Multidimensional Imaging Research Articles

Advances in multi-dimensional single molecule imaging

The predecessor of China Optics was China Optics and Applied Optics Digest, which was founded in 1985. At that time, it was the only retrieval journal in the field of optics in China. At the end of 2008, China Optics and Applied Optics Digest was renamed

Culture of Human iPSC-Derived Motoneurons in Compartmentalized Microfluidic Devices and Quantitative Assays for Studying Axonal Phenotypes.

In order to use induced Pluripotent Stem Cells (iPSCs) to model neurodegenerative diseases, efficient and homogeneous generation of neurons in vitro represents a key step. Here we describe a method to obtain and characterize functional human spinal and cranial motoneurons using a combined approach of microfluidic chips and programs designed for scientific multidimensional imaging. We have used this approach to analyze axonal phenotypes. These tools are useful to investigate the cellular and molecular bases of neuromuscular diseases, including amyotrophic lateral sclerosis and spinal muscular atrophy.

Time-Resolved Fluorescence Microscopy Screens on Host Protein Subversion During Bacterial Cell Invasion.

Intracellular bacterial pathogens have evolved a plethora of strategies to invade eukaryotic cells. By manipulating host signaling pathways, in particular vesicular trafficking, these microbes subvert host functions to promote their internalization and to establish an intracellular niche. During these events, host endomembrane compartments are dynamically reorganized. Shigella flexneri, the causative agent of bacillary dysentery, recruits components of the host recycling pathway and the exocyst of non-phagocytic enterocytes in the vicinity of its entry site to facilitate its access to the host cytosol. These factors are either dynamically tethered to in situ formed macropinosomes or to the bacteria-containing vacuole itself. The underlying interactions cannot readily be monitored as individual bacterial infection events take place without synchronicity using cellular infection models. Therefore, time-resolved screens by fluorescence microscopy represent a powerful tool for the study of host subversion. Such screens can be performed with libraries of fluorescently tagged host factors. Using the cytosolic pathogenic agent Shigella flexneri as a model, we provide detailed protocols for such medium-to-high throughput multidimensional imaging screening of the dynamic host-pathogen cross talk. Our workflow is designed to be easily adapted for the study of different host factor libraries and different pathogen models.

Atypical drainage of a persistent left vena cava superior into the left atrial appendage detected by multidimensional imaging: a\xa0case report and review of the literature

BackgroundWhile it is the most common thoracic venous anomaly, a persistent left vena cava superior may present in atypical variations, which are important to consider during clinical management.Case presentationHere we report a 35-year-old Caucasian female patient with drainage into the left atrial appendage who presented with shortness of breath accompanied by mild hypoxemia. Venous contrast filling in the context of pulmonary scintigraphy suspected an additional superior caval vein connected to the left atrial appendage. Diagnosis was confirmed by transesophageal echocardiography. Cardiac catheterization revealed a minor right-to-left shunt. The symptoms could be allocated to a bronchial asthma and treated according to guidelines. Cerebral lesions detected in the patient were due to a coincident multiple sclerosis rather than cerebral embolisms. Thus, the venous anomaly was classified as an incidental finding currently requiring no treatment.ConclusionsTo the best of our knowledge, this is the first report of a persistent left vena cava superior draining into the left atrial appendage.

Effect of Electroacupuncture on Shoulder Subluxation in Poststroke Patients with Hemiplegic Shoulder Pain: A Sham-Controlled Study Using Multidimensional Musculoskeletal Ultrasound Assessment.

