One step surgical scene restoration for robot assisted minimally invasive surgery.

Minimally invasive surgery (MIS) offers several advantages to patients including minimum blood loss and quick recovery time. However, lack of tactile or haptic feedback and poor visualization of the surgical site often result in some unintentional tissue damage. Visualization aspects further limits the collection of imaged frame contextual details, therefore the utility of computational methods such as tracking of tissue and tools, scene segmentation, and depth estimation are of paramount interest. Here, we discuss an online preprocessing framework that overcomes routinely encountered visualization challenges associated with the MIS. We resolve three pivotal surgical scene reconstruction tasks in a single step; namely, (i) denoise, (ii) deblur, and (iii) color correction. Our proposed method provides a latent clean and sharp image in the standard RGB color space from its noisy, blurred, and raw inputs in a single preprocessing step (end-to-end in one step). The proposed approach is compared against current state-of-the-art methods that perform each of the image restoration tasks separately. Results from knee arthroscopy show that our method outperforms existing solutions in tackling high-level vision tasks at a significantly reduced computation time.

Species Dependence of SYTO 9 Staining of Bacteria.

SYTO 9 is a fluorescent nucleic acid stain that is widely used in microbiology, particularly for fluorescence microscopy and flow cytometry analyzes. Fluorimetry-based analysis, i.e., analysis of fluorescence intensity from a bulk sample measurement, is more cost effective, rapid and accessible than microscopy or flow cytometry but requires application-specific calibration. Here we show the relevance of SYTO 9 for food safety analysis. We stained four bacterial species of relevance to food safety (Bacillus cereus, Escherichia coli, Salmonella enterica subspecies enterica ser. Typhimurium, Staphylococcus aureus) with different concentrations of SYTO 9, with and without the presence of ethylenediaminetetraacetic acid (EDTA), for varying amounts of time, to investigate the effect of these treatment parameters on fluorescence intensity. The addition of EDTA and an increased staining duration did not significantly affect fluorescence intensity, and over the bacterial cell concentration range investigated (∼105-108 CFU/ml) there was no significant difference in using 0.5 or 1 µM SYTO 9. The effect of bacterial cell concentration on fluorescence intensity was species specific. At different bacterial cell concentrations, the effect of species on fluorescence intensity is different. This interaction complicates the development of a general fluorimetry-based protocol for the determination of bacterial cell concentration in a mixed bacterial suspension, as would be expected from samples taken from food safety settings.

Extraction of Common Task Features in EEG-fMRI Data Using Coupled Tensor-Tensor Decomposition.

The fusion of simultaneously recorded EEG and fMRI data is of great value to neuroscience research due to the complementary properties of the individual modalities. Traditionally, techniques such as PCA and ICA, which rely on strong non-physiological assumptions such as orthogonality and statistical independence, have been used for this purpose. Recently, tensor decomposition techniques such as parallel factor analysis have gained more popularity in neuroimaging applications as they are able to inherently contain the multidimensionality of neuroimaging data and achieve uniqueness in decomposition without making strong assumptions. Previously, the coupled matrix-tensor decomposition (CMTD) has been applied for the fusion of the EEG and fMRI. Only recently the coupled tensor-tensor decomposition (CTTD) has been proposed. Here for the first time, we propose the use of CTTD of a 4th order EEG tensor (space, time, frequency, and participant) and 3rd order fMRI tensor (space, time, participant), coupled partially in time and participant domains, for the extraction of the task related features in both modalities. We used both the sensor-level and source-level EEG for the coupling. The phase shifted paradigm signals were incorporated as the temporal initializers of the CTTD to extract the task related features. The validation of the approach is demonstrated on simultaneous EEG-fMRI recordings from six participants performing an N-Back memory task. The EEG and fMRI tensors were coupled in 9 components out of which seven components had a high correlation (more than 0.85) with the task. The result of the fusion recapitulates the well-known attention network as being positively, and the default mode network working negatively time-locked to the memory task.

Constrained temporal parallel decomposition for EEG-fMRI fusion.

