Neural network-based image reconstruction in swept-source optical coherence tomography using undersampled spectral data

Optical coherence tomography (OCT) is a widely used non-invasive biomedical imaging modality that can rapidly provide volumetric images of samples. Here, we present a deep learning-based image reconstruction framework that can generate swept-source OCT (SS-OCT) images using undersampled spectral data, without any spatial aliasing artifacts. This neural network-based image reconstruction does not require any hardware changes to the optical setup and can be easily integrated with existing swept-source or spectral-domain OCT systems to reduce the amount of raw spectral data to be acquired. To show the efficacy of this framework, we trained and blindly tested a deep neural network using mouse embryo samples imaged by an SS-OCT system. Using 2-fold undersampled spectral data (i.e., 640 spectral points per A-line), the trained neural network can blindly reconstruct 512 A-lines in 0.59 ms using multiple graphics-processing units (GPUs), removing spatial aliasing artifacts due to spectral undersampling, also presenting a very good match to the images of the same samples, reconstructed using the full spectral OCT data (i.e., 1280 spectral points per A-line). We also successfully demonstrate that this framework can be further extended to process 3× undersampled spectral data per A-line, with some performance degradation in the reconstructed image quality compared to 2× spectral undersampling. Furthermore, an A-line-optimized undersampling method is presented by jointly optimizing the spectral sampling locations and the corresponding image reconstruction network, which improved the overall imaging performance using less spectral data points per A-line compared to 2× or 3× spectral undersampling results. This deep learning-enabled image reconstruction approach can be broadly used in various forms of spectral-domain OCT systems, helping to increase their imaging speed without sacrificing image resolution and signal-to-noise ratio.

Spatial Aliasing and Three-Component Seismic Sensors

Temporal aliasing occurs when a waveform is sampled with less than two points per time period for a signal at a given frequency. This insufficiently sampled frequency will incorrectly be mapped into a lower (aliased) frequency. Analogous to this, spatial aliasing is said to occur when a propagating waveform is measured at spatial intervals larger than half the wavelength of any given signal in that waveform. Temporally aliased frequencies cannot be recovered with standard methods. On the other hand, we argue that "spatial aliasing" can be viewed as an expression of a non-uniqueness for estimating the direction of the propagation for signal at a given frequency, and that spatial aliasing may be overcome when three-component seismic sensors are used. Realizing this allows for using higher frequencies, and therefore enables the generation of higher resolution images from the data. This is particularly useful for borehole-seismic data which tend to contain higher frequencies than surface-seismic data, but does require that an array of three-component sensors is used, or that an array of less expensive single-component sensors is supplement by three-component sensors.

Quasi-two-day waves at 53°N latitude

<p>The quasi-two-day wave (Q2DW) is the strongest and most widely-studied planetary wave occurring in the mesosphere. Existing observational analyses are based on either single-satellite or -station approaches, which suffer from temporal and spatial aliasing, respectively. The current work implements and develops dual-station approaches to investigate the mesospheric Q2DWs  and their nonlinear interactions with tides using winds from two longitudinal sectors at 53°N latitude.  An 8-year composite analysis reveals seasonal and altitude variations of Q2DWs and their secondary waves (SWs) from nonlinear interactions with tides.   The Q2DWs maximize in local summer, whereas their 16hr and 9.6hr SWs appear more in winter.</p>

NMF-weighted SRP for multi-speaker direction of arrival estimation: robustness to spatial aliasing while exploiting sparsity in the atom-time domain

Localization of multiple speakers using microphone arrays remains a challenging problem, especially in the presence of noise and reverberation. State-of-the-art localization algorithms generally exploit the sparsity of speech in some representation for this purpose. Whereas the broadband approaches exploit time-domain sparsity for multi-speaker localization, narrowband approaches can additionally exploit sparsity and disjointness in the time-frequency representation. Broadband approaches are robust to spatial aliasing but do not optimally exploit the frequency domain sparsity, leading to poor localization performance for arrays with short inter-microphone distances. Narrowband approaches, on the other hand, are vulnerable to spatial aliasing, making them unsuitable for arrays with large inter-microphone spacing. Proposed here is an approach that decomposes a signal spectrum into a weighted sum of broadband spectral components (atoms) and then exploits signal sparsity in the time-atom representation for simultaneous multiple source localization. The decomposition into atoms is performed in situ using non-negative matrix factorization (NMF) of the short-term amplitude spectra and the localization estimate is obtained via a broadband steered-response power (SRP) approach for each active atom of a time frame. This SRP-NMF approach thereby combines the advantages of the narrowband and broadband approaches and performs well on the multi-speaker localization task for a broad range of inter-microphone spacings. On tests conducted on real-world data from public challenges such as SiSEC and LOCATA, and on data generated from recorded room impulse responses, the SRP-NMF approach outperforms the commonly used variants of narrowband and broadband localization approaches in terms of source detection capability and localization accuracy.

