“Brainless” cells, the living constituents inhabiting all biological materials, exhibit remarkably smart, i.e., stimuli-responsive and adaptive, behavior. The emergent spatial and temporal patterns of adaptation, observed as changes in cellular connectivity and tissue remodeling by cells, underpin neuroplasticity, muscle memory, immunological imprinting, and sentience itself, in diverse physiological systems from brain to bone. Connectomics addresses the direct connectivity of cells and cells’ adaptation to dynamic environments through manufacture of extracellular matrix, forming tissues and architectures comprising interacting organs and systems of organisms. There is imperative to understand the physical renderings of cellular experience throughout life, from the time of emergence, to growth, adaptation and aging-associated degeneration of tissues. Here we address this need through development of technological approaches that incorporate cross length scale (nm to m) structural data, acquired via multibeam scanning electron microscopy, with machine learning and information transfer using network modeling approaches. This pilot case study uses cutting edge imaging methods for nano- to meso-scale study of cellular inhabitants within human hip tissue resected during the normal course of hip replacement surgery. We discuss the technical approach and workflow and identify the resulting opportunities as well as pitfalls to avoid, delineating a path for cellular connectomics studies in diverse tissue/organ environments and their interactions within organisms and across species. Finally, we discuss the implications of the outlined approach for neuromechanics and the control of physical behavior and neuromuscular training.

Zusammenfassung Der Zylinderkopf und das Kurbelgehäuse gehören zu den meist beanspruchten Gussbauteilen im Verbrennungsmotor. Die hohe Funktionsintegration und der gleichzeitige Wandel der Automobilindustrie zum Leichtbau führen zu geometrisch hochkomplexen sowie mechanisch und thermisch stark belasteten Gussbauteilen. Die Inline-Computertomographie (CT) wird eingesetzt, um die geforderte Auslieferqualität jedes Bauteils im Takt der Fertigungslinie zu garantieren. Die Herausforderung bei der Prüfung besteht in der geringen zur Verfügung stehenden Prüfzeit. Der Takt der Fertigungsstraße, welcher teilweise weniger als eine Minute beträgt, gibt den Zeitrahmen für die Prüfung vor. Eine weitere zu bewältigende Aufgabe entsteht durch den Herstellungsprozess der Bauteile. Der eingesetzte Kokillenguss führt zu individuellen Abweichungen jedes Bauteiles von der Idealgeometrie, was den einfachen Vergleich zur Sollgeometrie unmöglich macht. Durch den Einsatz der CT-Prüfung können diese Abweichungen aufgezeigt, analysiert und bewertet werden. Die umfangreiche Analyse der Zylinderköpfe und Kurbelgehäuse in Kombination mit einem fehlenden Standard für die CT-spezifische Defektauswertung führen zu einem enorm hohen manuellen Aufwand. Der Einfluss des jeweiligen Mitarbeiters prägt dabei ein stark subjektiv beeinflusstes Prüfergebnis für jedes Bauteil. Die im Folgenden beschriebenen Weiterentwicklungen beziehen sich auf die automatische Analyse und Bewertung durch ein Inline-CT für Zylinderköpfe. Im Ergebnis kann eine effiziente Qualitätssicherung bei gleichzeitiger Reduktion des menschlichen Einflusses bei der Bauteilbewertung erreicht werden.

In this paper, we present a fully automatic evaluation approach that can be used for fast inline CT scanning. In contrast to classical defect-recognition algorithms, this approach does not require good image quality. Instead, it allows to distinguish CT artifacts from real defects introduced in the production process. To this end, a three-step workflow was developed, in which any deviations from a reference part are detected and subsequently classified and segmented, to allow automatic decision whether the part fulfills given quality requirements. We demonstrate this approach using CT scans of aluminum castings, typically used in the automotive industry. Also, a comparison between two different segmentation algorithms is shown.

The authors have withdrawn their manuscript after issues with the cell viability validation (Fig. 8) were found. In the interest of furthering science and ensuring that clinical decisions are based on best practices and evidence, the issue is described in more detail in the peer-reviewed, published paper: https://www.frontiersin.org/articles/10.3389/fphys.2021.647603/fullKnothe Tate ML, Srikantha A, Wojek C, Zeidler D (2021) Connectomics of Bone to Brain— Probing Physical Renderings of Cellular Experience, Frontiers in Physiology 12: 1018, doi: 10.3389/fphys.2021.647603As noted in that published work: “Osteocyte coordinates can be extracted from the YOLO classified image set, enabling high throughput analyses of massive datasets, which in the future could include other cellular inhabitants of tissues including blood cells, immune cells, chondrocytes, etc. While the method shows great promise for automated detection of cells, the greatest limitation of the method is the definition of appropriate and unbiased classifiers. The definition of osteocytes as pyknotic and viable based on the number of cell processes was shown to be flawed in a parallel study testing the assumption using biochemical based viability measures (Anastopolous and Knothe Tate, 2021).”Therefore, the authors do not wish this work to be cited as reference for the project.If you have any questions, please contact the corresponding author.

