Segmentation of pulmonary nodules in computed tomography using a regression neural network approach and its application to the Lung Image Database Consortium and Image Database Resource Initiative dataset

We present new pulmonary nodule segmentation algorithms for computed tomography (CT). These include a fully-automated (FA) system, a semi-automated (SA) system, and a hybrid system. Like most traditional systems, the new FA system requires only a single user-supplied cue point. On the other hand, the SA system represents a new algorithm class requiring 8 user-supplied control points. This does increase the burden on the user, but we show that the resulting system is highly robust and can handle a variety of challenging cases. The proposed hybrid system starts with the FA system. If improved segmentation results are needed, the SA system is then deployed. The FA segmentation engine has 2 free parameters, and the SA system has 3. These parameters are adaptively determined for each nodule in a search process guided by a regression neural network (RNN). The RNN uses a number of features computed for each candidate segmentation. We train and test our systems using the new Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) data. To the best of our knowledge, this is one of the first nodule-specific performance benchmarks using the new LIDC-IDRI dataset. We also compare the performance of the proposed methods with several previously reported results on the same data used by those other methods. Our results suggest that the proposed FA system improves upon the state-of-the-art, and the SA system offers a considerable boost over the FA system.

[1]  S. Armato,et al.  Automated detection of lung nodules in CT scans: preliminary results. , 2001, Medical physics.

[2]  David Mitton,et al.  Fast accurate stereoradiographic 3D-reconstruction of the spine using a combined geometric and statistic model. , 2004, Clinical biomechanics.

[3]  K. Cios.  An introduction to biological and artificial neural networks for pattern recognition: by Steven K. Rogers and Matthew Kabrisky, with contributing authors Dennis W. Ruck and Gregory L. Tarr. SPIE Optical Engineering Press, pp. 220, 1991, ISBN 0-8194-0534-5, $30.00 , 1995 .

[4]  D. Rajan.  Probability, Random Variables, and Stochastic Processes , 2017 .

[5]  Thomas F. Coleman,et al.  Segmentation of Pulmonary Nodule Images Using Total Variation Minimization , 1998 .

[6]  E. V. van Beek,et al.  The Lung Image Database Consortium (LIDC): a comparison of different size metrics for pulmonary nodule measurements. , 2007, Academic radiology.

[7]  Steven K. Rogers,et al.  An Introduction to Biological and Artificial Neural Networks for Pattern Recognition , 1991 .

[8]  Ning Xu,et al.  Automated lung nodule segmentation using dynamic programming and EM-based classification , 2002, SPIE Medical Imaging.

[9]  Rafael Wiemker,et al.  Performance analysis for computer-aided lung nodule detection on LIDC data , 2007, SPIE Medical Imaging.

[10]  Gregory G. Slabaugh,et al.  Image segmentation using joint spatial-intensity-shape features: application to CT lung nodule segmentation , 2009, Medical Imaging.

[11]  Hong Zhao,et al.  Efficient 3D texture feature extraction from CT images for computer-aided diagnosis of pulmonary nodules , 2014, Medical Imaging.

[12]  Dorin Comaniciu,et al.  Robust anisotropic Gaussian fitting for volumetric characterization of Pulmonary nodules in multislice CT , 2005, IEEE Transactions on Medical Imaging.

[13]  James S. Duncan,et al.  Medical Image Analysis , 1999, IEEE Pulse.

[14]  Laurent Younes,et al.  Incorporating user input in template-based segmentation , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[15]  L. Costaridou,et al.  Combining 2D wavelet edge highlighting and 3D thresholding for lung segmentation in thin-slice CT. , 2007, The British journal of radiology.

[16]  M. Giger,et al.  Image feature analysis and computer-aided diagnosis in digital radiography. 3. Automated detection of nodules in peripheral lung fields. , 1988, Medical physics.

[17]  Ivica Kostanic,et al.  Principles of Neurocomputing for Science and Engineering , 2000 .

[18]  Lubomir M. Hadjiiski,et al.  Computer-aided diagnosis of pulmonary nodules on CT scans: segmentation and classification using 3D active contours. , 2006, Medical physics.

[19]  Jacob D. Furst,et al.  Predicting LIDC diagnostic characteristics by combining spatial and diagnostic opinions , 2010, Medical Imaging.

[20]  Leif H. Finkel,et al.  CURRENT METHODS IN MEDICAL IMAGE SEGMENTATION1 , 2007 .

[21]  S. Armato,et al.  Computerized detection of pulmonary nodules on CT scans. , 1999, Radiographics : a review publication of the Radiological Society of North America, Inc.

