Search

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) $\mu$m for the human tooth, whereas the buffalo tooth exhibited a layer periodicity of 46 $\mu$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., Comment: 16 pages. Event: SPIE Smart Structures + Nondestructive Evaluation, 2022, Long Beach, California, United States

Background Fixation and embedding of post mortem brain tissue is a pre-requisite for both gold-standard conventional histology and X-ray virtual histology. This process alters the morphology and density of the brain microanatomy. New method To quantify these changes, we employed synchrotron radiation-based hard X-ray tomography with 3 μm voxel length to visualize the same mouse brain after fixation in 4% formalin, immersion in ethanol solutions (50%, 70%, 80%, 90%, and 100%), xylene, and finally after embedding in a paraffin block. The volumetric data were non-rigidly registered to the initial formalin-fixed state to align the microanatomy within the entire mouse brain. Results Volumetric strain fields were used to characterize local shrinkage, which was found to depend on the anatomical region and distance to external surface. X-ray contrast was altered and enhanced by preparation-induced inter-tissue density changes. The preparation step can be selected to highlight specific anatomical features. For example, fiber tract contrast is amplified in 100% ethanol. Comparison with existing methods Our method provides volumetric strain fields, unlike approaches based on feature-to-feature or volume measurements. Volumetric strain fields are produced by non-rigid registration, which is less labor-intensive and observer-dependent than volume change measurements based on manual segmentations. X-ray microtomography provides spatial resolution at least an order of magnitude higher than magnetic resonance microscopy, allowing for analysis of morphology and density changes within the brain’s microanatomy. Conclusion Our approach belongs to three-dimensional virtual histology with isotropic micrometer spatial resolution and therefore complements atlases based on a combination of magnetic resonance microscopy and optical micrographs of serial histological sections.

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., Comment: 10 pages, 7 figures

Computers & Graphics, 82, ISSN:0097-8493, ISSN:1873-7684

Purpose: Compensation for respiratory motion is important during abdominal cancer treatments. In this work we report the results of the 2015 MICCAI Challenge on Liver Ultrasound Tracking and extend the 2D results to relate them to clinical relevance in form of reducing treatment margins and hence sparing healthy tissues, while maintaining full duty cycle.Methods: We describe methodologies for estimating and temporally predicting respiratory liver motion from continuous ultrasound imaging, used during ultrasound‐guided radiation therapy. Furthermore, we investigated the trade‐off between tracking accuracy and runtime in combination with temporal prediction strategies and their impact on treatment margins.Results: Based on 2D ultrasound sequences from 39 volunteers, a mean tracking accuracy of 0.9 mm was achieved when combining the results from the 4 challenge submissions (1.2 to 3.3 mm). The two submissions for the 3D sequences from 14 volunteers provided mean accuracies of 1.7 and 1.8 mm. In combination with temporal prediction, using the faster (41 vs 228 ms) but less accurate (1.4 vs 0.9 mm) tracking method resulted in substantially reduced treatment margins (70% vs 39%) in contrast to mid‐ventilation margins, as it avoided non‐linear temporal prediction by keeping the treatment system latency low (150 vs 400 ms). Acceleration of the best tracking method would improve the margin reduction to 75%.Conclusions: Liver motion estimation and prediction during free‐breathing from 2D ultrasound images can substantially reduce the in‐plane motion uncertainty and hence treatment margins. Employing an accurate tracking method while avoiding non‐linear temporal prediction would be favorable. This approach has the potential to shorten treatment time compared to breath‐hold and gated approaches, and increase treatment efficiency and safety.

Navigated 2-D multi-slice dynamic magnetic resonance imaging (MRI) acquisitions are essential for MR guided therapies. This technique yields time-resolved volumetric images during free-breathing, which are ideal for visualizing and quantifying breathing induced motion. To achieve this, navigated dynamic imaging requires acquiring multiple navigator slices. Reducing the number of navigator slices would allow for acquiring more data slices in the same time, and hence, increasing through-plane resolution or alternatively the overall acquisition time can be reduced while keeping resolution unchanged. To this end, we propose temporal interpolation of navigator slices using convolutional neural networks (CNNs). Our goal is to acquire fewer navigators and replace the missing ones with interpolation. We evaluate the proposed method on abdominal navigated dynamic MRI sequences acquired from 14 subjects. Investigations with several CNN architectures and training loss functions show favorable results for ${L}_{\textsf {2}}$ cost and a simple feed-forward network with no skip connections. When compared with interpolation by non-linear registration, the proposed method achieves higher interpolation accuracy on average as quantified in terms of root mean square error and residual motion. Analysis of the differences shows that the better performance is due to more accurate interpolation at peak exhalation and inhalation positions. Furthermore, the CNN-based approach requires substantially lower execution times than that of the registration-based method. At last, experiments on dynamic volume reconstruction reveal minimal differences between reconstructions with acquired and interpolated navigator slices.