Purpose To develop and evaluate a software tool for automated detection of focal hyperpigmentary changes (FHC) in eyes with intermediate age-related macular degeneration (AMD). Methods Color fundus (CFP) and autofluorescence (AF) photographs of 33 eyes with FHC of 28 AMD patients (mean age 71 years) from the prospective longitudinal natural history MODIAMD-study were included. Fully automated to semiautomated registration of baseline to corresponding follow-up images was evaluated. Following the manual circumscription of individual FHC (four different readings by two readers), a machine-learning algorithm was evaluated for automatic FHC detection. Results The overall pixel distance error for the semiautomated (CFP follow-up to CFP baseline: median 5.7; CFP to AF images from the same visit: median 6.5) was larger as compared for the automated image registration (4.5 and 5.7; P < 0.001 and P < 0.001). The total number of manually circumscribed objects and the corresponding total size varied between 637 to 1163 and 520,848 pixels to 924,860 pixels, respectively. Performance of the learning algorithms showed a sensitivity of 96% at a specificity level of 98% using information from both CFP and AF images and defining small areas of FHC (“speckle appearance”) as “neutral.” Conclusions FHC as a high-risk feature for progression of AMD to late stages can be automatically assessed at different time points with similar sensitivity and specificity as compared to manual outlining. Upon further development of the research prototype, this approach may be useful both in natural history and interventional large-scale studies for a more refined classification and risk assessment of eyes with intermediate AMD. Translational Relevance Automated FHC detection opens the door for a more refined and detailed classification and risk assessment of eyes with intermediate AMD in both natural history and future interventional studies.

We study detecting cell events in phase-contrast microscopy sequences from few annotations. We first detect event candidates from the intensity difference of consecutive frames, and then train an unsupervised novelty detector on these candidates. The novelty detector assigns each candidate a degree of surprise. We annotate a tiny number of candidates chosen according to the novelty detector's output, and finally train a sparse Gaussian process (GP) classifier. We show that the steepest learning curve is achieved when a collaborative multi-output Gaussian process is used as novelty detector, and its predictive mean and variance are used together to measure the degree of surprise. Following this scheme, we closely approximate the fully-supervised event detection accuracy by annotating only 3% of all candidates. The novelty detector based annotation used here clearly outperforms the studied active learning based approaches.

In this paper, we present a novel probabilistic generative model for multi-object traffic scene understanding from movable platforms which reasons jointly about the 3D scene layout as well as the location and orientation of objects in the scene. In particular, the scene topology, geometry, and traffic activities are inferred from short video sequences. Inspired by the impressive driving capabilities of humans, our model does not rely on GPS, lidar, or map knowledge. Instead, it takes advantage of a diverse set of visual cues in the form of vehicle tracklets, vanishing points, semantic scene labels, scene flow, and occupancy grids. For each of these cues, we propose likelihood functions that are integrated into a probabilistic generative model. We learn all model parameters from training data using contrastive divergence. Experiments conducted on videos of 113 representative intersections show that our approach successfully infers the correct layout in a variety of very challenging scenarios. To evaluate the importance of each feature cue, experiments using different feature combinations are conducted. Furthermore, we show how by employing context derived from the proposed method we are able to improve over the state-of-the-art in terms of object detection and object orientation estimation in challenging and cluttered urban environments.

In this work we propose a novel framework for generic event monitoring in live cell culture videos, built on the assumption that unpredictable observations should correspond to biological events. We use a small set of event-free data to train a multioutput multikernel Gaussian process model that operates as an event predictor by performing autoregression on a bank of heterogeneous features extracted from consecutive frames of a video sequence. We show that the prediction error of this model can be used as a probability measure of the presence of relevant events, that can enable users to perform further analysis or monitoring of large-scale non-annotated data. We validate our approach in two phase-contrast sequence data sets containing mitosis and apoptosis events: a new private dataset of human bone cancer (osteosarcoma) cells and a benchmark dataset of stem cells.

Following recent advances in detection, context modeling, and tracking, scene understanding has been the focus of renewed interest in computer vision research. This paper presents a novel probabilistic 3D scene model that integrates state-of-the-art multiclass object detection, object tracking and scene labeling together with geometric 3D reasoning. Our model is able to represent complex object interactions such as inter-object occlusion, physical exclusion between objects, and geometric context. Inference in this model allows us to jointly recover the 3D scene context and perform 3D multi-object tracking from a mobile observer, for objects of multiple categories, using only monocular video as input. Contrary to many other approaches, our system performs explicit occlusion reasoning and is therefore capable of tracking objects that are partially occluded for extended periods of time, or objects that have never been observed to their full extent. In addition, we show that a joint scene tracklet model for the evidence collected over multiple frames substantially improves performance. The approach is evaluated for different types of challenging onboard sequences. We first show a substantial improvement to the state of the art in 3D multipeople tracking. Moreover, a similar performance gain is achieved for multiclass 3D tracking of cars and trucks on a challenging dataset.