Search

Deep neural network model extraction attack is the process of retraining a surrogate model based on the outputs of a target model with a given set of inputs. Such attacks are hard to defend for the sake of model owners' interest. Recently, some work propose model watermarking scheme for image processing networks, which is able to prove the intellectual property of deep models even after the model extraction attack. This scheme makes sure that, once the target model (an image processing network) is watermarked, we can extract the watermark from the output of the surrogate model. In this paper, we propose a new model extraction attack scheme to fight against the latest method. Instead of directly using the output images of a target model, we propose to use their reconstructed versions for model retraining, where an asymmetrical UNet is proposed for image reconstruction. To thoroughly remove the watermarking traces, we propose and incorporate a referenced subspace attention module in the asymmetrical UNet, which removes the watermark by projecting the outputs of the target model into the subspaces of the reference image. Various experiments demonstrate the effectiveness of our attack. [ABSTRACT FROM AUTHOR]

Motivation BISCAP is a state-of-the-art tool for automatically characterizing biofilm images obtained from Optical Coherence Tomography. Limited availability of other software tools is reported in the field. BISCAP's first version processes 2D images only. Processing 3D images is a problem of greater scientific relevance since it deals with the entire structure of biofilms instead of their 2D slices. Results Building on the image-processing principles and algorithms proposed earlier for 2D images, these were adapted to the 3D case, and a more general implementation of BISCAP was developed. The primary goal concerns the extension of the initial methodology to incorporate the depth axis in 3D images; multiple improvements were also made to boost computational performance. The calculation of structural properties and visual outputs was extended to offer new insights into the 3D structure of biofilms. BISCAP was tested using 3D images of biofilms with different morphologies, consistently delivering accurate characterizations of 3D structures in a few minutes using standard laptop machines. Low user dependency is required for image analysis. Availability and implementation BISCAP is available from https://github.com/diogonarciso/BISCAP. All images used in the tutorials and the validation examples are available from https://web.fe.up.pt/∼fgm/biscap3d. [ABSTRACT FROM AUTHOR]

We present extended point spread function (PSF) models for the Hyper Suprime-Cam Subaru Strategic Program Public Data Release 3 (HSC-SSP PDR3) in all g, r, i, Z , and Y -bands. Due to its 8.2 m primary mirror and long exposure periods, HSC combines deep images with wide-field coverage. Both properties make HSC one of the most suitable observing facilities for low-surface brightness (LSB) studies, which are particularly sensitive to the PSF. By applying a median stacking technique of point-like sources with different brightness, we show how to construct the HSC-SSP PDR3 PSF models to an extent of R ∼ 5.6 arcmin. These models are appropriate for the HSC-PDR3 intermediate-state data which do not have applied the final aggressive background subtraction. The intermediate-state data is especially stored for users interested in large extended objects, where our new PSFs provide them with a crucial tool to characterise LSB properties at large angles. We demonstrate that our HSC PSFs behave reasonably in two scenarios. In the first one, we generate 2D models of a bright star, showing no evidence of residual structures across the five bands. In the second scenario, we recreate the PSF-scattered light on mock images with special consideration of the effect of this additional flux on LSB measurements. Despite the well-behaved nature of the HSC-PDR3 PSFs, there is a non-negligible impact on the faint light present in the mock images. This impact could lead to incorrect LSB measurements if a proper star subtraction is not applied. The PSF models are publicly available to the astronomical community at github.com/luciagarate/HSC_PSFs (DOI: 10.5281/zenodo.11273118). [ABSTRACT FROM AUTHOR]

Adaptive optics (AO) systems correct optical phase aberrations of the incoming light generated by the atmosphere. To do so simultaneous estimators of the atmospheric turbulence parameters are required. For the family of wide-field AO (WFAO) systems, this information must be stratified in altitude. Among these vectorized estimations, wind profiling in altitude is needed for the reduction of temporal errors in AO loops or for the estimation of turbulence coherence time. This paper proposes a turbulence wind profiler called image processing based peak tracking algorithm (ipta). ipta is an image-processing based approach that automatically and reliably estimates wind velocity for several turbulent layers along the line of sight. The estimation of each wind layer is achieved by tracking peaks produced in cross-correlation maps from pairs of wavefront sensors (WFSs) slopes using the technique known as SLODAR (slope detection and ranging). Results for simulated and on-sky WFS data sets demonstrate that ipta outperforms one of the state of the art wind profiler methods [the profiler covariance parametrization of wind velocity (CAW)] in terms of accuracy and speed. Results also show that, in terms of execution time, our method scales better when the number of WFS lenslets is increased. Being an open source and reliable tool, we believe ipta can be a useful wind profiler for the AO community. [ABSTRACT FROM AUTHOR]

Seismic attributes are derived measures from seismic data that help characterize subsurface geological features and enhance the interpretation of subsurface structures: we propose to exploit the hidden layers of Long–Short Time Memory neural network predictions as possible new reflection seismic attributes. The idea is based on the inference process of a neural network, which in its hidden layers stores information related to different features embedded in the input data and which usually are not considered. Neural network applications typically ignore such intermediate steps because the main interest lies in the final output, which is considered as the exclusive exploitable feature of the process. On the contrary, here we analyse the possibility to exploit the intermediate prediction steps, hereafter referred as 'deep attributes' because they are produced by a deep learning algorithm, to highlight features and emphasize characteristics embedded in the data but neither recognizable by traditional interpretation, nor evident with classical attributes or multi-attribute approaches. Nowadays, classical signal attributes are numerous and used for different purposes; we here propose an original strategy to calculate attributes previously never exploited, which are potentially complementary or a good alternative to the classical ones. We tested the proposed procedure on synthetic and field 2-D and 3-D reflection seismic data sets to test and demonstrate the stability, affordability and versatility of the entire approach. Furthermore, we evaluated the performance of deep attributes on a 4-D seismic data set to assess the applicability and effectiveness for time-monitoring purposes and comparing them with the sweetness attribute. [ABSTRACT FROM AUTHOR]

The upcoming Nancy Grace Roman Space Telescope will carry out a wide-area survey in the near-infrared. A key science objective is the measurement of cosmic structure via weak gravitational lensing. Roman data will be undersampled, which introduces new challenges in the measurement of source galaxy shapes; a potential solution is to use linear algebra-based coaddition techniques such as imcom that combine multiple undersampled images to produce a single oversampled output mosaic with a desired 'target' point spread function (PSF). We present here an initial application of imcom to 0.64 square degrees of simulated Roman data, based on the Roman branch of the Legacy Survey of Space and Time (LSST) Dark Energy Science Collaboration (DESC) Data Challenge 2 (DC2) simulation. We show that imcom runs successfully on simulated data that includes features such as plate scale distortions, chip gaps, detector defects, and cosmic ray masks. We simultaneously propagate grids of injected sources and simulated noise fields as well as the full simulation. We quantify the residual deviations of the PSF from the target (the 'leakage'), as well as noise properties of the output images; we discuss how the overall tiling pattern as well as Moiré patterns appear in the final leakage and noise maps. We include appendices on interpolation algorithms and the interaction of undersampling with image processing operations that may be of broader applicability. The companion paper ('Paper II') explores the implications for weak lensing analyses. [ABSTRACT FROM AUTHOR]

