Screening for pulmonary tuberculosis in a Tanzanian prison and computer-aided interpretation of chest X-rays

被引:14
|
作者
Steiner, A. [1 ,2 ,3 ]
Mangu, C. [4 ]
van den Hombergh, J. [5 ]
van Deutekom, H. [6 ]
van Ginneken, B. [7 ]
Clowes, P. [4 ,8 ]
Mhimbira, F. [1 ,2 ,3 ]
Mfinanga, S. [9 ]
Rachow, A. [8 ,10 ]
Reither, K. [1 ,3 ]
Hoelscher, M. [4 ,8 ,10 ]
机构
[1] Swiss Trop & Publ Hlth Inst, Socinstr 57, CH-4051 Basel, Switzerland
[2] Ifakara Hlth Inst, Bagamoyo, Tanzania
[3] Univ Basel, Basel, Switzerland
[4] Mbeya Med Res Ctr, Natl Inst Med Res, Mbeya, Tanzania
[5] PharmAccess Fdn, Dar Es Salaam, Tanzania
[6] Municipal Hlth Serv, Dept TB Control, Amsterdam, Netherlands
[7] Radboud Univ Nijmegen, Med Ctr, NL-6525 ED Nijmegen, Netherlands
[8] Univ Munich, Med Ctr, Div Infect Dis & Trop Med, Munich, Germany
[9] Muhimbili Med Res Ctr, Dar Es Salaam, Tanzania
[10] German Ctr Infect Res, Munich, Germany
来源
PUBLIC HEALTH ACTION | 2015年 / 5卷 / 04期
关键词
tuberculosis; chest X-ray; computer-aided diagnosis;
D O I
10.5588/pha.15.0037
中图分类号
R56 [呼吸系及胸部疾病];
学科分类号
摘要
Setting: Tanzania is a high-burden country for tuberculosis (TB), and prisoners are a high-risk group that should be screened actively, as recommended by the World Health Organization. Screening algorithms, starting with chest X-rays (CXRs), can detect asymptomatic cases, but depend on experienced readers, who are scarce in the penitentiary setting. Recent studies with patients seeking health care for TB-related symptoms showed good diagnostic performance of the computer software CAD4TB. Objective: To assess the potential of computer-assisted screening using CAD4TB in a predominantly asymptomatic prison population. Design: Cross-sectional study. Results: CAD4TB and seven health care professionals reading CXRs in local tuberculosis wards evaluated a set of 511 CXRs from the Ukonga prison in Dar es Salaam. Performance was compared using a radiological reference. Two readers performed significantly better than CAD4TB, three were comparable, and two performed significantly worse (area under the curve 0.75 in receiver operating characteristics analysis). On a superset of 1321 CXRs, CAD4TB successfully interpreted >99%, with a predictably short time to detection, while 160 (12.2%) reports were delayed by over 24 h with conventional CXR reading. Conclusion: CAD4TB reliably evaluates CXRs from a mostly asymptomatic prison population, with a diagnostic performance inferior to that of expert readers but comparable to local readers.
引用
收藏
页码:249 / 254
页数:6
相关论文
共 50 条
  • [1] COMPUTER-AIDED QUANTIFICATION OF PULMONAL OPACITIES IN CHEST X-RAYS
    DESAGA, JF
    DENGLER, J
    WOLF, T
    ENGELMANN, U
    SCHEPPELMANN, D
    MEINZER, HP
    [J]. ATEMWEGS-UND LUNGENKRANKHEITEN, 1988, 14 (08) : 364 - 366
  • [2] Computer-aided diagnosis of pulmonary nodules from chest X-rays using rotation forest
    Htike, Zaw Zaw
    Naing, Wai Yan Nyein
    Win, Shoon Lei
    Khan, Sheroz
    [J]. Proceedings - 5th International Conference on Computer and Communication Engineering: Emerging Technologies via Comp-Unication Convergence, ICCCE 2014, 2015, : 96 - 99
  • [3] Computer-Aided Diagnosis of Pulmonary Nodules from Chest X-rays Using Rotation Forest
    Htike, Zaw Zaw
    Naing, Wai Yan Nyein
    Win, Shoon Lei
    Khan, Sheroz
    [J]. 2014 INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION ENGINEERING (ICCCE), 2014, : 96 - 99
  • [4] COMPUTER-AIDED RECOGNITION OF SMALL ROUNDED PNEUMOCONIOSIS OPACITIES IN CHEST X-RAYS
    SAVOL, AM
    LI, CC
    HOY, RJ
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1980, 2 (05) : 479 - 482
  • [5] Evaluation of a computer-aided method for measuring the Cobb angle on chest X-rays
    Pan, Yaling
    Chen, Qiaoran
    Chen, Tongtong
    Wang, Hanqi
    Zhu, Xiaolei
    Fang, Zhihui
    Lu, Yong
    [J]. EUROPEAN SPINE JOURNAL, 2019, 28 (12) : 3035 - 3043
  • [6] Evaluation of a computer-aided method for measuring the Cobb angle on chest X-rays
    Yaling Pan
    Qiaoran Chen
    Tongtong Chen
    Hanqi Wang
    Xiaolei Zhu
    Zhihui Fang
    Yong Lu
    [J]. European Spine Journal, 2019, 28 : 3035 - 3043
  • [7] A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays
    Melendez, Jaime
    van Ginneken, Bram
    Maduskar, Pragnya
    Philipsen, Rick H. H. M.
    Reither, Klaus
    Breuninger, Marianne
    Adetifa, Ifedayo M. O.
    Maane, Rahmatulai
    Ayles, Helen
    Sanchez, Clara I.
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2015, 34 (01) : 179 - 192
  • [8] Deep Learning Methods for Screening Pulmonary Tuberculosis Using Chest X-rays
    Dasanayaka, Chirath
    Dissanayake, Maheshi Buddhinee
    [J]. COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION, 2021, 9 (01): : 39 - 49
  • [9] Segmenting Anatomy in Chest X-rays for Tuberculosis Screening
    Karargyris, Alexandros
    Antani, Sameer
    Thoma, George
    [J]. 2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2011, : 7779 - 7782
  • [10] INTERPRETATION OF CHEST X-RAYS
    不详
    [J]. BMJ-BRITISH MEDICAL JOURNAL, 1947, 2 (4518): : 215 - 216