Self-adaptive deep learning-based segmentation for universal and functional clinical and preclinical CT image analysis.

BACKGROUND: Methods to monitor cardiac functioning non-invasively can accelerate preclinical and clinical research into novel treatment options for heart failure. However, manual image analysis of cardiac substructures is resource-intensive and error-prone. While automated methods exist for clinical CT images, translating these to preclinical µCT data is challenging. We employed deep learning to automate the extraction of quantitative data from both CT and µCT images. METHODS: We collected a public dataset of cardiac CT images of human patients, as well as acquired µCT images of wild-type and accelerated aging mice. The left ventricle, myocardium, and right ventricle were manually segmented in the µCT training set. After template-based heart detection, two separate segmentation neural networks were trained using the nnU-Net framework. RESULTS: The mean Dice score of the CT segmentation results (0.925 ± 0.019, n = 40) was superior to those achieved by state-of-the-art algorithms. Automated and manual segmentations of the µCT training set were nearly identical. The estimated median Dice score (0.940) of the test set results was comparable to existing methods. The automated volume metrics were similar to manual expert observations. In aging mice, ejection fractions had significantly decreased, and myocardial volume increased by age 24 weeks. CONCLUSIONS: With further optimization, automated data extraction expands the application of (µ)CT imaging, while reducing subjectivity and workload. The proposed method efficiently measures the left and right ventricular ejection fraction and myocardial mass. With uniform translation between image types, cardiac functioning in diastolic and systolic phases can be monitored in both animals and humans.

Distinct mobility patterns of BRCA2 molecules at DNA damage sites.

BRCA2 is an essential tumor suppressor protein involved in promoting faithful repair of DNA lesions. The activity of BRCA2 needs to be tuned precisely to be active when and where it is needed. Here, we quantified the spatio-temporal dynamics of BRCA2 in living cells using aberration-corrected multifocal microscopy (acMFM). Using multicolor imaging to identify DNA damage sites, we were able to quantify its dynamic motion patterns in the nucleus and at DNA damage sites. While a large fraction of BRCA2 molecules localized near DNA damage sites appear immobile, an additional fraction of molecules exhibits subdiffusive motion, providing a potential mechanism to retain an increased number of molecules at DNA lesions. Super-resolution microscopy revealed inhomogeneous localization of BRCA2 relative to other DNA repair factors at sites of DNA damage. This suggests the presence of multiple nanoscale compartments in the chromatin surrounding the DNA lesion, which could play an important role in the contribution of BRCA2 to the regulation of the repair process.

Automated image registration of cerebral digital subtraction angiography.

PURPOSE: Our aim is to automatically align digital subtraction angiography (DSA) series, recorded before and after endovascular thrombectomy. Such alignment may enable quantification of procedural success. METHODS: Firstly, we examine the inherent limitations for image registration, caused by the projective characteristics of DSA imaging, in a representative set of image pairs from thrombectomy procedures. Secondly, we develop and assess various image registration methods (SIFT, ORB). We assess these methods using manually annotated point correspondences for thrombectomy image pairs. RESULTS: Linear transformations that account for scale differences are effective in aligning DSA sequences. Two anatomical landmarks can be reliably identified for registration using a U-net. Point-based registration using SIFT and ORB proves to be most effective for DSA registration and are applicable to recordings for all patient sub-types. Image-based techniques are less effective and did not refine the results of the best point-based registration method. CONCLUSION: We developed and assessed an automated image registration approach for cerebral DSA sequences, recorded before and after endovascular thrombectomy. Accurate results were obtained for approximately 85% of our image pairs.

Compartmentalization of androgen receptors at endogenous genes in living cells.

A wide range of nuclear proteins are involved in the spatio-temporal organization of the genome through diverse biological processes such as gene transcription and DNA replication. Upon stimulation by testosterone and translocation to the nucleus, multiple androgen receptors (ARs) accumulate in microscopically discernable foci which are irregularly distributed in the nucleus. Here, we investigated the formation and physical nature of these foci, by combining novel fluorescent labeling techniques to visualize a defined chromatin locus of AR-regulated genes-PTPRN2 or BANP-simultaneously with either AR foci or individual AR molecules. Quantitative colocalization analysis showed evidence of AR foci formation induced by R1881 at both PTPRN2 and BANP loci. Furthermore, single-particle tracking (SPT) revealed three distinct subdiffusive fractional Brownian motion (fBm) states: immobilized ARs were observed near the labeled genes likely as a consequence of DNA-binding, while the intermediate confined state showed a similar spatial behavior but with larger displacements, suggesting compartmentalization by liquid-liquid phase separation (LLPS), while freely mobile ARs were diffusing in the nuclear environment. All together, we show for the first time in living cells the presence of AR-regulated genes in AR foci.