In the realm of radio astronomy, the detection of radio frequency interference (RFI) stands as a pivotal pursuit. This study performs a novel comparative analysis of deep learning methodologies and introduces a novel transfer learning method, called fine-tuning. We compare various aspects and factors relating to this problem, including supervised fully convolutional network (FCN) architectures used within the literature, loss functions, regularization techniques, and training methodologies, to establish the most effective strategies for RFI detection. Moreover, the relationship between parameters, FLOPS, and inference times are examined. Fine-tuning involves pre-training models with low-quality aoflagger reference outputs, a very popular and accessible RFI flagging software package, and thereafter re-training the models with high-quality reference outputs. We utilize two data sets: real observations from LOFAR and simulated data from HERA. The mean squared error (MSE) loss function emerges as a robust performer if a high recall is desired. In contrast, the binary cross-entropy (BCE) loss function excels in generalization but falls short in classification performance. The Dice loss function emerges as the top performer, maximizing the F1 score and thereby serving as the choice for our further investigations. Notably, we highlight the important role of data quality and model capacity. In particular, we find that low-capacity models exhibit resilience when trained with low-quality flags from aoflagger , showcasing their ability to mitigate overfitting and overflagging tendencies. In contrast, high-capacity models excel when trained with high-quality flags. Fine-tuning proved to be an effective method to unlearn the overflagging tendencies of aoflagger , whilst requiring very little data. [ABSTRACT FROM AUTHOR]

Studying the Universe through radio telescope observation is crucial. However, radio telescopes capture not only signals from the universe but also various interfering signals, known as radio frequency interference (RFI). The presence of RFI can significantly impact data analysis. Ensuring the accuracy, reliability, and scientific integrity of research findings by detecting and mitigating or eliminating RFI in observational data, presents a persistent challenge in radio astronomy. In this study, we proposed a novel deep learning model called EMSCA-UNet for RFI detection. The model employs multiscale convolutional operations to extract RFI features of various scale sizes. Additionally, an attention mechanism is utilized to assign different weights to the extracted RFI feature maps, enabling the model to focus on vital features for RFI detection. We evaluated the performance of the model using real data observed from the 40 m radio telescope at Yunnan Observatory. Furthermore, we compared our results to other models, including U-Net, RFI-Net, and R-Net, using four commonly employed evaluation metrics: precision, recall, F1 score, and IoU. The results demonstrate that our model outperforms the other models on all evaluation metrics, achieving an average improvement of approximately 5 per cent compared to U-Net. Our model not only enhances the accuracy and comprehensiveness of RFI detection but also provides more detailed edge detection while minimizing the loss of useful signals. [ABSTRACT FROM AUTHOR]

Interferometric synthetic aperture radar (InSAR) decorrelation that creates great challenges to phase unwrapping has been a critical issue for mapping large earthquake deformation. Some studies have proposed a 'remove-and-return model' solution to tackle this problem, but it has not been fully validated yet, and therefore has rarely been applied to real earthquake scenarios. In this study, we use the 2023 M w 7.8 and 7.6 earthquake doublet in Turkey and Syria as a case example to develop an iterative modelling method for InSAR-based coseismic mapping. We first derive surface deformation fields using Sentinel-1 offset tracking and Sentinel-2 optical image correlation, and invert them for an initial coseismic slip model, based on which we simulate InSAR coseismic phase measurements. We then remove the simulated phase from the actual Sentinel-1 phase and conduct unwrapping. The simulated phase is added back to the unwrapped phase to produce the final phase measurements. Comparing to the commonly used unwrapping method, our proposed approach can significantly improve coherence and reduce phase gradients, enabling accurate InSAR measurements. Combining InSAR, offset tracking and optical image correlation, we implement a joint inversion to obtain an optimal coseismic slip model. Our model shows that slip on the Çardak Fault is concentrated on a ∼100 km segment; to both ends, slip suddenly diminished. On the contrary, rupture on the East Anatolian Fault Zone propagated much longer as its geometry is fairly smooth. The iterative coseismic modelling method is proven efficient and can be easily applied to other continental earthquakes. [ABSTRACT FROM AUTHOR]

Muography is a promising and rapidly developing physical prospecting technique based on the attenuation of muon flux. The feasibility and potential of applying muography to mining were presented in a small number of previous case studies. In this work, we aimed to address three challenges that limit the applicability and efficiency of muography in mineral exploration: (1) application to low-density-contrast ore body exploration, (2) analysis of altitudinal impacts on measurements and (3) precise and efficient reconstruction. We conducted the first case of applying muography to the exploration for low-density-contrast ore bodies. Six muon imaging systems were placed underground to collect surviving muons for roughly half a year. We analysed the altitudinal impact on the data measurements and proposed a simplified method to eliminate it. We also developed the seed algorithm, a novel 3-D reconstruction algorithm, that can reconstruct anomalies located far away from the detectors and avoid their elongation along the observed directions. Benefitting from the seed algorithm, a low-density-contrast ore body and a limonitic siliceous slate structure were reconstructed, demonstrating the sensitivity of this technique in density distinction; discoveries of several mined-out areas are important for accident avoidance; and reconstruction of the stope and scarps served as strong circumstantial evidence of the reliability of the result. The success of this experiment shows the great value of muography in the economic, research and safety aspects of mineral exploration and inspection. Moreover, the overcoming of challenges is helpful for the development of muography, making it an effective and competitive technique in this field. [ABSTRACT FROM AUTHOR]

This paper presents a new methodology to assist geophysicists in determining the first-break event in a 3-D seismic data set using the well-known technique called dynamic time warping algorithm (DTW), which is usually used to find the optimal alignment between two time-series. We used the optimal path from the cost matrix to identify the first break in the seismogram using a few picks (seeds) made by an interpreter as a reference to perform this task. Furthermore, the data were pre-conditioned by the topographic and linear moveout to improve the method's accuracy. To demonstrate the technique's robustness, first, we applied the methodology in a synthetic seismic data. After demonstrating the efficiency of the algorithm, we applied the aforementioned methodology in the Polo-Miranga 3-D seismic cube located in the Recôncavo sedimentary basin, Bahia-Brazil, and in the seismic data acquired from the Blackfoot field in Alberta, Canada. The high-quality results showed consistency in determining the first break in all ranges of offsets, demonstrating an alternative way to accelerate this seismic processing step. Furthermore, we compared the results obtained by the proposed methodology with an algorithm based on comparing the short-time averages with long-time averages. Finally, we performed the static correction calculation to ensure that the time distortion resulting from the terrain and the low-velocity layer was mitigated in shoot gathers and in the stacked section. [ABSTRACT FROM AUTHOR]

Dense array observation and seismic interferometry have revolutionized the imaging schemes of the earth structure. It is becoming possible to directly obtain the lateral variation of the earth's structure by applying array-based methods such as the cross-correlation beamforming (CBF) of the ambient noise to the subsets of the dense array, without tomography. CBF has been proven to extract the azimuth-averaged multimode surface wave dispersion curves. However, the resolution of the dispersion image generated by conventional CBF is low at high frequencies in the frequency–velocity (f - v) domain. Moreover, the irregular array geometry and uneven source distribution would bias the result of CBF, especially for the estimation of azimuth-dependent velocity. In this paper, two beamforming (BF) es are suggested to improve the resolution of multimode dispersion images in the f - v domain. First, the geometrical spreading of the wavefield is corrected to enhance the amplitude at high frequency (or large distance) and thereby improve the resolution of the dispersion image at high frequency. We call this scheme weighted correlation beamforming (WCBF). The azimuth-averaged velocity can be estimated with sufficient resolution using WCBF by stacking the BF output at each azimuth. We show that WCBF is the 2-D Fourier transform of the spatial wavefield from the viewpoint of the wavefield transform. Secondly, a modified beamforming scheme (MCBF) is suggested to reduce the effect of uneven source and/or irregular array geometry. The delay and summation in MCBF are performed only for plane waves incident from the stationary phase region. The azimuth-dependent velocity can therefore be estimated by MCBF with less dependence on the array geometry, as well as on the uneven source distribution. In terms of the estimation of azimuth-averaged phase velocity, we show the F-J method, another array-based method for extracting multimode surface waves from ambient noise using the Fourier–Bessel transform, is the azimuth-averaged version of WCBF. The reliability of WCBF and MCBF is verified based on the synthetic and field data using the array with different geometry. The dispersion image of multimode Rayleigh wave phase velocity at local and regional scales can be generated by WCBF or MCBF with high resolution. In particular, multimode dispersion curves at the local scale can be measured by MCBF with sufficient accuracy using quite short recordings from hours to days. This offers the possibility of a rapid assessment of the media properties. [ABSTRACT FROM AUTHOR]

