scholarly journals Harmonization of diffusion MRI datasets with adaptive dictionary learning

2019 ◽  
Author(s):  
Samuel St-Jean ◽  
Max A. Viergever ◽  
Alexander Leemans
Keyword(s):  
Dictionary Learning ◽  
Statistical Power ◽  
Free Water ◽  
Training Data ◽  
Multicenter Studies ◽  
Essential Information ◽  
Native Space ◽  
Diffusion Weighted Images ◽  
Spatial Registration ◽  
Water Compartment

AbstractDiffusion magnetic resonance imaging can indirectly infer the microstructure of tissues and provide metrics subject to normal variability in a population. Potentially abnormal values may yield essential information to support analysis of controls and patients cohorts, but subtle confounds could be mistaken for purely biologically driven variations amongst subjects. In this work, we propose a new harmonization algorithm based on adaptive dictionary learning to mitigate the unwanted variability caused by different scanner hardware while preserving the natural biological variability of the data. Our harmonization algorithm does not require paired training datasets, nor spatial registration or matching spatial resolution. Overcomplete dictionaries are learned iteratively from all datasets at the same time with an adaptive regularization criterion. removing variability attributable to the scanners in the process. The obtained mapping is applied directly in the native space of each subject towards a scanner-space. The method is evaluated with a public database which consists of two different protocols acquired on three different scanners. Results show that the effect size of the four studied diffusion metrics is preserved while removing variability attributable to the scanner. Experiments with alterations using a free water compartment, which is not simulated in the training data, shows that the modifications applied to the diffusion weighted images are preserved in the diffusion metrics after harmonization, while still reducing global variability at the same time. The algorithm could help multicenter studies pooling their data by removing scanner specific confounds, and increase statistical power in the process.

scholarly journals INFRASTRUCTURE DEGRADATION AND POST-DISASTER DAMAGE DETECTION USING ANOMALY DETECTING GENERATIVE ADVERSARIAL NETWORKS

2020 ◽  
Vol V-2-2020 ◽  
pp. 573-582 ◽  
Author(s):  
S. M. Tilon ◽  
F. Nex ◽  
D. Duarte ◽  
N. Kerle ◽  
G. Vosselman
Keyword(s):  
Deep Learning ◽  
Damage Detection ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Essential Information ◽  
Urban Scenes ◽  
Adversarial Network ◽  
Collapsed Buildings ◽  
Post Disaster

Abstract. Degradation and damage detection provides essential information to maintenance workers in routine monitoring and to first responders in post-disaster scenarios. Despite advance in Earth Observation (EO), image analysis and deep learning techniques, the quality and quantity of training data for deep learning is still limited. As a result, no robust method has been found yet that can transfer and generalize well over a variety of geographic locations and typologies of damages. Since damages can be seen as anomalies, occurring sparingly over time and space, we propose to use an anomaly detecting Generative Adversarial Network (GAN) to detect damages. The main advantages of using GANs are that only healthy unannotated images are needed, and that a variety of damages, including the never before seen damage, can be detected. In this study we aimed to investigate 1) the ability of anomaly detecting GANs to detect degradation (potholes and cracks) in asphalt road infrastructures using Mobile Mapper imagery and building damage (collapsed buildings, rubble piles) using post-disaster aerial imagery, and 2) the sensitivity of this method against various types of pre-processing. Our results show that we can detect damages in urban scenes at satisfying levels but not on asphalt roads. Future work will investigate how to further classify the found damages and how to improve damage detection for asphalt roads.

Altered brainstem anatomy in migraine

Cephalalgia ◽  
2017 ◽  
Vol 38 (3) ◽  
pp. 476-486 ◽  
Author(s):  
Kasia K Marciszewski ◽  
Noemi Meylakh ◽  
Flavia Di Pietro ◽  
Vaughan G Macefield ◽  
Paul M Macey ◽  
...  
Keyword(s):  
Grey Matter ◽  
Diffusion Tensor ◽  
Free Water ◽  
Trigeminal System ◽  
Grey Matter Volume ◽  
Matter Volume ◽  
Diffusion Weighted Images ◽  
Diffusion Tensor Images ◽  
And Diffusion ◽  
Brainstem Anatomy