Objective This study aimed to use multidimensional musculoskeletal ultrasound imaging technique to investigate the effect of electroacupuncture (EA) on shoulder subluxation in poststroke patients with hemiplegic shoulder pain. Methods In this prospective single-blind, randomized, sham-controlled study, thirty-four patients with shoulder subluxation and hemiplegic shoulder pain were recruited and randomly assigned into the EA group or the sham EA (SEA) group. In the EA group, EA was applied to the Jian yu (LI15), Bi nao (LI14), Jian zhen (SI9), and Jian liao (TE14) acupoints. In the SEA group, the EA was applied 15 mm away from the Lou gu (SP7), Di ji (SP8), Jiao xin (KI8), and Zhu bin (KI9) acupoints. Both groups underwent treatment 30 minutes/day, five days a week, for two weeks using dense waves with a frequency of 2/100 Hz. A Visual Analogue Scale (VAS) was used to evaluate the effectiveness of treatment in reducing shoulder pain. Musculoskeletal ultrasound was used to evaluate the changes of measures of shoulder subluxation in multidimensions (i.e., the acromiohumeral distance, AHD; acromion-greater tuberosity, AGT; and acromion-lesser tuberosity, ALT). Both the within- and between-groups treatment effects were assessed. Results The pain intensity measured by VAS and shoulder subluxation measured by musculoskeletal ultrasound (i.e., AHD, AGT, and ALT) showed significant (p < 0.05) within-group difference in both groups. The between-group difference appeared in the pain intensity (p < 0.05), while it disappeared in the three measures of shoulder subluxation (p > 0.05). Conclusions Using VAS for measuring pain intensity and multidimensional musculoskeletal ultrasound imaging technique for measuring shoulder subluxation, this study finds that the hemiplegic shoulder pain can be improved significantly by the EA while the shoulder subluxation cannot be. Our findings further reveal the analgesic mechanism of EA on hemiplegic shoulder pain following stroke.

Optical signal detection in turbid water using multidimensional integral imaging with deep learning.

Optical signal detection in turbid and occluded environments is a challenging task due to the light scattering and beam attenuation inside the medium. Three-dimensional (3D) integral imaging is an imaging approach which integrates two-dimensional images from multiple perspectives and has proved to be useful for challenging conditions such as occlusion and turbidity. In this manuscript, we present an approach for the detection of optical signals in turbid water and occluded environments using multidimensional integral imaging employing temporal encoding with deep learning. In our experiments, an optical signal is temporally encoded with gold code and transmitted through turbid water via a light-emitting diode (LED). A camera array captures videos of the optical signals from multiple perspectives and performs the 3D signal reconstruction of temporal signal. The convolutional neural network-based bidirectional Long Short-Term Network (CNN-BiLSTM) network is trained with clear water video sequences to perform classification on the binary transmitted signal. The testing data was collected in turbid water scenes with partial signal occlusion, and a sliding window with CNN-BiLSTM-based classification was performed on the reconstructed 3D video data to detect the encoded binary data sequence. The proposed approach is compared to previously presented correlation-based detection models. Furthermore, we compare 3D integral imaging to conventional two-dimensional (2D) imaging for signal detection using the proposed deep learning strategy. The experimental results using the proposed approach show that the multidimensional integral imaging-based methodology significantly outperforms the previously reported approaches and conventional 2D sensing-based methods. To the best of our knowledge, this is the first report on underwater signal detection using multidimensional integral imaging with deep neural networks.

Recent Advances of Manganese-Based Hybrid Nanomaterials for Cancer Precision Medicine.

Cancer precision medicine (CPM) could tailor the best treatment for individual cancer patients, while imaging techniques play important roles in its application. With the characteristics of noninvasion, nonionized, radiation-free, multidimensional imaging function, and real-time monitoring, magnetic resonance imaging (MRI) is an effective way for early tumor detection, and it has become a tower of strength in CPM imaging techniques. Due to linkage with nephrogenic systemic fibrosis (NSF), gadolinium (Gd)-based contrast agent (CA), which was long used in MRI, has been restricted by the Food and Drug Administration (FDA). In this review, we would like to introduce the manganese (Mn)-based CAs that could significantly increase the safety of MRI CAs by realizing more superior performance and functions simultaneously in the diagnosis and treatment of tumors. Also, recent advances in Mn-based hybrid nanomaterials for CPM are summarized and discussed.

A FRET pair for quantitative and superresolution imaging of amyloid fibril formation

The presence of neuritic plaques and amyloid fibrils arising from the misfolding of certain proteins is the principal molecular indicator of neurodegenerative diseases such as Alzheimer's and Parkinson's disease. Methodologies for studying the early stages of amyloid aggregation are rapidly arising to provide a better understanding of the mechanism of fibrillization and cytotoxicity and to identify potential targets for diagnosis and therapy. The method presented here involves the simultaneous use of two different fluorophores, a quinolimide derivative and Nile Blue A. These are capable of interacting with and reporting on the formation of preamyloid aggregates and fibrils of apoferritin through fluorescence resonance energy transfer (FRET), which occurs between them, thus maximizing the contrast in detection and quantitative information of such amyloid species by using multidimensional fluorescence lifetime imaging microscopy (FLIM).

