arXiv subjects

Christine Tanner

Publications and source records attributed to Christine Tanner.

13 recordsLinked to original sources

arXiv2025

In vivo imaging of central nervous system fluid spaces using synchrotron radiation-based micro computed tomography

Current approaches to in vivo imaging of the mouse central nervous system (CNS) do not offer a combination of micrometer resolution and a whole-brain field of view. To address this limitation, we introduce an approach based on synchrotron radiation-based hard X-ray micro computed tomography (SR$\mu$CT). We performed intravital SR$\mu$CT acquisitions of mouse CNS fluid spaces at three synchrotron radiation facilities. Imaging was conducted on both anesthetized free-breathing and ventilated animals, with and without retrospective cardiac gating. We achieved whole-brain imaging at 6.3 $\mu$m uniform voxel size, observed the distribution of cerebrospinal fluid (CSF) contrast agent over time and quantified choroid plexus movement. SR$\mu$CT bridges the gap between multiphoton microscopy and magnetic resonance imaging, offering dynamic imaging with micrometer-scale resolution and whole-organ field of view. Intravital SR$\mu$CT will play a crucial role in validating and integrating hypotheses on CSF dynamics and solute transport by providing unique data that cannot be acquired otherwise.

physics.med-ph↗

arXiv2024

Synchrotron radiation-based tomography of an entire mouse brain with sub-micron voxels: augmenting interactive brain atlases with terabyte data

Synchrotron radiation-based X-ray microtomography is uniquely suited for post mortem three-dimensional visualization of organs such as the mouse brain. Tomographic imaging of the entire mouse brain with isotropic cellular resolution requires an extended field-of-view and produces datasets of multiple terabytes in size. These data must be processed and made accessible to domain experts who may have only limited image processing knowledge. We present extended-field X-ray microtomography with 0.65 $\mu$m voxel size covering an entire mouse brain. The 4,495 projections from 8 x 8 offset acquisitions were stitched to reconstruct a volume of 15,000$^3$ voxels. The microtomography volume was non-rigidly registered to the Allen Mouse Brain Common Coordinate Framework v3 based on a combination of image intensity and landmark pairs. The data were transformed block-wise and stored in a public repository with a hierarchical format for navigation and overlay with anatomical annotations in online viewers such as Neuroglancer or siibra-explorer. This study demonstrates X-ray imaging and data processing for a full mouse brain, augmenting current atlases by improving resolution in the third dimension by an order of magnitude. The 3.3-teravoxel dataset is publicly available and easily accessible for domain experts via browser-based viewers.

physics.med-ph↗

arXiv2024

Aligner-induced tooth movements in three dimensions using clinical data of two patients

The effectiveness of a series of optically transparent aligners for orthodontic treatments depends on the anchoring of each tooth. In contrast with roots, the crowns' positions and orientations are measurable with intraoral scans, thus avoiding any X-ray dose. Exemplified by two patients, we demonstrate that three-dimensional crown movements could be determined with micrometer precision by registering weekly intraoral scans. The data show the movement and orientation changes of the individual crowns of the upper and lower jaws as the result of the forces generated by the series of aligners. During the first weeks, the canines and incisors were more affected than the premolars and molars. We detected an overall tooth movement of up to about 1 mm during a nine-week treatment. The data on these orthodontic treatments indicate the extent to which actual tooth movement lags behind the treatment plan as represented by the aligner shapes. The proposed procedure can not only be used to quantify the clinical outcome of the therapy, but also to improve future planning of orthodontic treatments for each specific patient. The study should be treated with caution because only two cases have been investigated and the approach should be applied to a reasonably large cohort to reach strong conclusions regarding efficiency and efficacy of the therapeutic approach.

physics.med-ph↗

arXiv2022

Three-dimensional imaging of porcine joint tissues down to the subcellular level

Joint tissues consist of trabecular and cortical bone as well as calcified and hyaline cartilage, which presents a challenge for hard X-ray-based visualization on the sub-cellular level due to the wide range of local X-ray absorption values. The density of the calcified tissues requires rather high photon energy, which often leads to insufficient contrast within the cartilage and impedes the visualization of individual biological cells. Decalcification of the tissues reduces the total and local X-ray absorption values and allows for selecting a lower photon energy. Further contrast enhancement can be achieved by ethanol fixation and paraffin tissue embedding. In this study, we (i) searched for an appropriate visualization method to investigate lesions generated by a laser osteotome and (ii) visualized a decalcified porcine joint after ethanol fixation and subsequent paraffin embedding using laboratory- and synchrotron radiation-based microtomography. The experiments at the ANATOMIX beamline of Synchrotron SOLEIL were performed in off-axis scan mode with a pixel size of 1.3 um. Individual cells in all layers of the joint could be made visible and the effect of ethanol fixation and paraffin embedding demonstrated.

physics.med-ph↗

arXiv2022

Three-dimensional imaging and analysis of annual layers in tree trunk and tooth cementum

