A major challenge of tuberculosis diagnosis is the lack of universal accessibility to bacteriological confirmation. Computer-aided diagnostic interventions have been developed to address this gap and their successful implementation depends on many health systems factors. A socio-technical system to implement a computer-aided diagnostic tuberculosis diagnosis was preliminary tested in five primary health centers located in Lima, Peru. We recruited nurses (n = 7) and tuberculosis physicians (n = 5) from these health centers to participate in a field trial of an mHealth tool (eRx X-ray diagnostic app). From September 2018 to February 2019, the nurses uploaded images of chest X-rays using smartphones and the physicians reviewed those images on web-based platforms using tablets. Both completed weekly written feedback about their experience. Each nurse participated for a median duration of 12 weeks (interquartile range = 7.5–15.5), but image upload was only possible at a median of 58 percent (interquartile range = 35.1%–84.4%) of those weeks. Each physician participated for a median duration of 17 weeks (interquartile range = 12–17), but X-ray image review was only possible at a median of 52 percent (interquartile range = 49.7%–57.4%) of those weeks. Heavy workload was most frequently provided as the reason for missing data. Several infrastructural and technological challenges impaired the effective implementation of the mHealth tool, irrespective of its diagnostic accuracy.
Tuberculosis (TB) is a highly contagious disease leading to the deaths of approximately 2 million people annually. TB primarily affects the lungs and is spread through
the air when people cough, sneeze, or spit. Providing healthcare professionals with better information, at a faster pace, is essential for combating this disease, especially in Low and Middle Income Countries (LMICs) 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-nobreakdash-CNN, Mask R-nobreakdash-CNN, Cascade versions of each, and SOLOv2, 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 object detection and instance segmentation of CXRs can be achieved with a dataset of high-quality, object level annotations, and could be used as part of an automated TB screening process. This work has the potential to improve the speed of TB diagnosis in LMICs, if properly integrated into the healthcare system and adapted to existing clinical workflows and local regulations.
Tuberculosis (TB) is a contagious disease affecting millions of people annually worldwide. Treatment of this disease and reduction in local epidemics can be improved markedly by increasing the speed and efficiency of screening and diagnosis. eRxNet is a pipeline of convolutional neural networks designed to provide healthcare professionals with detailed and accurate analysis of chest X-rays (CXRs) for TB screening. The pipeline combines whole image classification, object detection (bounding boxes), and instance segmentation (polygonal masks) to provide data analysis at varying levels of detail. In order to construct a high performing system, a comparison of different CNN architectures applied to these tasks is presented. Images from two large TB datasets, UML-Peru and TBX11K, were used for training and evaluation of the models. Combining the two datasets required the development of a preprocessing stage which includes lung segmentation and image enhancement. We show that the resulting four-stage pipeline of CNNs, using a combination of DenseNet, Faster R-CNN, and Mask R-CNN, has sufficiently strong performance to be a useful tool for TB screening.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.