Automatic Segmentation and Alignment of Uterine Shapes from 3D Ultrasound Data.

BACKGROUND: The uterus is the most important organ in the female reproductive system. Its shape plays a critical role in fertility and pregnancy outcomes. Advances in medical imaging, such as 3D ultrasound, have significantly improved the exploration of the female genital tract, thereby enhancing gynecological healthcare. Despite well-documented data for organs like the liver and heart, large-scale studies on the uterus are lacking. Existing classifications, such as VCUAM and ESHRE/ESGE, provide different definitions for normal uterine shapes but are not based on real-world measurements. Moreover, the lack of comprehensive datasets significantly hinders research in this area. Our research, part of the larger NURSE study, aims to fill this gap by establishing the shape of a normal uterus using real-world 3D vaginal ultrasound scans. This will facilitate research into uterine shape abnormalities associated with infertility and recurrent miscarriages. METHODS: We developed an automated system for the segmentation and alignment of uterine shapes from 3D ultrasound data, which consists of two steps: automatic segmentation of the uteri in 3D ultrasound scans using deep learning techniques, and alignment of the resulting shapes with standard geometrical approaches, enabling the extraction of the normal shape for future analysis. The system was trained and validated on a comprehensive dataset of 3D ultrasound images from multiple medical centers. Its performance was evaluated by comparing the automated results with manual annotations provided by expert clinicians. RESULTS: The presented approach demonstrated high accuracy in segmenting and aligning uterine shapes from 3D ultrasound data. The segmentation achieved an average Dice similarity coefficient (DSC) of 0.90. Our method for aligning uterine shapes showed minimal translation and rotation errors compared to traditional methods, with the preliminary average shape exhibiting characteristics consistent with expert findings of a normal uterus. CONCLUSION: We have presented an approach to automatically segment and align uterine shapes from 3D ultrasound data. We trained a deep learning nnU-Net model that achieved high accuracy and proposed an alignment method using a combination of standard geometrical techniques. Additionally, we have created a publicly available dataset of 3D transvaginal ultrasound volumes with manual annotations of uterine cavities to support further research and development in this field. The dataset and the trained models are available at https://github.com/UL-FRI-LGM/UterUS.

Dr. KID: Direct Remeshing and K-Set Isometric Decomposition for Scalable Physicalization of Organic Shapes.

Dr. KID is an algorithm that uses isometric decomposition for the physicalization of potato-shaped organic models in a puzzle fashion. The algorithm begins with creating a simple, regular triangular surface mesh of organic shapes, followed by iterative K-means clustering and remeshing. For clustering, we need similarity between triangles (segments) which is defined as a distance function. The distance function maps each triangle's shape to a single point in the virtual 3D space. Thus, the distance between the triangles indicates their degree of dissimilarity. K-means clustering uses this distance and sorts segments into k classes. After this, remeshing is applied to minimize the distance between triangles within the same cluster by making their shapes identical. Clustering and remeshing are repeated until the distance between triangles in the same cluster reaches an acceptable threshold. We adopt a curvature-aware strategy to determine the surface thickness and finalize puzzle pieces for 3D printing. Identical hinges and holes are created for assembling the puzzle components. For smoother outcomes, we use triangle subdivision along with curvature-aware clustering, generating curved triangular patches for 3D printing. Our algorithm was evaluated using various models, and the 3D-printed results were analyzed. Findings indicate that our algorithm performs reliably on target organic shapes with minimal loss of input geometry.

Nanotilus: Generator of Immersive Guided-Tours in Crowded 3D Environments.

Immersive virtual reality environments are gaining popularity for studying and exploring crowded three-dimensional structures. When reaching very high structural densities, the natural depiction of the scene produces impenetrable clutter and requires visibility and occlusion management strategies for exploration and orientation. Strategies developed to address the crowdedness in desktop applications, however, inhibit the feeling of immersion. They result in nonimmersive, desktop-style outside-in viewing in virtual reality. This article proposes Nanotilus-a new visibility and guidance approach for very dense environments that generates an endoscopic inside-out experience instead of outside-in viewing, preserving the immersive aspect of virtual reality. The approach consists of two novel, tightly coupled mechanisms that control scene sparsification simultaneously with camera path planning. The sparsification strategy is localized around the camera and is realized as a multi-scale, multi-shell, variety-preserving technique. When Nanotilus dives into the structures to capture internal details residing on multiple scales, it guides the camera using depth-based path planning. In addition to sparsification and path planning, we complete the tour generation with an animation controller, textual annotation, and text-to-visualization conversion. We demonstrate the generated guided tours on mesoscopic biological models - SARS-CoV-2 and HIV. We evaluate the Nanotilus experience with a baseline outside-in sparsification and navigational technique in a formal user study with 29 participants. While users can maintain a better overview using the outside-in sparsification, the study confirms our hypothesis that Nanotilus leads to stronger engagement and immersion.

