Automated method for extraction of lung tumors using a machine learning classifier with knowledge of radiation oncologists on data sets of planning CT and FDG-PET/CT images

We have developed an automated method for extraction of lung tumors using a machine learning classifier with knowledge of radiation oncologists on data sets of treatment planning computed tomography (CT) and 18F-fluorodeoxyglucose (FDG)-positron emission tomography (PET)/CT images. First, the PET images were registered with the treatment planning CT images through the diagnostic CT images of PET/CT. Second, six voxel-based features including voxel values and magnitudes of image gradient vectors were derived from each voxel in the planning CT and PET /CT image data sets. Finally, lung tumors were extracted by using a support vector machine (SVM), which learned 6 voxel-based features inside and outside each true tumor region determined by radiation oncologists. The results showed that the average DSCs for 3 and 6 features for three cases were 0.744 and 0.899, and thus the SVM may need 6 features to learn the distinguishable characteristics. The proposed method may be useful for assisting treatment planners in delineation of the tumor region.

[1]  Habib Zaidi,et al.  A novel fuzzy C-means algorithm for unsupervised heterogeneous tumor quantification in PET. , 2010, Medical physics.

[2]  Dimitris Visvikis,et al.  PET functional volume delineation: a robustness and repeatability study , 2011, European Journal of Nuclear Medicine and Molecular Imaging.

[3]  Ali Kamen,et al.  Constrained Surface Evolutions for Prostate and Bladder Segmentation in CT Images , 2005, CVBIA.

[4]  B. C. Penney,et al.  A Gaussian mixture model for definition of lung tumor volumes in positron emission tomography. , 2007, Medical physics.

[5]  Arjan Bel,et al.  Definition of gross tumor volume in lung cancer: inter-observer variability. , 2002, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[6]  Carolyn A. Bucholtz,et al.  Shape-based interpolation , 1992, IEEE Computer Graphics and Applications.

[7]  Christian Roux,et al.  A Fuzzy Locally Adaptive Bayesian Segmentation Approach for Volume Determination in PET , 2009, IEEE Transactions on Medical Imaging.

[8]  M. Miften,et al.  A region growing method for tumor volume segmentation on PET images for rectal and anal cancer patients. , 2009, Medical physics.

[9]  Masayuki Sasaki,et al.  Phantom study on three-dimensional target volume delineation by PET/CT-based auto-contouring. , 2010, Fukuoka igaku zasshi = Hukuoka acta medica.

[10]  Sasa Mutic,et al.  Concurrent multimodality image segmentation by active contours for radiotherapy treatment planning. , 2007, Medical physics.

[11]  Jeffrey D Bradley,et al.  Implementing biologic target volumes in radiation treatment planning for non-small cell lung cancer. , 2004, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[12]  Max A. Viergever,et al.  Mutual-information-based registration of medical images: a survey , 2003, IEEE Transactions on Medical Imaging.

[13]  Sasa Mutic,et al.  18F-FDG PET definition of gross tumor volume for radiotherapy of non-small cell lung cancer: is a single standardized uptake value threshold approach appropriate? , 2006, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[14]  Icru.  Prescribing, recording, and reporting photon beam therapy , 1993 .

[15]  Naofumi Hayabuchi,et al.  Variation of clinical target volume definition among Japanese radiation oncologists in external beam radiotherapy for prostate cancer. , 2008, Japanese journal of clinical oncology.

[16]  Soulimane Abdellaoui,et al.  Atlas-based semiautomatic target volume definition (CTV) for head-and-neck tumors. , 2010, International journal of radiation oncology, biology, physics.

[17]  Anne Bol,et al.  A gradient-based method for segmenting FDG-PET images: methodology and validation , 2007, European Journal of Nuclear Medicine and Molecular Imaging.