lancet-header

Preprints with The Lancet is part of SSRN´s First Look, a place where journals identify content of interest prior to publication. Authors have opted in at submission to The Lancet family of journals to post their preprints on Preprints with The Lancet. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early stage research papers that have not been peer-reviewed. The findings should not be used for clinical or public health decision making and should not be presented to a lay audience without highlighting that they are preliminary and have not been peer-reviewed. For more information on this collaboration, see the comments published in The Lancet about the trial period, and our decision to make this a permanent offering, or visit The Lancet´s FAQ page, and for any feedback please contact preprints@lancet.com.

Deep-Learning Based Automated Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs: Diagnostic Performance in Systematic Screening of Asymptomatic Individuals

35 Pages Posted: 28 Apr 2019

See all articles by Jong Hyuk Lee

Jong Hyuk Lee

Armed Forces Seoul District Hospital

Sunggyun Park

Lunit Inc

Eui Jin Hwang

Seoul National University - Department of Radiology and Institute of Radiation Medicine

Jin Mo Goo

Seoul National University - Department of Radiology and Institute of Radiation Medicine

Woo Young Lee

Armed Forces Seoul District Hospital; Airforce Surgeon General Office

Sangho Lee

Armed Forces Seoul District Hospital; Armed Forces Capital Hospital

Hyungjin Kim

Seoul National University - Department of Radiology and Institute of Radiation Medicine

Jason R Andrews

Stanford University - Division of Infectious Diseases and Geographic Medicine

Chang Min Park

Seoul National University - Department of Radiology and Institute of Radiation Medicine

More...

Multiple version iconThere are 2 versions of this paper

Abstract

Background: Performance of deep-learning based automated detection (DLAD) algorithms in systematic screening for active pulmonary tuberculosis is unknown. We aimed to validate DLAD algorithm for detection of active pulmonary tuberculosis and any radiologicallyidentifiable relevant abnormality on chest radiographs (CRs) in this setting.

Methods: We performed out-of-sample testing of a trained DLAD algorithm, using CRs from 19,686 asymptomatic individuals (male: 19,475, female: 211; mean ± standard deviation: 21.3 ± 1.9 years) as part of systematic screening for tuberculosis between January 2013 and July 2018. Area under the receiver operating characteristic curves (AUC) of DLAD for diagnosis of tuberculosis and any relevant abnormalities were measured. Accuracy measures including sensitivities, specificities, positive predictive values (PPVs), negative predictive values (NPVs) were calculated at predefined operating thresholds (high sensitivity threshold, 0·16; high specificity threshold, 0·46).

Findings: All five CRs with active pulmonary tuberculosis were correctly classified as having abnormal findings by DLAD with specificities of 0·959 and 0·997, PPVs of 0·006 and 0·068, and NPVs of both 1·000 at high sensitivity and high specificity thresholds, respectively. With high specificity thresholds, DLAD showed comparable diagnostic measures for tuberculosis to the pooled radiologists (P values > 0·05). For the detection of any radiologically-identifiable relevant abnormality (n=28), DLAD showed AUC value of 0·967 (95% confidence interval, 0·938-0·996) with sensitivities of 0·821 and 0·679, specificities of 0·960 and 0·997, PPVs of 0·028 and 0·257, and NPVs of both 1·000 at high sensitivity and high specificity thresholds, respectively.

Interpretation: In systematic screening for tuberculosis in a lowprevalence setting, DLAD algorithm demonstrated excellent diagnostic performance, comparable to the radiologists in the detection of active pulmonary tuberculosis.

Funding Statement: This study was supported by the Seoul Research & Business Development Program (grant number: FI170002), and Lunit Inc. provided technical supports for this study.

Declaration of Interests: There is a major research agreement between Seoul National University Hospital and Lunit Inc, in which roles of researchers and Lunit Inc. were described. However, the funder and Lunit Inc. did not have any role either in the study design; in the collection, analysis, and interpretation of the data; in the writing of the report; and in the decision to submit the article for publication. Researchers (J.H.L., E.J.H., W.Y.L., S.L., J.R.A.) who controlled, manipulated and analyzed data, did not have any conflict of interest. Three authors (J.M.G., H.K., C.M.P.) received research grants from Lunit Inc. for outside of this study.

Ethics Approval Statement: This retrospective study was approved by the institutional review board of The Armed Forces Medical Command of Korea, and the requirement for informed consent was waived.

Keywords: tuberculosis; systematic screening; deep learning; accuracy study; diagnostic performance; chest radiographs

Suggested Citation

Lee, Jong Hyuk and Park, Sunggyun and Hwang, Eui Jin and Goo, Jin Mo and Lee, Woo Young and Lee, Sangho and Kim, Hyungjin and Andrews, Jason R and Park, Chang Min, Deep-Learning Based Automated Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs: Diagnostic Performance in Systematic Screening of Asymptomatic Individuals (April 24, 2019). Available at SSRN: https://ssrn.com/abstract=3377561 or http://dx.doi.org/10.2139/ssrn.3377561

Jong Hyuk Lee

Armed Forces Seoul District Hospital

Seoul
Korea, Republic of (South Korea)

Sunggyun Park

Lunit Inc

175 Yeoksam-ro
Seoul, 06247
Korea, Republic of (South Korea)

Eui Jin Hwang

Seoul National University - Department of Radiology and Institute of Radiation Medicine

101 Daehak-ro, Jongno-gu
Seoul, 03080
Korea, Republic of (South Korea)

Jin Mo Goo

Seoul National University - Department of Radiology and Institute of Radiation Medicine

101 Daehak-ro, Jongno-gu
Seoul, 03080
Korea, Republic of (South Korea)

Woo Young Lee

Armed Forces Seoul District Hospital

Seoul
Korea, Republic of (South Korea)

Airforce Surgeon General Office

Korea, Republic of (South Korea)

Sangho Lee

Armed Forces Seoul District Hospital

Seoul
Korea, Republic of (South Korea)

Armed Forces Capital Hospital

Korea, Republic of (South Korea)

Hyungjin Kim

Seoul National University - Department of Radiology and Institute of Radiation Medicine

101 Daehak-ro, Jongno-gu
Seoul, 03080
Korea, Republic of (South Korea)

Jason R Andrews

Stanford University - Division of Infectious Diseases and Geographic Medicine

Stanford, CA
United States

Chang Min Park (Contact Author)

Seoul National University - Department of Radiology and Institute of Radiation Medicine ( email )

101 Daehak-ro, Jongno-gu
Seoul, 03080
Korea, Republic of (South Korea)