We present a novel machine-learning approach for detecting faint point sources in high-contrast adaptive optics (AO) imaging data sets. The most widely used algorithms for primary subtraction aim to decouple bright stellar speckle noise from planetary signatures by subtracting an approximation of the temporally evolving stellar noise from each frame in an imaging sequence. Our approach aims to improve the stellar noise approximation and increase the planet detection sensitivity by leveraging deep learning in a novel direct imaging post-processing algorithm. We show that a convolutional autoencoder neural network, trained on an extensive reference library of real imaging sequences, accurately reconstructs the stellar speckle noise at the location of a potential planet signal. This tool is used in a post-processing algorithm we call Direct Exoplanet Detection with Convolutional Image Reconstruction, or
We introduce a new framework for point-spread function subtraction based on the spatiotemporal variation of speckle noise in high-contrast imaging data where the sampling timescale is faster than the speckle evolution timescale. One way that space–time covariance arises in the pupil is as atmospheric layers translate across the telescope aperture and create small, time-varying perturbations in the phase of the incoming wavefront. The propagation of this field to the focal plane preserves some of that space–time covariance. To utilize this covariance, our new approach uses a Karhunen–Loève transform on an image sequence, as opposed to a set of single reference images as in previous applications of Karhunen–Loève Image Processing (KLIP) for high-contrast imaging. With the recent development of photon-counting detectors, such as microwave kinetic inductance detectors, this technique now has the potential to improve contrast when used as a post-processing step. Preliminary testing on simulated data shows this technique can improve contrast by at least 10%–20% from the original image, with significant potential for further improvement. For certain choices of parameters, this algorithm may provide larger contrast gains than spatial-only KLIP.
more » « less- NSF-PAR ID:
- 10391969
- Publisher / Repository:
- DOI PREFIX: 10.3847
- Date Published:
- Journal Name:
- The Astronomical Journal
- Volume:
- 165
- Issue:
- 2
- ISSN:
- 0004-6256
- Format(s):
- Medium: X Size: Article No. 59
- Size(s):
- ["Article No. 59"]
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract ConStruct . The reliability and sensitivity ofConStruct are assessed using real Keck/NIRC2 angular differential imaging data sets. Of the 30 unique point sources we examine,ConStruct yields a higher signal-to-noise ratio than traditional principal component analysis-based processing for 67% of the cases and improves the relative contrast by up to a factor of 2.6. This work demonstrates the value and potential of deep learning to take advantage of a diverse reference library of point-spread function realizations to improve direct imaging post-processing.ConStruct and its future improvements may be particularly useful as tools for post-processing high-contrast images from JWST and extreme AO instruments, both for the current generation and those being designed for the upcoming 30 m class telescopes. -
High performance carbon and glass fibers are widely used as reinforcements in composite material systems for aerospace, automotive, and defense applications. Modifications to fiber surface treatment (sizing) is one of the ways to improve the strength of fibers and hence the overall longitudinal tensile strength of the composite. Single fiber tensile tests at the millimeter scale are typically used to characterize the effect of sizing on fiber strength. However, the characteristic length-scale governing the composite failure due to a cluster of fiber breaks is in the micro-scales. To access such micro-scale gage-lengths, we aim to employ indenters of varying radii to transversely load fibers and use scanning electron microscope (SEM) with digital image correlation (DIC) to measure strains at these lengthscales. The use of DIC technique requires creation of a uniform, random, and high contrast speckle pattern on the fiber surface such as that shown in Figure 1. In this work, we investigate the formation of sub-microscale speckle pattern on carbon fiber surface via sputter deposition and pulsed laser deposition techniques (PLD) using Gold-Palladium (Au-Pd) and Niobium-doped SrTiO3 (Nb:STO) targets respectively. Different processing conditions are investigated for both sputter deposition: sputtering current and coating duration, and PLD: number of pulses respectively to create sub-micron scale patterns viable for micro-DIC on both sized and unsized carbon fibers. By varying the deposition conditions and SEM-imaging the deposited patterns on fibers, successful pattern formation at sub-micron scale is demonstrated for both as-received sized and unsized IM7 carbon fibers of average diameter 5.2 µm via sputter deposition and PLD respectively.more » « less
-
more » « less