Earthquake source parameters can be estimated using seismological observations, but the identification of the fault responsible is often complicated by location uncertainties and the inherent ambiguity between nodal planes. Satellite Interferometric Synthetic Aperture Radar (InSAR) can be used to observe ground deformation and model fault geometry but is limited by climate conditions (water vapour) and ground coverage (dense vegetation). In the tropics, the atmosphere is dynamic and most regions are densely vegetated, making detecting coseismic deformation challenging. Here, we perform a systematic inspection of coseismic interferograms from Sentinel-1 SAR images, to assess their suitability for detecting coseismic deformation in Costa Rica. Using data from the seismological network, we target seven earthquakes between 2016 and 2020 with depths |$\le \, 20$| km and magnitudes M w 5.3–6.2. For each event, we use the seismic parameters to compute line-of-sight displacements for ascending and descending geometries and for both nodal planes and generate 12- and 24-d coseismic interferograms where available. We obtain interferograms with coseismic displacement signals for three of the seven earthquakes. We invert the geodetic data to retrieve the earthquake source parameters but the lack of offshore geodetic coverage causes trade-offs between parameters and large uncertainties. The Jacó and Golfito earthquakes likely occurred on the subduction interface and the geodetic locations were 6–9 km closer to the coast than previous seismic estimates. The Burica earthquake occurred on a shallow steeply dipping thrust fault in the outer forearc. For the other earthquakes, no coseismic deformation was detected due to atmospheric noise or poor coherence. These results demonstrate the suitability of 12-d Sentinel-1 interferograms for monitoring shallow earthquakes of magnitude > M w 5.7 in Central America. This approach can be used to begin a surface deformation catalogue for the region, which will ultimately help improve the understanding of active deformation processes and improve hazard maps. [ABSTRACT FROM AUTHOR]

One challenge for applying current weak lensing analysis tools to the Nancy Grace Roman Space Telescope is that individual images will be undersampled. Our companion paper presented an initial application of Imcom – an algorithm that builds an optimal mapping from input to output pixels to reconstruct a fully sampled combined image – on the Roman image simulations. In this paper, we measure the output noise power spectra, identify the sources of the major features in the power spectra, and show that simple analytic models that ignore sampling effects underestimate the power spectra of the coadded noise images. We compute the moments of both idealized injected stars and fully simulated stars in the coadded images, and their one- and two-point statistics. We show that the idealized injected stars have root-mean-square ellipticity errors (1–6) × 10−4 per component depending on the band; the correlation functions are ≥2 orders of magnitude below requirements, indicating that the image combination step itself is using a small fraction of the overall Roman second moment error budget, although the fourth moments are larger and warrant further investigation. The stars in the simulated sky images, which include blending and chromaticity effects, have correlation functions near the requirement level (and below the requirement level in a wide-band image constructed by stacking all four filters). We evaluate the noise-induced biases in the ellipticities of injected stars, and explain the resulting trends with an analytical model. We conclude by enumerating the next steps in developing an image coaddition pipeline for Roman. [ABSTRACT FROM AUTHOR]

In this paper, we introduce the software package propane , written for the r data analysis language. propane combines the full range of wcslib projections with the C++ image manipulation routines provided by the cimg library. propane offers routines for image warping and combining (including stacking), and various related tasks such as image alignment tweaking and pixel masking. It can stack an effectively unlimited number of target frames using multiple parallel cores, and offers threading for many lower level routines. It has been used for a number of current and upcoming large surveys, and we present a range of its capabilities and features. propane is already available under a permissive open-source LGPL-3 license at github.com/asgr/ProPane (DOI: 10.5281/zenodo.10057053). [ABSTRACT FROM AUTHOR]

Objectives To develop and validate a super-resolution (SR) algorithm generating clinically feasible chest radiographs from 64-fold reduced data. Methods An SR convolutional neural network was trained to produce original-resolution images (output) from 64-fold reduced images (input) using 128 × 128 patches (n  = 127 030). For validation, 112 radiographs—including those with pneumothorax (n  = 17), nodules (n  = 20), consolidations (n  = 18), and ground-glass opacity (GGO; n  = 16)—were collected. Three image sets were prepared: the original images and those reconstructed using SR and conventional linear interpolation (LI) using 64-fold reduced data. The mean-squared error (MSE) was calculated to measure similarity between the reconstructed and original images, and image noise was quantified. Three thoracic radiologists evaluated the quality of each image and decided whether any abnormalities were present. Results The SR-images were more similar to the original images than the LI-reconstructed images (MSE: 9269 ± 1015 vs. 9429 ± 1057; P =.02). The SR-images showed lower measured noise and scored better noise level by three radiologists than both original and LI-reconstructed images (P s <.01). The radiologists' pooled sensitivity with the SR-reconstructed images was not significantly different compared with the original images for detecting pneumothorax (SR vs. original, 90.2% [46/51] vs. 96.1% [49/51]; P =.19), nodule (90.0% [54/60] vs. 85.0% [51/60]; P =.26), consolidation (100% [54/54] vs. 96.3% [52/54]; P =.50), and GGO (91.7% [44/48] vs. 95.8% [46/48]; P =.69). Conclusions SR-reconstructed chest radiographs using 64-fold reduced data showed a lower noise level than the original images, with equivalent sensitivity for detecting major abnormalities. Advances in knowledge This is the first study applying super-resolution in data reduction of chest radiographs. [ABSTRACT FROM AUTHOR]

The Chinese Space Station Telescope (CSST) is scheduled to launch soon, which is expected to provide a vast amount of image potentially containing low-surface brightness galaxies (LSBGs). However, detecting and characterizing LSBGs is known to be challenging due to their faint surface brightness, posing a significant hurdle for traditional detection methods. In this paper, we propose LSBGnet, a deep neural network specifically designed for automatic detection of LSBGs. We established LSBGnet-SDSS model using data set from the Sloan Digital Sky Survey (SDSS). The results demonstrate a significant improvement compared to our previous work, achieving a recall of 97.22 per cent and a precision of 97.27 per cent on the SDSS test set. Furthermore, we use the LSBGnet-SDSS model as a pre-training model, employing transfer learning to retrain the model with LSBGs from Dark Energy Survey (DES), and establish the LSBGnet-DES model. Remarkably, after retraining the model on a small DES sample, it achieves over 90 per cent precision and recall. To validate the model's capabilities, we utilize the trained LSBGnet-DES model to detect LSBG candidates within a selected 5 sq. deg area in the DES footprint. Our analysis reveals the detection of 204 LSBG candidates, characterized by a mean surface brightness range of |$23.5\ \mathrm{ mag}\ \mathrm{ arcsec}^{-2}\le \bar{\mu }_{\text{eff}}(g)\le 26.8\ \mathrm{ mag}\ \mathrm{ arcsec}^{-2}$| and a half-light radius range of 1.4 arcsec ≤ r 1/2 ≤ 8.3 arcsec. Notably, 116 LSBG candidates exhibit a half-light radius ≥2.5 arcsec. These results affirm the remarkable performance of our model in detecting LSBGs, making it a promising tool for the upcoming CSST. [ABSTRACT FROM AUTHOR]