OBJECTIVE: Multimodal neuroimaging has become a common practice in neuroscience research. Simultaneous EEG-fMRI is a popular multimodal recording approach due to the complementary spatiotemporal relationship between the two modalities. Several data fusion techniques have been proposed in the literature for EEG-fMRI fusion, including joint-ICA and parallel-ICA frameworks. Previous EEG-fMRI fusion approaches have used sensor-level EEG features. Recently, we introduced source-space ICA for EEG-MEG source reconstruction and component identification, which was shown to be a superior alternative to sensor-space ICA. APPROACH: Here, we extend source-space ICA to the fusion of EEG-fMRI data. Additionally, we incorporate the use of a paradigm signal (constrained) and a lag-based signal decomposition approach to accommodate recent findings demonstrating the potentially variable lag structure between electrophysiological and BOLD signals. We evaluated this method on simulated concurrent EEG-fMRI during a boxcar task design, as well as real concurrent EEG-fMRI data from three participants performing an N-Back working memory task. The block diagram of the algorithm and corresponding source codes are provided. MAIN RESULTS: Based on the results of the real working memory task, for all three subjects, one frontal theta component, and one right posterior alpha component had the highest contribution coefficients (~0.5) to the paradigm-related fused component. There were also two more alpha band components with contribution coefficients of 0.3. The highest contributing fMRI component (~0.8) was one known in the literature to be related to the attention network. The second fMRI component was related to the well-known default mode network, with a contribution coefficient of 0.3. SIGNIFICANCE: The proposed EEG-fMRI fusion approach, is capable of estimating the brain maps of the EEG and fMRI for the fused components and account for the variable lag structure between electrophysiological and BOLD signals.

Microsleeps are Associated with Stage-2 Sleep Spindles from Hippocampal-Temporal Network.

Behavioral microsleeps are associated with complete disruption of responsiveness for [Formula: see text][Formula: see text]s to 15[Formula: see text]s. They can result in injury or death, especially in transport and military sectors. In this study, EEGs were obtained from five nonsleep-deprived healthy male subjects performing a 1[Formula: see text]h 2D tracking task. Microsleeps were detected in all subjects. Microsleep-related activities in the EEG were detected, characterized, separated from eye closure-related activity, and, via source-space-independent component analysis and power analysis, the associated sources were localized in the brain. Microsleeps were often, but not always, found to be associated with strong alpha-band spindles originating bilaterally from the anterior temporal gyri and hippocampi. Similarly, theta-related activity was identified as originating bilaterally from the frontal-orbital cortex. The alpha spindles were similar to sleep spindles in terms of frequency, duration, and amplitude-profile, indicating that microsleeps are equivalent to brief instances of Stage-2 sleep.

Source-space ICA for MEG source imaging.

OBJECTIVE: One of the most widely used approaches in electroencephalography/magnetoencephalography (MEG) source imaging is application of an inverse technique (such as dipole modelling or sLORETA) on the component extracted by independent component analysis (ICA) (sensor-space ICA + inverse technique). The advantage of this approach over an inverse technique alone is that it can identify and localize multiple concurrent sources. Among inverse techniques, the minimum-variance beamformers offer a high spatial resolution. However, in order to have both high spatial resolution of beamformer and be able to take on multiple concurrent sources, sensor-space ICA + beamformer is not an ideal combination. APPROACH: We propose source-space ICA for MEG as a powerful alternative approach which can provide the high spatial resolution of the beamformer and handle multiple concurrent sources. The concept of source-space ICA for MEG is to apply the beamformer first and then singular value decomposition + ICA. In this paper we have compared source-space ICA with sensor-space ICA both in simulation and real MEG. The simulations included two challenging scenarios of correlated/concurrent cluster sources. MAIN RESULTS: Source-space ICA provided superior performance in spatial reconstruction of source maps, even though both techniques performed equally from a temporal perspective. Real MEG from two healthy subjects with visual stimuli were also used to compare performance of sensor-space ICA and source-space ICA. We have also proposed a new variant of minimum-variance beamformer called weight-normalized linearly-constrained minimum-variance with orthonormal lead-field. SIGNIFICANCE: As sensor-space ICA-based source reconstruction is popular in EEG and MEG imaging, and given that source-space ICA has superior spatial performance, it is expected that source-space ICA will supersede its predecessor in many applications.