The growth of plants, animals, and humans can give rise to layered structures associated with annual periodicity. Thickness variations are often correlated to nutrition supply and stress factors. The annual layers in a tree trunk with millimeter thickness can be directly counted, whereas the layers in tooth cementum with micrometer thickness are made visible using optical microscopy. These optical techniques rely on the surface evaluation or thin, optically transparent slices. Hard X-ray tomography with micrometer resolution, however, provides a three-dimensional view without physical slicing. We have developed a procedure to enhance the tomography data of annual layers in human and bovid tooth cementum. The analysis of a substantial part of an archeological human tooth demonstrated that the detected number of layers depended on the selected region and could vary between 13 and 27. The related average thickness of the annual layers was found to be (5.4 $\pm$ 1.9) $μ$m for the human tooth, whereas the buffalo tooth exhibited a layer periodicity of 46 $μ$m. The present study elucidates the potential of combining computational tools with high-quality micro computed tomography data to quantify the annual layers in tooth cementum for a variety of purposes including age-at-death determination.

physics.bio-ph↗

arXiv2020

Delineating Bone Surfaces in B-Mode Images Constrained by Physics of Ultrasound Propagation

Bone surface delineation in ultrasound is of interest due to its potential in diagnosis, surgical planning, and post-operative follow-up in orthopedics, as well as the potential of using bones as anatomical landmarks in surgical navigation. We herein propose a method to encode the physics of ultrasound propagation into a factor graph formulation for the purpose of bone surface delineation. In this graph structure, unary node potentials encode the local likelihood for being a soft tissue or acoustic-shadow (behind bone surface) region, both learned through image descriptors. Pair-wise edge potentials encode ultrasound propagation constraints of bone surfaces given their large acoustic-impedance difference. We evaluate the proposed method in comparison with four earlier approaches, on in-vivo ultrasound images collected from dorsal and volar views of the forearm. The proposed method achieves an average root-mean-square error and symmetric Hausdorff distance of 0.28mm and 1.78mm, respectively. It detects 99.9% of the annotated bone surfaces with a mean scanline error (distance to annotations) of 0.39mm.

cs.CV↗

arXiv2019

Active Learning for Segmentation Based on Bayesian Sample Queries

Segmentation of anatomical structures is a fundamental image analysis task for many applications in the medical field. Deep learning methods have been shown to perform well, but for this purpose large numbers of manual annotations are needed in the first place, which necessitate prohibitive levels of resources that are often unavailable. In an active learning framework of selecting informed samples for manual labeling, expert clinician time for manual annotation can be optimally utilized, enabling the establishment of large labeled datasets for machine learning. In this paper, we propose a novel method that combines representativeness with uncertainty in order to estimate ideal samples to be annotated, iteratively from a given dataset. Our novel representativeness metric is based on Bayesian sampling, by using information-maximizing autoencoders. We conduct experiments on a shoulder magnetic resonance imaging (MRI) dataset for the segmentation of four musculoskeletal tissue classes. Quantitative results show that the annotation of representative samples selected by our proposed querying method yields an improved segmentation performance at each active learning iteration, compared to a baseline method that also employs uncertainty and representativeness metrics. For instance, with only 10% of the dataset annotated, our method reaches within 5% of Dice score expected from the upper bound scenario of all the dataset given as annotated (an impractical scenario due to resource constraints), and this gap drops down to a mere 2% when less than a fifth of the dataset samples are annotated. Such active learning approach to selecting samples to annotate enables an optimal use of the expert clinician time, being often the bottleneck in realizing machine learning solutions in medicine.

cs.CV↗

arXiv2019

SCATGAN for Reconstruction of Ultrasound Scatterers Using Generative Adversarial Networks

Computational simulation of ultrasound (US) echography is essential for training sonographers. Realistic simulation of US interaction with microscopic tissue structures is often modeled by a tissue representation in the form of point scatterers, convolved with a spatially varying point spread function. This yields a realistic US B-mode speckle texture, given that a scatterer representation for a particular tissue type is readily available. This is often not the case and scatterers are nontrivial to determine. In this work we propose to estimate scatterer maps from sample US B-mode images of a tissue, by formulating this inverse mapping problem as image translation, where we learn the mapping with Generative Adversarial Networks, using a US simulation software for training. We demonstrate robust reconstruction results, invariant to US viewing and imaging settings such as imaging direction and center frequency. Our method is shown to generalize beyond the trained imaging settings, demonstrated on in-vivo US data. Our inference runs orders of magnitude faster than optimization-based techniques, enabling future extensions for reconstructing 3D B-mode volumes with only linear computational complexity.

eess.IV↗

arXiv2019

Siamese Networks with Location Prior for Landmark Tracking in Liver Ultrasound Sequences

Image-guided radiation therapy can benefit from accurate motion tracking by ultrasound imaging, in order to minimize treatment margins and radiate moving anatomical targets, e.g., due to breathing. One way to formulate this tracking problem is the automatic localization of given tracked anatomical landmarks throughout a temporal ultrasound sequence. For this, we herein propose a fully-convolutional Siamese network that learns the similarity between pairs of image regions containing the same landmark. Accordingly, it learns to localize and thus track arbitrary image features, not only predefined anatomical structures. We employ a temporal consistency model as a location prior, which we combine with the network-predicted location probability map to track a target iteratively in ultrasound sequences. We applied this method on the dataset of the Challenge on Liver Ultrasound Tracking (CLUST) with competitive results, where our work is the first to effectively apply CNNs on this tracking problem, thanks to our temporal regularization.