The Chinese Space Station Telescope (abbreviated as CSST) is a future advanced space telescope. Real-time identification of galaxy and nebula/star cluster (abbreviated as NSC) images is of great value during CSST survey. While recent research on celestial object recognition has progressed, the rapid and efficient identification of high-resolution local celestial images remains challenging. In this study, we conducted galaxy and NSC image classification research using deep learning methods based on data from the Hubble Space Telescope. We built a local celestial image data set and designed a deep learning model named HR-CelestialNet for classifying images of the galaxy and NSC. HR-CelestialNet achieved an accuracy of 89.09 per cent on the testing set, outperforming models such as AlexNet, VGGNet, and ResNet, while demonstrating faster recognition speeds. Furthermore, we investigated the factors influencing CSST image quality and evaluated the generalization ability of HR-CelestialNet on the blurry image data set, demonstrating its robustness to low image quality. The proposed method can enable real-time identification of celestial images during CSST survey mission. [ABSTRACT FROM AUTHOR]

Gravity surveys constitute an important method for investigating the Earth's interior based on density contrasts related to Earth material differentials. Because lithology depends on the environment and the period of formation, there are generally clear boundaries between rocks with different lithologies. Inversions with convex functions for approximating the L 0 norm are used to detect boundaries in reconstructed models. Optimizations can easily be found because of the convex transformations; however, the volume of the reconstructed model depends on the weighting parameter and the density constraint rather than the model sparsity. To determine and adapt the modelling size, a novel non-convex framework for gravity inversion is proposed. The proposed optimization aims to directly reduce the L 0 norm of the density matrix. An improved iterative hard thresholding algorithm is developed to linearly reduce the L 0 penalty during the inner iteration. Accordingly, it is possible to determine the modelling scale during the iteration and achieve an expected scale for the reconstructed model. Both simple and complex model experiments demonstrate that the proposed method efficiently reconstructs models. In addition, granites formed during the Yanshanian and Indosinian periods in the Nanling region, China, are reconstructed according to the modelling size evaluated in agreement with the magnetotelluric profile and density statistics of rock samples. The known ores occur at the contact zones between the sedimentary rocks and the reconstructed Yanshanian granites. The ore-forming bodies, periods, and processes are identified, providing guidance for further deep resource exploration in the study area. [ABSTRACT FROM AUTHOR]

This paper introduces a technique called needlet Karhunen–Loéve (NKL), which cleans both polarized and unpolarized foregrounds from H  i intensity maps by applying a Karhunen–Loéve transform on the needlet coefficients. In NKL, one takes advantage of correlations not only along the line of sight, but also between different angular regions, referred to as 'chunks'. This provides a distinct advantage over many of the standard techniques applied to map space that one finds in the literature, which do not consider such spatial correlations. Moreover, the NKL technique does not require any priors on the nature of the foregrounds, which is important when considering polarized foregrounds. We also introduce a modified version of Generalized Needlet Internal Linear Combination (GNILC), referred to as MGNILC, which incorporates an approximation of the foregrounds to improve performance. The NKL and MGNILC techniques are tested on simulated maps which include polarized foregrounds. Their performance is compared to the GNILC, generalized morphological component analysis, independent component analysis, and principal component analysis techniques. Two separate tests were performed. One at 1.84 < z < 2.55 and the other at 0.31 < z < 0.45. NKL was found to provide the best performance in both tests, providing a factor of 10–50 improvement over GNILC at |$k \lt 0.1\, {\rm hMpc^{-1}}$| in the higher redshift case and |$k \lt 0.03 \, {\rm hMpc^{-1}}$| in the lower redshift case. However, none of the methods were found to recover the power spectrum satisfactorily at all baryon acoustic oscillations scales. [ABSTRACT FROM AUTHOR]

This study investigated the genetic basis of carrot root shape traits using composite interval mapping in two biparental populations (n = 119 and n = 128). The roots of carrot F2:3 progenies were grown over 2 years and analyzed using a digital imaging pipeline to extract root phenotypes that compose market class. Broad-sense heritability on an entry-mean basis ranged from 0.46 to 0.80 for root traits. Reproducible quantitative trait loci (QTL) were identified on chromosomes 2 and 6 on both populations. Colocalization of QTLs for phenotypically correlated root traits was also observed and coincided with previously identified QTLs in published association and linkage mapping studies. Individual QTLs explained between 14 and 27% of total phenotypic variance across traits, while four QTLs for length-to-width ratio collectively accounted for up to 73% of variation. Predicted genes associated with the OFP-TRM (OVATE Family Proteins—TONNEAU1 Recruiting Motif) and IQD (IQ67 domain) pathway were identified within QTL support intervals. This observation raises the possibility of extending the current regulon model of fruit shape to include carrot storage roots. Nevertheless, the precise molecular mechanisms through which this pathway operates in roots characterized by secondary growth originating from cambium layers remain unknown. [ABSTRACT FROM AUTHOR]

Motivation Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structures of large protein complexes. Picking single protein particles from cryo-EM micrographs (images) is a crucial step in reconstructing protein structures from them. However, the widely used template-based particle picking process requires some manual particle picking and is labor-intensive and time-consuming. Though machine learning and artificial intelligence (AI) can potentially automate particle picking, the current AI methods pick particles with low precision or low recall. The erroneously picked particles can severely reduce the quality of reconstructed protein structures, especially for the micrographs with low signal-to-noise ratio. Results To address these shortcomings, we devised CryoTransformer based on transformers, residual networks, and image processing techniques to accurately pick protein particles from cryo-EM micrographs. CryoTransformer was trained and tested on the largest labeled cryo-EM protein particle dataset—CryoPPP. It outperforms the current state-of-the-art machine learning methods of particle picking in terms of the resolution of 3D density maps reconstructed from the picked particles as well as F1-score, and is poised to facilitate the automation of the cryo-EM protein particle picking. Availability and implementation The source code and data for CryoTransformer are openly available at: https://github.com/jianlin-cheng/CryoTransformer. [ABSTRACT FROM AUTHOR]

The low surface brightness (LSB) regime (μg  ≳  26 mag arcsec−2) comprises a vast, mostly unexplored discovery space, from dwarf galaxies to the diffuse interstellar medium. Accessing this regime requires precisely removing instrumental signatures and light contamination, including, most critically, night sky emission. This is not trivial, as faint astrophysical and instrumental contamination can bias sky models at the precision needed to characterize LSB structures. Using idealized synthetic images, we assess how this bias impacts two common LSB-oriented sky-estimation algorithms: (1) masking and parametric modelling, and (2) stacking and smoothing dithered exposures. Undetected flux limits both methods by imposing a pedestal offset to all derived sky models. Careful, deep masking of fixed sources can mitigate this, but source density always imposes a fundamental limit. Stellar scattered light can contribute ∼28–29 mag arcsec−2 of background flux even in low-density fields; its removal is critical prior to sky estimation. For complex skies, image combining is an effective non-parametric approach, although it strongly depends on observing strategy and adds noise to images on the smoothing kernel scale. Preemptive subtraction of fixed sources may be the only practical approach for robust sky estimation. We thus tested a third algorithm, subtracting a preliminary sky-subtracted coadd from exposures to isolate sky emission. Unfortunately, initial errors in sky estimation propagate through all subsequent sky models, making the method impractical. For large-scale surveys like Legacy Survey of Space and Time, where key science goals constrain observing strategy, masking and modelling remain the optimal sky estimation approach, assuming stellar scattered light is removed first. [ABSTRACT FROM AUTHOR]

Lung cancer is a leading cause of cancer mortality globally, highlighting the importance of understanding its mortality risks to design effective patient-centered therapies. The National Lung Screening Trial (NLST) employed computed tomography texture analysis, which provides objective measurements of texture patterns on CT scans, to quantify the mortality risks of lung cancer patients. Partially linear Cox models have gained popularity for survival analysis by dissecting the hazard function into parametric and nonparametric components, allowing for the effective incorporation of both well-established risk factors (such as age and clinical variables) and emerging risk factors (eg, image features) within a unified framework. However, when the dimension of parametric components exceeds the sample size, the task of model fitting becomes formidable, while nonparametric modeling grapples with the curse of dimensionality. We propose a novel Penalized Deep Partially Linear Cox Model (Penalized DPLC), which incorporates the smoothly clipped absolute deviation (SCAD) penalty to select important texture features and employs a deep neural network to estimate the nonparametric component of the model. We prove the convergence and asymptotic properties of the estimator and compare it to other methods through extensive simulation studies, evaluating its performance in risk prediction and feature selection. The proposed method is applied to the NLST study dataset to uncover the effects of key clinical and imaging risk factors on patients' survival. Our findings provide valuable insights into the relationship between these factors and survival outcomes. [ABSTRACT FROM AUTHOR]