Source-space ICA for EEG source separation, localization, and time-course reconstruction.

We propose source-space independent component analysis (ICA) for separation, tomography, and time-course reconstruction of EEG and MEG source signals. Source-space ICA is based on the application of singular value decomposition and ICA on the neuroelectrical signals from all brain voxels obtained post minimum-variance beamforming of sensor-space EEG or MEG. We describe the theoretical background and equations, then evaluate the performance of this technique in several different situations, including weak sources, bilateral correlated sources, multiple sources, and cluster sources. In this approach, tomographic maps of sources are obtained by back-projection of the ICA mixing coefficients into the source-space (3-D brain template). The advantages of source-space ICA over the popular alternative approaches of sensor-space ICA together with dipole fitting and power mapping via minimum-variance beamforming are demonstrated. Simulated EEG data were produced by forward head modeling to project the simulated sources onto scalp sensors, then superimposed on real EEG background. To illustrate the application of source-space ICA to real EEG source reconstruction, we show the localization and time-course reconstruction of visual evoked potentials. Source-space ICA is superior to the minimum-variance beamforming in the reconstruction of multiple weak and strong sources, as ICA allows weak sources to be identified and reconstructed in the presence of stronger sources. Source-space ICA is also superior to sensor-space ICA on accuracy of localization of sources, as source-space ICA applies ICA to the time-courses of voxels reconstructed from minimum-variance beamforming on a 3D scanning grid and these time-courses are optimally unmixed via the beamformer. Each component identified by source-space ICA has its own tomographic map which shows the extent to which each voxel has contributed to that component.

Voxel-ICA for reconstruction of source signal time-series and orientation in EEG and MEG.

In electroencephalography (EEG) and magnetoencephalography signal processing, scalar beamformers are a popular technique for reconstruction of the time-course of a brain source in a single time-series. A prerequisite for scalar beamformers, however, is that the orientation of the source must be known or estimated, whereas in reality the orientation of a brain source is often not known in advance and current techniques for estimation of brain source orientation are effective only for high signal-to-noise ratio (SNR) brain sources. As a result, vector beamformers are applied which do not need the orientation of the source and reconstruct the source time-course in three orthogonal (x, y, and z) directions. To obtain a single time-course, the vector magnitude of the three orthogonal outputs of the beamformer can be calculated at each time point (often called neural activity index, NAI). The NAI, however, is different from the actual time-course of a source since it contains only positive values. Moreover, in estimating the magnitude of the desired source, the background activity (undesired signals) in the beamformer outputs also become all positive values, which, when added to each other, leads to a drop in the SNR. This becomes a serious problem when the desired source is weak. We propose applying independent component analysis (ICA) to the orthogonal time-courses of a brain voxel, as reconstructed by a vector beamformer, to reconstruct the time-course of a desired source in a single time-series. This approach also provides a good estimation of dipole orientation. Simulated and real EEG data were used to demonstrate the performance of voxel-ICA and were compared with a scalar beamformer and the magnitude time-series of a vector beamformer. This approach is especially helpful when the desired source is weak and the orientation of the source cannot be estimated by other means.

Electromagnetic tomography via source-space-ICA.

We propose a technique, called source-space-ICA to provide spatiotemporal reconstruction of brain sources. First, the weight-vector-normalized minimum variance beamformer is applied to reconstruct the electrical activity of a 3D scanning grid which covers the whole brain. Second, principal component analysis is used to reduce the dimension of the reconstructed signal matrix of the source-space, then independent component analysis (ICA) is applied on the resulting matrix to identify multiple signal sources in the source-space. Third, the demixing weight vectors obtained by ICA for the identified independent components are projected back into the SS to obtain tomographic maps of the sources. Besides localization, the proposed source-space-ICA approach reconstructs the time-course of each source in a single time-series without requiring prior knowledge of location, orientation, and number of sources for a given segment of EEG/MEG. Simulated EEG was used to evaluate the source-space-ICA. The results show that the source-space-ICA approach is able to separate and localize multiple weak sources and is robust to interference from other sources as it identifies the sources based on their statistical independence.