Researchers at the University of Southampton in the UK have developed a new computational model to examine X-ray images of lungs, paving way for the diagnosis of related diseases such as chronic obstructive pulmonary disease (COPD).
The team included mathematicians, clinicians and image experts who used a part of mathematics called topology to create a new approach for numerically describing the three-dimensional structure of the lung.
Go deeper with GlobalData
They employed computed tomography (CT) scans, high-performance computing and algorithms to quantify numerical characteristics of the complete bronchial trees of 64 subjects, in three dimensions.
The patients were divided into four groups – healthy non-smokers, healthy smokers, patients with moderate COPD and those with mild COPD.
Upon analysing various features such as the bronchial tree’s structure and size, length and direction of its branches and changes in shape during breathing, the researchers found that a large and complex tree is associated with better lung function.
In addition, the mathematical model provided accurate differentiation between the different patient groups, their lung function characteristics and the various stages of their condition.
The team noted that the approach was able to detect characteristics that could not be identified by the naked eye.
They predict that using the technique with a larger image database and its combination with other findings could result in a clinical tool for the early and precise diagnosis of lung conditions and their severity.
University of Southampton lead researcher Jacek Brodzki said: “Our study shows that this new method, employing topological data analysis, can complement and expand on established techniques to give a valuable, accurate range of information about the lung function of individuals.
“Further research is needed, but this could eventually aid decisions about the treatment of patients with serious, or potentially serious, lung conditions.”
