A Deep Learning System That Generates Quantitative CT Reports for Diagnosing Pulmonary Tuberculosis
This provides an effective reference for clinical doctors in diagnosing PTB, but it is incremental as it builds on existing 3D CNN models and transfer learning methods.
The researchers tackled the problem of diagnosing Pulmonary Tuberculosis (PTB) by developing a deep learning system that automatically generates quantitative CT reports, achieving recall and precision rates of 98.7% and 93.7% for PTB cases and 90.9% precision for lesion type classification.
We developed a deep learning model-based system to automatically generate a quantitative Computed Tomography (CT) diagnostic report for Pulmonary Tuberculosis (PTB) cases.501 CT imaging datasets from 223 patients with active PTB were collected, and another 501 cases from a healthy population served as negative samples.2884 lesions of PTB were carefully labeled and classified manually by professional radiologists.Three state-of-the-art 3D convolution neural network (CNN) models were trained and evaluated in the inspection of PTB CT images. Transfer learning method was also utilized during this process. The best model was selected to annotate the spatial location of lesions and classify them into miliary, infiltrative, caseous, tuberculoma and cavitary types simultaneously.Then the Noisy-Or Bayesian function was used to generate an overall infection probability.Finally, a quantitative diagnostic report was exported.The results showed that the recall and precision rates, from the perspective of a single lesion region of PTB, were 85.9% and 89.2% respectively. The overall recall and precision rates,from the perspective of one PTB case, were 98.7% and 93.7%, respectively. Moreover, the precision rate of the PTB lesion type classification was 90.9%.The new method might serve as an effective reference for decision making by clinical doctors.