Background The exact mechanisms responsible for migraine remain unknown, although it has been proposed that changes in brainstem anatomy and function, even between attacks, may contribute to the initiation and maintenance of headache during migraine attacks. The aim of this investigation is to use brainstem-specific analyses of anatomical and diffusion weighted images to determine if the trigeminal system displays altered structure in individuals with migraine. Methods Voxel-based morphometry of T1-weighted anatomical images (57 controls, 24 migraineurs) and diffusion tensor images (22 controls, 24 migraineurs) were used to assess brainstem anatomy in individuals with migraine compared with controls. Results We found grey matter volume decreases in migraineurs in the spinal trigeminal nucleus and dorsomedial pons. In addition, reduced grey matter volume and increased free water diffusivity occurred in areas of the descending pain modulatory system, including midbrain periaqueductal gray matter, dorsolateral pons, and medullary raphe. These changes were not correlated to migraine frequency, duration, intensity or time to next migraine. Conclusion Brainstem anatomy changes may underlie changes in activity that result in activation of the ascending trigeminal pathway and the perception of head pain during a migraine attack.

Brain tumor classification and segmentation using sparse coding and dictionary learning

2016 ◽  
Vol 61 (4) ◽  
pp. 413-429 ◽  
Author(s):  
Saif Dawood Salman Al-Shaikhli ◽  
Michael Ying Yang ◽  
Bodo Rosenhahn
Keyword(s):  
Brain Tumor ◽  
Dictionary Learning ◽  
Sparse Coding ◽  
Image Data ◽  
Ground Truth ◽  
Tumor Classification ◽  
Training Data ◽  
Tumor Segmentation ◽  
Feature Dictionary ◽  
The Brain

AbstractThis paper presents a novel fully automatic framework for multi-class brain tumor classification and segmentation using a sparse coding and dictionary learning method. The proposed framework consists of two steps: classification and segmentation. The classification of the brain tumors is based on brain topology and texture. The segmentation is based on voxel values of the image data. Using K-SVD, two types of dictionaries are learned from the training data and their associated ground truth segmentation: feature dictionary and voxel-wise coupled dictionaries. The feature dictionary consists of global image features (topological and texture features). The coupled dictionaries consist of coupled information: gray scale voxel values of the training image data and their associated label voxel values of the ground truth segmentation of the training data. For quantitative evaluation, the proposed framework is evaluated using different metrics. The segmentation results of the brain tumor segmentation (MICCAI-BraTS-2013) database are evaluated using five different metric scores, which are computed using the online evaluation tool provided by the BraTS-2013 challenge organizers. Experimental results demonstrate that the proposed approach achieves an accurate brain tumor classification and segmentation and outperforms the state-of-the-art methods.

scholarly journals Stable Anatomy Detection in Multimodal Imaging Through Sparse Group Regularization: A Comparative Study of Iron Accumulation in the Aging Brain

2021 ◽  
Vol 15 ◽  
Author(s):  
Matthew Pietrosanu ◽  
Li Zhang ◽  
Peter Seres ◽  
Ahmed Elkady ◽  
Alan H. Wilman ◽  
...  
Keyword(s):  
Multimodal Imaging ◽  
Statistical Power ◽  
Healthy Aging ◽  
Group Lasso ◽  
Quantitative Mri ◽  
Training Data ◽  
Imaging Modalities ◽  
Aging Brain ◽  
Structural Level ◽  
Multiple Imaging

Multimodal neuroimaging provides a rich source of data for identifying brain regions associated with disease progression and aging. However, present studies still typically analyze modalities separately or aggregate voxel-wise measurements and analyses to the structural level, thus reducing statistical power. As a central example, previous works have used two quantitative MRI parameters—R2* and quantitative susceptibility (QS)—to study changes in iron associated with aging in healthy and multiple sclerosis subjects, but failed to simultaneously account for both. In this article, we propose a unified framework that combines information from multiple imaging modalities and regularizes estimates for increased interpretability, generalizability, and stability. Our work focuses on joint region detection problems where overlap between effect supports across modalities is encouraged but not strictly enforced. To achieve this, we combine L1 (lasso), total variation (TV), and L2 group lasso penalties. While the TV penalty encourages geometric regularization by controlling estimate variability and support boundary geometry, the group lasso penalty accounts for similarities in the support between imaging modalities. We address the computational difficulty in this regularization scheme with an alternating direction method of multipliers (ADMM) optimizer. In a neuroimaging application, we compare our method against independent sparse and joint sparse models using a dataset of R2* and QS maps derived from MRI scans of 113 healthy controls: our method produces clinically-interpretable regions where specific iron changes are associated with healthy aging. Together with results across multiple simulation studies, we conclude that our approach identifies regions that are more strongly associated with the variable of interest (e.g., age), more accurate, and more stable with respect to training data variability. This work makes progress toward a stable and interpretable multimodal imaging analysis framework for studying disease-related changes in brain structure and can be extended for classification and disease prediction tasks.

