Visual exploratory analysis of DCE-MRI data in breast cancer by dimensional data reduction: A comparative study

Automated Detection and Segmentation of Nonmass-Enhancing Breast Tumors with Dynamic Contrast-Enhanced Magnetic Resonance Imaging

Nonmass-enhancing (NME) lesions constitute a diagnostic challenge in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast. Computer-aided diagnosis (CAD) systems provide physicians with advanced tools for analysis, assessment, and evaluation that have a significant impact on the diagnostic performance. Here, we propose a new approach to address the challenge of NME lesion detection and segmentation, taking advantage of independent component analysis (ICA) to extract data-driven dynamic lesion characterizations. A set of independent sources was obtained from the DCE-MRI dataset of breast cancer patients, and the dynamic behavior of the different tissues was described by multiple dynamic curves, together with a set of eigenimages describing the scores for each voxel. A new test image is projected onto the independent source space using the unmixing matrix, and each voxel is classified by a support vector machine (SVM) that has already been trained with manually delineated data. A solution to the high false-positive rate problem is proposed by controlling the SVM hyperplane location, outperforming previously published approaches.

ClassiMap: A New Dimension Reduction Technique for Exploratory Data Analysis of Labeled Data

Multidimensional scaling techniques are unsupervised Dimension Reduction (DR) techniques which use multidimensional data pairwise similarities to represent data into a plane enabling their visual exploratory analysis. Considering labeled data, the DR techniques face two objectives with potentially different priorities: one is to account for the data points' similarities, the other for the data classes' structures. Unsupervised DR techniques attempt to preserve original data similarities, but they do not consider their class label hence they can map originally separated classes as overlapping ones. Conversely, the state-of-the-art so-called supervised DR techniques naturally handle labeled data, but they do so in a predictive modeling framework where they attempt to separate the classes in order to improve a classification accuracy measure in the low-dimensional space, hence they can map as separated even originally overlapping classes. We propose ClassiMap, a DR technique which optimizes a new objective function enabling Exploratory Data Analysis (EDA) of labeled data. Mapping distortions known as tears and false neighborhoods cannot be avoided in general due to the reduction of the data dimension. ClassiMap intends primarily to preserve data similarities but tends to distribute preferentially unavoidable tears among the different-label data and unavoidable false neighbors among the same-label data. Standard quality measures to evaluate the quality of unsupervised mappings cannot tell about the preservation of within-class or between-class structures, while classification accuracy used to evaluate supervised mappings is only relevant to the framework of predictive modeling. We propose two measures better suited to the evaluation of DR of labeled data in an EDA framework. We use these two label-aware indices and four other standard unsupervised indices to compare ClassiMap to other state-of-the-art supervised and unsupervised DR techniques on synthetic and real datasets. ClassiMap appears to provide a better tradeoff between pairwise similarities and class structure preservation according to these new measures.

Consensus embedding: theory, algorithms and application to segmentation and classification of biomedical data

Background

Dimensionality reduction (DR) enables the construction of a lower dimensional space (embedding) from a higher dimensional feature space while preserving object-class discriminability. However several popular DR approaches suffer from sensitivity to choice of parameters and/or presence of noise in the data. In this paper, we present a novel DR technique known as consensus embedding that aims to overcome these problems by generating and combining multiple low-dimensional embeddings, hence exploiting the variance among them in a manner similar to ensemble classifier schemes such as Bagging. We demonstrate theoretical properties of consensus embedding which show that it will result in a single stable embedding solution that preserves information more accurately as compared to any individual embedding (generated via DR schemes such as Principal Component Analysis, Graph Embedding, or Locally Linear Embedding). Intelligent sub-sampling (via mean-shift) and code parallelization are utilized to provide for an efficient implementation of the scheme.

Results

Applications of consensus embedding are shown in the context of classification and clustering as applied to: (1) image partitioning of white matter and gray matter on 10 different synthetic brain MRI images corrupted with 18 different combinations of noise and bias field inhomogeneity, (2) classification of 4 high-dimensional gene-expression datasets, (3) cancer detection (at a pixel-level) on 16 image slices obtained from 2 different high-resolution prostate MRI datasets. In over 200 different experiments concerning classification and segmentation of biomedical data, consensus embedding was found to consistently outperform both linear and non-linear DR methods within all applications considered.

Conclusions

We have presented a novel framework termed consensus embedding which leverages ensemble classification theory within dimensionality reduction, allowing for application to a wide range of high-dimensional biomedical data classification and segmentation problems. Our generalizable framework allows for improved representation and classification in the context of both imaging and non-imaging data. The algorithm offers a promising solution to problems that currently plague DR methods, and may allow for extension to other areas of biomedical data analysis.

Exploring nonlinear feature space dimension reduction and data representation in breast Cadx with Laplacian eigenmaps and t-SNE

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.