[22]  Bram van Ginneken,et al.  Supervised Probabilistic Segmentation of Pulmonary Nodules in CT Scans , 2006, MICCAI.

[23]  Anthony P. Reeves,et al.  THREE-DIMENSIONAL MULTICRITERION AUTOMATIC SEGMENTATION OF PULMONARY NODULES OF HELICAL COMPUTED TOMOGRAPHY IMAGES , 1999 .

[24]  Richard C. Pais,et al.  The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. , 2011, Medical physics.

[25]  O. Miettinen,et al.  CT screening for lung cancer: frequency and significance of part-solid and nonsolid nodules. , 2002, AJR. American journal of roentgenology.

[26]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[27]  Zaid J. Towfic,et al.  The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation , 2007, SPIE Medical Imaging.

[28]  Jie Tian,et al.  Automated delineation of lung tumors from CT images using a single click ensemble segmentation approach , 2013, Pattern Recognit..

[29]  Shoji Kido,et al.  Automatic segmentation of pulmonary nodules on CT images by use of NCI lung image database consortium , 2006, SPIE Medical Imaging.

[30]  Russell C. Hardie,et al.  Automatic segmentation of small pulmonary nodules in computed tomography data using a radial basis function neural network with application to volume estimation , 2008 .

[31]  Berkman Sahiner,et al.  Medical Imaging 2007: Image Perception, Observer Performance, and Technology Assessment , 2007 .

[32]  Berkman Sahiner,et al.  Effect of CAD on radiologists' detection of lung nodules on thoracic CT scans: observer performance study , 2007, SPIE Medical Imaging.

[33]  Daniel C. Moura,et al.  Fast 3D Reconstruction of the Spine Using User-Defined Splines and a Statistical Articulated Model , 2009, ISVC.

[34]  U. G. Dailey.  Cancer,Facts and Figures about. , 2022, Journal of the National Medical Association.

[35]  Li Fan,et al.  Automatic segmentation of pulmonary nodules by using dynamic 3D cross-correlation for interactive CAD systems , 2002, SPIE Medical Imaging.

[36]  Zohreh Azimifar,et al.  Lung nodule segmentation and recognition using SVM classifier and active contour modeling: A complete intelligent system , 2013, Comput. Biol. Medicine.

[37]  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.

[38]  Bram van Ginneken.  Supervised probabilistic segmentation of pulmonary nodules in CT scans. , 2006, Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention.

[39]  Max A. Viergever,et al.  Computer-aided diagnosis in chest radiography: a survey , 2001, IEEE Transactions on Medical Imaging.

[40]  Temesguen Messay,et al.  A new computationally efficient CAD system for pulmonary nodule detection in CT imagery , 2010, Medical Image Anal..

[41]  Abderrahim Elmoataz,et al.  Fast and Simple Discrete Approach for Active Contours for Biomedical Applications , 2001, Int. J. Pattern Recognit. Artif. Intell..

[42]  R. Engelmann,et al.  Segmentation of pulmonary nodules in three-dimensional CT images by use of a spiral-scanning technique. , 2007, Medical physics.

[43]  M. Giger,et al.  Computerized detection of pulmonary nodules in digital chest images: use of morphological filters in reducing false-positive detections. , 1990, Medical physics.

[44]  K. Doi,et al.  Computerized detection of lung nodules in thin-section CT images by use of selective enhancement filters and an automated rule-based classifier. , 2008, Academic Radiology.

[45]  Bram van Ginneken,et al.  Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images , 2014, Medical Image Anal..

[46]  Claus Bendtsen,et al.  X-Ray Computed Tomography: Semiautomated Volumetric Analysis of Late-Stage Lung Tumors as a Basis for Response Assessments , 2011, Int. J. Biomed. Imaging.

[47]  F Lavaste,et al.  [Geometrical modeling of the spine and the thorax for the biomechanical analysis of scoliotic deformities using the finite element method]. , 1995, Annales de chirurgie.

[48]  Antoni B. Chan,et al.  On measuring the change in size of pulmonary nodules , 2006, IEEE Transactions on Medical Imaging.

[49]  Margrit Betke,et al.  Small pulmonary nodules: volume measurement at chest CT--phantom study. , 2003, Radiology.

[50]  Tomaso A. Poggio,et al.  Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[51]  David Mitton,et al.  3D reconstruction method from biplanar radiography using non-stereocorresponding points and elastic deformable meshes , 2000, Medical and Biological Engineering and Computing.