scholarly journals Opposing white matter microstructure abnormalities in 22q11.2 deletion and duplication carriers

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Johanna Seitz-Holland ◽  
Monica Lyons ◽  
Leila Kushan ◽  
Amy Lin ◽  
Julio E. Villalon-Reina ◽  
...  
Keyword(s):  
White Matter ◽  
Psychiatric Morbidity ◽  
Free Water ◽  
Water Model ◽  
22Q11.2 Deletion ◽  
Tissue Properties ◽  
Diffusion Weighted Images ◽  
Diffusion Weighted ◽  
Water Elimination ◽  
Number Variation

AbstractDeletions and duplications at the 22q11.2 locus are associated with significant neurodevelopmental and psychiatric morbidity. Previous diffusion-weighted magnetic resonance imaging (MRI) studies in 22q11.2 deletion carriers (22q-del) found nonspecific white matter (WM) abnormalities, characterized by higher fractional anisotropy. Here, utilizing novel imaging and processing methods that allow separation of signal contribution from different tissue properties, we investigate whether higher anisotropy is driven by (1) extracellular changes, (2) selective degeneration of secondary fibers, or (3) volumetric differences. We further, for the first time, investigate WM microstructure in 22q11.2 duplication carriers (22q-dup). Multi-shell diffusion-weighted images were acquired from 26 22q-del, 19 22q-dup, and 18 healthy individuals (HC). Images were fitted with the free-water model to estimate anisotropy following extracellular free-water elimination and with the novel BedpostX model to estimate fractional volumes of primary and secondary fiber populations. Outcome measures were compared between groups, with and without correction for WM and cerebrospinal fluid (CSF) volumes. In 22q-del, anisotropy following free-water elimination remained significantly higher compared with controls. BedpostX did not identify selective secondary fiber degeneration. Higher anisotropy diminished when correcting for the higher CSF and lower WM volumes. In contrast, 22q-dup had lower anisotropy and greater extracellular space than HC, not influenced by macrostructural volumes. Our findings demonstrate opposing effects of reciprocal 22q11.2 copy-number variation on WM, which may arise from distinct pathologies. In 22q-del, microstructural abnormalities may be secondary to enlarged CSF space and more densely packed WM. In 22q-dup, we see evidence for demyelination similar to what is commonly observed in neuropsychiatric disorders.

scholarly journals A fully automated deep learning pipeline for high-throughput colony segmentation and classification

2019 ◽  
Author(s):  
Sarah H. Carl ◽  
Lea Duempelmann ◽  
Yukiko Shimada ◽  
Marc Bühler
Keyword(s):  
Neural Networks ◽  
Statistical Power ◽  
Training Data ◽  
Large Numbers ◽  
Manual Counting ◽  
Epigenetic Events ◽  
Colony Color ◽  
Automated Pipeline ◽  
Screening Assays ◽  
Experienced Researcher

AbstractBackgroundAdenine auxotrophy is a commonly used non-selective genetic marker in yeast research. It allows investigators to easily visualize and quantify various genetic and epigenetic events by simply reading out colony color. However, manual counting of large numbers of colonies is extremely time-consuming, difficult to reproduce and possibly inaccurate.ResultsUsing cutting-edge neural networks, we have developed a fully automated pipeline for colony segmentation and classification, which speeds up white/red colony quantification 100-fold over manual counting by an experienced researcher.ConclusionsOur approach uses readily available training data and can be smoothly integrated into existing protocols, vastly speeding up screening assays and increasing the statistical power of experiments that employ adenine auxotrophy.

