Computerized three-class classification of MRI-based prognostic markers for breast cancer

被引:34
作者
Bhooshan, Neha [1 ]
Giger, Maryellen [1 ]
Edwards, Darrin [1 ]
Yuan, Yading [1 ]
Jansen, Sanaz [1 ]
Li, Hui [1 ]
Lan, Li [1 ]
Sattar, Husain [2 ]
Newstead, Gillian [1 ]
机构
[1] Univ Chicago, Dept Radiol, Chicago, IL 60637 USA
[2] Univ Chicago, Dept Pathol, Chicago, IL 60637 USA
关键词
OBSERVER VARIABILITY; AIDED-DIAGNOSIS; LESIONS; ANGIOGENESIS; SURVIVAL; GRADE; FEATURES; IMAGES; CAD;
D O I
10.1088/0031-9155/56/18/014
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
The purpose of this study is to investigate whether computerized analysis using three-class Bayesian artificial neural network (BANN) feature selection and classification can characterize tumor grades (grade 1, grade 2 and grade 3) of breast lesions for prognostic classification on DCE-MRI. A database of 26 IDC grade 1 lesions, 86 IDC grade 2 lesions and 58 IDC grade 3 lesions was collected. The computer automatically segmented the lesions, and kinetic and morphological lesion features were automatically extracted. The discrimination tasks-grade 1 versus grade 3, grade 2 versus grade 3, and grade 1 versus grade 2 lesions-were investigated. Step-wise feature selection was conducted by three-class BANNs. Classification was performed with three-class BANNs using leave-one-lesion-out cross-validation to yield computer-estimated probabilities of being grade 3 lesion, grade 2 lesion and grade 1 lesion. Two-class ROC analysis was used to evaluate the performances. We achieved AUC values of 0.80 +/- 0.05, 0.78 +/- 0.05 and 0.62 +/- 0.05 for grade 1 versus grade 3, grade 1 versus grade 2, and grade 2 versus grade 3, respectively. This study shows the potential for (1) applying three-class BANN feature selection and classification to CADx and (2) expanding the role of DCE-MRI CADx from diagnostic to prognostic classification in distinguishing tumor grades.
引用
收藏
页码:5995 / 6008
页数:14
相关论文
共 54 条
  • [31] Potential of computer-aided diagnosis to reduce variability in radiologists' interpretations of mammograms depicting microcalcifications
    Jiang, YL
    Nishikawa, RM
    Schmidt, RA
    Toledano, AY
    Doi, K
    [J]. RADIOLOGY, 2001, 220 (03) : 787 - 794
  • [32] Rim enhancement of breast cancers on contrast-enhanced MR imaging: relationship with prognostic factors.
    Jinguji M.
    Kajiya Y.
    Kamimura K.
    Nakajo M.
    Sagara Y.
    Takahama T.
    Ando M.
    Rai Y.
    Sagara Y.
    Ohi Y.
    Yoshida H.
    [J]. Breast Cancer, 2006, 13 (1) : 64 - 73
  • [33] Predicting Survival and Early Clinical Response to Primary Chemotherapy for Patients With Locally Advanced Breast Cancer Using DCE-MRI
    Johansen, Roar
    Jensen, Line R.
    Rydand, Jana
    Goa, Pal E.
    Kvistad, Kjell A.
    Bathen, Tone F.
    Axelson, David E.
    Lundgren, Steinar
    Gribbestad, Ingrid S.
    [J]. JOURNAL OF MAGNETIC RESONANCE IMAGING, 2009, 29 (06) : 1300 - 1307
  • [34] Observer variability and applicability of BI-RADS terminology for breast MR imaging: Invasive carcinomas as focal masses
    Kim, SJ
    Morris, EA
    Liberman, L
    Ballon, DJ
    La Trenta, LR
    Hadar, O
    Abramson, A
    Dershaw, DD
    [J]. AMERICAN JOURNAL OF ROENTGENOLOGY, 2001, 177 (03) : 551 - 557
  • [35] Dynamic breast MR imaging: Are signal intensity time course data useful for differential diagnosis of enhancing lesions?
    Kuhl, CK
    Mielcareck, P
    Klaschik, S
    Leutner, C
    Wardelmann, E
    Gieseke, J
    Schild, HH
    [J]. RADIOLOGY, 1999, 211 (01) : 101 - 110
  • [36] Ideal observer approximation using Bayesian classification neural networks
    Kupinski, MA
    Edwards, DC
    Giger, ML
    Metz, CE
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2001, 20 (09) : 886 - 899
  • [37] Breast lesion analysis of shape technique: Semiautomated vs. manual morphological description
    Liney, GP
    Sreenivas, M
    Gibbs, P
    Garcia-Alvarez, R
    Turnbull, LW
    [J]. JOURNAL OF MAGNETIC RESONANCE IMAGING, 2006, 23 (04) : 493 - 498
  • [38] Statistical comparison of two ROC-curve estimates obtained from partially-paired datasets
    Metz, CE
    Herman, BA
    Roe, CA
    [J]. MEDICAL DECISION MAKING, 1998, 18 (01) : 110 - 121
  • [40] Dynamic MR imaging of invasive breast cancer: Correlation with tumour grade and other histological factors
    Mussurakis, S
    Buckley, DL
    Horsman, A
    [J]. BRITISH JOURNAL OF RADIOLOGY, 1997, 70 (833) : 446 - 451