Modeling the magnetization dynamics for large ensembles of immobilized magnetic nanoparticles in multi-dimensional magnetic particle imaging

Magnetic nanoparticles (MNPs) play an important role in biomedical applications including imaging modalities such as magnetic resonance imaging (MRI) and magnetic particle imaging (MPI). The latter one exploits the non-linear magnetization response of a large ensemble of magnetic nanoparticles to magnetic fields which allows determining the spatial distribution of the MNP concentration from measured voltage signals. The image-to-voltage mapping is linear and described by a system matrix. Currently, modeling the voltage signals of large ensembles of MNPs in an MPI environment is not yet accurately possible, especially for liquid tracers in multi-dimensional magnetic excitation fields. As an immediate consequence, the system matrix is still obtained in a time consuming calibration procedure. While the ferrofluidic case can be seen as the typical setting, more recently immobilized and potentially oriented MNPs have received considerable attention. By aligning the particles magnetic easy axis during immobilization one can encode the angle of the particle’s magnetic easy axis into the magnetization response providing a relevant benchmark system for model-based approaches. In this work we address the modeling problem for immobilized and oriented MNPs in the context of MPI. We investigate a model-based approach where the magnetization response is simulated by a Néel rotation model for the particle’s magnetic moments and the ensemble magnetization is obtained by solving a Fokker–Planck equation approach. Since the parameters of the model are a-priori unknown, we investigate different methods for performing a parameter identification and discuss two different models: One where a single function vector is used from the space spanned by the model parameters and another where a superposition of function vectors is considered. We show that our model can much more accurately reproduce the orientation dependent signal response when compared to the equilibrium model, which marks the current state-of-the-art for model-based system matrix simulations in MPI.

Multi-dimensional and spatiotemporal correlative imaging at the plasma membrane of live cells to determine the continuum nano-to-micro scale lipid adaptation and collective motion.

The primary cilium is a specialized plasma membrane protrusion with important receptors for signalling pathways. In polarized epithelial cells, the primary cilium assembles after the midbody remnant (MBR) encounters the centrosome at the apical surface. The membrane surrounding the MBR, namely remnant-associated membrane patch (RAMP), once situated next to the centrosome, releases some of its lipid components to form a centrosome-associated membrane patch (CAMP) from which the ciliary membrane stems. The RAMP undergoes a spatiotemporal membrane refinement during the formation of the CAMP, which becomes highly enriched in condensed membranes with low lateral mobility. To better understand this process, we have developed a correlative imaging approach that yields quantitative information about the lipid lateral packing, its mobility and collective assembly at the plasma membrane at different spatial scales over time. Our work paves the way towards a quantitative understanding of the spatiotemporal lipid collective assembly at the plasma membrane as a functional determinant in cell biology and its direct correlation with the membrane physicochemical state. These findings allowed us to gain a deeper insight into the mechanisms behind the biogenesis of the ciliary membrane of polarized epithelial cells.

Automatic feature extraction and fusion recognition of motor imagery EEG using multilevel multiscale CNN.

A motor imagery EEG (MI-EEG) signal is often selected as the driving signal in an active brain computer interface (BCI) system, and it has been a popular field to recognize MI-EEG images via convolutional neural network (CNN), which poses a potential problem for maintaining the integrity of the time-frequency-space information in MI-EEG images and exploring the feature fusion mechanism in the CNN. However, information is excessively compressed in the present MI-EEG image, and the sequential CNN is unfavorable for the comprehensive utilization of local features. In this paper, a multidimensional MI-EEG imaging method is proposed, which is based on time-frequency analysis and the Clough-Tocher (CT) interpolation algorithm. The time-frequency matrix of each electrode is generated via continuous wavelet transform (WT), and the relevant section of frequency is extracted and divided into nine submatrices, the longitudinal sums and lengths of which are calculated along the directions of frequency and time successively to produce a 3 × 3 feature matrix for each electrode. Then, feature matrix of each electrode is interpolated to coincide with their corresponding coordinates, thereby yielding a WT-based multidimensional image, called WTMI. Meanwhile, a multilevel and multiscale feature fusion convolutional neural network (MLMSFFCNN) is designed for WTMI, which has dense information, low signal-to-noise ratio, and strong spatial distribution. Extensive experiments are conducted on the BCI Competition IV 2a and 2b datasets, and accuracies of 92.95% and 97.03% are yielded based on 10-fold cross-validation, respectively, which exceed those of the state-of-the-art imaging methods. The kappa values and p values demonstrate that our method has lower class skew and error costs. The experimental results demonstrate that WTMI can fully represent the time-frequency-space features of MI-EEG and that MLMSFFCNN is beneficial for improving the collection of multiscale features and the fusion recognition of general and abstract features for WTMI.