For guidance of orthopedic surgery, the registration of preoperative images and corresponding surgical plans with the surgical setting can be of great value. Ultrasound (US) is an ideal modality for surgical guidance, as it is non-ionizing, real time, easy to use, and requires minimal (magnetic/radiation) safety limitations. By extracting bone surfaces from 3D freehand US and registering these to preoperative bone models, complementary information from these modalities can be fused and presented in the surgical realm. A partial bone surface is extracted from US using phase symmetry and a factor graph-based approach. This is registered to the detailed 3D bone model, conventionally generated for preoperative planning, based on a proposed multi-initialization and surface-based scheme robust to partial surfaces. 36 forearm US volumes acquired using a tracked US probe were independently registered to a 3D model of the radius, manually extracted from MRI. Given intraoperative time restrictions, a computationally efficient algorithm was determined based on a comparison of different approaches. For all 36 registrations, a mean (± SD) point-to-point surface distance of $$0.57\,(\pm \,0.08)\,\hbox {mm}$$ was obtained from manual gold standard US bone annotations (not used during the registration) to the 3D bone model. A registration framework based on the bone surface extraction from 3D freehand US and a subsequent fast, automatic surface alignment robust to single-sided view and large false-positive rates from US was shown to achieve registration accuracy feasible for practical orthopedic scenarios and a qualitative outcome indicating good visual image alignment.

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., 8 pages, 4 figures, Accepted to MICCAI 2018 Workshop: Deep Learning in Medical Image Analysis (DLMIA)

The Challenge on Liver Ultrasound Tracking (CLUST) was held in conjunction with the MICCAI 2014 conference to enable direct comparison of tracking methods for this application. This paper reports the outcome of this challenge, including setup, methods, results and experiences. The database included 54 2D and 3D sequences of the liver of healthy volunteers and tumor patients under free breathing. Participants had to provide the tracking results of 90% of the data (test set) for pre-defined point-landmarks (healthy volunteers) or for tumor segmentations (patient data). In this paper we compare the best six methods which participated in the challenge. Quantitative evaluation was performed by the organizers with respect to manual annotations. Results of all methods showed a mean tracking error ranging between 1.4 mm and 2.1 mm for 2D points, and between 2.6 mm and 4.6 mm for 3D points. Fusing all automatic results by considering the median tracking results, improved the mean error to 1.2 mm (2D) and 2.5 mm (3D). For all methods, the performance is still not comparable to human inter-rater variability, with a mean tracking error of 0.5-0.6 mm (2D) and 1.2-1.8 mm (3D). The segmentation task was fulfilled only by one participant, resulting in a Dice coefficient ranging from 76.7% to 92.3%. The CLUST database continues to be available and the online leader-board will be updated as an ongoing challenge.

Focused ultrasound surgery (FUS) is a non-invasive method for tissue ablation that has the potential for complete and controlled local tumour destruction with minimal side effects. The treatment of abdominal organs such as the liver, however, requires particular technological support in order to enable a safe, efficient and effective treatment. As FUS is applied from outside the patient's body, suitable imaging methods, such as magnetic resonance imaging or diagnostic ultrasound, are needed to guide and track the procedure. To facilitate an efficient FUS procedure in the liver, the organ motion during breathing and the partial occlusion by the rib cage need to be taken into account in real time, demanding a continuous patient-specific adaptation of the treatment configuration. Modelling the patient's respiratory motion and combining this with tracking data improves the accuracy of motion predictions. Modelling and simulation of the FUS effects within the body allows the use of treatment planning and has the potential to be used within therapy to increase knowledge about the patient status. This article describes integrated model-based software for patient-specific modelling and prediction for FUS treatments of moving abdominal organs.

We propose an unconventional approach for transferring of information between multi-modal images. It exploits the temporal commonality of multi-modal images acquired from the same organ during free-breathing. Strikingly there is no need for capturing the same region by the modalities. The method is based on extracting a low-dimensional description of the image sequences, selecting the common cause signal (breathing) for both modalities and finding the most similar sub-sequences for predicting image feature location. The approach was evaluated for 3 volunteers on sequences of 2D MRI and 2D US images of the liver acquired at different locations. Simultaneous acquisition of these images allowed for quantitative evaluation (predicted versus ground truth MRI feature locations). The best performance was achieved with signal extraction by slow feature analysis resulting in an average error of 2.6 mm (4.2 mm) for sequences acquired at the same (a different) time.