Application of artificial neural networks to the analysis of dynamic MR imaging features of the breast

被引:0
|
作者
Botond K. Szabó
Maria Kristoffersen Wiberg
Beata Boné
Peter Aspelin
机构
[1] Huddinge University Hospital,Division of Diagnostic Radiology, Center for Surgical Sciences, Karolinska Institute
来源
European Radiology | 2004年 / 14卷
关键词
Magnetic resonance imaging; Breast cancer; Artificial neural networks;
D O I
暂无
中图分类号
学科分类号
摘要
The discriminative ability of established diagnostic criteria for MRI of the breast is assessed, and their relative relevance using artificial neural networks (ANNs) is determined. A total of 89 women with 105 histopathologically verified breast lesions (73 invasive cancers, 2 in situ cancers, and 30 benign lesions) were included in this study. A T1-weighted 3D FLASH sequence was acquired before and seven times after the intravenous administration of gadopentetate dimeglumine at a dose of 0.2 mmol/kg body weight. ANN models were built to test the discriminative ability of kinetic, morphologic, and combined MR features. The subjects were randomly divided into two parts: a training set of 59 lesions and a verification set of 46 lesions. The training set was used for learning, and the performance of each model was evaluated on the verification set by measuring the area under the ROC curve (Az). An optimally minimized model was constructed using the most relevant input variables that were determined by the automatic relevance determination (ARD) method. ANN models were compared with the performance of a human reader. Margin type, time-to-peak enhancement, and washout ratio showed the highest discriminative ability among diagnostic criteria and comprised the minimized model. Compared with the expert radiologist (Az=0.799), using the same prediction scale, the minimized ANN model performed best (Az=0.771), followed by the best kinetic (Az=0.743), the maximized (Az=0.727), and the morphologic model (Az=0.678). The performance of a neural network prediction model is comparable to that of an expert radiologist. A neurostatistical approach is preferred for the analysis of diagnostic criteria when many parameters are involved and complex nonlinear relationships exist in the data set.
引用
收藏
页码:1217 / 1225
页数:8
相关论文
共 50 条
  • [21] Predicting breast cancer invasion with artificial neural networks on the basis of mammographic features
    Lo, JY
    Baker, JA
    Kornguth, PJ
    Iglehart, JD
    Floyd, CE
    RADIOLOGY, 1997, 203 (01) : 159 - 163
  • [22] An application of artificial neural networks in breast cancer recognition using scintimammography
    Swietlik, Dariusz
    Bandurski, Tomasz
    Masiuk, Mariusz
    WSPOLCZESNA ONKOLOGIA-CONTEMPORARY ONCOLOGY, 2007, 11 (08): : 385 - 389
  • [23] Imaging features of breast malignancy: breast ultrasound and MR imaging correlation
    Giuliano, Vincenzo
    Giuliano, Concetta
    CLINICAL IMAGING, 2013, 37 (03) : 415 - 419
  • [24] Application of Artificial Neural Networks for Estimating Dynamic Modulus of Asphalt Concrete
    Far, Maryam Sadat Sakhaei
    Underwood, B. Shane
    Ranjithan, S. Ranji
    Kim, Y. Richard
    Jackson, Newton
    TRANSPORTATION RESEARCH RECORD, 2009, (2127) : 173 - 186
  • [25] Sub-basalt imaging problems and the application of Artificial Neural Networks
    Fitzgerald, EM
    Bean, CJ
    JOURNAL OF APPLIED GEOPHYSICS, 2001, 48 (04) : 183 - 197
  • [26] Convolutional Neural Networks for Static and Dynamic Breast Infrared Imaging Classification
    Baffa, Matheus F. O.
    Lattari, Lucas G.
    PROCEEDINGS 2018 31ST SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 2018, : 174 - 181
  • [27] Application of Artificial Neural Networks for the Alloy Features Assessment Based on the Alloy Compound
    Sydikhov, A. S.
    Tyagunov, A. G.
    Milder, O. B.
    Ganeev, A. A.
    INTERNATIONAL CONFERENCE ON NUMERICAL ANALYSIS AND APPLIED MATHEMATICS (ICNAAM-2018), 2019, 2116
  • [28] A dynamic architecture for artificial neural networks
    Ghiassi, M
    Saidane, H
    NEUROCOMPUTING, 2005, 63 : 397 - 413
  • [29] Soybean Expansion Analysis: An Application of Multivariate Analysis and Artificial Neural Networks
    Paiva, Marina S.
    Nagano, Marcelo S.
    Kuang Hongyu
    SIGMAE, 2019, 8 (02): : 554 - 563
  • [30] A further study of the application of artificial neural network to diagnosis of Alzheimers disease with MR imaging
    Li, K
    Deng, X
    Liu, SL
    RADIOLOGY, 2000, 217 : 553 - 553