Wen Zhou1,2, Guanxun Cheng1, Ziqi Zhang3, Litong Zhu4, Stefan Jaeger5, Fleming Y M Lure6, Lin Guo6. 1. Department of Radiology, Peking University Shenzhen Hospital, Shenzhen, China. 2. Department of Radiology, Peking University First Hospital, Beijing, China. 3. Tsinghua-Berkeley Shenzhen Institute, Tsinghua University, Shenzhen, China. 4. Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China. 5. National Library of Medicine, National Institutes of Health, Bethesda, MD, USA. 6. Shenzhen Smart Imaging Healthcare Co., Ltd., Shenzhen, China.
Abstract
Background: It is critical to have a deep learning-based system validated on an external dataset before it is used to assist clinical prognoses. The aim of this study was to assess the performance of an artificial intelligence (AI) system to detect tuberculosis (TB) in a large-scale external dataset. Methods: An artificial, deep convolutional neural network (DCNN) was developed to differentiate TB from other common abnormalities of the lung on large-scale chest X-ray radiographs. An internal dataset with 7,025 images was used to develop the AI system, including images were from five sources in the U.S. and China, after which a 6-year dynamic cohort accumulation dataset with 358,169 images was used to conduct an independent external validation of the trained AI system. Results: The developed AI system provided a delineation of the boundaries of the lung region with a Dice coefficient of 0.958. It achieved an AUC of 0.99 and an accuracy of 0.948 on the internal data set, and an AUC of 0.95 and an accuracy of 0.931 on the external data set when it was used to detect TB from normal images. The AI system achieved an AUC of more than 0.9 on the internal data set, and an AUC of over 0.8 on the external data set when it was applied to detect TB, non-TB abnormal and normal images. Conclusions: We conducted a real-world independent validation, which showed that the trained system can be used as a TB screening tool to flag possible cases for rapid radiologic review and guide further examinations for radiologists. 2022 Quantitative Imaging in Medicine and Surgery. All rights reserved.
Background: It is critical to have a deep learning-based system validated on an external dataset before it is used to assist clinical prognoses. The aim of this study was to assess the performance of an artificial intelligence (AI) system to detect tuberculosis (TB) in a large-scale external dataset. Methods: An artificial, deep convolutional neural network (DCNN) was developed to differentiate TB from other common abnormalities of the lung on large-scale chest X-ray radiographs. An internal dataset with 7,025 images was used to develop the AI system, including images were from five sources in the U.S. and China, after which a 6-year dynamic cohort accumulation dataset with 358,169 images was used to conduct an independent external validation of the trained AI system. Results: The developed AI system provided a delineation of the boundaries of the lung region with a Dice coefficient of 0.958. It achieved an AUC of 0.99 and an accuracy of 0.948 on the internal data set, and an AUC of 0.95 and an accuracy of 0.931 on the external data set when it was used to detect TB from normal images. The AI system achieved an AUC of more than 0.9 on the internal data set, and an AUC of over 0.8 on the external data set when it was applied to detect TB, non-TB abnormal and normal images. Conclusions: We conducted a real-world independent validation, which showed that the trained system can be used as a TB screening tool to flag possible cases for rapid radiologic review and guide further examinations for radiologists. 2022 Quantitative Imaging in Medicine and Surgery. All rights reserved.
Entities:
Keywords:
Tuberculosis detection; chest radiography; deep learning; external validation; large-scale test
Authors: Jimena Olveres; Germán González; Fabian Torres; José Carlos Moreno-Tagle; Erik Carbajal-Degante; Alejandro Valencia-Rodríguez; Nahum Méndez-Sánchez; Boris Escalante-Ramírez Journal: Quant Imaging Med Surg Date: 2021-08
Authors: Morgan P McBee; Omer A Awan; Andrew T Colucci; Comeron W Ghobadi; Nadja Kadom; Akash P Kansagra; Srini Tridandapani; William F Auffermann Journal: Acad Radiol Date: 2018-03-30 Impact factor: 3.173
Authors: Joshua Burrill; Christopher J Williams; Gillian Bain; Gabriel Conder; Andrew L Hine; Rakesh R Misra Journal: Radiographics Date: 2007 Sep-Oct Impact factor: 5.333
Authors: Eui Jin Hwang; Sunggyun Park; Kwang-Nam Jin; Jung Im Kim; So Young Choi; Jong Hyuk Lee; Jin Mo Goo; Jaehong Aum; Jae-Joon Yim; Chang Min Park Journal: Clin Infect Dis Date: 2019-08-16 Impact factor: 9.079