Expression of miR-200c corresponds with increased reactive oxygen species and hypoxia markers after transient focal ischemia in mice

Embolic stroke results in a necrotic core of cells destined to die, but also a peri-ischemic, watershed penumbral region of potentially salvageable brain tissue. Approaches to effectively differentiate between the ischemic and peri-ischemic zones is critical for novel therapeutic discovery to improve outcomes in survivors of stroke. MicroRNAs are a class of small non-coding RNAs regulating gene translation that have region- and cell-specific expression and responses to ischemia. We have previously reported that global inhibition of cerebral microRNA-200c after experimental stroke in mice is protective, however delineating the post-stroke sub-regional and cell-type specific patterns of post-stroke miR-200c expression are necessary to minimize off-target effects and advance translational application. Here, we detail a novel protocol to visualize regional miR-200c expression after experimental stroke, complexed with visualization of regional ischemia and markers of oxidative stress in an experimental stroke model in mice. In the present study we demonstrate that the fluorescent hypoxia indicator pimonidazole hydrochloride, the reactive-oxygen-species marker 8-hydroxy-deoxyguanosine, neuronal marker MAP2 and NeuN, and the reactive astrocyte marker GFAP can be effectively complexed to determine regional differences in ischemic injury as early as 30 min post-reperfusion after experimental stroke, and can be effectively used to distinguish ischemic core from surrounding penumbral and unaffected regions for targeted therapy. This multi-dimensional post-stroke immunofluorescent imaging protocol enables a greater degree of sub-regional mechanistic investigation, with the ultimate goal of developing more effective post-stroke pharmaceutical therapy.

Multi-Dimensional Diffusion Tensor Imaging Biomarkers for Cognitive Decline From the Preclinical Stage: A Study of Post-stroke Small Vessel Disease.

Objectives: We aim to investigate whether multi-dimensional diffusion tensor imaging (DTI) measures can sensitively identify different cognitive status of cerebral small vessel disease (CSVD) and to explore the underlying pattern of white matter disruption in CSVD.Methods: Two hundred and two participants were recruited, composed of 99 CSVD patients with mild cognitive impairment (VaMCI) and 60 with no cognitive impairment (NCI) and 43 healthy subjects as normal controls (NC). Full domain neuropsychological tests and diffusion-weighted imaging were performed on each subject. DTI metrics such as fractional anisotropy (FA), mean diffusivity (MD), the skeletonized mean diffusivity (PSMD), and structural brain network measures including network strength, global efficiency (EGlobal), and local efficiency (ELocal) were calculated. Region of interest (ROI) analysis of 42 white matter tracts was performed to examine the regional anatomical white matter disruption for each group.Results: Significant differences of multiple cognitive test scores across all cognitive domains especially processing and executive function existed among the three groups. DTI measures (FA, MD, and PSMD) showed significant group difference with the cognitive status changing. FA and EGlobal showed significant correlation with processing speed, executive function, and memory. ROI analysis found that white matter integrity impairment occurred from the preclinical stage of vascular cognitive impairment (VCI) due to CSVD. These lesions in the NCI group mainly involved some longitudinal fibers such as right superior longitudinal fasciculus (SLF-R), right superior fronto-occipital fasciculus (SFO-R), and right uncinate fasciculus (UNC-R), which might be more vulnerable to the cerebrovascular aging and disease process.Conclusions: DTI measures are sensitive neuroimaging markers in detecting the early cognitive impairment and able to differentiate the different cognitive status due to CSVD. Subtle changes of some vulnerable white matter tracts may be observed from the preclinical stage of VCI and have a local to general spreading pattern during the disease progression.

Multi-photon absorption properties of semiconducting nanomaterials

Multiphoton absorption (MPA) is a nonlinear optical process that involves simultaneous absorption of two or more photons by a material to promote its ground state to an excited state. Multiphoton absorption promises many important applications such as multi-dimensional fluorescence imaging, three dimensional (3D) data storage. Physical and chemical properties of nanometer sized semiconductor materials change drastically due to quantum size effect. Combination of both multiphoton absorption and quantum effects will be an interesting study. Multiphoton absorption of semiconducting nanomaterials is an exciting phenomenon which promotes many important applications. This paper reviews multi-photon absorption properties of different kinds of semiconducting nanomaterials starting from chalcogenide-based nanomaterials to perovskites nanomaterials and their applications in various fields.