CLASP2 safeguards hematopoietic stem cell properties during mouse and fish development.

Hematopoietic stem cells (HSCs) express a large variety of cell surface receptors that are associated with acquisition of self-renewal and multipotent properties. Correct expression of these receptors depends on a delicate balance between cell surface trafficking, recycling, and degradation and is controlled by the microtubule network and Golgi apparatus, whose roles have hardly been explored during embryonic/fetal hematopoiesis. Here we show that, in the absence of CLASP2, a microtubule-associated protein, the overall production of HSCs is reduced, and the produced HSCs fail to self-renew and maintain their stemness throughout mouse and zebrafish development. This phenotype can be attributed to decreased cell surface expression of the hematopoietic receptor c-Kit, which originates from increased lysosomal degradation in combination with a reduction in trafficking to the plasma membrane. A dysfunctional Golgi apparatus in CLASP2-deficient HSCs seems to be the underlying cause of the c-Kit expression and signaling imbalance.

Objective comparison of methods to decode anomalous diffusion.

Deviations from Brownian motion leading to anomalous diffusion are found in transport dynamics from quantum physics to life sciences. The characterization of anomalous diffusion from the measurement of an individual trajectory is a challenging task, which traditionally relies on calculating the trajectory mean squared displacement. However, this approach breaks down for cases of practical interest, e.g., short or noisy trajectories, heterogeneous behaviour, or non-ergodic processes. Recently, several new approaches have been proposed, mostly building on the ongoing machine-learning revolution. To perform an objective comparison of methods, we gathered the community and organized an open competition, the Anomalous Diffusion challenge (AnDi). Participating teams applied their algorithms to a commonly-defined dataset including diverse conditions. Although no single method performed best across all scenarios, machine-learning-based approaches achieved superior performance for all tasks. The discussion of the challenge results provides practical advice for users and a benchmark for developers.

SMARCAD1-mediated active replication fork stability maintains genome integrity.

The stalled fork protection pathway mediated by breast cancer 1/2 (BRCA1/2) proteins is critical for replication fork stability. However, it is unclear whether additional mechanisms are required to maintain replication fork stability. We describe a hitherto unknown mechanism, by which the SWI/SNF-related matrix-associated actin-dependent regulator of chromatin subfamily-A containing DEAD/H box-1 (SMARCAD1) stabilizes active replication forks, that is essential to maintaining resistance towards replication poisons. We find that SMARCAD1 prevents accumulation of 53BP1-associated nucleosomes to preclude toxic enrichment of 53BP1 at the forks. In the absence of SMARCAD1, 53BP1 mediates untimely dissociation of PCNA via the PCNA-unloader ATAD5, causing frequent fork stalling, inefficient fork restart, and accumulation of single-stranded DNA. Although loss of 53BP1 in SMARCAD1 mutants rescues these defects and restores genome stability, this rescued stabilization also requires BRCA1-mediated fork protection. Notably, fork protection-challenged BRCA1-deficient naïve- or chemoresistant tumors require SMARCAD1-mediated active fork stabilization to maintain unperturbed fork progression and cellular proliferation.

Protein Phosphatase 2B Dual Function Facilitates Synaptic Integrity and Motor Learning.

Protein phosphatase 2B (PP2B) is critical for synaptic plasticity and learning, but the molecular mechanisms involved remain unclear. Here we identified different types of proteins that interact with PP2B, including various structural proteins of the postsynaptic densities (PSDs) of Purkinje cells (PCs) in mice. Deleting PP2B reduced expression of PSD proteins and the relative thickness of PSD at the parallel fiber to PC synapses, whereas reexpression of inactive PP2B partly restored the impaired distribution of nanoclusters of PSD proteins, together indicating a structural role of PP2B. In contrast, lateral mobility of surface glutamate receptors solely depended on PP2B phosphatase activity. Finally, the level of motor learning covaried with both the enzymatic and nonenzymatic functions of PP2B. Thus, PP2B controls synaptic function and learning both through its action as a phosphatase and as a structural protein that facilitates synapse integrity.SIGNIFICANCE STATEMENT Phosphatases are generally considered to serve their critical role in learning and memory through their enzymatic operations. Here, we show that protein phosphatase 2B (PP2B) interacts with structural proteins at the synapses of cerebellar Purkinje cells. Differentially manipulating the enzymatic and structural domains of PP2B leads to different phenotypes in cerebellar learning. We propose that PP2B is crucial for cerebellar learning via two complementary actions, an enzymatic and a structural operation.