Disruptions to dopamine and noradrenergic neurotransmission are noted in several neurodegenerative and psychiatric disorders. Neuromelanin-sensitive (NM)-MRI offers a non-invasive approach to visualize and quantify the structural and functional integrity of the substantia nigra and locus coeruleus. This method may aid in the diagnosis and quantification of longitudinal changes of disease and could provide a stratification tool for predicting treatment success of pharmacological interventions targeting the dopaminergic and noradrenergic systems. Given the growing clinical interest in NM-MRI, understanding the contrast mechanisms that generate this signal is crucial for appropriate interpretation of NM-MRI outcomes and for the continued development of quantitative MRI biomarkers that assess disease severity and progression. To date, most studies associate NM-MRI measurements to the content of the neuromelanin pigment and/or density of neuromelanin-containing neurons, while recent studies suggest that the main source of the NM-MRI contrast is not the presence of neuromelanin but the high-water content in the dopaminergic and noradrenergic neurons. In this review, we consider the biological and physical basis for the NM-MRI contrast and discuss a wide range of interpretations of NM-MRI. We describe different acquisition and image processing approaches and discuss how these methods could be improved and standardized to facilitate large-scale multisite studies and translation into clinical use. We review the potential clinical applications in neurological and psychiatric disorders and the promise of NM-MRI as a biomarker of disease, and finally, we discuss the current limitations of NM-MRI that need to be addressed before this technique can be utilized as a biomarker and translated into clinical practice and offer suggestions for future research. [ABSTRACT FROM AUTHOR]

We report on three optically bright, ∼16th mag, point sources within 10 arcsec of each other that vanished within 1 h, based on two consecutive exposures at Palomar Observatory on 1952 July 19 (POSS I Red and Blue). The three point sources have continued to be absent in telescope exposures during 71 yr with detection thresholds of ∼21st mag. We obtained two deep exposures with the 10.4-m Gran Telescopio Canarias on 2023 April 25 and 27 in r and g band, both reaching magnitude 25.5 (3σ). The three point sources are still absent, implying they have dimmed by more than 10 mag within an hour back in 1952. When bright in 1952, the most isolated transient source has a profile nearly the same as comparison stars, implying the sources are subarcsec in angular size and they exhibit no elongation due to movement. This triple transient has observed properties similar to other cases where groups of transients ('multiple transients') have appeared and vanished in a small region within a plate exposure. The explanation for these three transients and the previously reported cases remains unclear. Models involving background objects that are optically luminous for less than 1 h coupled with foreground gravitational lensing seem plausible. If so, a significant population of massive objects with structure serving as the lenses, to produce three images, are required to explain the subhour transients. [ABSTRACT FROM AUTHOR]

Source conditions are a key tool in regularisation theory that are needed to derive error estimates and convergence rates for ill-posed inverse problems. In this paper, we provide a recipe to practically compute source condition elements as the solution of convex minimisation problems that can be solved with first-order algorithms. We demonstrate the validity of our approach by testing it on two inverse problem case studies in machine learning and image processing: sparse coefficient estimation of a polynomial via LASSO regression and recovering an image from a subset of the coefficients of its discrete Fourier transform. We further demonstrate that the proposed approach can easily be modified to solve the machine learning task of identifying the optimal sampling pattern in the Fourier domain for a given image and variational regularisation method, which has applications in the context of sparsity promoting reconstruction from magnetic resonance imaging data. [ABSTRACT FROM AUTHOR]

We introduce a novel technique to mitigate the adverse effects of atmospheric turbulence on astronomical imaging. Utilizing a video-to-image neural network trained on simulated data, our method processes a sliding sequence of short-exposure (∼0.2 s) stellar field images to reconstruct an image devoid of both turbulence and noise. We demonstrate the method with simulated and observed stellar fields, and show that the brief exposure sequence allows the network to accurately associate speckles to their originating stars and effectively disentangle light from adjacent sources across a range of seeing conditions, all while preserving flux to a lower signal-to-noise ratio than an average stack. This approach results in a marked improvement in angular resolution without compromising the astrometric stability of the final image. [ABSTRACT FROM AUTHOR]

Molecular property prediction faces the challenge of limited labeled data as it necessitates a series of specialized experiments to annotate target molecules. Data augmentation techniques can effectively address the issue of data scarcity. In recent years, Mixup has achieved significant success in traditional domains such as image processing. However, its application in molecular property prediction is relatively limited due to the irregular, non-Euclidean nature of graphs and the fact that minor variations in molecular structures can lead to alterations in their properties. To address these challenges, we propose a novel data augmentation method called Mix-Key tailored for molecular property prediction. Mix-Key aims to capture crucial features of molecular graphs, focusing separately on the molecular scaffolds and functional groups. By generating isomers that are relatively invariant to the scaffolds or functional groups, we effectively preserve the core information of molecules. Additionally, to capture interactive information between the scaffolds and functional groups while ensuring correlation between the original and augmented graphs, we introduce molecular fingerprint similarity and node similarity. Through these steps, Mix-Key determines the mixup ratio between the original graph and two isomers, thus generating more informative augmented molecular graphs. We extensively validate our approach on molecular datasets of different scales with several Graph Neural Network architectures. The results demonstrate that Mix-Key consistently outperforms other data augmentation methods in enhancing molecular property prediction on several datasets. [ABSTRACT FROM AUTHOR]

The physical mechanisms controlling deep-focus earthquakes, or those observed at depths greater than 300 km, remain enigmatic. The leading processes by which deep-focus earthquakes are thought to occur include transformational faulting, thermal runaway and dehydration embrittlement, but distinguishing observations in support of one or more prevailing mechanisms are needed. In this study, we use a modified back-projection method, data recorded by the Hi-net array in Japan and a 3-D velocity model to produce source images of 19 deep-focus earthquakes within the Izu-Bonin subduction zone. We find that the rupture properties and fault plane orientations of imaged events separate according to reported moment magnitude, indicating the distinct operation of two moment-dependent causal mechanisms of deep-focus earthquakes in this region. We discuss these results in the context of previous observational, laboratory and numerical studies and emphasize the importance of continued research to validate the dual-mechanism hypothesis both in and outside Izu-Bonin. Such work may not only improve our understanding of the nucleation and propagation of deep-focus earthquakes, but also help clarify slab structure and subduction zone dynamics. [ABSTRACT FROM AUTHOR]

Determination of individual age is one essential step in the accurate assessment of fish stocks. In non-tropical environments, the manual count of ring-like growth patterns in fish otoliths (ear stones) is the standard method. It relies on visual means and individual judgment and thus is subject to bias and interpretation errors. The use of automated pattern recognition based on machine learning may help to overcome this problem. Here, we employ two deep learning methods based on Convolutional Neural Networks (CNNs). The first approach utilizes the Mask R-CNN algorithm to perform object detection on the major otolith reading axes. The second approach employs the U-Net architecture to perform semantic segmentation on the otolith image in order to segregate the regions of interest. For both methods, we applied a simple postprocessing to count the rings on the output masks returned, which corresponds to the age prediction. Multiple benchmark tests indicate the promising performance of our implemented approaches, comparable to recently published methods based on classical image processing and traditional CNN implementation. Furthermore, our algorithms showed higher robustness compared to the existing methods, while also having the capacity to extrapolate missing age groups and to adapt to a new domain or data source. [ABSTRACT FROM AUTHOR]