A Pilot Study of Multidimensional Diffusion MRI for Assessment of Tissue Heterogeneity in Prostate Cancer.

The objectives of this exploratory study were to investigate the feasibility of multidimensional diffusion magnetic resonance imaging (MddMRI) in assessing diffusion heterogeneity at both a macroscopic and microscopic level in prostate cancer (PCa). Informed consent was obtained from 46 subjects who underwent 3.0-T prostate multiparametric MRI, complemented with a prototype spin echo-based MddMRI sequence in this institutional review board-approved study. Prostate cancer tumors and comparative normal tissue from each patient were contoured on both apparent diffusion coefficient and MddMRI-derived mean diffusivity (MD) maps (from which microscopic diffusion heterogeneity [MKi] and microscopic diffusion anisotropy were derived) using 3D Slicer. The discriminative ability of MddMRI-derived parameters to differentiate PCa from normal tissue was determined using the Friedman test. To determine if tumor diffusion heterogeneity is similar on macroscopic and microscopic scales, the linear association between SD of MD and mean MKi was estimated using robust regression (bisquare weighting). Hypothesis testing was 2 tailed; P values less than 0.05 were considered statistically significant. All MddMRI-derived parameters could distinguish tumor from normal tissue in the fixed-effects analysis (P < 0.0001). Tumor MKi was higher (P < 0.05) compared with normal tissue (median, 0.40; interquartile range, 0.29-0.52 vs 0.20-0.18; 0.25), as was tumor microscopic diffusion anisotropy (0.55; 0.36-0.81 vs 0.20-0.15; 0.28). The MKi could not be predicted (no significant association) by SD of MD. There was a significant correlation between tumor volume and SD of MD (R2 = 0.50, slope = 0.008 μm2/ms per millimeter, P < 0.001) but not between tumor volume and MKi. This explorative study demonstrates that MddMRI provides novel information on MKi and microscopic anisotropy, which differ from measures at the macroscopic level. MddMRI has the potential to characterize tumor tissue heterogeneity at different spatial scales.

4-Dimensional Imaging of Zebrafish Optic Cup Morphogenesis

Visual system function requires the establishment of precise tissue and organ structures. In the vertebrate eye, structural defects are a common cause of visual impairment, yet mechanisms of eye morphogenesis are still poorly understood. The basic organization of the embryonic eye is conserved throughout vertebrates, thus live imaging of zebrafish embryos has become a powerful approach to directly observe eye development at real time under normal and pathological conditions. Dynamic cell processes including movements, morphologies, interactions, division, and death can be visualized in the embryo. We have developed methods for uniform labeling of subcellular structures and timelapse confocal microscopy of early eye development in zebrafish. This protocol outlines the method of generating capped mRNA for injection into the 1-cell zebrafish embryo, mounting embryos at optic vesicle stage (~12 hours post fertilization, hpf), and performing multi-dimensional timelapse imaging of optic cup morphogenesis on a laser scanning confocal microscope, such that multiple datasets are acquired sequentially in the same imaging session. Such an approach yields data that can be used for a variety of purposes, including cell tracking, volume measurements, three-dimensional (3D) rendering, and visualization. Our approaches allow us to pinpoint the cellular and molecular mechanisms driving optic cup development, in both wild type and genetic mutant conditions. These methods can be employed directly by other groups or adapted to visualize many additional aspects of zebrafish eye development.

4-Dimensional Imaging of Zebrafish Optic Cup Morphogenesis.

Visual system function requires the establishment of precise tissue and organ structures. In the vertebrate eye, structural defects are a common cause of visual impairment, yet mechanisms of eye morphogenesis are still poorly understood. The basic organization of the embryonic eye is conserved throughout vertebrates, thus live imaging of zebrafish embryos has become a powerful approach to directly observe eye development at real time under normal and pathological conditions. Dynamic cell processes including movements, morphologies, interactions, division, and death can be visualized in the embryo. We have developed methods for uniform labeling of subcellular structures and timelapse confocal microscopy of early eye development in zebrafish. This protocol outlines the method of generating capped mRNA for injection into the 1-cell zebrafish embryo, mounting embryos at optic vesicle stage (~12 hours post fertilization, hpf), and performing multi-dimensional timelapse imaging of optic cup morphogenesis on a laser scanning confocal microscope, such that multiple datasets are acquired sequentially in the same imaging session. Such an approach yields data that can be used for a variety of purposes, including cell tracking, volume measurements, three-dimensional (3D) rendering, and visualization. Our approaches allow us to pinpoint the cellular and molecular mechanisms driving optic cup development, in both wild type and genetic mutant conditions. These methods can be employed directly by other groups or adapted to visualize many additional aspects of zebrafish eye development.

