Correcting Misalignment of Automatic 3D Detection by Classification: Ileo-Cecal Valve False Positive Reduction in CT Colonography

Ileo-Cecal Valve (ICV) is an important small soft organ which appears in human abdomen CT scans and connects colon and small intestine. Automated detection of ICV is of great clinical value for removing false positive (FP) findings in computer aided diagnosis (CAD) of colon cancers using CT colongraphy (CTC) [1,2,3]. However full 3D object detection, especially for small objects with large shape and pose variations as ICV, is very challenging. The final spatial detection accuracy often trades for robustness to find instances under variable conditions [4]. In this paper, we describe two significant post-parsing processes after the normal procedure of object (e.g., ICV) detection [4], to probabilistically interpret multiple hypotheses detections. It achieves nearly 300% performance improvement on (polyp detection) FP removal rate of [4], with about 1% extra computional overhead. First, a new multiple detection spatial-fusion method utilizes the initial single detection as an anchor identity and iteratively integrates other "trustful" detections by maximizing their spatial gains (if included) in a linkage. The ICV detection output is thus a set of N spatially connected boxes instead of a single box as top candidate, which allows to correct 3D detection misalignment inaccuracy. Next, we infer the spatial relationship between CAD generated polyp candidates and the detected ICV bounding boxes in 3D volume, and convert as a set of continuous valued, ICV-association features per candidate which allows further statistical analysis and classification for more rigorous false positive deduction in colon CAD. Based on our annotated 116 training cases, the spatial coverage ratio between the new N-box ICV detection and annotation is improved by 13.0% (N=2) and 19.6% (N=3) respectively. An evaluation on large scale datasets of total ∼ 1400 CTC volumes, with different tagging preparations, reports average 5.1 FP candidates are removed at Candidate-Generation stage per scan; and the final CAD system mean FP rate drops from 2.2 to 1.82 per volume, without affecting the sensitivity.

[1]  M E Baker,et al.  Computer-aided detection (CAD) for CT colonography: a tool to address a growing need. , 2005, The British journal of radiology.

[2]  Zhuowen Tu,et al.  Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[3]  David G. Stork,et al.  Pattern Classification , 1973 .

[4]  Jianhua Yao,et al.  CT colonography with computer-aided detection: automated recognition of ileocecal valve to reduce number of false-positive detections. , 2004, Radiology.

[5]  A K Dixon,et al.  Case report: False negative 16 detector multislice CT for scaphoid fracture. , 2005, The British journal of radiology.

[6]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[7]  David H. Eberly,et al.  3D Game Engine Design, Second Edition: A Practical Approach to Real-Time Computer Graphics (The Morgan Kaufmann Series in Interactive 3D Technology) , 2006 .

[8]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[9]  H. Yoshida,et al.  CAD techniques, challenges, andcontroversies in computed tomographic colonography , 2004, Abdominal Imaging.

[10]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[11]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[12]  David H. Eberly,et al.  3D game engine design - a practical approach to real-time computer graphics , 2000 .

[13]  Byung Ihn Choi,et al.  An anthropomorphic phantom study of computer-aided detection performance for polyp detection on CT colonography: a comparison of commercially and academically available systems. , 2009, AJR. American journal of roentgenology.

[14]  Ingemar J. Cox,et al.  An Efficient Implementation of Reid's Multiple Hypothesis Tracking Algorithm and Its Evaluation for the Purpose of Visual Tracking , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Ramakant Nevatia,et al.  Segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses , 2008, CVPR.

[16]  Dorin Comaniciu,et al.  Simultaneous Detection and Registration for Ileo-Cecal Valve Detection in 3D CT Colonography , 2008, ECCV.

[17]  A Gordon,et al.  Classification, 2nd Edition , 1999 .

[18]  Gregory G. Slabaugh,et al.  A Robust and Fast System for CTC Computer-Aided Detection of Colorectal Lesions , 2010, Algorithms.

[19]  Jianhua Yao,et al.  CT colonography with computer-aided polyp detection: volume and attenuation thresholds to reduce false-positive findings owing to the ileocecal valve. , 2006, Radiology.

[20]  Zhuowen Tu,et al.  Probabilistic 3D Polyp Detection in CT Images: The Role of Sample Alignment , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[21]  M. Macari,et al.  CAD for Colonography: A tool to address a growing need , 2004 .

[22]  Dorin Comaniciu,et al.  Robust object detection using marginal space learning and ranking-based multi-detector aggregation: Application to left ventricle detection in 2D MRI images , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  BlakeAndrew,et al.  C ONDENSATION Conditional Density Propagation forVisual Tracking , 1998 .

[24]  Dorin Comaniciu,et al.  Fast Automatic Heart Chamber Segmentation from 3D CT Data Using Marginal Space Learning and Steerable Features , 2007, 2007 IEEE 11th International Conference on Computer Vision.