We develop a new deconvolution method to recover the precise Crab Nebula image taken by the Hitomi HXT, suppressing the artifact due to the bright Crab pulsar. We extend the Richardson–Lucy method, introducing two components corresponding to the nebula and pulsar with regularization for smoothness and flux, respectively, and performing simultaneous deconvolution of multi-pulse-phase images. The structures, including the torus and jets, seen in the deconvolved nebula image at the lowest energy band of 3.6–15 keV appear consistent with those identified in the high-resolution Chandra X-ray image. Above 15 keV, we confirm NuSTAR's findings that the nebula size decreases in higher energy bands. We find that the north-east side of the nebula is fainter in higher energy bands. Our deconvolution method is applicable for any telescope images of faint diffuse objects containing a bright point source. [ABSTRACT FROM AUTHOR]

Muography is an imaging technique that relies on the attenuation of the muon flux traversing geological or anthropogenic structures. Several simulation frameworks help to perform muography studies by combining specialized codes: for muon generation through muon transport to muon detector performance. This methodology is precise but requires significant computational resources and time. We present an end-to-end python-based MUographY Simulation Code, which implements a muography simulation framework capable of rapidly estimating muograms of any geological structure worldwide. This framework considers the generated muon flux as the observation point; the energy loss of muons passing through the geological target; the integrated muon flux detected by the telescope and estimates the 3-D density distribution of the target using algebraic reconstruction techniques. The simulations ignore the relatively small muon flux variance caused by geomagnetic effects, solar modulation and atmospheric conditions. We validate the code performance by comparing our simulation results with data from other frameworks. [ABSTRACT FROM AUTHOR]

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as noise and galactic foreground contamination that pose a challenge for accurate detection. In this study, we present the SegU-Net v2 framework, an enhanced version of our convolutional neural network, built to identify neutral and ionized regions in the 21-cm signal contaminated with foreground emission. We trained our neural network on 21-cm image data processed by a foreground removal method based on Principal Component Analysis achieving an average classification accuracy of 71 per cent between redshift z  = 7 and 11. We tested SegU-Net v2 against various foreground removal methods, including Gaussian Process Regression, Polynomial Fitting, and Foreground-Wedge Removal. Results show comparable performance, highlighting SegU-Net v2 's independence on these pre-processing methods. Statistical analysis shows that a perfect classification score with |${\rm AUC}=95~{{\ \rm per\ cent}}$| is possible for 8 < z < 10. While the network prediction lacks the ability to correctly identify ionized regions at higher redshift and differentiate well the few remaining neutral regions at lower redshift due to low contrast between 21-cm signal, noise, and foreground residual in images. Moreover, as the photon sources driving reionization are expected to be located inside ionized regions, we show that SegU-Net v2 can be used to correctly identify and measure the volume of isolated bubbles with |$V_{\rm ion}\gt (10\, {\rm cMpc})^3$| at z > 9, for follow-up studies with infrared/optical telescopes to detect these sources. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) and deep learning techniques are playing an increasing role in astronomy to deal with the data avalanche. Here we describe an application for finding resolved planetary nebulae (PNe) in crowded, wide-field, narrow-band Hα survey imagery in the Galactic plane, to test and facilitate more objective, reproducible, efficient and reliable trawls for them. PNe are important for studying the late-stage stellar evolution of low-mass to intermediate-mass stars. However, the confirmed ∼3800 Galactic PNe fall far short of the numbers expected. Traditional visual searching for resolved PNe is time-consuming because of the large data size and areal coverage of modern astronomical surveys. The training and validation data set of our algorithm was built with the INT Photometric Hα Survey (IPHAS) and true PNe from the Hong Kong/AAO/Strasbourg Hα (HASH) data base. Our algorithm correctly identified 444 PNe in the validation set of 454 PNe, with only 16 explicable 'false' positives, achieving a precision rate of 96.5 per cent and a recall rate of 97.8 per cent. After transfer learning, it was then applied to the VST Photometric Hα Survey of the Southern Galactic plane and bulge (VPHAS+), examining 979 out of 2284 survey fields, each covering 1° × 1°. It returned ∼20 000 detections, including 2637 known PNe and other kinds of catalogued non-PNe. A total of 815 new high-quality PNe candidates were found, 31 of which were selected as top-quality targets for optical spectroscopic follow-up. We found that 74 per cent of them are true, likely, and possible PNe. Representative preliminary confirmatory spectroscopy results are presented here to demonstrate the effectiveness of our techniques, with full details to be given in our forthcoming paper. [ABSTRACT FROM AUTHOR]

Remote sensing data are important for assessing ecological change, but their value is often restricted by their limited temporal coverage. Major historical events that affected the environment, such as those associated with colonial history, World War II, or the Green Revolution are not captured by modern remote sensing. In the present article, we highlight the potential of globally available black-and-white satellite photographs to expand ecological and conservation assessments back to the 1960s and to illuminate ecological concepts such as shifting baselines, time-lag responses, and legacy effects. This historical satellite photography can be used to monitor ecosystem extent and structure, species' populations and habitats, and human pressures on the environment. Even though the data were declassified decades ago, their use in ecology and conservation remains limited. But recent advances in image processing and analysis can now unlock this research resource. We encourage the use of this opportunity to address important ecological and conservation questions. [ABSTRACT FROM AUTHOR]

Upcoming imaging surveys will use weak gravitational lensing to study the large-scale structure of the Universe, demanding sub-per cent accuracy for precise cosmic shear measurements. We present a new differentiable implementation of our perturbation-based shear estimator (fpfs), using jax , which is publicly available as part of a new suite of analytic shear algorithms called anacal. This code can analytically calibrate the shear response of any non-linear observable constructed with the fpfs shapelets and detection modes utilizing autodifferentiation (ad), generalizing the formalism to include a family of shear estimators with corrections for detection and selection biases. Using the ad capability of jax , it calculates the full Hessian matrix of the non-linear observables, which improves the previously presented second-order noise bias correction in the shear estimation. As an illustration of the power of the new anacal framework, we optimize the effective galaxy number density in the space of the generalized shear estimators using an LSST-like galaxy image simulation for the 10 yr LSST. For the generic shear estimator, the magnitude of the multiplicative bias | m | is below 3 × 10−3 (99.7 per cent confidence interval), and the effective galaxy number density is improved by 5 per cent . We also discuss some planned future additions to the anacal software suite to extend its applicability beyond the fpfs measurements. [ABSTRACT FROM AUTHOR]

Chronic changes on kidney biopsy specimens include increasing amounts of arteriosclerosis, glomerulosclerosis, interstitial fibrosis and tubular atrophy, enlarged nephron size, and reduced nephron number. These chronic changes are difficult to accurately assess by visual inspection but are reasonably quantified using morphometry. This review describes the various patient populations that have undergone morphometric analysis of kidney biopsies. The common approaches to morphometric analysis are described. The chronic kidney disease outcomes associated with various chronic changes by morphometry are also summarized. Morphometry enriches the characterization of chronicity on a kidney biopsy and this can supplement the pathologist's diagnosis. Artificial intelligence image processing tools are needed to automate the annotations needed for practical morphometric analysis of kidney biopsy specimens in routine clinical care. [ABSTRACT FROM AUTHOR]