Molecular and Nonmolecular Imaging of Macrophages in Atherosclerosis.

Atherosclerosis is a major cause of ischemic heart disease, and the increasing medical burden associated with atherosclerotic cardiovascular disease has become a major public health concern worldwide. Macrophages play an important role in all stages of the dynamic progress of atherosclerosis, from its initiation and lesion expansion increasing the vulnerability of plaques, to the formation of unstable plaques and clinical manifestations. Early imaging can identify patients at risk of coronary atherosclerotic disease and its complications, enabling preventive measures to be initiated. Recent advances in molecular imaging have involved the noninvasive and semi-quantitative targeted imaging of macrophages and their related molecules in vivo, which can detect atheroma earlier and more accurately than conventional imaging. Multimodal imaging integrates vascular structure, function, and molecular imaging technology to achieve multi-dimensional imaging, which can be used to comprehensively evaluate blood vessels and obtain clinical information based on anatomical structure and molecular level. At the same time, the rapid development of nonmolecular imaging technologies, such as intravascular imaging, which have the unique advantages of having intuitive accuracy and providing rich information to identify macrophage inflammation and inform targeted personalized treatment, has also been seen. In this review, we highlight recent methods and research hotspots in molecular and nonmolecular imaging of macrophages in atherosclerosis that have enormous potential for rapid clinical application.

White light three-dimensional imaging using a quasi-random lens.

Coded aperture imaging (CAI) technology is a rapidly evolving indirect imaging method with extraordinary potential. In recent years, CAI based on chaotic optical waves have been shown to exhibit multidimensional, multispectral, and multimodal imaging capabilities with a signal to noise ratio approaching the range of lens based direct imagers. However, most of the earlier studies used only narrow band illumination. In this study, CAI based on chaotic optical waves is investigated for white light illumination. A numerical study was carried out using scalar diffraction formulation and correlation optics and the lateral and axial resolving power for different spectral width were compared. A binary diffractive quasi-random lens was fabricated using electron beam lithography and the lateral and axial point spread holograms are recorded for white light. Three-dimensional imaging was demonstrated using thick objects consisting of two planes. An integrated sequence of signal processing tools such as non-linear filter, low-pass filter, median filter and correlation filter were applied to reconstruct images with an improved signal to noise ratio. A denoising deep learning neural network (DLNN) was trained using synthetic noisy images generated by the convolution of recorded point spread functions with the virtual object functions under a wide range of aberrations and noises. The trained DLNN was found to reduce further the reconstruction noises.

Deep Learning-Based ECG-Free Cardiac Navigation for Multi-Dimensional and Motion-Resolved Continuous Magnetic Resonance Imaging.

For the clinical assessment of cardiac vitality, time-continuous tomographic imaging of the heart is used. To further detect e.g., pathological tissue, multiple imaging contrasts enable a thorough diagnosis using magnetic resonance imaging (MRI). For this purpose, time-continous and multi-contrast imaging protocols were proposed. The acquired signals are binned using navigation approaches for a motion-resolved reconstruction. Mostly, external sensors such as electrocardiograms (ECG) are used for navigation, leading to additional workflow efforts. Recent sensor-free approaches are based on pipelines requiring prior knowledge, e.g., typical heart rates. We present a sensor-free, deep learning-based navigation that diminishes the need for manual feature engineering or the necessity of prior knowledge compared to previous works. A classifier is trained to estimate the R-wave timepoints in the scan directly from the imaging data. Our approach is evaluated on 3-D protocols for continuous cardiac MRI, acquired in-vivo and free-breathing with single or multiple imaging contrasts. We achieve an accuracy of > 98% on previously unseen subjects, and a well comparable image quality with the state-of-the-art ECG-based reconstruction. Our method enables an ECG-free workflow for continuous cardiac scans with simultaneous anatomic and functional imaging with multiple contrasts. It can be potentially integrated without adapting the sampling scheme to other continuous sequences by using the imaging data for navigation and reconstruction.