Finding Nano-Ötzi: Cryo-Electron Tomography Visualization Guided by Learned Segmentation.

Cryo-electron tomography (cryo-ET) is a new 3D imaging technique with unprecedented potential for resolving submicron structural details. Existing volume visualization methods, however, are not able to reveal details of interest due to low signal-to-noise ratio. In order to design more powerful transfer functions, we propose leveraging soft segmentation as an explicit component of visualization for noisy volumes. Our technical realization is based on semi-supervised learning, where we combine the advantages of two segmentation algorithms. First, the weak segmentation algorithm provides good results for propagating sparse user-provided labels to other voxels in the same volume and is used to generate dense pseudo-labels. Second, the powerful deep-learning-based segmentation algorithm learns from these pseudo-labels to generalize the segmentation to other unseen volumes, a task that the weak segmentation algorithm fails at completely. The proposed volume visualization uses deep-learning-based segmentation as a component for segmentation-aware transfer function design. Appropriate ramp parameters can be suggested automatically through frequency distribution analysis. Furthermore, our visualization uses gradient-free ambient occlusion shading to further suppress the visual presence of noise, and to give structural detail the desired prominence. The cryo-ET data studied in our technical experiments are based on the highest-quality tilted series of intact SARS-CoV-2 virions. Our technique shows the high impact in target sciences for visual data analysis of very noisy volumes that cannot be visualized with existing techniques.

Automatic segmentation and reconstruction of intracellular compartments in volumetric electron microscopy data.

BACKGROUND AND OBJECTIVES: In recent years, electron microscopy is enabling the acquisition of volumetric data with resolving power to directly observe the ultrastructure of intracellular compartments. New insights and knowledge about cell processes that are offered by such data require a comprehensive analysis which is limited by the time-consuming manual segmentation and reconstruction methods. METHOD: We present methods for automatic segmentation, reconstruction, and analysis of intracellular compartments from volumetric data obtained by the dual-beam electron microscopy. We specifically address segmentation of fusiform vesicles and the Golgi apparatus, reconstruction of mitochondria and fusiform vesicles, and morphological analysis of the reconstructed mitochondria. RESULTS AND CONCLUSION: Evaluation on the public UroCell dataset demonstrated high accuracy of the proposed methods for segmentation of fusiform vesicles and the Golgi apparatus, as well as for reconstruction of mitochondria and analysis of their shapes, while reconstruction of fusiform vesicles proved to be more challenging. We published an extension of the UroCell dataset with all of the data used in this work, to further contribute to research on automatic analysis of the ultrastructure of intracellular compartments.

GPU Accelerated 3D Tomographic Reconstruction and Visualization from Noisy Electron Microscopy Tilt-Series.

We present a novel framework for 3D tomographic reconstruction and visualization of tomograms from noisy electron microscopy tilt-series. Our technique takes as an input aligned tilt-series from cryogenic electron microscopy and creates denoised 3D tomograms using a proximal jointly-optimized approach that iteratively performs reconstruction and denoising, relieving the users of the need to select appropriate denoising algorithms in the pre-reconstruction or post-reconstruction steps. The whole process is accelerated by exploiting parallelism on modern GPUs, and the results can be visualized immediately after the reconstruction using volume rendering tools incorporated in the framework. We show that our technique can be used with multiple combinations of reconstruction algorithms and regularizers, thanks to the flexibility provided by proximal algorithms. Additionally, the reconstruction framework is open-source and can be easily extended with additional reconstruction and denoising methods. Furthermore, our approach enables visualization of reconstruction error throughout the iterative process within the reconstructed tomogram and on projection planes of the input tilt-series. We evaluate our approach in comparison with state-of-the-art approaches and additionally show how our error visualization can be used for reconstruction evaluation.

Real-Time Interpolated Rendering of Terrain Point Cloud Data.

