Object Detection and Segmentation in Chest X-rays for Tuberculosis Screening

Abstract

Tuberculosis (TB) is a contagious disease leading to the deaths of approximately 2 million people annually. Providing healthcare professionals with better information, at a faster pace, is essential for combating this disease, especially in Low and Middle Income Countries with resource-constrained health systems. In this paper we describe how using convolution neural networks (CNNs) with an object level annotated dataset of chest X-rays (CXRs) allows us to identify the location of pulmonary issues indicative of TB. We compare the performance of Faster R-CNN, Mask R-CNN, and Cascade versions of each, demonstrating reasonable results with a small dataset. We present a method to reduce the false positive rate by comparing the location of a detected object with the known location of areas where the detected class is likely to occur in the lung. Our results show that with a dataset of high-quality, object level annotations, object detection and segmentation of CXRs is possible and could be used as part of an automated TB screening process. This work has the potential to improve the speed of TB diagnosis, if implemented within the corresponding health care system and adapted to existing clinical worktlows.