On the application of (topographic) independent and tree-dependent component analysis for the examination of DCE-MRI data

In this contribution we investigate the applicability of different methods from the field of independent component analysis (ICA) for the examination of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data from breast cancer research. DCE-MRI has evolved in recent years as a powerful complement to X-ray based mammography for breast cancer diagnosis and monitoring. In DCE-MRI the time related development of the signal intensity after the administration of a contrast agent can provide valuable information about tissue states and characteristics. To this end, techniques related to ICA, offer promising options for data integration and feature extraction at voxel level. In order to evaluate the applicability of ICA, topographic ICA and tree-dependent component analysis (TCA), these methods are applied to twelve clinical cases from breast cancer research with a histopathologically confirmed diagnosis. For ICA these experiments are complemented by a reliability analysis of the estimated components. The outcome of all algorithms is quantitatively evaluated by means of receiver operating characteristics (ROC) statistics whereas the results for specific data sets are discussed exemplarily in terms of reification, score-plots and score images.

A comprehensive segmentation, registration, and cancer detection scheme on 3 Tesla in vivo prostate DCE-MRI

Recently, high resolution 3 Tesla (T) Dynamic Contrast-Enhanced MRI (DCE-MRI) of the prostate has emerged as a promising modality for detecting prostate cancer (CaP). Computer-aided diagnosis (CAD) schemes for DCE-MRI data have thus far been primarily developed for breast cancer and typically involve model fitting of dynamic intensity changes as a function of contrast agent uptake by the lesion. Comparatively there is relatively little work in developing CAD schemes for prostate DCE-MRI. In this paper, we present a novel unsupervised detection scheme for CaP from 3 T DCE-MRI which comprises 3 distinct steps. First, a multi-attribute active shape model is used to automatically segment the prostate boundary from 3 T in vivo MR imagery. A robust multimodal registration scheme is then used to non-linearly align corresponding whole mount histological and DCE-MRI sections from prostatectomy specimens to determine the spatial extent of CaP. Non-linear dimensionality reduction schemes such as locally linear embedding (LLE) have been previously shown to be useful in projecting such high dimensional biomedical data into a lower dimensional subspace while preserving the non-linear geometry of the data manifold. DCE-MRI data is embedded via LLE and then classified via unsupervised consensus clustering to identify distinct classes. Quantitative evaluation on 21 histology-MRI slice pairs against registered CaP ground truth estimates yielded a maximum CaP detection accuracy of 77.20% while the popular three time point (3TP) scheme yielded an accuracy of 67.37%.

Visual MRI: merging information visualization and non-parametric clustering techniques for MRI dataset analysis

OBJECTIVE

This paper presents Visual MRI, an innovative tool for the magnetic resonance imaging (MRI) analysis of tumoral tissues. The main goal of the analysis is to separate each magnetic resonance image in meaningful clusters, highlighting zones which are more probably related with the cancer evolution. Such non-invasive analysis serves to address novel cancer treatments, resulting in a less destabilizing and more effective type of therapy than the chemotherapy-based ones. The advancements brought by Visual MRI are two: first, it is an integration of effective information visualization (IV) techniques into a clustering framework, which separates each MRI image in a set of informative clusters; the second improvement relies in the clustering framework itself, which is derived from a recently re-discovered non-parametric grouping strategy, i.e., the mean shift.

METHODOLOGY

The proposed methodology merges visualization methods and data mining techniques, providing a computational framework that allows the physician to move effectively from the MRI image to the images displaying the derived parameter space. An unsupervised non-parametric clustering algorithm, derived from the mean shift paradigm, and called MRI-mean shift, is the novel data mining technique proposed here. The main underlying idea of such approach is that the parameter space is regarded as an empirical probability density function to estimate: the possible separate modes and their attraction basins represent separated clusters. The mean shift algorithm needs sensibility threshold values to be set, which could lead to highly different segmentation results. Usually, these values are set by hands. Here, with the MRI-mean shift algorithm, we propose a strategy based on a structured optimality criterion which faces effectively this issue, resulting in a completely unsupervised clustering framework. A linked brushing visualization technique is then used for representing clusters on the parameter space and on the MRI image, where physicians can observe further anatomical details. In order to allow the physician to easily use all the analysis and visualization tools, a visual interface has been designed and implemented, resulting in a computational framework susceptible of evaluation and testing by physicians.

RESULTS

Visual MRI has been adopted by physicians in a real clinical research setting. To describe the main features of the system, some examples of usage on real cases are shown, following step by step all the actions scientists can do on an MRI image. To assess the contribution of Visual MRI given to the research setting, a validation of the clustering results in a medical sense has been carried out.

CONCLUSIONS

From a general point of view, the two main objectives reached in this paper are: (1) merging information visualization and data mining approaches to support clinical research and (2) proposing an effective and fully automated clustering technique. More particularly, a new application for MRI data analysis, named Visual MRI, is proposed, aiming at improving the support of medical researchers in the context of cancer therapy; moreover, a non-parametric technique for cluster analysis, named MRI-mean shift, has been drawn. The results show the effectiveness and the efficacy of the proposed application.