Most real-time terrain point cloud rendering techniques do not address the empty space between the points but rather try to minimize it by changing the way the points are rendered by either rendering them bigger or with more appropriate shapes such as paraboloids. In this work, we propose an alternative approach to point cloud rendering, which addresses the empty space between the points and tries to fill it with appropriate values to achieve the best possible output. The proposed approach runs in real time and outperforms several existing point cloud rendering techniques in terms of speed and render quality.

Slovenian Validation of the Children's Perceived Use of Self-Regulated Learning Inventory.

The importance of self-regulated learning (SRL) has increased during the COVID-19 pandemic and measures for assessing students' self-regulation skills and knowledge are greatly needed. We present the results of the first thorough adaptation of the Children's Perceived use of Self-Regulated Learning Inventory (CP-SRLI). The inventory, consisting of 15 scales measuring nine components of SRL, was administered to a sample of 541 Slovenian ninth graders. Confirmatory factor analyses supported internal structure validity of most components, but two components required some structural modifications. Internal consistency coefficients were acceptable for the majority of scale scores and were highly comparable to the original ones. While metric invariance across gender was confirmed, the scalar invariance of some scales needs further examination. Meaningful correlations with relevant externally assessed and self-reported self-regulation and school performance variables indicated good criterion validity of the inventory. The Slovenian version of the CP-SRLI thus proved to be a sufficiently valid and reliable instrument for assessing pupils' learning self-regulation.

Web-Based 3D Visualisation of Biological and Medical Data.

In this chapter we present an overview of web-based frameworks for visualisation of medical and biological data, with emphasis on visualisation of volumetric data such as radiological data (e.g. magnetic resonance imaging, computed tomography or positron emission tomography) and microscopy data (e.g. focused ion beam scanning electron microscopy). We compare web-based frameworks with state-of-the-art standalone visualisation tools and point out the advantages and disadvantages of both. We also present our open-source web-based visualisation environment Med3D.

Automatic segmentation of mitochondria and endolysosomes in volumetric electron microscopy data.

Automatic segmentation of intracellular compartments is a powerful technique, which provides quantitative data about presence, spatial distribution, structure and consequently the function of cells. With the recent development of high throughput volumetric data acquisition techniques in electron microscopy (EM), manual segmentation is becoming a major bottleneck of the process. To aid the cell research, we propose a technique for automatic segmentation of mitochondria and endolysosomes obtained from urinary bladder urothelial cells by the dual beam EM technique. We present a novel publicly available volumetric EM dataset - the first of urothelial cells, evaluate several state-of-the-art segmentation methods on the new dataset and present a novel segmentation pipeline, which is based on supervised deep learning and includes mechanisms that reduce the impact of dependencies in the input data, artefacts and annotation errors. We show that our approach outperforms the compared methods on the proposed dataset.

Aerial LiDAR Data Augmentation for Direct Point-Cloud Visualisation.

Direct point-cloud visualisation is a common approach for visualising large datasets of aerial terrain LiDAR scans. However, because of the limitations of the acquisition technique, such visualisations often lack the desired visual appeal and quality, mostly because certain types of objects are incomplete or entirely missing (e.g., missing water surfaces, missing building walls and missing parts of the terrain). To improve the quality of direct LiDAR point-cloud rendering, we present a point-cloud processing pipeline that uses data fusion to augment the data with additional points on water surfaces, building walls and terrain through the use of vector maps of water surfaces and building outlines. In the last step of the pipeline, we also add colour information, and calculate point normals for illumination of individual points to make the final visualisation more visually appealing. We evaluate our approach on several parts of the Slovenian LiDAR dataset.

V-RBNN Based Small Drone Detection in Augmented Datasets for 3D LADAR System.

A common countermeasure to detect threatening drones is the electro-optical infrared (EO/IR) system. However, its performance is drastically reduced in conditions of complex background, saturation and light reflection. 3D laser sensor LiDAR is used to overcome the problems of 2D sensors like EO/IR, but it is not enough to detect small drones at a very long distance because of low laser energy and resolution. To solve this problem, A 3D LADAR sensor is under development. In this work, we study the detection methodology adequate to the LADAR sensor which can detect small drones at up to 2 km. First, a data augmentation method is proposed to generate a virtual target considering the laser beam and scanning characteristics, and to augment it with the actual LADAR sensor data for various kinds of tests before full hardware system developed. Second, a detection algorithm is proposed to detect drones using voxel-based background subtraction and variable radially bounded nearest neighbor (V-RBNN) method. The results show that 0.2 m L2 distance and 60% expected average overlap (EAO) indexes are satisfied for the required specification to detect 0.3 m size of small drones.