Please use this identifier to cite or link to this item: https://doi.org/10.1007/s11548-013-0832-8
DC FieldValue
dc.titleComputer-aided focal liver lesion detection
dc.contributor.authorChi, Y.
dc.contributor.authorZhou, J.
dc.contributor.authorVenkatesh, S.K.
dc.contributor.authorHuang, S.
dc.contributor.authorTian, Q.
dc.contributor.authorHennedige, T.
dc.contributor.authorLiu, J.
dc.date.accessioned2016-09-06T09:10:11Z
dc.date.available2016-09-06T09:10:11Z
dc.date.issued2013-07
dc.identifier.citationChi, Y., Zhou, J., Venkatesh, S.K., Huang, S., Tian, Q., Hennedige, T., Liu, J. (2013-07). Computer-aided focal liver lesion detection. International Journal of Computer Assisted Radiology and Surgery 8 (4) : 511-525. ScholarBank@NUS Repository. https://doi.org/10.1007/s11548-013-0832-8
dc.identifier.issn18616410
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/126946
dc.description.abstractPurpose: 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 30 ml. It achieved a true-positive rate of 36 % when tested on the lesions less than 4 ml. The average computing time of the lesion detection is 4 min and 28 s per CT volume on a PC with 2.67 GHz CPU and 4.0 GB 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. © 2013 CARS.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1007/s11548-013-0832-8
dc.sourceScopus
dc.subject3D focal liver lesion detection
dc.subjectBackground subtraction
dc.subjectComputer-aided detection
dc.subjectNon-lesion modeling
dc.typeArticle
dc.contributor.departmentDIAGNOSTIC RADIOLOGY
dc.description.doi10.1007/s11548-013-0832-8
dc.description.sourcetitleInternational Journal of Computer Assisted Radiology and Surgery
dc.description.volume8
dc.description.issue4
dc.description.page511-525
dc.identifier.isiut000321520200002
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

12
checked on Jan 14, 2020

WEB OF SCIENCETM
Citations

11
checked on Jan 14, 2020

Page view(s)

45
checked on Jan 17, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.