Comparative study with new accuracy metrics for target volume contouring in PET image guided radiation therapy.

The impact of PET on radiation therapy is held back by poor methods of defining functional volumes of interest. Many new software tools are being proposed for contouring target volumes but the different approaches are not adequately compared and their accuracy is poorly evaluated due to the illdefinition of ground truth. This paper compares the largest cohort to date of established, emerging and proposed PET contouring methods, in terms of accuracy and variability. We emphasise spatial accuracy and present a new metric that addresses the lack of unique ground truth. 30 methods are used at 13 different institutions to contour functional VOIs in clinical PET/CT and a custom-built PET phantom representing typical problems in image guided radiotherapy. Contouring methods are grouped according to algorithmic type, level of interactivity and how they exploit structural information in hybrid images. Experiments reveal benefits of high levels of user interaction, as well as simultaneous visualisation of CT images and PET gradients to guide interactive procedures. Method-wise evaluation identifies the danger of over-automation and the value of prior knowledge built into an algorithm.

[1]  R L Wahl,et al.  Standardized uptake values of normal tissues at PET with 2-[fluorine-18]-fluoro-2-deoxy-D-glucose: variations with body weight and a method for correction. , 1993, Radiology.

[2]  Mithat Gonen,et al.  Head and neck cancer: clinical usefulness and accuracy of PET/CT image fusion. , 2004, Radiology.

[3]  Dimitris Visvikis,et al.  Accurate automatic delineation of heterogeneous functional volumes in positron emission tomography for oncology applications. , 2010, International journal of radiation oncology, biology, physics.

[4]  John Aldo Lee,et al.  Edge-Preserving Filtering of Images with Low Photon Counts , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  C Nutting Intensity-modulated radiotherapy (IMRT): the most important advance in radiotherapy since the linear accelerator? , 2003, The British journal of radiology.

[6]  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.

[7]  J. Keyes SUV: standard uptake or silly useless value? , 1995, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[8]  Chunming Li,et al.  Minimization of Region-Scalable Fitting Energy for Image Segmentation , 2008, IEEE Transactions on Image Processing.

[9]  N. Otsu A threshold selection method from gray level histograms , 1979 .

[10]  F Hofheinz,et al.  Effects of cold sphere walls in PET phantom measurements on the volume reproducing threshold , 2010, Physics in medicine and biology.

[11]  L. R. Dice Measures of the Amount of Ecologic Association Between Species , 1945 .

[12]  W. Oyen,et al.  SUV: From Silly Useless Value to Smart Uptake Value , 2010, Journal of Nuclear Medicine.

[13]  Rodney J Hicks,et al.  18F-FDG PET in candidates for radiation therapy: is it important and how do we validate its impact? , 2003, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

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

[15]  Mithat Gönen,et al.  Evaluation of Different Methods of 18F-FDG-PET Target Volume Delineation in the Radiotherapy of Head and Neck Cancer , 2008, American journal of clinical oncology.

[16]  H. Zaidi,et al.  Assessment of various strategies for 18F-FET PET-guided delineation of target volumes in high-grade glioma patients , 2009, European Journal of Nuclear Medicine and Molecular Imaging.

[17]  D. Hellwig,et al.  18F-FDG PET for Mediastinal Staging of Lung Cancer: Which SUV Threshold Makes Sense? , 2007, Journal of Nuclear Medicine.

[18]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[19]  J. Lee,et al.  Segmentation of positron emission tomography images: some recommendations for target delineation in radiation oncology. , 2010, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[20]  S M Larson,et al.  Segmentation of lung lesion volume by adaptive positron emission tomography image thresholding , 1997, Cancer.

[21]  Stan Z. Li,et al.  Markov Random Field Models in Computer Vision , 1994, ECCV.

[22]  Daniel A Low,et al.  A novel PET tumor delineation method based on adaptive region-growing and dual-front active contours. , 2008, Medical physics.

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

[24]  J. Swets ROC analysis applied to the evaluation of medical imaging techniques. , 1979, Investigative radiology.

[25]  S. Katsuragawa,et al.  Abstract1095: Impact of FDG-PET/CT Fusion Imaging on Nodal Staging and Radiation-Therapy Planning for Head-and-Neck Squamous Cell Carcinoma , 2006 .

[26]  Jean-François Daisne,et al.  Tumor volume in pharyngolaryngeal squamous cell carcinoma: comparison at CT, MR imaging, and FDG PET and validation with surgical specimen. , 2004, Radiology.

[27]  Liane Oehme,et al.  A method for model-free partial volume correction in oncological PET , 2012, EJNMMI Research.