Concerted action of kinesins KIF5B and KIF13B promotes efficient secretory vesicle transport to microtubule plus ends.

Intracellular transport relies on multiple kinesins, but it is poorly understood which kinesins are present on particular cargos, what their contributions are and whether they act simultaneously on the same cargo. Here, we show that Rab6-positive secretory vesicles are transported from the Golgi apparatus to the cell periphery by kinesin-1 KIF5B and kinesin-3 KIF13B, which determine the location of secretion events. KIF5B plays a dominant role, whereas KIF13B helps Rab6 vesicles to reach freshly polymerized microtubule ends, to which KIF5B binds poorly, likely because its cofactors, MAP7-family proteins, are slow in populating these ends. Sub-pixel localization demonstrated that during microtubule plus-end directed transport, both kinesins localize to the vesicle front and can be engaged on the same vesicle. When vesicles reverse direction, KIF13B relocates to the middle of the vesicle, while KIF5B shifts to the back, suggesting that KIF5B but not KIF13B undergoes a tug-of-war with a minus-end directed motor.

Deep-learning method for data association in particle tracking.

MOTIVATION: Biological studies of dynamic processes in living cells often require accurate particle tracking as a first step toward quantitative analysis. Although many particle tracking methods have been developed for this purpose, they are typically based on prior assumptions about the particle dynamics, and/or they involve careful tuning of various algorithm parameters by the user for each application. This may make existing methods difficult to apply by non-expert users and to a broader range of tracking problems. Recent advances in deep-learning techniques hold great promise in eliminating these disadvantages, as they can learn how to optimally track particles from example data. RESULTS: Here, we present a deep-learning-based method for the data association stage of particle tracking. The proposed method uses convolutional neural networks and long short-term memory networks to extract relevant dynamics features and predict the motion of a particle and the cost of linking detected particles from one time point to the next. Comprehensive evaluations on datasets from the particle tracking challenge demonstrate the competitiveness of the proposed deep-learning method compared to the state of the art. Additional tests on real-time-lapse fluorescence microscopy images of various types of intracellular particles show the method performs comparably with human experts. AVAILABILITY AND IMPLEMENTATION: The software code implementing the proposed method as well as a description of how to obtain the test data used in the presented experiments will be available for non-commercial purposes from https://github.com/yoyohoho0221/pt_linking. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Multifaceted actions of Zeb2 in postnatal neurogenesis from the ventricular-subventricular zone to the olfactory bulb.

The transcription factor Zeb2 controls fate specification and subsequent differentiation and maturation of multiple cell types in various embryonic tissues. It binds many protein partners, including activated Smad proteins and the NuRD co-repressor complex. How Zeb2 subdomains support cell differentiation in various contexts has remained elusive. Here, we studied the role of Zeb2 and its domains in neurogenesis and neural differentiation in the young postnatal ventricular-subventricular zone (V-SVZ), in which neural stem cells generate olfactory bulb-destined interneurons. Conditional Zeb2 knockouts and separate acute loss- and gain-of-function approaches indicated that Zeb2 is essential for controlling apoptosis and neuronal differentiation of V-SVZ progenitors before and after birth, and we identified Sox6 as a potential downstream target gene of Zeb2. Zeb2 genetic inactivation impaired the differentiation potential of the V-SVZ niche in a cell-autonomous fashion. We also provide evidence that its normal function in the V-SVZ also involves non-autonomous mechanisms. Additionally, we demonstrate distinct roles for Zeb2 protein-binding domains, suggesting that Zeb2 partners co-determine neuronal output from the mouse V-SVZ in both quantitative and qualitative ways in early postnatal life.

Dynamic coronary roadmapping via catheter tip tracking in X-ray fluoroscopy with deep learning based Bayesian filtering.

