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

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.

[Study on total flavonoids purified from Folium Gynurae divaricatae by macroporous resin combined with ZTC].

OBJECTIVE: To study the purification effect of macroporous resin combined with ZTC natural clarifying agent on Folium Gynurae Divaricatae extracts and to determine the ideal purification process. METHOD: The content of total flavonoids in Folium Gynurae Divaricatae was determined by ultraviolet spectrophotometry spectrophotometer. The reservation ratio and transferring ratio of total flavonoids were used as indicator to detect such impacting factors as the macroporous resin model, the pH value of ethanol-extraction liquid and elution agent as well as cleaning agents, the concentration of ethanol-extraction liquid, the flow speed for adsorption, the ratio of polyamide to crude drug, the ratio of diameter to height of polyamide column, the flow speed of cleaning agents, the alcohol content and flow speed of the elution agent. RESULT: The optimized purification conditions of total flavonoids in Folium Gynurae Divaricatae were as follows: the macroporous resin model was HPD600, the pH value of ethanol-extraction liquid and elution agent as well as cleaning agents was adjusted to 6.0, the concentration of extraction liquid was 0.25 g x mL(-1), the flow speed for adsorption was 2 BV x h(-1), the ratio of crude drug and the resin was 4:1, the ratio of diameter to height of resin column was 1:10, the flow speed of cleaning agents was 5 BV x h(-1), the dosage of cleaning agents was 5 BV, the dosage of elution agent was 9 BV, with 70% alcohol as elution agent, and the flow speed of elution agent as 5 BV x h(-1). Under the purification condition, the content of total flavonoids increased from 2.47% to 24.2%. CONCLUSION: Macroporous resin and ZTC natural clarifying agent used in combination can improve the internal quality of the product, shorten the production cycle, reduce use and cost of organic solvent, thus it is worth popularizing.