Pancreatic ductal adenocarcinoma (PDAC) presents a critical global health challenge, and early detection is crucial for improving the 5-year survival rate. Recent medical imaging and computational algorithm advances offer potential solutions for early diagnosis. Deep learning, particularly in the form of convolutional neural networks (CNNs), has demonstrated success in medical image analysis tasks, including classification and segmentation. However, the limited availability of clinical data for training purposes continues to represent a significant obstacle. Data augmentation, generative adversarial networks (GANs), and cross-validation are potential techniques to address this limitation and improve model performance, but effective solutions are still rare for 3D PDAC, where the contrast is especially poor, owing to the high heterogeneity in both tumor and background tissues. In this study, we developed a new GAN-based model, named 3DGAUnet, for generating realistic 3D CT images of PDAC tumors and pancreatic tissue, which can generate the inter-slice connection data that the existing 2D CT image synthesis models lack. The transition to 3D models allowed the preservation of contextual information from adjacent slices, improving efficiency and accuracy, especially for the poor-contrast challenging case of PDAC. PDAC’s challenging characteristics, such as an iso-attenuating or hypodense appearance and lack of well-defined margins, make tumor shape and texture learning challenging. To overcome these challenges and improve the performance of 3D GAN models, our innovation was to develop a 3D U-Net architecture for the generator, to improve shape and texture learning for PDAC tumors and pancreatic tissue. Thorough examination and validation across many datasets were conducted on the developed 3D GAN model, to ascertain the efficacy and applicability of the model in clinical contexts. Our approach offers a promising path for tackling the urgent requirement for creative and synergistic methods to combat PDAC. The development of this GAN-based model has the potential to alleviate data scarcity issues, elevate the quality of synthesized data, and thereby facilitate the progression of deep learning models, to enhance the accuracy and early detection of PDAC tumors, which could profoundly impact patient outcomes. Furthermore, the model has the potential to be adapted to other types of solid tumors, hence making significant contributions to the field of medical imaging in terms of image processing models.
-
more » « less
Measurement of blood flow in tissue provides vital information for the diagnosis and therapeutic monitoring of various vascular diseases. A noncontact, camera-based, near-infrared speckle contrast diffuse correlation tomography (scDCT) technique has been recently developed for 3D imaging of blood flow index (αDB) distributions in deep tissues up to a centimeter. A limitation with the continuous-wave scDCT measurement of blood flow is the assumption of constant and homogenous tissue absorption coefficient (
μ a ). The present study took the advantage of rapid, high-density, noncontact scDCT measurements of both light intensities and diffuse speckle contrast at multiple source-detector distances and developed two-step fitting algorithms for extracting bothμ a and αDB. The new algorithms were tested in tissue-simulating phantoms with known optical properties and human forearms. Measurement results were compared against established near-infrared spectroscopy (NIRS) and diffuse correlation spectroscopy (DCS) techniques. The accuracies of our new fitting algorithms with scDCT measurements in phantoms (up to 16% errors) and forearms (up to 23% errors) are comparable to relevant study results (up to 25% errors). Knowledge ofμ a not only improved the accuracy in calculating αDBbut also provided the potential for quantifying tissue blood oxygenation via spectral measurements. A multiple-wavelength scDCT system with new algorithms is currently developing to fit multi-wavelength and multi-distance data for 3D imaging of both blood flow and oxygenation distributions in deep tissues. -
Summary The covariance structure of multivariate functional data can be highly complex, especially if the multivariate dimension is large, making extensions of statistical methods for standard multivariate data to the functional data setting challenging. For example, Gaussian graphical models have recently been extended to the setting of multivariate functional data by applying multivariate methods to the coefficients of truncated basis expansions. However, compared with multivariate data, a key difficulty is that the covariance operator is compact and thus not invertible. This paper addresses the general problem of covariance modelling for multivariate functional data, and functional Gaussian graphical models in particular. As a first step, a new notion of separability for the covariance operator of multivariate functional data is proposed, termed partial separability, leading to a novel Karhunen–Loève-type expansion for such data. Next, the partial separability structure is shown to be particularly useful in providing a well-defined functional Gaussian graphical model that can be identified with a sequence of finite-dimensional graphical models, each of identical fixed dimension. This motivates a simple and efficient estimation procedure through application of the joint graphical lasso. Empirical performance of the proposed method for graphical model estimation is assessed through simulation and analysis of functional brain connectivity during a motor task.more » « less