cs.CV↗

arXiv2018

Iterative Interaction Training for Segmentation Editing Networks

Automatic segmentation has great potential to facilitate morphological measurements while simultaneously increasing efficiency. Nevertheless often users want to edit the segmentation to their own needs and will need different tools for this. There has been methods developed to edit segmentations of automatic methods based on the user input, primarily for binary segmentations. Here however, we present an unique training strategy for convolutional neural networks (CNNs) trained on top of an automatic method to enable interactive segmentation editing that is not limited to binary segmentation. By utilizing a robot-user during training, we closely mimic realistic use cases to achieve optimal editing performance. In addition, we show that an increase of the iterative interactions during the training process up to ten improves the segmentation editing performance substantially. Furthermore, we compare our segmentation editing CNN (interCNN) to state-of-the-art interactive segmentation algorithms and show a superior or on par performance.

cs.CV↗

arXiv2018

Generative Adversarial Networks for MR-CT Deformable Image Registration

Deformable Image Registration (DIR) of MR and CT images is one of the most challenging registration task, due to the inherent structural differences of the modalities and the missing dense ground truth. Recently cycle Generative Adversarial Networks (cycle-GANs) have been used to learn the intensity relationship between these 2 modalities for unpaired brain data. Yet its usefulness for DIR was not assessed. In this study we evaluate the DIR performance for thoracic and abdominal organs after synthesis by cycle-GAN. We show that geometric changes, which differentiate the two populations (e.g. inhale vs. exhale), are readily synthesized as well. This causes substantial problems for any application which relies on spatial correspondences being preserved between the real and the synthesized image (e.g. plan, segmentation, landmark propagation). To alleviate this problem, we investigated reducing the spatial information provided to the discriminator by decreasing the size of its receptive fields. Image synthesis was learned from 17 unpaired subjects per modality. Registration performance was evaluated with respect to manual segmentations of 11 structures for 3 subjects from the VISERAL challenge. State-of-the-art DIR methods based on Normalized Mutual Information (NMI), Modality Independent Neighborhood Descriptor (MIND) and their novel combination achieved a mean segmentation overlap ratio of 76.7, 67.7, 76.9%, respectively. This dropped to 69.1% or less when registering images synthesized by cycle-GAN based on local correlation, due to the poor performance on the thoracic region, where large lung volume changes were synthesized. Performance for the abdominal region was similar to that of CT-MRI NMI registration (77.4 vs. 78.8%) when using 3D synthesizing MRIs (12 slices) and medium sized receptive fields for the discriminator.

cs.CV↗

arXiv2018

Active Learning for Segmentation by Optimizing Content Information for Maximal Entropy

Segmentation is essential for medical image analysis tasks such as intervention planning, therapy guidance, diagnosis, treatment decisions. Deep learning is becoming increasingly prominent for segmentation, where the lack of annotations, however, often becomes the main limitation. Due to privacy concerns and ethical considerations, most medical datasets are created, curated, and allow access only locally. Furthermore, current deep learning methods are often suboptimal in translating anatomical knowledge between different medical imaging modalities. Active learning can be used to select an informed set of image samples to request for manual annotation, in order to best utilize the limited annotation time of clinical experts for optimal outcomes, which we focus on in this work. Our contributions herein are two fold: (1) we enforce domain-representativeness of selected samples using a proposed penalization scheme to maximize information at the network abstraction layer, and (2) we propose a Borda-count based sample querying scheme for selecting samples for segmentation. Comparative experiments with baseline approaches show that the samples queried with our proposed method, where both above contributions are combined, result in significantly improved segmentation performance for this active learning task.

cs.CV↗

arXiv2018

Temporal Interpolation via Motion Field Prediction

Navigated 2D multi-slice dynamic Magnetic Resonance (MR) imaging enables high contrast 4D MR imaging during free breathing and provides in-vivo observations for treatment planning and guidance. Navigator slices are vital for retrospective stacking of 2D data slices in this method. However, they also prolong the acquisition sessions. Temporal interpolation of navigator slices an be used to reduce the number of navigator acquisitions without degrading specificity in stacking. In this work, we propose a convolutional neural network (CNN) based method for temporal interpolation via motion field prediction. The proposed formulation incorporates the prior knowledge that a motion field underlies changes in the image intensities over time. Previous approaches that interpolate directly in the intensity space are prone to produce blurry images or even remove structures in the images. Our method avoids such problems and faithfully preserves the information in the image. Further, an important advantage of our formulation is that it provides an unsupervised estimation of bi-directional motion fields. We show that these motion fields can be used to halve the number of registrations required during 4D reconstruction, thus substantially reducing the reconstruction time.

stat.ML↗