Abstract:
Tuberculosis (TB) is an infectious disease resulting in 1.5 M deaths worldwide every year. Early diagnosis can play an important role in reducing TB induced mortality rat...Show MoreMetadata
Abstract:
Tuberculosis (TB) is an infectious disease resulting in 1.5 M deaths worldwide every year. Early diagnosis can play an important role in reducing TB induced mortality rates. A common inexpensive approach to test for TB is a manual examination of sputum smear images under the light/fluorescent microscope. To enhance the process, computer-aided diagnostic devices and machine learning algorithms have been developed with the capability of identifying TB bacilli using image processing techniques. Here, we propose a novel statistical model of the shape and color of TB bacilli in Ziehl-Neelsen stained images under the light microscope to identify bacilli in these images. These simple statistical models are utilized as a general library for reconstructing any bacillus with various background colors and can overcome the difficulties associated with geometric feature extraction methods. We use various methods to classify the individual bacilli and overlapping bacilli from the rest of the image based on the eigenvalues of the shape and color models. Our results show that the k-NN classifier performs best among selected classifiers with an average accuracy of 82.7% for single bacilli and overlapping bacilli detection, and 99.1% accuracy of identifying individual bacilli alone from overlapping bacilli and other objects.
Date of Conference: 14-17 December 2020
Date Added to IEEE Xplore: 23 February 2021
ISBN Information: