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
  • [1] Application of artificial neural networks to the analysis of dynamic MR imaging features of the breast
    Szabó, BK
    Wiberg, MK
    Boné, B
    Aspelin, P
    EUROPEAN RADIOLOGY, 2004, 14 (07) : 1217 - 1225
  • [2] Application of artificial neural networks for dynamic analysis of building frames
    Joshi, Shardul G.
    Londhe, Shreenivas N.
    Kwatra, Naveen
    COMPUTERS AND CONCRETE, 2014, 13 (06): : 765 - 780
  • [3] Application of artificial neural networks to the dynamic analysis of the voltage stability problem
    Schmidt, HP
    IEE PROCEEDINGS-GENERATION TRANSMISSION AND DISTRIBUTION, 1997, 144 (04) : 371 - 376
  • [4] Artificial Neural Networks for Quantitative Microwave Breast Imaging
    Ambrosanio, M.
    Franceschini, S.
    Baselice, F.
    Pascazio, V
    PROCEEDINGS OF THE 13TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES, VOL 2: BIOIMAGING, 2020, : 204 - 208
  • [5] Automated data extraction and classification of breast cancer on dynamic MR imaging using artificial neural network
    Abdolmaleki, P
    Buadu, LD
    Murakami, J
    Murayama, S
    Masuda, K
    RADIOLOGY, 1997, 205 : 1673 - 1673
  • [6] Neural network classification of breast cancer using MR imaging features
    Buadu, LD
    Abdolmaleki, P
    Murakami, J
    Murayama, S
    Hashiguchi, N
    Masuda, K
    RADIOLOGY, 1997, 205 : 400 - 400
  • [7] Application of Artificial Neural Networks to stylometric analysis
    Stanczyk, Urszula
    Cyran, Krzysztof A.
    PROCEEDINGS OF THE 8TH WSEAS INTERNATIONAL CONFERENCE ON SYSTEMS THEORY AND SCIENTIFIC COMPUTATION (ISTAC'08): NEW ASPECTS OF SYSTEMS THEORY AND SCIENTIFIC COMPUTATION, 2008, : 25 - 30
  • [8] Diagnostic architectural and dynamic features at breast MR imaging:: Multicenter study
    Schnall, MD
    Blume, J
    Bluemke, DA
    DeAngelis, GA
    DeBruhl, N
    Harms, S
    Heywang-Köbrunner, SH
    Hylton, N
    Kuhl, CK
    Pisano, ED
    Causer, P
    Schnitt, SJ
    Thickman, D
    Stelling, CB
    Weatherall, PT
    Lehman, C
    Gatsonis, CA
    RADIOLOGY, 2006, 238 (01) : 42 - 53
  • [9] Application of Artificial Neural Networks for Early Detection of Breast Cancer
    Urbaniak, Krzysztof
    Lewenstein, Krzysztof
    RECENT GLOBAL RESEARCH AND EDUCATION: TECHNOLOGICAL CHALLENGES, 2017, 519 : 425 - 433
  • [10] MR imaging features of breast lymphoma
    Demirkazik, FB
    EUROPEAN JOURNAL OF RADIOLOGY, 2002, 42 (01) : 62 - 64