The pleural thickening approximation from thoracic CT scans

Abstract

The involvement of medical imaging in medical procedures plays an important role in the diagnosis and planning of a therapeutic treatment. Computerized tomography (CT), which is a tomographic acquisition imaging modality, is commonly used in combination with a medical diagnostic aid system. Therapists use these systems to properly diagnose and plan the therapeutic gesture in the preoperative phase. The aim of this study is to propose a diagnostic aid system that is capable of segmenting and measuring the pleural thickening caused by a pleural disease called ”Malignant Pleural Mesothelioma”. In the clinical case, radiologists perform linear measurements to take several one-dimensional (1D) segments on specic sections in each CT scan of the patient. As a result they can estimate the tumor thickness. Disease progression and response to therapy are then quantied by comparing the representative lengths calculated for the same patient at two dierent time points. Adjacent structures such as the thoracic cage may provide useful information about the pleural thickening location in the CT volume. We have used this property to propose a computerized method, which aims to delimit the chest cavity and approximate the pleural thickening in order to determine the stage of cancer and its progression. The method was validated on a representative database and the results obtained for ten test series were very encouraging.