Large-scale astronomical surveys can capture numerous images of celestial objects, including galaxies and nebulae. Analysing and processing these images can reveal the intricate internal structures of these objects, allowing researchers to conduct comprehensive studies on their morphology, evolution, and physical properties. However, varying noise levels and point-spread functions can hamper the accuracy and efficiency of information extraction from these images. To mitigate these effects, we propose a novel image restoration algorithm that connects a deep-learning-based restoration algorithm with a high-fidelity telescope simulator. During the training stage, the simulator generates images with different levels of blur and noise to train the neural network based on the quality of restored images. After training, the neural network can restore images obtained by the telescope directly, as represented by the simulator. We have tested the algorithm using real and simulated observation data and have found that it effectively enhances fine structures in blurry images and increases the quality of observation images. This algorithm can be applied to large-scale sky survey data, such as data obtained by the Large Synoptic Survey Telescope (LSST), Euclid , and the Chinese Space Station Telescope (CSST), to further improve the accuracy and efficiency of information extraction, promoting advances in the field of astronomical research. [ABSTRACT FROM AUTHOR]

The recent serendipitous discovery of a new population of short duration X-ray transients, thought to be associated with collisions of compact objects or stellar explosions in distant galaxies, has motivated efforts to build up statistical samples by mining X-ray telescope archives. Most searches to date, however, do not fully exploit recent developments in the signal and imaging processing research domains to optimize searches for short X-ray flashes. This paper addresses this issue by presenting a new source detection pipeline, STATiX (Space and Time Algorithm for Transients in X-rays), which directly operates on three-dimensional X-ray data cubes consisting of two spatial and one temporal dimension. The algorithm leverages wavelet transforms and the principles of sparsity to denoise X-ray observations and then detect source candidates on the denoised data cubes. The light curves of the detected sources are then characterized using the Bayesian blocks algorithm to identify flaring periods. We describe the implementation of STATiX in the case of XMM–Newton data, present extensive validation and performance verification tests based on simulations and also apply the pipeline to a small subset of seven XMM–Newton observations, which are known to contain transients sources. In addition to known flares in the selected fields, we report a previously unknown short duration transient found by our algorithm that is likely associated with a flaring Galactic star. This discovery demonstrates the potential of applying STATiX to the full XMM–Newton archive. [ABSTRACT FROM AUTHOR]

We report on the detection of three icy cavities on the nucleus of comet 67P/Churyumov–Gerasimenko. They were identified on high-resolution anaglyphs built from images acquired by the Optical, Spectroscopic, and Infrared Remote Imaging System instrument aboard the Rosetta spacecraft on 2016 April 9 and 10. Visually, they appear as bright patches of typically 15 to 30 m across whose large reflectances and spectral slopes in the visible substantiate the presence of sub-surface water ice. Using a new high-resolution photogrammetric shape model, we determined the three-dimensional shape of these cavities whose depth ranges from 20 to 47 m. Spectral slopes were interpreted with models combining water ice and refractory dark material and the water ice abundances in the cavities were found to amount to a few per cent. The determination of the lifetime of the icy cavities was strongly biased by the availability of appropriate and favourable observations, but we found evidence of values of up to 2 yr. The icy cavities were found to be connected to jets well documented in past studies. A thermal model allowed us to track their solar insolation over a large part of the orbit of the comet and a transitory bright jet on 2015 July 18 was unambiguously linked to the brief illumination of the icy bottom of one of the cavities. These cavities are likely to be the first potential subsurface access points detected on a cometary nucleus and their lifetimes suggest that they reveal pristine sub-surface icy layers or pockets rather than recently recondensed water vapour. [ABSTRACT FROM AUTHOR]

We present the deepest J −Ks near-infrared photometry of the globular cluster M5 (NGC 5904) from observations taken with the Gemini South Adaptive Optics Imager in tandem with the Gemini Multi-conjugate adaptive optics System (GeMS) on the 8.1-m Gemini South telescope. Point spread function (PSF) photometry was carried out using a spatially variable PSF, zero-point calibrations based on correlations to a standard photometric catalogue, colour corrections, and crowding corrections. The latter corrections provided a new challenge given the field variations of the adaptive optics corrections in the central crowded regions of this cluster. The final photometric precision in our J− Ks colour–magnitude diagram exposes a dispersion among the lower main-sequence stars of M5 for the first time. This dispersion occurs below a main-sequence knee due to variations in the helium and CNO (carbon, nitrogen, and oxygen) abundances from multiple stellar populations, consistent with results from the bright evolved stars in this cluster from ultraviolet to near-infrared Hubble Space Telescope photometry and ground-based spectroscopy. This paper completes our original GeMS quality analysis programme, providing insights into adaptive optics analyses in crowded fields. [ABSTRACT FROM AUTHOR]

It is crucial for a deeper understanding of the formation and evolution of galaxies in the Universe to study stellar mass (M *) and star formation rate (SFR). Traditionally, astronomers infer the properties of galaxies from spectra, which are highly informative, but expensive and hard to be obtained. Fortunately, modern sky surveys obtained a vast amount of high-spatial-resolution photometric images. The photometric images are obtained relatively economically than spectra, and it is very helpful for related studies if M * and SFR can be estimated from photometric images. Therefore, this paper conducted some preliminary researches and explorations on this regard. We constructed a deep learning model named Galaxy Efficient Network (GalEffNet) for estimating integrated M * and specific star formation rate (sSFR) from Dark Energy Spectroscopic Instrument galaxy images. The GalEffNet primarily consists of a general feature extraction module and a parameter feature extractor. The research results indicate that the proposed GalEffNet exhibits good performance in estimating M * and sSFR, with σ reaching 0.218 and 0.410 dex. To further assess the robustness of the network, prediction uncertainty was performed. The results show that our model maintains good consistency within a reasonable bias range. We also compared the performance of various network architectures and further tested the proposed scheme using image sets with various resolutions and wavelength bands. Furthermore, we conducted applicability analysis on galaxies of various sizes, redshifts, and morphological types. The results indicate that our model performs well across galaxies with various characteristics and indicate its potentials of broad applicability. [ABSTRACT FROM AUTHOR]

In the past decade, ALMA observations of protoplanetary disks revealed various substructures including gaps and rings. Their origin of substructures may be probed through statistical studies of their physical properties. We present the analyses of archival ALMA Band 6 continuum data of 43 disks (39 Class II and four Herbig Ae) in the Taurus–Auriga region. We employ a novel 2D super-resolution imaging technique based on sparse modeling to obtain images with high fidelity and spatial resolution. As a result, we have obtained images with spatial resolutions comparable to a few au (⁠|${0_{.}^{\prime\prime}02}$| – |${0_{.}^{\prime\prime}1}$|⁠), which is two to three times better than conventional CLEAN methods. All dust disks are spatially resolved, with the radii ranging from 8 to 238 au with a median radius of 45 au. Half of the disks harbor clear gap structures, the radial locations of which show a bimodal distribution with peaks at ≲20 au and ≳30 au. We also see structures indicating weak gaps at all the radii in the disk. We find that the widths of these gaps increase with their depths, which is consistent with the model of planet–disk interactions. The inferred planet mass–orbital radius distribution indicates that the planet distribution is analogous to our solar system. However, planets with Neptune mass or lower may exist in all the radii. [ABSTRACT FROM AUTHOR]

