Developing and verifying automatic detection of active pulmonary tuberculosis from multi-slice spiral CT images based on deep learning

Article type: Research Article

Authors: Ma, Luyao^{a; b; 1} | Wang, Yun^{a; b; 2} | Guo, Lin^{c; *} | Zhang, Yu^a | Wang, Ping^{a; b} | Pei, Xu^{a; b} | Qian, Lingjun^c | Jaeger, Stefan^d | Ke, Xiaowen^c | Yin, Xiaoping^{a; *} | Lure, Fleming Y.M.^{c; e}

Affiliations: [a] CT-MRI Room, Affiliated Hospital of Hebei University, Baoding, Hebei, China | [b] Clinical Medical College, Hebei University, Baoding, Hebei, China | [c] Shenzhen Zhiying Medical Imaging, Shenzhen, Guangdong, China | [d] National Library of Medicine, National Institutes of Health, Bethesda, MD, USA | [e] MS Technologies Corp, Rockville, MD, USA

Correspondence: [*] Corresponding authors: Xiaoping Yin, E-mail: yinxiaoping78@sina.com and Lin Guo, E-mail: guolin913@outlook.com.

Note: [1] First author: Luyao Ma.

Note: [2] Joint first author: Yun Wang.

Abstract: OBJECTIVE:Diagnosis of tuberculosis (TB) in multi-slice spiral computed tomography (CT) images is a difficult task in many TB prevalent locations in which experienced radiologists are lacking. To address this difficulty, we develop an automated detection system based on artificial intelligence (AI) in this study to simplify the diagnostic process of active tuberculosis (ATB) and improve the diagnostic accuracy using CT images. DATA:A CT image dataset of 846 patients is retrospectively collected from a large teaching hospital. The gold standard for ATB patients is sputum smear, and the gold standard for normal and pneumonia patients is the CT report result. The dataset is divided into independent training and testing data subsets. The training data contains 337 ATB, 110 pneumonia, and 120 normal cases, while the testing data contains 139 ATB, 40 pneumonia, and 100 normal cases, respectively. METHODS:A U-Net deep learning algorithm was applied for automatic detection and segmentation of ATB lesions. Image processing methods are then applied to CT layers diagnosed as ATB lesions by U-Net, which can detect potentially misdiagnosed layers, and can turn 2D ATB lesions into 3D lesions based on consecutive U-Net annotations. Finally, independent test data is used to evaluate the performance of the developed AI tool. RESULTS:For an independent test, the AI tool yields an AUC value of 0.980. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value are 0.968, 0.964, 0.971, 0.971, and 0.964, respectively, which shows that the AI tool performs well for detection of ATB and differential diagnosis of non-ATB (i.e. pneumonia and normal cases). CONCLUSION:An AI tool for automatic detection of ATB in chest CT is successfully developed in this study. The AI tool can accurately detect ATB patients, and distinguish between ATB and non- ATB cases, which simplifies the diagnosis process and lays a solid foundation for the next step of AI in CT diagnosis of ATB in clinical application.

Keywords: Active tuberculosis (ATB), artificial intelligence (AI), deep learning

DOI: 10.3233/XST-200662

Journal: Journal of X-Ray Science and Technology, vol. 28, no. 5, pp. 939-951, 2020