Percutaneous coronary intervention (PCI) is typically performed with image guidance using X-ray angiograms in which coronary arteries are opacified with X-ray opaque contrast agents. Interventional cardiologists typically navigate instruments using non-contrast-enhanced fluoroscopic images, since higher use of contrast agents increases the risk of kidney failure. When using fluoroscopic images, the interventional cardiologist needs to rely on a mental anatomical reconstruction. This paper reports on the development of a novel dynamic coronary roadmapping approach for improving visual feedback and reducing contrast use during PCI. The approach compensates cardiac and respiratory induced vessel motion by ECG alignment and catheter tip tracking in X-ray fluoroscopy, respectively. In particular, for accurate and robust tracking of the catheter tip, we proposed a new deep learning based Bayesian filtering method that integrates the detection outcome of a convolutional neural network and the motion estimation between frames using a particle filtering framework. The proposed roadmapping and tracking approaches were validated on clinical X-ray images, achieving accurate performance on both catheter tip tracking and dynamic coronary roadmapping experiments. In addition, our approach runs in real-time on a computer with a single GPU and has the potential to be integrated into the clinical workflow of PCI procedures, providing cardiologists with visual guidance during interventions without the need of extra use of contrast agent.

Particle Mobility Analysis Using Deep Learning and the Moment Scaling Spectrum.

Quantitative analysis of dynamic processes in living cells using time-lapse microscopy requires not only accurate tracking of every particle in the images, but also reliable extraction of biologically relevant parameters from the resulting trajectories. Whereas many methods exist to perform the tracking task, there is still a lack of robust solutions for subsequent parameter extraction and analysis. Here a novel method is presented to address this need. It uses for the first time a deep learning approach to segment single particle trajectories into consistent tracklets (trajectory segments that exhibit one type of motion) and then performs moment scaling spectrum analysis of the tracklets to estimate the number of mobility classes and their associated parameters, providing rich fundamental knowledge about the behavior of the particles under study. Experiments on in-house datasets as well as publicly available particle tracking data for a wide range of proteins with different dynamic behavior demonstrate the broad applicability of the method.

Automated Neuron Detection in High-Content Fluorescence Microscopy Images Using Machine Learning.

The study of neuronal morphology in relation to function, and the development of effective medicines to positively impact this relationship in patients suffering from neurodegenerative diseases, increasingly involves image-based high-content screening and analysis. The first critical step toward fully automated high-content image analyses in such studies is to detect all neuronal cells and distinguish them from possible non-neuronal cells or artifacts in the images. Here we investigate the performance of well-established machine learning techniques for this purpose. These include support vector machines, random forests, k-nearest neighbors, and generalized linear model classifiers, operating on an extensive set of image features extracted using the compound hierarchy of algorithms representing morphology, and the scale-invariant feature transform. We present experiments on a dataset of rat hippocampal neurons from our own studies to find the most suitable classifier(s) and subset(s) of features in the common practical setting where there is very limited annotated data for training. The results indicate that a random forests classifier using the right feature subset ranks best for the considered task, although its performance is not statistically significantly better than some support vector machine based classification models.

An objective comparison of cell-tracking algorithms.

We present a combined report on the results of three editions of the Cell Tracking Challenge, an ongoing initiative aimed at promoting the development and objective evaluation of cell segmentation and tracking algorithms. With 21 participating algorithms and a data repository consisting of 13 data sets from various microscopy modalities, the challenge displays today's state-of-the-art methodology in the field. We analyzed the challenge results using performance measures for segmentation and tracking that rank all participating methods. We also analyzed the performance of all of the algorithms in terms of biological measures and practical usability. Although some methods scored high in all technical aspects, none obtained fully correct solutions. We found that methods that either take prior information into account using learning strategies or analyze cells in a global spatiotemporal video context performed better than other methods under the segmentation and tracking scenarios included in the challenge.

EB1 and EB3 regulate microtubule minus end organization and Golgi morphology.

End-binding proteins (EBs) are the core components of microtubule plus end tracking protein complexes, but it is currently unknown whether they are essential for mammalian microtubule organization. Here, by using CRISPR/Cas9-mediated knockout technology, we generated stable cell lines lacking EB2 and EB3 and the C-terminal partner-binding half of EB1. These cell lines show only mild defects in cell division and microtubule polymerization. However, the length of CAMSAP2-decorated stretches at noncentrosomal microtubule minus ends in these cells is reduced, microtubules are detached from Golgi membranes, and the Golgi complex is more compact. Coorganization of microtubules and Golgi membranes depends on the EB1/EB3-myomegalin complex, which acts as membrane-microtubule tether and counteracts tight clustering of individual Golgi stacks. Disruption of EB1 and EB3 also perturbs cell migration, polarity, and the distribution of focal adhesions. EB1 and EB3 thus affect multiple interphase processes and have a major impact on microtubule minus end organization.

Automated Analysis of Intracellular Dynamic Processes.

