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

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.

The Clinical Value of Multislice Spiral Computed Tomography in the Diagnosis of Upper Digestive Tract Diseases

“…CTVE is a computer software function that processes the images obtained from spiral CT volume scanning to simulate a threedimensional image of the inner surface of the cavity, which can simulate the view of an endoscope to observe the interior of the cavity. It has the advantages of short time, noninvasive, and good tolerance, and it can also use the data for multiple, multiplanar reconstruction to reduce the leakage caused by human factors [17]. Although it started late, as an emerging technique for endoluminal imaging, it is particularly useful for some patients who are unable or unwilling to do invasive endoscopy [18].…”

Application of the Artificial Neural Network in the Diagnosis of Infantile Bronchial Bridge with 64-Slice Multislice Spiral CT

“…This design idea has many technical advantages that single-source CT is not prepared for, and it is a milestone breakthrough in the history of CT development [ 5 ]. Ma et al proposed diagnosing the artificial neural network-assisted CT image in medicine [ 6 ]. Mohandes et al showed that CT has high sensitivity and specificity in the imaging diagnosis of the trachea and bronchial foreign bodies, with an accuracy of up to 97%, providing outstanding contributions to the diagnosis and differential diagnosis of difficult cases [ 7 ].…”

Spiral Computed Tomography in the Quantitative Measurement of the Adjacent Structure of the Left Atrial Appendage in Patients with Atrial Fibrillation

“…It relies on the further understanding of the anatomy of the aortic sinus and its frequent adjacent tissues. At present, there are a few studies in China and abroad, and most of them focus on animal observation, autopsy, or visual observation during cardiac surgery, which lacks clinical guidance [ 8 ]. This is achieved by the slip ring technology and a continuous flat movement of the scanning bed [ 9 ].…”