[52]  Anne C. Lusk,et al.  Risk of injury for bicycling on cycle tracks versus in the street , 2011, Injury Prevention.

[53]  A. Reeves,et al.  Two-dimensional multi-criterion segmentation of pulmonary nodules on helical CT images. , 1999, Medical physics.

[54]  Jerry L Prince,et al.  Current methods in medical image segmentation. , 2000, Annual review of biomedical engineering.

[55]  Tarek M. Taha,et al.  GPGPU acceleration of a novel calibration method for industrial robots , 2011, Proceedings of the 2011 IEEE National Aerospace and Electronics Conference (NAECON).

[56]  E. Hoffman,et al.  Lung image database consortium: developing a resource for the medical imaging research community. , 2004, Radiology.

[57]  M. Giger,et al.  Computerized Detection of Pulmonary Nodules in Computed Tomography Images , 1994, Investigative radiology.

[58]  Alejandro F. Frangi,et al.  Active shape model segmentation with optimal features , 2002, IEEE Transactions on Medical Imaging.

[59]  Qian Wang,et al.  Segmentation of lung nodules in computed tomography images using dynamic programming and multidirection fusion techniques. , 2009, Academic radiology.

[60]  Guido Valli,et al.  3-D Segmentation Algorithm of Small Lung Nodules in Spiral CT Images , 2008, IEEE Transactions on Information Technology in Biomedicine.

[61]  Umut Akdemir,et al.  Blob segmentation using joint space-intensity likelihood ratio test: application to 3D tumor segmentation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[62]  Heinz-Otto Peitgen,et al.  Advanced Segmentation Techniques for Lung Nodules, Liver Metastases, and Enlarged Lymph Nodes in CT Scans , 2009, IEEE Journal of Selected Topics in Signal Processing.

[63]  Geoffrey McLennan,et al.  The Lung Image Database Consortium (LIDC): an evaluation of radiologist variability in the identification of lung nodules on CT scans. , 2007, Academic radiology.

[64]  Robin N. Strickland.  Image-Processing Techniques for Tumor Detection , 2007 .

[65]  B. Ginneken.  Computer-aided diagnosis in chest radiography , 2001 .

[66]  Marcos Salganicoff,et al.  Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models , 2011, Medical Image Anal..

[67]  Russell C. Hardie,et al.  Performance analysis of a new computer aided detection system for identifying lung nodules on chest radiographs , 2008, Medical Image Anal..

[68]  William M. Wells,et al.  Medical Image Computing and Computer-Assisted Intervention — MICCAI’98 , 1998, Lecture Notes in Computer Science.

[69]  Margrit Betke,et al.  Segmentation of nodules on chest computed tomography for growth assessment. , 2004, Medical physics.

[70]  Bram van Ginneken,et al.  Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database , 2006, Medical Image Anal..

[71]  Françoise J. Prêteux,et al.  3D Automated Lung Nodule Segmentation in HRCT , 2003, MICCAI.

[72]  Noboru Niki,et al.  Pulmonary nodule segmentation in thoracic 3D CT images integrating boundary and region information , 2003, SPIE Medical Imaging.

[73]  Anthony P. Reeves,et al.  Three-dimensional segmentation and growth-rate estimation of small pulmonary nodules in helical CT images , 2003, IEEE Transactions on Medical Imaging.

[74]  N. Moshtagh.  MINIMUM VOLUME ENCLOSING ELLIPSOIDS , 2005 .

[75]  Audra E. Kosh,et al.  Linear Algebra and its Applications , 1992 .

[76]  Dag Wormanns,et al.  Characterization of small pulmonary nodules by CT , 2004, European Radiology.

[77]  Rafael Wiemker,et al.  Optimal thresholding for 3D segmentation of pulmonary nodules in high resolution CT , 2001, CARS.

[78]  Ying Bai,et al.  Probabilistic minimal path for automated esophagus segmentation , 2006, SPIE Medical Imaging.

[79]  Timo Ropinski,et al.  From Imprecise User Input to Precise Vessel Segmentations , 2012, VCBM.

[80]  Antanas Verikas,et al.  Feature selection with neural networks , 2002, Pattern Recognit. Lett..

[81]  Jamshid Dehmeshki,et al.  Segmentation of Pulmonary Nodules in Thoracic CT Scans: A Region Growing Approach , 2008, IEEE Transactions on Medical Imaging.

[82]  Shigeo Abe,et al.  Neural Networks and Fuzzy Systems , 1996, Springer US.

[83]  Derek Partridge,et al.  Assessing the Impact of Input Features in a Feedforward Neural Network , 2000, Neural Computing & Applications.