Automatic Detection of Pulmonary Embolism in CTA Images

Pulmonary embolism (PE) is a common life-threatening disorder for which an early diagnosis is desirable. We propose a new system for the automatic detection of PE in contrast-enhanced CT images. The system consists of candidate detection, feature computation and classification. Candidate detection focusses on the inclusion of PE-even complete occlusions-and the exclusion of false detections, such as tissue and parenchymal diseases. Feature computation does not only focus on the intensity, shape and size of an embolus, but also on locations and the shape of the pulmonary vascular tree. Several classifiers have been tested and the results show that the performance is optimized by using a bagged tree classifier with two features based on the shape of a blood vessel and the distance to the vessel boundary. The system was trained on 38 CT data sets. Evaluation on 19 other data sets showed that the system generalizes well. The sensitivity of our system on the evaluation data is 63% at 4.9 false positives per data set, which allowed the radiologist to improve the number of detected PE by 22%.

[1]  Azriel Rosenfeld,et al.  Sequential Operations in Digital Picture Processing , 1966, JACM.

[2]  W. Kurkiewicz,et al.  [Lung scanning in the diagnosis of pulmonary embolism]. , 1973, Polski tygodnik lekarski.

[3]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[4]  Charles Elkan,et al.  Estimating the Accuracy of Learned Concepts , 1993, IJCAI.

[5]  L. V. van Vliet,et al.  Better geometric measurements based on photometric information , 1994, Conference Proceedings. 10th Anniversary. IMTC/94. Advanced Technologies in I & M. 1994 IEEE Instrumentation and Measurement Technolgy Conference (Cat. No.94CH3424-9).

[6]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[7]  Cao Feng,et al.  STATLOG: COMPARISON OF CLASSIFICATION ALGORITHMS ON LARGE REAL-WORLD PROBLEMS , 1995 .

[8]  R. Tibshirani,et al.  Improvements on Cross-Validation: The 632+ Bootstrap Method , 1997 .

[9]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[10]  Pierre Soille,et al.  Morphological Image Analysis , 1999 .

[11]  J. Remy,et al.  Spiral CT angiography of the pulmonary circulation. , 1999, Radiology.

[12]  Robert P. W. Duin,et al.  PRTools - Version 3.0 - A Matlab Toolbox for Pattern Recognition , 2000 .

[13]  L Martí-Bonmatí,et al.  Interobserver agreement in the diagnosis of pulmonary embolism with helical CT. , 2000, European journal of radiology.

[14]  Qingfen Lin,et al.  Efficient Detection of Second-Degree Variations in 2D and 3D Images , 2001, J. Vis. Commun. Image Represent..

[15]  P. Molina.  Spiral CT in the diagnosis of pulmonary embolism , 2001 .

[16]  P. Goodman,et al.  Computed tomography pulmonary angiography: Diagnostic pitfalls and artifacts , 2001, Applied Radiology.

[17]  Kunio Doi,et al.  Computerized detection of pulmonary embolism in spiral CT angiography based on volumetric image analysis , 2002, IEEE Transactions on Medical Imaging.

[18]  Berkman Sahiner,et al.  Computerized detection of pulmonary embolism in 3D computed tomographic (CT) images: vessel tracking and segmentation techniques , 2003, SPIE Medical Imaging.

[19]  Jorien van der Peijl.  Automated detection and segmentation of the lungs in CT datasets , 2003 .

[20]  Foster J. Provost,et al.  Confidence Bands for Roc Curves , 2004, ROCAI.

[21]  David P. Naidich,et al.  A novel method for pulmonary emboli visualization from high-resolution CT images , 2004, Medical Imaging: Image-Guided Procedures.

[22]  Joseph M. Reinhardt,et al.  Smoothing lung segmentation surfaces in 3D x-ray CT images using anatomic guidance , 2004, SPIE Medical Imaging.

[23]  A. Pforte.  Epidemiology, diagnosis, and therapy of pulmonary embolism. , 2004, European journal of medical research.

[24]  Cristian Lorenz,et al.  Automatic extraction of the pulmonary artery tree from multi-slice CT data , 2005, SPIE Medical Imaging.

[25]  R. Günther,et al.  CT imaging in acute pulmonary embolism: diagnostic strategies , 2005, European Radiology.

[26]  Berkman Sahiner,et al.  Preliminary investigation of computer-aided detection of pulmonary embolism in three-dimensional computed tomography pulmonary angiography images. , 2005, Academic radiology.

[27]  L. Goodman,et al.  Small pulmonary emboli: what do we know? , 2005, Radiology.

[28]  S. Schoenberg,et al.  MRI expands options in lung assessment , 2005 .

[29]  Jane P. Ko,et al.  A comparison of 2D and 3D evaluation methods for pulmonary embolism detection in CT images , 2006, SPIE Medical Imaging.

[30]  M. Godoy,et al.  Computer-aided Detection of Pulmonary Embolism on CT Angiography: Initial Experience , 2007, Journal of thoracic imaging.

[31]  Kunio Doi,et al.  Some practical issues for assessment of computer-aided diagnostic schemes , 2007, SPIE Medical Imaging.

[32]  K. L. Lewis,et al.  Multidetector Computed Tomography for Acute Pulmonary Embolism , 2007 .