TY - GEN
T1 - Reduction of lymph tissue false positives in pulmonary embolism detection
AU - Ghanem, Bernard
AU - Liang, Jianming
AU - Bi, Jinbo
AU - Salganicoff, Marcos
AU - Krishnan, Arun
PY - 2008
Y1 - 2008
N2 - Pulmonary embolism (PE) is a serious medical condition, characterized by the partial/complete blockage of an artery within the lungs. We have previously developed a fast yet effective approach for computer aided detection of PE in computed topographic pulmonary angiography (CTPA),1 which is capable of detecting both acute and chronic PEs, achieving a benchmark performance of 78% sensitivity at 4 false positives (FPs) per volume. By reviewing the FPs generated by this system, we found the most dominant type of FP, roughly one third of all FPs, to be lymph/connective tissue. In this paper, we propose a novel approach that specifically aims at reducing this FP type. Our idea is to explicitly exploit the anatomical context configuration of PE and lymph tissue in the lungs: a lymph FP connects to the airway and is located outside the artery, while a true PE should not connect to the airway and must be inside the artery. To realize this idea, given a detected candidate (i.e. a cluster of suspicious voxels), we compute a set of contextual features, including its distance to the airway based on local distance transform and its relative position to the artery based on fast tensor voting and Hessian "vesselness" scores. Our tests on unseen cases show that these features can reduce the lymph FPs by 59%, while improving the overall sensitivity by 3.4%.
AB - Pulmonary embolism (PE) is a serious medical condition, characterized by the partial/complete blockage of an artery within the lungs. We have previously developed a fast yet effective approach for computer aided detection of PE in computed topographic pulmonary angiography (CTPA),1 which is capable of detecting both acute and chronic PEs, achieving a benchmark performance of 78% sensitivity at 4 false positives (FPs) per volume. By reviewing the FPs generated by this system, we found the most dominant type of FP, roughly one third of all FPs, to be lymph/connective tissue. In this paper, we propose a novel approach that specifically aims at reducing this FP type. Our idea is to explicitly exploit the anatomical context configuration of PE and lymph tissue in the lungs: a lymph FP connects to the airway and is located outside the artery, while a true PE should not connect to the airway and must be inside the artery. To realize this idea, given a detected candidate (i.e. a cluster of suspicious voxels), we compute a set of contextual features, including its distance to the airway based on local distance transform and its relative position to the artery based on fast tensor voting and Hessian "vesselness" scores. Our tests on unseen cases show that these features can reduce the lymph FPs by 59%, while improving the overall sensitivity by 3.4%.
KW - Classification and classifier design
KW - Detection
KW - Feature extraction
KW - Multiple instance learning
KW - Segmentation
KW - Tensor voting
KW - X-ray CT
UR - http://www.scopus.com/inward/record.url?scp=44249128888&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=44249128888&partnerID=8YFLogxK
U2 - 10.1117/12.770847
DO - 10.1117/12.770847
M3 - Conference contribution
AN - SCOPUS:44249128888
SN - 9780819470997
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2008 - Computer-Aided Diagnosis
T2 - Medical Imaging 2008 - Computer-Aided Diagnosis
Y2 - 19 February 2008 through 21 February 2008
ER -