A computer-aided detection (CAD) system for the selection of lung nodules in computer tomography (CT) images is presented. The system is based on region growing (RG) algorithms and a new active ...contour model (ACM), implementing a local convex hull, able to draw the correct contour of the lung parenchyma and to include the pleural nodules. The CAD consists of three steps: (1) the lung parenchymal volume is segmented by means of a RG algorithm; the pleural nodules are included through the new ACM technique; (2) a RG algorithm is iteratively applied to the previously segmented volume in order to detect the candidate nodules; (3) a double-threshold cut and a neural network are applied to reduce the false positives (FPs). After having set the parameters on a clinical CT, the system works on whole scans, without the need for any manual selection. The CT database was recorded at the Pisa center of the ITALUNG-CT trial, the first Italian randomized controlled trial for the screening of the lung cancer. The detection rate of the system is
88.5
%
with 6.6 FPs/CT on 15 CT scans (about 4700 sectional images) with 26 nodules: 15 internal and 11 pleural. A reduction to 2.47 FPs/CT is achieved at
80
%
efficiency.
Positron emission tomography/computed tomography (PET/CT) diagnosis relies on quality of the reconstructed images which strongly depends on the algorithms used. The aim of this work was to assess if ...the introduction of high resolution algorithms allows a better identification of reduced diameter lesions, leading to improved diagnosis in clinical setting.
The performances of a Siemens Biograph6 True Point PET/CT used for this work were checked for both standard and high resolution algorithms. Clinical studies of thirteen patients referred for PET/CT were selected and grouped according to the metabolic tumor volume and their position in the FOV and then reconstructed with both algorithms; clinical studies were estimated in terms of geometric characteristics and uptake values (SUVmax, SUVmean) of the lesions.
FWHM, spatial resolution, contrast ratio and image quality of the PET/CT scanner used for this work are in agreement with the performances declared by the manufacturers. For the clinical studies, the results obtained using TrueX algorithm showed an increase in SUVmax and SUVmean of 20% and 10% respectively for lesions with volume higher than 2 cm3 and of about 26% and 15% for smaller lesions. The enhancement of SUVmean was around 10% for in axis lesions and of about 12% for off axis lesions. For SUVmax the increase was 23% for both the positions. For small lesions TrueX algorithm led to a metabolic volume higher than with the iterative one while no significant differences were found for big lesions.
The advances in 3D PET reconstruction algorithms lead to images with improved quantitative accuracy and image quality performance.
PDF