scholarly journals Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery

2021 ◽  
Vol 13 (22) ◽  
pp. 4711
Author(s):  
Katja Berger ◽  
Tobias Hank ◽  
Andrej Halabuk ◽  
Juan Pablo Rivera-Caicedo ◽  
Matthias Wocher ◽  
...  
Keyword(s):  
Hyperspectral Image ◽  
Quantitative Estimation ◽  
Gaussian Process Regression ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Canopy Reflectance ◽  
Data Set ◽  
Area Index ◽  
Essential Information ◽  
Wide Range

Non-photosynthetic vegetation (NPV) biomass has been identified as a priority variable for upcoming spaceborne imaging spectroscopy missions, calling for a quantitative estimation of lignocellulosic plant material as opposed to the sole indication of surface coverage. Therefore, we propose a hybrid model for the retrieval of non-photosynthetic cropland biomass. The workflow included coupling the leaf optical model PROSPECT-PRO with the canopy reflectance model 4SAIL, which allowed us to simulate NPV biomass from carbon-based constituents (CBC) and leaf area index (LAI). PROSAIL-PRO provided a training database for a Gaussian process regression (GPR) algorithm, simulating a wide range of non-photosynthetic vegetation states. Active learning was employed to reduce and optimize the training data set. In addition, we applied spectral dimensionality reduction to condense essential information of non-photosynthetic signals. The resulting NPV-GPR model was successfully validated against soybean field data with normalized root mean square error (nRMSE) of 13.4% and a coefficient of determination (R2) of 0.85. To demonstrate mapping capability, the NPV-GPR model was tested on a PRISMA hyperspectral image acquired over agricultural areas in the North of Munich, Germany. Reliable estimates were mainly achieved over senescent vegetation areas as suggested by model uncertainties. The proposed workflow is the first step towards the quantification of non-photosynthetic cropland biomass as a next-generation product from near-term operational missions, such as CHIME.

scholarly journals AIRBORNE LIDAR POINTS CLASSIFICATION BASED ON TENSOR SPARSE REPRESENTATION

2017 ◽  
Vol IV-2/W4 ◽  
pp. 107-114
Author(s):  
N. Li ◽  
N. Pfeifer ◽  
C. Liu
Keyword(s):  
Sparse Representation ◽  
Statistical Methods ◽  
Dictionary Learning ◽  
Supervised Classification ◽  
Airborne Lidar ◽  
Training Data ◽  
Sparse Representation Classification ◽  
The Common

The common statistical methods for supervised classification usually require a large amount of training data to achieve reasonable results, which is time consuming and inefficient. This paper proposes a tensor sparse representation classification (SRC) method for airborne LiDAR points. The LiDAR points are represented as tensors to keep attributes in its spatial space. Then only a few of training data is used for dictionary learning, and the sparse tensor is calculated based on tensor OMP algorithm. The point label is determined by the minimal reconstruction residuals. Experiments are carried out on real LiDAR points whose result shows that objects can be distinguished by this algorithm successfully.

scholarly journals A fully automated deep learning pipeline for high-throughput colony segmentation and classification

Biology Open ◽  
2020 ◽  
Vol 9 (6) ◽  
pp. bio052936
Author(s):  
Sarah H. Carl ◽  
Lea Duempelmann ◽  
Yukiko Shimada ◽  
Marc Bühler
Keyword(s):  
Neural Networks ◽  
Statistical Power ◽  
Training Data ◽  
Large Numbers ◽  
Manual Counting ◽  
Epigenetic Events ◽  
Colony Color ◽  
Automated Pipeline ◽  
Screening Assays ◽  
Experienced Researcher

ABSTRACTAdenine auxotrophy is a commonly used non-selective genetic marker in yeast research. It allows investigators to easily visualize and quantify various genetic and epigenetic events by simply reading out colony color. However, manual counting of large numbers of colonies is extremely time-consuming, difficult to reproduce and possibly inaccurate. Using cutting-edge neural networks, we have developed a fully automated pipeline for colony segmentation and classification, which speeds up white/red colony quantification 100-fold over manual counting by an experienced researcher. Our approach uses readily available training data and can be smoothly integrated into existing protocols, vastly speeding up screening assays and increasing the statistical power of experiments that employ adenine auxotrophy.

Sign in / Sign up

Export Citation Format

Share Document