Abstract
The aim of this article is to facilitate the estimation of the distributed diffusion coefficient (DDC) of breast tissue in quantitative diffusion-weighted imaging using artificial neural networks. Diffusion signals of breast lesions and of healthy glandular tissue of contralateral breasts from 174 women measured on diffusion-weighted images captured with a 3T MR scanner using small region of interests were used. Traditional DDC estimates were obtained by a stretched exponential model and nonlinear least-squares fitting applied to the diffusion signals. Various multilayer perceptrons having one hidden layer but with different number of neurons were developed. Diffusion signals normalized and DDCs estimated traditionally were the input vectors and the target outputs of the neural networks, respectively, that were randomly divided into training, validation and test datasets. Supervised leanings were performed with the training and the validation datasets using a backpropagation algorithm followed by tests with the test dataset. DDC estimation by least-squares fitting takes 38 ms, on average. Strong positive correlations are observable between the DDC estimates by least-squares fitting and by the neural networks (overall r = 0.962–0.999). However, a network having seventeen neurons in its hidden layer provides the strongest correlation (r = 1.000). Once the learning of the network is accomplished, the network computes a DDC estimate only in 73 μs without requiring any initial value or any boundary constraint. Multilayer perceptrons facilitate the estimation of the distributed diffusion coefficient of breast tissue in diffusion-weighted imaging by offering less computational complexity and reduced computation time compared to nonlinear least-squares fitting.
Similar content being viewed by others
References
Basheer IA, Hajmeer M (2000) Artificial neural networks: fundamentals, computing, design, and application. J Microbiol Methods 43(1):3–31
Bennett KM, Schmainda KM, Bennett R, Rowe DB, Lu H, Hyde JS (2003) Characterization of continuously distributed cortical water diffusion rates with a stretched-exponential model. Magn Reson Med 50:727–734
Bertleff M, Domsch S, Weingärtner S, Zapp J, O’Brien K, Barth M, Schad LR (2016) Diffusion parameter mapping with the combined intravoxel incoherent motion and kurtosis model using artificial neural networks at 3 T. NMR in Biomed 30:e3833
Bickel H, Pinker-Domenig K, Bogner W, Spick C, Bagó-Horváth Z, Weber M, Helbich T, Baltzer P (2015) Quantitative apparent diffusion coefficient as a noninvasive imaging biomarker for the differentiation of invasive breast cancer and ductal carcinoma in situ. Investig Radiol 50:95–100
Byrd RH, Schnabel RB, Shultz GA (1988) Approximate solution of the trust region problem by minimization over two-dimensional subspaces. Math Program 40:247–263
Chen X, Li W, Zhang Y, Wu Q, Guo Y, Bai Z (2010) Meta-analysis of quantitative diffusion-weighted MR imaging in the differential diagnosis of breast lesions. BMC Cancer 10:693
Chen W, Zhang J, Long D, Wang Z, Zhu JM (2017) Optimization of intra-voxel incoherent motion measurement in diffusion-weighted imaging of breast cancer. J Appl Clin Med Phys 18:191–199
Cheng L, Bai Y, Zhang J, Liu M, Li X, Zhang A, Zhang X, Ma L (2013) Optimization of apparent diffusion coefficient measured by diffusion-weighted MRI for diagnosis of breast lesions presenting as mass and non-mass-like enhancement. Tumour Biol 34(3):1537–1545
Coleman TF, Li Y (1996) An interior, trust region approach for nonlinear minimization subject to bounds. SIAM J Optim 6:418–445
Costantini M, Belli P, Rinaldi P, Bufi E, Giardina G, Franceschini G, Petrone G, Bonomo L (2010) Diffusion-weighted imaging in breast cancer: relationship between apparent diffusion coefficient and tumour aggressiveness. Clin Radiol 65(12):1005–1012
Dijkstra H, Baron P, Kappert P, Oudkerk M, Sijens PE (2012) Effects of microperfusion in hepatic diffusion weighted imaging. Eur Radiol 22:891–899
Ertas G, Onaygil C, Akin Y, Kaya H, Aribal E (2016) Quantitative differentiation of breast lesions at 3T diffusion-weighted imaging (DWI) using the ratio of distributed diffusion coefficient (DDC). J Magn Reson Imaging 44:1633–1641
Fahmi A, Abdullah S, Amin F, Siddque N, Ali A (2017) Aggregation operators on triangular cubic fuzzy numbers and its application to multi-criteria decision making problems. J Intell Fuzzy Syst 33(6):3323–3337
Fahmi A, Abdullah S, Amin F, Ali A (2018a) Weighted average rating (war) method for solving group decision making problem using triangular cubic fuzzy hybrid aggregation (Tcfha). Punjab Univ J Math 50(1):23–34
Fahmi A, Abdullah S, Amin F, Ahmed R, Ali A (2018b) Triangular cubic linguistic hesitant fuzzy aggregation operators and their application in group decision making. J Intell Fuzzy Syst 34(4):2401–2416
