Exploring nonlinear feature space dimension reduction and data representation in breast CADx with Laplacian eigenmaps and t -SNE
Reads0
Chats0
TLDR
In this preliminary study, recently developed unsupervised nonlinear dimension reduction (DR) and data representation techniques were applied to computer-extracted breast lesion feature spaces across three separate imaging modalities and were shown to possess the added benefit of delivering sparse lower dimensional representations for visual interpretation.Abstract:
Purpose: In this preliminary study, recently developed unsupervised nonlinear dimension reduction (DR) and data representation techniques were applied to computer-extracted breast lesion feature spaces across three separate imaging modalities: Ultrasound (U.S.) with 1126 cases, dynamic contrast enhanced magnetic resonance imaging with 356 cases, and full-field digital mammography with 245 cases. Two methods for nonlinear DR were explored: Laplacian eigenmaps [M. Belkin and P. Niyogi, “Laplacian eigenmaps for dimensionality reduction and data representation,” Neural Comput. 15, 1373–1396 (2003)] and t-distributed stochastic neighbor embedding (t-SNE) [L. van der Maaten and G. Hinton, “Visualizing data using t-SNE,” J. Mach. Learn. Res. 9, 2579–2605 (2008)].
Methods: These methods attempt to map originally high dimensional feature spaces to more human interpretable lower dimensional spaces while preserving both local and global information. The properties of these methods as applied to breast computer-aided diagnosis (CADx) were evaluated in the context of malignancy classification performance as well as in the visual inspection of the sparseness within the two-dimensional and three-dimensional mappings. Classification performance was estimated by using the reduced dimension mapped feature output as input into both linear and nonlinear classifiers: Markov chain Monte Carlo based Bayesian artificial neural network (MCMC-BANN) and linear discriminant analysis. The new techniques were compared to previously developed breast CADx methodologies, including automatic relevance determination and linear stepwise (LSW) feature selection, as well as a linear DR method based on principal component analysis. Using ROC analysis and 0.632+bootstrap validation, 95% empirical confidence intervals were computed for the each classifier’s AUC performance.
Results: In the large U.S. data set, sample high performance results include, AUC0.632+=0.88 with 95% empirical bootstrap interval [0.787;0.895] for 13 ARD selected features and AUC0.632+=0.87 with interval [0.817;0.906] for four LSW selected features compared to 4D t-SNE mapping (from the original 81D feature space) giving AUC0.632+=0.90 with interval [0.847;0.919], all using the MCMC-BANN.
Conclusions: Preliminary results appear to indicate capability for the new methods to match or exceed classification performance of current advanced breast lesion CADx algorithms. While not appropriate as a complete replacement of feature selection in CADx problems, DR techniques offer a complementary approach, which can aid elucidation of additional properties associated with the data. Specifically, the new techniques were shown to possess the added benefit of delivering sparse lower dimensional representations for visual interpretation, revealing intricate data structure of the feature space.read more
Citations
More filters
Journal ArticleDOI
Origin, fate and dynamics of macrophages at central nervous system interfaces.
Tobias Goldmann,Peter Wieghofer,Marta Joana Costa Jordão,Fabiola Prutek,Nora Hagemeyer,Kathrin Frenzel,Lukas Amann,Ori Staszewski,Katrin Kierdorf,Martin Krueger,Giuseppe Locatelli,Hannah Hochgerner,Robert Zeiser,Slava Epelman,Frederic Geissmann,Josef Priller,Fabio M.V. Rossi,Ingo Bechmann,Martin Kerschensteiner,Sten Linnarsson,Steffen Jung,Marco Prinz +21 more
TL;DR: Using parabiosis and fate-mapping approaches in mice, it is found that CNS macrophages arose from hematopoietic precursors during embryonic development and established stable populations, with the notable exception of choroid plexus macrophage, which had dual origins and a shorter life span.
Journal ArticleDOI
Artificial intelligence in cancer imaging: Clinical challenges and applications.
Wenya Linda Bi,Ahmed Hosny,Matthew B. Schabath,Maryellen L. Giger,Nicolai Juul Birkbak,Nicolai Juul Birkbak,Alireza Mehrtash,Alireza Mehrtash,Tavis Allison,Tavis Allison,Omar Arnaout,Christopher Abbosh,Christopher Abbosh,Ian F. Dunn,Raymond H. Mak,Rulla M. Tamimi,Clare M. Tempany,Charles Swanton,Charles Swanton,Udo Hoffmann,Lawrence H. Schwartz,Lawrence H. Schwartz,Robert J. Gillies,Raymond Y. Huang,Hugo J.W.L. Aerts,Hugo J.W.L. Aerts +25 more
TL;DR: The authors review the current state of AI as applied to medical imaging of cancer and describe advances in 4 tumor types to illustrate how common clinical problems are being addressed.
Journal ArticleDOI
Machine Learning in Medical Imaging.
TL;DR: In the future, machine learning in radiology is expected to have a substantial clinical impact with imaging examinations being routinely obtained in clinical practice, providing an opportunity to improve decision support in medical image interpretation.
Journal ArticleDOI
A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets.
TL;DR: A novel breast CADx methodology that can be used to more effectively characterize breast lesions in comparison to existing methods is proposed, which is computationally efficient and circumvents the need for image preprocessing.
Journal ArticleDOI
Visualizing non-metric similarities in multiple maps
TL;DR: The extension t-SNE is presented, which aims to address the problems of traditional multidimensional scaling techniques when these techniques are used to visualize non-metric similarities, by constructing a collection of maps that reveal complementary structure in the similarity data.
References
More filters
Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Journal ArticleDOI
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
TL;DR: A representation and interpretation of the area under a receiver operating characteristic (ROC) curve obtained by the "rating" method, or by mathematical predictions based on patient characteristics, is presented and it is shown that in such a setting the area represents the probability that a randomly chosen diseased subject is (correctly) rated or ranked with greater suspicion than a random chosen non-diseased subject.
Journal ArticleDOI
Laplacian Eigenmaps for dimensionality reduction and data representation
Mikhail Belkin,Partha Niyogi +1 more
TL;DR: In this article, the authors proposed a geometrically motivated algorithm for representing high-dimensional data, based on the correspondence between the graph Laplacian, the Laplace Beltrami operator on the manifold and the connections to the heat equation.
Journal ArticleDOI
Basic principles of ROC analysis
TL;DR: ROC analysis is shown to be related in a direct and natural way to cost/benefit analysis of diagnostic decision making and the concepts of "average diagnostic cost" and "average net benefit" are developed and used to identify the optimal compromise among various kinds of diagnostic error.