Publications
Detailed Information
Multilevel analysis of spatiotemporal association features for differentiation of tumor enhancement patterns in breast DCE-MRI
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Sang Ho | - |
dc.contributor.author | Kim, Jong Hyo | - |
dc.contributor.author | Cho, Nariya | - |
dc.contributor.author | Park, Jeong Seon | - |
dc.contributor.author | Jung, Yun Sub | - |
dc.contributor.author | Moon, Woo Kyung | - |
dc.contributor.author | Yang, Zepa | - |
dc.date.accessioned | 2012-07-04T01:19:30Z | - |
dc.date.available | 2012-07-04T01:19:30Z | - |
dc.date.issued | 2010-08 | - |
dc.identifier.citation | MEDICAL PHYSICS; Vol.37 8; 3940-3956 | ko_KR |
dc.identifier.issn | 0094-2405 | - |
dc.identifier.uri | https://hdl.handle.net/10371/78359 | - |
dc.description.abstract | Purpose: Analyzing spatiotemporal enhancement patterns is an important task for the differential diagnosis of breast tumors in dynamic contrast-enhanced MRI (DCE-MRI), and yet remains challenging because of complexities in analyzing the time-series of three-dimensional image data. The authors propose a novel approach to breast MRI computer-aided diagnosis (CAD) using a multi-level analysis of spatiotemporal association features for tumor enhancement patterns in DCE-MRI. Methods: A database of 171 cases consisting of 111 malignant and 60 benign tumors was used. Time-series contrast-enhanced MR images were obtained from two different types of MR scanners and protocols. The images were first registered for motion compensation, and then tumor regions were segmented using a fuzzy c-means clustering-based method. Spatiotemporal associations of tumor enhancement patterns were analyzed at three levels: Mapping of pixelwise kinetic features within a tumor, extraction of spatial association features from kinetic feature maps, and extraction of kinetic association features at the spatial feature level. A total of 84 initial features were extracted. Predictable values of these features were evaluated with an area under the ROC curve, and were compared between the spatiotemporal association features and a subset of simple form features which do not reflect spatiotemporal association. `Several optimized feature sets were identified among the spatiotemporal association feature group or among the simple feature group based on a feature ranking criterion using a support vector machine based recursive feature elimination algorithm. A least-squares support vector machine (LS-SVM) classifier was used for tumor differentiation and the performances were evaluated using a leave-one-out testing. Results: Predictable values of the extracted single features ranged in 0.52-0.75. By applying multilevel analysis strategy, the spatiotemporal association features became more informative in predicting tumor malignancy, which was shown by a statistical testing in ten spatiotemporal association features. By using a LS-SVM classifier with the optimized second and third level feature set, the CAD scheme showed A(z) of 0.88 in classification of malignant and benign tumors. When this performance was compared to the same LS-SVM classifier with simple form features which do not reflect spatiotemporal association, there was a statistically significant difference (0.88 vs 0.79, p<0.05), suggesting that the multilevel analysis strategy yields a significant performance improvement. Conclusions: The results suggest that the multilevel analysis strategy characterizes the complex tumor enhancement patterns effectively with the spatiotemporal association features, which in turn leads to an improved tumor differentiation. The proposed CAD scheme has a potential for improving diagnostic performance in breast DCE-MRI. (C) 2010 American Association of Physicists in Medicine. [DOI: 10.1118/1.3446799] | ko_KR |
dc.language.iso | en | ko_KR |
dc.publisher | AMER ASSOC PHYSICISTS MEDICINE AMER INST PHYSICS | ko_KR |
dc.subject | breast dynamic contrast-enhanced MRI | ko_KR |
dc.subject | support vector machines | ko_KR |
dc.subject | tumor characterization | ko_KR |
dc.subject | 3D moment invariants | ko_KR |
dc.subject | spatiotemporal association | ko_KR |
dc.subject | feature extraction | ko_KR |
dc.subject | classification | ko_KR |
dc.subject | computer-aided diagnosis | ko_KR |
dc.title | Multilevel analysis of spatiotemporal association features for differentiation of tumor enhancement patterns in breast DCE-MRI | ko_KR |
dc.type | Article | ko_KR |
dc.contributor.AlternativeAuthor | 이상호 | - |
dc.contributor.AlternativeAuthor | 김종효 | - |
dc.contributor.AlternativeAuthor | 조나리야 | - |
dc.contributor.AlternativeAuthor | 박정선 | - |
dc.contributor.AlternativeAuthor | 정윤섭 | - |
dc.contributor.AlternativeAuthor | 문우경 | - |
dc.identifier.doi | 10.1118/1.3446799 | - |