[28]  Anne Bol,et al.  Evaluation of a multimodality image (CT, MRI and PET) coregistration procedure on phantom and head and neck cancer patients: accuracy, reproducibility and consistency. , 2003, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[29]  Arthur W. Toga,et al.  Online resource for validation of brain segmentation methods , 2009, NeuroImage.

[30]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Mila Nikolova,et al.  Algorithms for Finding Global Minimizers of Image Segmentation and Denoising Models , 2006, SIAM J. Appl. Math..

[32]  Di Yan,et al.  Defining a radiotherapy target with positron emission tomography. , 2002, International journal of radiation oncology, biology, physics.

[33]  Sébastien Lefèvre,et al.  Knowledge from Markers in Watershed Segmentation , 2007, CAIP.

[34]  Nico Karssemeijer,et al.  A novel iterative method for lesion delineation and volumetric quantification with FDG PET , 2007, Nuclear medicine communications.

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

[36]  C. Rübe,et al.  Comparison of different methods for delineation of 18F-FDG PET-positive tissue for target volume definition in radiotherapy of patients with non-Small cell lung cancer. , 2005, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

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

[38]  Damien Bolton,et al.  Histopathological correlation of (11)C-choline PET scans for target volume definition in radical prostate radiotherapy. , 2011, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[39]  Heinz-Otto Peitgen,et al.  Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic CT scans , 2006, IEEE Transactions on Medical Imaging.

[40]  Anne Bol,et al.  Tri-dimensional automatic segmentation of PET volumes based on measured source-to-background ratios: influence of reconstruction algorithms. , 2003, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[41]  Mariano Alcañiz Raya,et al.  Aorta segmentation using the watershed algorithm for an augmented reality system in laparoscopic surgery , 2011, 2011 18th IEEE International Conference on Image Processing.

[42]  Huan Yu,et al.  Coregistered FDG PET/CT-Based Textural Characterization of Head and Neck Cancer for Radiation Treatment Planning , 2009, IEEE Transactions on Medical Imaging.

[43]  Andrea Schaefer,et al.  A contrast-oriented algorithm for FDG-PET-based delineation of tumour volumes for the radiotherapy of lung cancer: derivation from phantom measurements and validation in patient data , 2008, European Journal of Nuclear Medicine and Molecular Imaging.

[44]  Habib Zaidi,et al.  PET-guided delineation of radiation therapy treatment volumes: a survey of image segmentation techniques , 2010, European Journal of Nuclear Medicine and Molecular Imaging.

[45]  A. Riegel,et al.  Variability of gross tumor volume delineation in head-and-neck cancer using CT and PET/CT fusion. , 2005, International journal of radiation oncology, biology, physics.

[46]  Brian O'Sullivan,et al.  Intraobserver and interobserver variability in GTV delineation on FDG-PET-CT images of head and neck cancers. , 2007, International journal of radiation oncology, biology, physics.

[47]  V. Pekar,et al.  Head and Neck Auto-segmentation Challenge , 2009, The MIDAS Journal.

[48]  Yuji Nakamoto,et al.  Reproducibility of common semi-quantitative parameters for evaluating lung cancer glucose metabolism with positron emission tomography using 2-deoxy-2-[18F]fluoro-D-glucose. , 2002, Molecular imaging and biology : MIB : the official publication of the Academy of Molecular Imaging.

[49]  F Hofheinz,et al.  Automatic volume delineation in oncological PET , 2011, Nuklearmedizin.

[50]  J. Buatti,et al.  Globally Optimal Tumor Segmentation in PET-CT Images: A Graph-Based Co-segmentation Method , 2011, IPMI.

[51]  I. Poon,et al.  Automated radiation targeting in head-and-neck cancer using region-based texture analysis of PET and CT images. , 2009, International journal of radiation oncology, biology, physics.

[52]  William M. Wells,et al.  Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation , 2004, IEEE Transactions on Medical Imaging.

[53]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[54]  Chunming Li,et al.  Split Bregman Method for Minimization of Region-Scalable Fitting Energy for Image Segmentation , 2010, ISVC.

[55]  Toshinori Hirai,et al.  Impact of FDG-PET/CT imaging on nodal staging for head-and-neck squamous cell carcinoma. , 2007, International journal of radiation oncology, biology, physics.

[56]  Dominique Hasboun,et al.  Anatomically constrained region deformation for the automated segmentation of the hippocampus and the amygdala: Method and validation on controls and patients with Alzheimer’s disease , 2007, NeuroImage.

[57]  R. Real,et al.  The Probabilistic Basis of Jaccard's Index of Similarity , 1996 .

[58]  A. Tversky Features of Similarity , 1977 .