Cross-streamer wavefield reconstruction through wavelet domain learning

Seismic exploration in complex geologic settings and shallow geologic targets has led to a demand for higher spatial and temporal resolution in the final migrated image. Conventional marine seismic and wide-azimuth data acquisition lack near-offset coverage, which limits imaging in these settings. A new marine source-over-cable survey, with split-spread configuration, known as TopSeis, was introduced in 2017 to address the shallow-target problem. However, wavefield reconstruction in the near offsets is challenging in the shallow part of the seismic record due to the high temporal frequencies and coarse sampling that leads to severe spatial aliasing. We have investigated deep learning as a tool for the reconstruction problem, beyond spatial aliasing. Our method is based on a convolutional neural network (CNN) approach trained in the wavelet domain that is used to reconstruct the wavefield across the streamers. We determine the performance of the proposed method on broadband synthetic data and TopSeis field data from the Barents Sea. From our synthetic example, we find that the CNN can be learned in the inline direction and applied in the crossline direction, and that the approach preserves the characteristics of the geologic model in the migrated section. In addition, we compare our method to an industry-standard Fourier-based interpolation method, in which the CNN approach shows an improvement in the root-mean-square (rms) error close to a factor of two. In our field data example, we find that the approach reconstructs the wavefield across the streamers in the shot domain, and it displays promising characteristics of a reconstructed 3D wavefield.

Interpolation artifacts as a result of spatial aliasing: A case study of the airborne magnetic data set of southeastern Minas Gerais, Brazil

Linear features at an acute angle with the flight direction are imaged as a series of aligned circular anomalies in the images of Area 15 aeromagnetic survey, which covered part of the Brazilian southeastern region. These features are interpolation artifacts, a recurring problem found in airborne magnetic images that cause problems for qualitative and quantitative geophysical-geologic interpretation. This imaging problem is attributed to spatial aliasing. By running simulations of magnetic data on a synthetic model, we have physically demonstrated that the interpolation artifacts from Area 15 are due to inappropriate survey design. Besides the most common expression of artifacts, we described a geologically noncoherent linear pattern as a new type of artifact. Supported by spectral analyses, we found that the Area 15 aliased spectrum is similar to geologic high-frequency magnetic features, which constitutes a motive for unearthing the correct geophysical signal. Thus, we made use of four techniques for removing the artifacts. The trend enforcement method partially improved the images, whereas the inverse interpolation method was ineffective, apparently because Area 15 data are severely aliased. The constrained coherence diffusion and multitrend gridding methods were able to significantly reduce the presence of artifacts. Despite the high-frequency attenuation, these tools adequately enhanced the magnetic trends and minimized the artifacts. Therefore, the improved images are better suited for reliable geologic interpretation.

Layer-steered filter for enhancing seismic reflection interpretability

Seismic artifacts due to random and linear noises, low fold coverage, statics, and spatial aliasing are frequently affecting uncertainties in seismic interpretation. Several conventional methods, such as median filter, have been implemented to reduce random noises. However, this method can not be utilized for the area in which rich with stratigraphic features such as clinoforms and in the area with strong dips. We implemented layer-steered filter in order to attenuate random noises in this kind of situation. Layer-steered filter has ability to attenuate random noises but still respects to local dip events; therefore, the method provides better preservation of events and stratigraphics compared to other conventional methods such as median filter and dip-steered filter.

Multiresolution Speech Enhancement Based on Proposed Circular Nested Microphone Array in Combination with Sub-Band Affine Projection Algorithm

Speech enhancement is one of the most important fields in audio and speech signal processing. The speech enhancement methods are divided into the single and multi-channel algorithms. The multi-channel methods increase the speech enhancement performance by providing more information with the use of more microphones. In addition, spatial aliasing is one of the destructive factors in speech enhancement strategies. In this article, we first propose a uniform circular nested microphone array (CNMA) for data recording. The microphone array increases the accuracy of the speech processing methods by increasing the information. Moreover, the proposed nested structure eliminates the spatial aliasing between microphone signals. The circular shape in the proposed nested microphone array implements the speech enhancement algorithm with the same probability for the speakers in all directions. In addition, the speech signal information is different in frequency bands, where the sub-band processing is proposed by the use of the analysis filter bank. The frequency resolution is increased in low frequency components by implementing the proposed filter bank. Then, the affine projection algorithm (APA) is implemented as an adaptive filter on sub-bands that were obtained by the proposed nested microphone array and analysis filter bank. This algorithm adaptively enhances the noisy speech signal. Next, the synthesis filters are implemented for reconstructing the enhanced speech signal. The proposed circular nested microphone array in combination with the sub-band affine projection algorithm (CNMA-SBAPA) is compared with the least mean square (LMS), recursive least square (RLS), traditional APA, distributed multichannel Wiener filter (DB-MWF), and multichannel nonnegative matrix factorization-minimum variance distortionless response (MNMF-MVDR) in terms of the segmental signal-to-noise ratio (SegSNR), perceptual evaluation of speech quality (PESQ), mean opinion score (MOS), short-time objective intelligibility (STOI), and speed of convergence on real and simulated data for white and colored noises. In all scenarios, the proposed method has high accuracy at different levels and noise types by the lower distortion in comparison with other works and, furthermore, the speed of convergence is higher than the compared researches.