naa a22 4500 510807941 CHVBK 20180411083426.0 cr unu---uuuuu 180411e20130701xx s 000 0 eng 10.1007/s11548-013-0832-8 doi (NATIONALLICENCE)springer-10.1007/s11548-013-0832-8 Computer-aided focal liver lesion detection [Elektronische Daten] [Yanling Chi, Jiayin Zhou, Sudhakar Venkatesh, Su Huang, Qi Tian, Tiffany Hennedige, Jimin Liu] Purpose: Our aim is to develop an automatic method which can detect diverse focal liver lesions (FLLs) in 3D CT volumes. Method: A hybrid generative-discriminative framework is proposed. It first uses a generative model to describe non-lesion components and then identifies all candidate FLLs within a 3D liver volume by eliminating non-lesion components. It subsequently uses a discriminative approach to suppress false positives with the advantage of tumoroid, a novel measurement combining three shape features spherical symmetry, compactness and size. Results: This method was tested on 71 abdominal CT datasets (5,854 slices from 61 patients, with 261 FLLs covering six pathological types) and evaluated using the free-response receiver operating characteristic (FROC) curves. Overall, it achieved a true positive rate of 90% with one false positive per liver. It degenerated gently with the decrease in lesion sizes to 30ml. It achieved a true-positive rate of 36% when tested on the lesions less than 4ml. The average computing time of the lesion detection is 4min and 28s per CT volume on a PC with 2.67GHz CPU and 4.0GB RAM. Conclusions: The proposed method is comparable to the radiologists' visual investigation in terms of efficiency. The tool has great potential to reduce radiologists' burden in going through thousands of images routinely. CARS, 2013 Computer-aided detection nationallicence 3D focal liver lesion detection nationallicence Background subtraction nationallicence Non-lesion modeling nationallicence Chi Yanling Singapore Bioimaging Consortium, Agency for Science, Technology and Research, 30 Biopolis Street, #07-01, Matrix, 138671, Singapore, Singapore aut Zhou Jiayin Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore, Singapore aut Venkatesh Sudhakar Department of Diagnostic Imaging, National University Hospital, Singapore, Singapore aut Huang Su Singapore Bioimaging Consortium, Agency for Science, Technology and Research, 30 Biopolis Street, #07-01, Matrix, 138671, Singapore, Singapore aut Tian Qi Singapore Bioimaging Consortium, Agency for Science, Technology and Research, 30 Biopolis Street, #07-01, Matrix, 138671, Singapore, Singapore aut Hennedige Tiffany Department of Diagnostic Imaging, National University Hospital, Singapore, Singapore aut Liu Jimin Singapore Bioimaging Consortium, Agency for Science, Technology and Research, 30 Biopolis Street, #07-01, Matrix, 138671, Singapore, Singapore aut International Journal of Computer Assisted Radiology and Surgery Springer Berlin Heidelberg 8/4(2013-07-01), 511-525 1861-6410 8:4<511 2013 8 11548 https://doi.org/10.1007/s11548-013-0832-8 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11548-013-0832-8 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Chi Yanling Singapore Bioimaging Consortium, Agency for Science, Technology and Research, 30 Biopolis Street, #07-01, Matrix, 138671, Singapore, Singapore aut NATIONALLICENCE 700 1- Zhou Jiayin Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore, Singapore aut NATIONALLICENCE 700 1- Venkatesh Sudhakar Department of Diagnostic Imaging, National University Hospital, Singapore, Singapore aut NATIONALLICENCE 700 1- Huang Su Singapore Bioimaging Consortium, Agency for Science, Technology and Research, 30 Biopolis Street, #07-01, Matrix, 138671, Singapore, Singapore aut NATIONALLICENCE 700 1- Tian Qi Singapore Bioimaging Consortium, Agency for Science, Technology and Research, 30 Biopolis Street, #07-01, Matrix, 138671, Singapore, Singapore aut NATIONALLICENCE 700 1- Hennedige Tiffany Department of Diagnostic Imaging, National University Hospital, Singapore, Singapore aut NATIONALLICENCE 700 1- Liu Jimin Singapore Bioimaging Consortium, Agency for Science, Technology and Research, 30 Biopolis Street, #07-01, Matrix, 138671, Singapore, Singapore aut NATIONALLICENCE 773 0- International Journal of Computer Assisted Radiology and Surgery Springer Berlin Heidelberg 8/4(2013-07-01), 511-525 1861-6410 8:4<511 2013 8 11548 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer