KEYWORDS: Image segmentation, Brain, Convolutional neural networks, Neuroimaging, Medical imaging, Monte Carlo methods, Magnetic resonance imaging, Statistical analysis, Image registration, Data modeling
For proper generalization performance of convolutional neural networks (CNNs) in medical image segmentation, the learnt features should be invariant under particular non-linear shape variations of the input. To induce invariance in CNNs to such transformations, we propose Probabilistic Augmentation of Data using Diffeomorphic Image Transformation (PADDIT) – a systematic framework for generating realistic transformations that can be used to augment data for training CNNs. The main advantage of PADDIT is the ability to produce transformations that capture the morphological variability in the training data. To this end, PADDIT constructs a mean template which represents the main shape tendency of the training data. A Hamiltonian Monte Carlo(HMC) scheme is used to sample transformations which warp the training images to the generated mean template. Augmented images are created by warping the training images using the sampled transformations. We show that CNNs trained with PADDIT outperforms CNNs trained without augmentation and with generic augmentation (0.2 and 0.15 higher dice accuracy respectively) in segmenting white matter hyperintensities from T1 and FLAIR brain MRI scans.
Brain atrophy from structural magnetic resonance images (MRIs) is widely used as an imaging surrogate marker for Alzheimers disease. Their utility has been limited due to the large degree of variance and subsequently high sample size estimates. The only consistent and reasonably powerful atrophy estimation methods has been the boundary shift integral (BSI). In this paper, we first propose a tensor-based morphometry (TBM) method to measure voxel-wise atrophy that we combine with BSI. The combined model decreases the sample size estimates significantly when compared to BSI and TBM alone.
Obtaining regional volume changes from a deformation field is more precise when using simplex counting (SC) compared with Jacobian integration (JI) due to the numerics involved in the latter. Although SC has been proposed before, numerical properties underpinning the method and a thorough evaluation of the method against JI is missing in the literature. The contributions of this paper are: (a) we propose surface propagation (SP)—a simplification to SC that significantly reduces its computational complexity; (b) we will derive the orders of approximation of SP which can also be extended to SC. In the experiments, we will begin by empirically showing that SP is indeed nearly identical to SC, and that both methods are more stable than JI in presence of moderate to large deformation noise. Since SC and SP are identical, we consider SP as a representative of both the methods for a practical evaluation against JI. In a real application on Alzheimer’s disease neuroimaging initiative data, we show the following: (a) SP produces whole brain and medial temporal lobe atrophy numbers that are significantly better than JI at separating between normal controls and Alzheimer’s disease patients; (b) SP produces disease group atrophy differences comparable to or better than those obtained using FreeSurfer, demonstrating the validity of the obtained clinical results. Finally, in a reproducibility study, we show that the voxel-wise application of SP yields significantly lower variance when compared to JI.
Interpolating kernels are crucial to solving a stationary velocity field (SVF) based image registration problem. This is because, velocity fields need to be computed in non-integer locations during integration. The regularity in the solution to the SVF registration problem is controlled by the regularization term. In a variational formulation, this term is traditionally expressed as a squared norm which is a scalar inner product of the interpolating kernels parameterizing the velocity fields. The minimization of this term using the standard spline interpolation kernels (linear or cubic) is only approximative because of the lack of a compatible norm. In this paper, we propose to replace such interpolants with a norm-minimizing interpolant - the Wendland kernel which has the same computational simplicity like B-Splines. An application on the Alzheimer's disease neuroimaging initiative showed that Wendland SVF based measures separate (Alzheimer's disease v/s normal controls) better than both B-Spline SVFs (p<0.05 in amygdala) and B-Spline freeform deformation (p<0.05 in amygdala and cortical gray matter).
This work investigates a novel way of looking at the regions in the brain and their relationship as possible markers to classify normal control (NC), mild cognitive impaired (MCI), and Alzheimer Disease (AD) subjects. MRI scans from a subset of 101 subjects from the ADNI study at baseline was used for this study. 40 regions in the brain including hippocampus, amygdala, thalamus, white, and gray matter were segmented using FreeSurfer. From this data, we calculated the distance between the center of mass of each region, the normalized number of voxels and the percentage volume and surface connectivity shared between the regions. These markers were used for classification using a linear discriminant analysis in a leave-one-out manner. We found that the percentage of surface and volume connectivity between regions gave a significant classification between NC and AD and borderline significant between MCI and AD even after correction for whole brain volume at baseline. The results show that the morphometric connectivity markers include more information than whole brain volume or distance markers. This suggests that one can gain additional information by combining morphometric connectivity markers with traditional volume and shape markers.
Classification is widely used in the context of medical image analysis and in order to illustrate the mechanism
of a classifier, we introduce the notion of an exaggerated image stereotype based on training data and trained
classifier. The stereotype of some image class of interest should emphasize/exaggerate the characteristic patterns
in an image class and visualize the information the employed classifier relies on. This is useful for gaining insight
into the classification and serves for comparison with the biological models of disease.
In this work, we build exaggerated image stereotypes by optimizing an objective function which consists of a
discriminative term based on the classification accuracy, and a generative term based on the class distributions.
A gradient descent method based on iterated conditional modes (ICM) is employed for optimization. We use
this idea with Fisher's linear discriminant rule and assume a multivariate normal distribution for samples within
a class. The proposed framework is applied to computed tomography (CT) images of lung tissue with emphysema.
The synthesized stereotypes illustrate the exaggerated patterns of lung tissue with emphysema, which is
underpinned by three different quantitative evaluation methods.
KEYWORDS: Prototyping, Lung, Niobium, Pattern recognition, Image classification, Computed tomography, Signal attenuation, Medical imaging, Computer aided diagnosis and therapy, Current controlled current source
A good problem representation is important for a pattern recognition system to be successful. The traditional approach to statistical pattern recognition is feature representation. More specifically, objects are represented by a number of features in a feature vector space, and classifiers are built in this representation. This is also the general trend in lung parenchyma classification in computed tomography (CT) images, where the features often are measures on feature histograms. Instead, we propose to build normal density based classifiers in dissimilarity representations for lung parenchyma classification. This allows for the classifiers to work on dissimilarities between objects, which might be a more natural way of representing lung parenchyma. In this context, dissimilarity is defined between CT regions of interest (ROI)s. ROIs are represented by their CT attenuation histogram and ROI dissimilarity is defined as a histogram dissimilarity measure between the attenuation histograms. In this setting, the full histograms are utilized according to the chosen histogram dissimilarity measure.
We apply this idea to classification of different emphysema patterns as well as normal, healthy tissue.
Two dissimilarity representation approaches as well as different histogram dissimilarity measures are considered. The approaches are evaluated on a set of 168 CT ROIs using normal density based classifiers all showing good performance. Compared to using histogram dissimilarity directly as distance in a emph{k} nearest neighbor classifier, which achieves a classification accuracy of $92.9%$, the best dissimilarity representation based classifier is significantly better with a classification accuracy of 97.0% ($text{emph{p" border="0" class="imgtopleft"> = 0.046$).
We propose a system for tracking of human spermatozoa in
phase-contrast microscopy image sequences.
One of the main aims of a computer-aided sperm analysis (CASA) system is to
automatically assess sperm quality based on spermatozoa motility
variables. In our case, the problem of assessing sperm quality is
cast as a multi-object tracking problem, where the objects being
tracked are the spermatozoa.
The system combines a particle
filter and Kalman filters for robust motion estimation of the
spermatozoa tracks. Further, the combinatorial aspect of assigning
observations to labels in the particle filter is formulated as a
linear assignment problem solved using the Hungarian algorithm on a
rectangular cost matrix, making the algorithm capable of handling
missing or spurious observations. The costs are calculated using
hidden Markov models that express the plausibility of an
observation being the next position in the track history of the
particle labels. Observations are extracted using a scale-space blob
detector utilizing the fact that the spermatozoa appear as bright
blobs in a phase-contrast microscope. The output
of the system is the complete motion track of each of the spermatozoa. Based on
these tracks, different CASA motility variables can be computed, for example curvilinear velocity or straight-line velocity.
The performance of the system is tested
on three different phase-contrast image sequences of varying complexity, both by visual inspection of the estimated spermatozoa tracks and by measuring the mean squared error (MSE) between the estimated spermatozoa tracks and manually annotated tracks, showing good agreement.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.