Application of supervised range-constrained thresholding to extract lung pleura for automated detection of pleural thickenings from thoracic CT images

Abstract

We develop an image analysis system to automatically detect pleural thickenings and assess their characteristic values from patients' thoracic spiral CT images. Algorithms are described to carry out the segmentation of pleural contours and to find the pleural thickenings. The method of thresholding was selected as the technique to separate lung's tissue from other. Instead thresholding based only on empirical considerations, the so-called "supervised range-constrained thresholding" is applied. The automatic detection of pleural thickenings is carried out based on the examination of its concavity and on the characteristic Hounsfield unit of tumorous tissue. After detection of pleural thickenings, in order to assess their growth rate, a spline-based interpolation technique is used to create a model of healthy pleura. Based on this healthy model, the size of the pleural thickenings is calculated. In conjunction with the spatio-temporal matching of CT images acquired at different times, the oncopathological assessment of morbidity can be documented. A graphical user interface is provided which is also equipped with 3D visualization of the pleura. Our overall aim is to develop an image analysis system for an efficient and reliable diagnosis of early stage pleural mesothelioma in order to ease the consequences of the expected peak of malignant pleural mesothelioma caused by asbestos exposure.