The study of intracellular dynamic processes is of fundamental importance for understanding a wide variety of diseases and developing effective drugs and therapies. Advanced fluorescence microscopy imaging systems nowadays allow the recording of virtually any type of process in space and time with super-resolved detail and with high sensitivity and specificity. The large volume and high information content of the resulting image data, and the desire to obtain objective, quantitative descriptions and biophysical models of the processes of interest, require a high level of automation in data analysis. Two key tasks in extracting biologically meaningful information about intracellular dynamics from image data are particle tracking and particle trajectory analysis. Here we present state-of-the-art software tools for these tasks and describe how to use them.

Stochastic optimization with randomized smoothing for image registration.

Image registration is typically formulated as an optimization process, which aims to find the optimal transformation parameters of a given transformation model by minimizing a cost function. Local minima may exist in the optimization landscape, which could hamper the optimization process. To eliminate local minima, smoothing the cost function would be desirable. In this paper, we investigate the use of a randomized smoothing (RS) technique for stochastic gradient descent (SGD) optimization, to effectively smooth the cost function. In this approach, Gaussian noise is added to the transformation parameters prior to computing the cost function gradient in each iteration of the SGD optimizer. The approach is suitable for both rigid and nonrigid registrations. Experiments on synthetic images, cell images, public CT lung data, and public MR brain data demonstrate the effectiveness of the novel RS technique in terms of registration accuracy and robustness.

A Hidden Markov Model for 3D Catheter Tip Tracking With 2D X-ray Catheterization Sequence and 3D Rotational Angiography.

In minimal invasive image guided catheterization procedures, physicians require information of the catheter position with respect to the patient's vasculature. However, in fluoroscopic images, visualization of the vasculature requires toxic contrast agent. Static vasculature roadmapping, which can reduce the usage of iodine contrast, is hampered by the breathing motion in abdominal catheterization. In this paper, we propose a method to track the catheter tip inside the patient's 3D vessel tree using intra-operative single-plane 2D X-ray image sequences and a peri-operative 3D rotational angiography (3DRA). The method is based on a hidden Markov model (HMM) where states of the model are the possible positions of the catheter tip inside the 3D vessel tree. The transitions from state to state model the probabilities for the catheter tip to move from one position to another. The HMM is updated following the observation scores, based on the registration between the 2D catheter centerline extracted from the 2D X-ray image, and the 2D projection of 3D vessel tree centerline extracted from the 3DRA. The method is extensively evaluated on simulated and clinical datasets acquired during liver abdominal catheterization. The evaluations show a median 3D tip tracking error of 2.3 mm with optimal settings in simulated data. The registered vessels close to the tip have a median distance error of 4.7 mm with angiographic data and optimal settings. Such accuracy is sufficient to help the physicians with an up-to-date roadmapping. The method tracks in real-time the catheter tip and enables roadmapping during catheterization procedures.

Isolation of Functional Tubulin Dimers and of Tubulin-Associated Proteins from Mammalian Cells.

The microtubule (MT) cytoskeleton forms a dynamic filamentous network that is essential for many processes, including mitosis, cell polarity and shape, neurite outgrowth and migration, and ciliogenesis [1, 2]. MTs are built up of α/ß-tubulin heterodimers, and their dynamic behavior is in part regulated by tubulin-associated proteins (TAPs). Here we describe a novel system to study mammalian tubulins and TAPs. We co-expressed equimolar amounts of triple-tagged α-tubulin and ß-tubulin using a 2A "self-cleaving" peptide and isolated functional fluorescent tubulin dimers from transfected HEK293T cells with a rapid two-step approach. We also produced two mutant tubulins that cause brain malformations in tubulinopathy patients [3]. We then applied a paired mass-spectrometry-based method to identify tubulin-binding proteins in HEK293T cells and describe both novel and known TAPs. We find that CKAP5 and the CLASPs, which are MT plus-end-tracking proteins with TOG(L)-domains [4], bind tubulin efficiently, as does the Golgi-associated protein GCC185, which interacts with the CLASPs [5]. The N-terminal TOGL domain of CLASP1 contributes to tubulin binding and allows CLASP1 to function as an autonomous MT-growth-promoting factor. Interestingly, mutant tubulins bind less well to a number of TAPs, including CLASPs and GCC185, and incorporate less efficiently into cellular MTs. Moreover, expression of these mutants in cells impairs several MT-growth-related processes involving TAPs. Thus, stable tubulin-TAP interactions regulate MT nucleation and growth in cells. Combined, our results provide a resource for investigating tubulin interactions and functions and widen the spectrum of tubulin-related disease mechanisms.