Jambor I, Merisaari H, Taimen P, Boström P, Minn H, Pesola M, Aronen HJ (2015) Evaluation of different mathematical models for diffusion-weighted imaging of normal prostate and prostate cancer using high b-values: a repeatability study. Magn Reson Med 73:1988–1998
Jensen JH, Helpern JA, Ramani A, Lu H, Kaczynski K (2005) Diffusional kurtosis imaging: the quantification of non-Gaussian water diffusion by means of magnetic resonance imaging. Magn Reson Med 53(6):1432–1440
Koh DM, Padhani AR (2006) Diffusion-weighted MRI: a new functional clinical technique for tumour imaging. Br J Radiol 79(944):633–635
Lavine BK, Blank TR (2009) Feed-forward neural networks. In: Brown SD, Tauler R, Walczak B (eds) Comprehensive chemometrics. Elsevier, Oxford, pp 571–586
Le Bihan D (2013) Apparent diffusion coefficient and beyond: what diffusion MR imaging can tell us about tissue structure. Radiology 268(2):318–322
Liu C, Liang C, Liu Z, Zhang S, Huang B (2013) Intravoxel incoherent motion (IVIM) in evaluation of breast lesions: comparison with conventional DWI. Eur J Radiol 82(12):e782–e789
Marquardt DW (1963) An algorithm for least-squares estimation of nonlinear parameters. J Soc Ind Appl Math 11:431–441
Padhani AR, Liu G, Koh DM, Chenevert TL, Thoeny HC, Takahara T, Dzik-Jurasz A, Ross BD, Van Cauteren M, Collins D, Hammoud DA, Rustin GJ, Taouli B, Choyke PL (2009) Diffusion-weighted magnetic resonance imaging as a cancer biomarker: consensus and recommendations. Neoplasia 11(2):102–125
Panek R, Borri M, Orton M, O’Flynn E, Morgan V, Giles SL, deSouza N, Leach MO, Schmidt MA (2015) Evaluation of diffusion models in breast cancer. Med Phys 42:4833–4839
Pasini A (2015) Artificial neural networks for small dataset analysis. J Thoracic Dis 7(5):953–960
Patrikar AM (2013) Approximating Gaussian mixture model or radial basis function network with multilayer perceptron. IEEE Trans Neural Netw Learn Syst 24:1161–1166
Peters NH, Vincken KL, van den Bosch MA, Luijten PR, Mali WP, Bartels LW (2010) Quantitative diffusion weighted imaging for differentiation of benign and malignant breast lesions: the influence of the choice of b-values. J Magn Reson Imaging 31(5):1100–1105
Ramchoun H, Idrissi MAJ, Ghanou Y, Ettaouil M (2016) Multilayer perceptron: architecture optimization and training. Int J f Interact Multim Artif Intell 4:26–30
Sharma U, Sah RG, Agarwal K, Parshad R, Seenu V, Mathur SR, Hari S, Jagannathan NR (2016) Potential of diffusion-weighted imaging in the characterization of malignant, benign, and healthy breast tissues and molecular subtypes of breast cancer. Front Oncol 6:126
Suo S, Lin N, Wang H, Zhang L, Wang R, Zhang S, Hua J, Xu J (2015) Intravoxel incoherent motion diffusion-weighted MR imaging of breast cancer at 3.0 tesla: comparison of different curve-fitting methods. J Magn Reson Imaging 42(2):362–370
Tamura T, Usui S, Murakami S, Arihiro K, Akiyama Y, Naito K, Akiyama M (2010) Biexponential signal attenuation analysis of diffusion-weighted imaging of breast. Magn Reson Med Sci 9(4):195–207
Tamura T, Usui S, Murakami S, Arihiro K, Fujimoto T, Yamada T, Naito K, Akiyama M (2012) Comparisons of multi b-value DWI signal analysis with pathological specimen of breast cancer. Magn Reson Med 68:890–897
Tamura T, Murakami S, Naito K, Yamada T, Fujimoto T, Kikkawa T (2014) Investigation of the optimal b-value to detect breast tumors with diffusion weighted imaging by 1.5-T MRI. Cancer Imaging 14(1):11
Toivonen J, Merisaari H, Pesola M, Taimen P, Bostrom PJ, Pahikkala T, Aronen HJ, Jambor I (2015) Mathematical model for diffusion-weighted imaging of prostate cancer using b values up to 2000s/mm2: correlation with Gleason score and repeatability of region of interest analysis. Magn Reson Med 73:1116–1124
Wu Y, Wang H, Zhang B, Du KL (2012) Using radial basis function networks for function approximation and classification. ISRN Appl Math. https://doi.org/10.5402/2012/324194
Yablonskiy DA, Bretthorst GL, Ackerman JJ (2003) Statistical model for diffusion attenuated MR signal. Magn Reson Med 50(4):664–669
Acknowledgements
We are grateful to Can Onaygil, MD, Institute of Diagnostic and Interventional Radiology, Oberlausitz-Kliniken gGmbH, Bautzen, Germany, and Erkin Aribal, MD, Department of Radiology, Acibadem Altunizade Hospital, Istanbul, Turkey, for providing data enabling us to evaluate this diffusion coefficient estimation approach.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical Approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards. For this type of study, formal consent is not required.
Additional information
Communicated by V. Loia.
Publisher's Note
Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ertas, G. Estimating the distributed diffusion coefficient of breast tissue in diffusion-weighted imaging using multilayer perceptrons. Soft Comput 23, 7821–7830 (2019). https://doi.org/10.1007/s00500-018-3412-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-018-3412-6