Image analysis techniques for classification of pulmonary disease in cattle

Abstract

Histologic analysis of tissue samples is often a critical step in the diagnosis of disease. However, this type of assessment is inherently subjective, and consequently a high degree of variability may occur between results produced by different pathologists. Histologic analysis is also a very time-consuming task for pathologists. Computer-based quantitative analysis of tissue samples shows promise for both reducing the subjectivity of traditional manual tissue assessments, as well as potentially reducing the time required to analyze each sample. The objective of this thesis project was to investigate image processing techniques and to develop software which could be used as a diagnostic aid in pathology assessments of cattle lung tissue samples. The software examines digital images of tissue samples, identifying and highlighting the presence of a set of features that indicate disease, and that can be used to distinguish various pulmonary diseases from one another. The output of the software is a series of segmented images with relevant disease indicators highlighted, and measurements quantifying the occurrence of these features within the tissue samples. Results of the software analysis of a set of 50 cattle lung tissue samples were compared to the detailed manual analysis of these samples by a pathology expert.The combination of image analysis techniques implemented in the thesis software shows potential. Detection of each of the disease indicators is successful to some extent, and in some cases the analysis results are extremely good. There is a large difference in accuracy rates for identification of the set of disease indicators, however, with sensitivity values ranging from a high of 94.8% to a low of 22.6%. This wide variation in result scores is partially due to limitations of the methodology used to determine accuracy.