley-Hartill ◽  
Joanne K Lee ◽  
Gerrit Woltmann ◽  
...  
Keyword(s):  
Mycobacterium Tuberculosis ◽  
Animal Models ◽  
Pulmonary Tuberculosis ◽  
Latent Infection ◽  
High Sensitivity ◽  
Active Pulmonary Tuberculosis ◽  
Low Level ◽  
Blood Assay ◽  
Immunocompetent Patients

AbstractThe haematogenous dissemination of Mycobacterium tuberculosis (Mtb) is critical to the pathogenesis of progressive tuberculous infections in animal models. Using a novel, phage-based blood assay, we report the first concordant evidence in well-characterized, immunocompetent human cohorts, demonstrating associations of Mtb bacteremia with progressive phenotypes of latent infection and active pulmonary tuberculosis.

scholarly journals Development and Validation of Deep Learning–based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs

Radiology ◽  
2019 ◽  
Vol 290 (1) ◽  
pp. 218-228 ◽  
Author(s):  
Ju Gang Nam ◽  
Sunggyun Park ◽  
Eui Jin Hwang ◽  
Jong Hyuk Lee ◽  
Kwang-Nam Jin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Pulmonary Nodules ◽  
Automatic Detection ◽  
Detection Algorithm ◽  
Chest Radiographs ◽  
Development And Validation ◽  
Automatic Detection Algorithm

scholarly journals Automatic detection of COVID-19 from chest radiographs using deep learning

Radiography ◽  
2020 ◽  
Author(s):  
M.K. Pandit ◽  
S.A. Banday ◽  
R. Naaz ◽  
M.A. Chishti
Keyword(s):  
Deep Learning ◽  
Automatic Detection ◽  
Chest Radiographs
Sign in / Sign up

Export Citation Format

Share Document