@MastersThesis{Dolejsi-TR-2007-05,
  IS = { zkontrolovano 13 Dec 2007 },
  UPDATE  = { 2007-06-11 },
  author =	{Dolej{\v s}{\'\i}, Martin},
  supervisor =	{Kybic, Jan},
  title =	{Detection of Pulmonary Nodules from {CT} Scans},
  school =	{Center for Machine Perception, 
                 K13133 FEE Czech Technical University},
  address =	{Prague, Czech Republic},
  year =	{2007},
  month =	{January},
  day =		{19},
  type =	{{MSc Thesis CTU--CMP--2007--05}},
  ISSN =	{1213-2365},
  pages =	{65},
  figures =	{28},
  authorship =	{100},
  psurl =	{[Dolejsi-TR-2007-05.pdf]},
  project =	{NR8314 3/2005, 1ET101050403},
  annote = {We present a computer-aided diagnosis (CAD) system to
    detect small-size (from 2mm to around 10mm) pulmonary nodules from
    helical CT scans. A pulmonary nodule is a small, round
    (parenchymal nodule) or worm (juxtapleural nodule) shaped lesion
    in the lungs. Both have greater radio-density than lungs
    parenchyma, so they appear white in images. Lung nodules might
    indicate a lung cancer and their detection in the early stage
    improves the survival rate of patients. CT is considered to be the
    most accurate imaging modality for nodule detection. However, the
    large amount of data per examination makes the interpretation
    difficult. This leads to omission of nodules by human
    radiologist. The presented CAD system is designed to help lower
    the number of omissions and to decrease the time needed to examine
    the scan by a radiologist. Our system uses two different schemes
    to locate juxtapleural nodules and parenchymal nodules
    respectively. For juxtapleural nodules, morphological closing and
    thresholding is used to find nodule candidates. To locate
    non-pleural nodule candidates, we use a 3D blob detector based on
    multiscale filtration. To define which of the nodule candidates
    are in fact nodules, an additional classification step is
    applied. Linear and multi-threshold classifiers are
    used. Ellipsoid model is fitted on nodules to provide geometrical
    features. The system was tested on 18 cases (4853 slices) with
    total sensitivity of 96%, with about 12 false
    positives/slice. The classification step reduces the number of
    false positives to 9 per slice without significantly decreasing
    sensitivity (89.6%). The algorithm was implemented in Matlab and
    tested under Windows and Unix systems. For easy control, a simple
    graphic user interface is included.},
  keywords =	{Computer aided diagnosis, nodule detection, 
    matematical morphology, 3D blob detector, linear classifier},
}