dc.citation.journaltitle | MEDICAL PHYSICS | - |
dc.description.citedreference | Shi JZ, 2009, MED PHYS, V36, P5052, DOI 10.1118/1.3238101 | - |
dc.description.citedreference | Zheng YJ, 2009, MED PHYS, V36, P3192, DOI 10.1118/1.3151811 | - |
dc.description.citedreference | Baltzer PAT, 2009, ACAD RADIOL, V16, P435, DOI 10.1016/j.acra.2008.10.007 | - |
dc.description.citedreference | Ng B, 2009, IEEE T MED IMAGING, V28, P261, DOI 10.1109/TMI.2008.929097 | - |
dc.description.citedreference | Leach MO, 2009, NMR BIOMED, V22, P17, DOI 10.1002/nbm.1326 | - |
dc.description.citedreference | Levman J, 2008, IEEE T MED IMAGING, V27, P688, DOI 10.1109/TMI.2008.916959 | - |
dc.description.citedreference | Li KL, 2007, MAGN RESON MED, V58, P572, DOI 10.1002/mrm.21361 | - |
dc.description.citedreference | Williams TC, 2007, RADIOLOGY, V244, P94, DOI 10.1148/radiol.2441060634 | - |
dc.description.citedreference | Sardanelli F, 2007, RADIOLOGY, V242, P698, DOI 10.1148/radiol.2423051965 | - |
dc.description.citedreference | Alderliesten T, 2007, INVEST RADIOL, V42, P42 | - |
dc.description.citedreference | Meinel LA, 2007, J MAGN RESON IMAGING, V25, P89, DOI 10.1002/jmri.20794 | - |
dc.description.citedreference | ZHENG Y, 2007, P 4 IEEE INT S BIOM, P520 | - |
dc.description.citedreference | Schnall MD, 2006, RADIOLOGY, V238, P42, DOI 10.1148/radiol.2381042117 | - |
dc.description.citedreference | Chen WJ, 2006, ACAD RADIOL, V13, P63, DOI 10.1016/j.acra.2005.08.035 | - |
dc.description.citedreference | TANNER C, 2006, P 3 IEEE INT S BIOM, P466 | - |
dc.description.citedreference | Kuhl CK, 2005, J CLIN ONCOL, V23, P8469, DOI 10.1200/JCO.2004.00.4960 | - |
dc.description.citedreference | Leach MO, 2005, LANCET, V365, P1769, DOI 10.1016/S0140-6736(05)66481-1 | - |
dc.description.citedreference | Liberman L, 2004, NEW ENGL J MED, V351, P497 | - |
dc.description.citedreference | Ikeda O, 2004, ACTA RADIOL, V45, P446, DOI 10.1080/02841850410005372 | - |
dc.description.citedreference | Chen WJ, 2004, MED PHYS, V31, P1076, DOI 10.1118/1.1695652 | - |
dc.description.citedreference | CHAI H, 2004, P 2 EUR WORKSH DAT M, P3 | - |
dc.description.citedreference | Szabo BK, 2003, ACTA RADIOL, V44, P379 | - |
dc.description.citedreference | Rohlfing T, 2003, IEEE T MED IMAGING, V22, P730, DOI 10.1109/TMI.2003.814791 | - |
dc.description.citedreference | RAKOTOMAMONJY A, 2003, J MACHINE LEARNING R, V3, P1357, DOI 10.1162/153244303322753706 | - |
dc.description.citedreference | *ACR, 2003, ACR BI RADS MRI | - |
dc.description.citedreference | Kelcz F, 2002, AM J ROENTGENOL, V179, P1485 | - |
dc.description.citedreference | Guyon I, 2002, MACH LEARN, V46, P389 | - |
dc.description.citedreference | SUYKENS J, 2002, LEAST SQUARES SUPPOR | - |
dc.description.citedreference | Stoutjesdijk MJ, 2001, J NATL CANCER I, V93, P1095 | - |
dc.description.citedreference | Furman-Haran E, 2001, J MAGN RESON IMAGING, V13, P862 | - |
dc.description.citedreference | Nunes LW, 2001, RADIOLOGY, V219, P484 | - |
dc.description.citedreference | Wedegartner U, 2001, EUR RADIOL, V11, P1645 | - |
dc.description.citedreference | Lucht REA, 2001, MAGN RESON IMAGING, V19, P51 | - |
dc.description.citedreference | HYLTON NM, 2001, MAGN RESON IMAGING C, V9, P321 | - |
dc.description.citedreference | Kinkel K, 2000, AM J ROENTGENOL, V175, P35 | - |
dc.description.citedreference | Liney GP, 1999, JMRI-J MAGN RESON IM, V10, P945 | - |
dc.description.citedreference | Rueckert D, 1999, IEEE T MED IMAGING, V18, P712, DOI 10.1109/42.796284 | - |
dc.description.citedreference | Suykens JAK, 1999, NEURAL PROCESS LETT, V9, P293 | - |
dc.description.citedreference | Kuhl CK, 1999, RADIOLOGY, V211, P101 | - |
dc.description.citedreference | Orel SG, 1999, RADIOLOGY, V211, P5 | - |
dc.description.citedreference | Furman-Haran E, 1998, CLIN CANCER RES, V4, P2299 | - |
dc.description.citedreference | Gilhuijs KGA, 1998, MED PHYS, V25, P1647 | - |
dc.description.citedreference | VAPNIK V, 1998, STAT LEARNING THEORY | - |
dc.description.citedreference | Degani H, 1997, NAT MED, V3, P780 | - |
dc.description.citedreference | Mussurakis S, 1997, J COMPUT ASSIST TOMO, V21, P431 | - |
dc.description.citedreference | Mussurakis S, 1997, BRIT J RADIOL, V70, P446 | - |
dc.description.citedreference | RIPLEY BD, 1996, PATTERN RECOGNITION | - |
dc.description.citedreference | WELLS WM, 1996, MED IMAGE ANAL, V1, P35 | - |
dc.description.citedreference | HANLEY JA, 1983, RADIOLOGY, V148, P839 | - |
dc.description.citedreference | SADJADI FA, 1980, IEEE T PATTERN ANAL, V2, P127 | - |
dc.description.citedreference | ENG J, ROC ANAL WEB BASED C | - |
dc.description.citedreference | PELCKMANS K, LS SVMLAB MATL C TOO | - |
dc.description.tc | 0 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.