STUDY QUESTION Can generative artificial intelligence (AI) models produce high-fidelity images of human blastocysts? SUMMARY ANSWER Generative AI models exhibit the capability to generate high-fidelity human blastocyst images, thereby providing substantial training datasets crucial for the development of robust AI models. WHAT IS KNOWN ALREADY The integration of AI into IVF procedures holds the potential to enhance objectivity and automate embryo selection for transfer. However, the effectiveness of AI is limited by data scarcity and ethical concerns related to patient data privacy. Generative adversarial networks (GAN) have emerged as a promising approach to alleviate data limitations by generating synthetic data that closely approximate real images. STUDY DESIGN, SIZE, DURATION Blastocyst images were included as training data from a public dataset of time-lapse microscopy (TLM) videos (n = 136). A style-based GAN was fine-tuned as the generative model. PARTICIPANTS/MATERIALS, SETTING, METHODS We curated a total of 972 blastocyst images as training data, where frames were captured within the time window of 110–120 h post-insemination at 1-h intervals from TLM videos. We configured the style-based GAN model with data augmentation (AUG) and pretrained weights (Pretrained-T: with translation equivariance; Pretrained-R: with translation and rotation equivariance) to compare their optimization on image synthesis. We then applied quantitative metrics including Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) to assess the quality and fidelity of the generated images. Subsequently, we evaluated qualitative performance by measuring the intelligence behavior of the model through the visual Turing test. To this end, 60 individuals with diverse backgrounds and expertise in clinical embryology and IVF evaluated the quality of synthetic embryo images. MAIN RESULTS AND THE ROLE OF CHANCE During the training process, we observed consistent improvement of image quality that was measured by FID and KID scores. Pretrained and AUG + Pretrained initiated with remarkably lower FID and KID values compared to both Baseline and AUG + Baseline models. Following 5000 training iterations, the AUG + Pretrained-R model showed the highest performance of the evaluated five configurations with FID and KID scores of 15.2 and 0.004, respectively. Subsequently, we carried out the visual Turing test, such that IVF embryologists, IVF laboratory technicians, and non-experts evaluated the synthetic blastocyst-stage embryo images and obtained similar performance in specificity with marginal differences in accuracy and sensitivity. LIMITATIONS, REASONS FOR CAUTION In this study, we primarily focused the training data on blastocyst images as IVF embryos are primarily assessed in blastocyst stage. However, generation of an array of images in different preimplantation stages offers further insights into the development of preimplantation embryos and IVF success. In addition, we resized training images to a resolution of 256 × 256 pixels to moderate the computational costs of training the style-based GAN models. Further research is needed to involve a more extensive and diverse dataset from the formation of the zygote to the blastocyst stage, e.g. video generation, and the use of improved image resolution to facilitate the development of comprehensive AI algorithms and to produce higher-quality images. WIDER IMPLICATIONS OF THE FINDINGS Generative AI models hold promising potential in generating high-fidelity human blastocyst images, which allows the development of robust AI models as it can provide sufficient training datasets while safeguarding patient data privacy. Additionally, this may help to produce sufficient embryo imaging training data with different (rare) abnormal features, such as embryonic arrest, tripolar cell division to avoid class imbalances and reach to even datasets. Thus, generative models may offer a compelling opportunity to transform embryo selection procedures and substantially enhance IVF outcomes. STUDY FUNDING/COMPETING INTEREST(S) This study was supported by a Horizon 2020 innovation grant (ERIN, grant no. EU952516) and a Horizon Europe grant (NESTOR, grant no. 101120075) of the European Commission to A.S. and M.Z.E. the Estonian Research Council (grant no. PRG1076) to A.S. and the EVA (Erfelijkheid Voortplanting & Aanleg) specialty program (grant no. KP111513) of Maastricht University Medical Centre (MUMC+) to M.Z.E. TRIAL REGISTRATION NUMBER Not applicable. [ABSTRACT FROM AUTHOR]

Radio galaxies exhibit a rich diversity of morphological characteristics, which make their classification into distinct types a complex challenge. To address this challenge effectively, we introduce an innovative approach for radio galaxy classification using COSFIRE filters. These filters possess the ability to adapt to both the shape and orientation of prototype patterns within images. The COSFIRE approach is explainable, learning-free, rotation-tolerant, efficient, and does not require a large training set. To assess the efficacy of our method, we conducted experiments on a benchmark radio galaxy data set comprising of 1180 training samples and 404 test samples. Notably, our approach achieved an average accuracy rate of 93.36 per cent. This achievement outperforms contemporary deep learning models, and it is the best result ever achieved on this data set. Additionally, COSFIRE filters offer better computational performance, ∼20 × fewer operations than the DenseNet-based competing method (when comparing at the same accuracy). Our findings underscore the effectiveness of the COSFIRE filter-based approach in addressing the complexities associated with radio galaxy classification. This research contributes to advancing the field by offering a robust solution that transcends the orientation challenges intrinsic to radio galaxy observations. Our method is versatile in that it is applicable to various image classification approaches. [ABSTRACT FROM AUTHOR]

Since the manufacture, import, and use of asbestos products have been completely abolished in Japan, the main cause of asbestos emissions into the atmosphere is the demolition and removal of buildings built with asbestos-containing materials. To detect and correct asbestos emissions from inappropriate demolition and removal operations at an early stage, a rapid method to measure atmospheric asbestos fibers is required. The current rapid measurement method is a combination of short-term atmospheric sampling and phase-contrast microscopy counting. However, visual counting takes a considerable amount of time and is not sufficiently fast. Using artificial intelligence (AI) to analyze microscope images to detect fibers may greatly reduce the time required for counting. Therefore, in this study, we investigated the use of AI image analysis for detecting fibers in phase-contrast microscope images. A series of simulated atmospheric samples prepared from standard samples of amosite and chrysotile were observed using a phase-contrast microscope. Images were captured, and training datasets were created from the counting results of expert analysts. We adopted 2 types of AI models—an instance segmentation model, namely the mask region-based convolutional neural network (Mask R-CNN), and a semantic segmentation model, namely the multi-level aggregation network (MA-Net)—that were trained to detect asbestos fibers. The accuracy of fiber detection achieved with the Mask R-CNN model was 57% for recall and 46% for precision, whereas the accuracy achieved with the MA-Net model was 95% for recall and 91% for precision. Therefore, satisfactory results were obtained with the MA-Net model. The time required for fiber detection was less than 1 s per image in both AI models, which was faster than the time required for counting by an expert analyst. [ABSTRACT FROM AUTHOR]

We previously constructed TheCellVision.org , a central repository for visualizing and mining data from yeast high-content imaging projects. At its inception, TheCellVision.org housed two high-content screening (HCS) projects providing genome-scale protein abundance and localization information for the budding yeast Saccharomyces cerevisiae , as well as a comprehensive analysis of the morphology of its endocytic compartments upon systematic genetic perturbation of each yeast gene. Here, we report on the expansion of TheCellVision.org by the addition of two new HCS projects and the incorporation of new global functionalities. Specifically, TheCellVision.org now hosts images from the Cell Cycle Omics project, which describes genome-scale cell cycle-resolved dynamics in protein localization, protein concentration, gene expression, and translational efficiency in budding yeast. Moreover, it hosts PIFiA, a computational tool for image-based predictions of protein functional annotations. Across all its projects, TheCellVision.org now houses >800,000 microscopy images along with computational tools for exploring both the images and their associated datasets. Together with the newly added global functionalities, which include the ability to query genes in any of the hosted projects using either yeast or human gene names, TheCellVision.org provides an expanding resource for single-cell eukaryotic biology. [ABSTRACT FROM AUTHOR]

Design randomizations and spatial corrections have increased understanding of genotypic, spatial, and residual effects in field experiments, but precisely measuring spatial heterogeneity in the field remains a challenge. To this end, our study evaluated approaches to improve spatial modeling using high-throughput phenotypes (HTP) via unoccupied aerial vehicle (UAV) imagery. The normalized difference vegetation index was measured by a multispectral MicaSense camera and processed using ImageBreed. Contrasting to baseline agronomic trait spatial correction and a baseline multitrait model, a two-stage approach was proposed. Using longitudinal normalized difference vegetation index data, plot level permanent environment effects estimated spatial patterns in the field throughout the growing season. Normalized difference vegetation index permanent environment were separated from additive genetic effects using 2D spline, separable autoregressive models, or random regression models. The Permanent environment were leveraged within agronomic trait genomic best linear unbiased prediction either modeling an empirical covariance for random effects, or by modeling fixed effects as an average of permanent environment across time or split among three growth phases. Modeling approaches were tested using simulation data and Genomes-to-Fields hybrid maize (Zea mays L.) field experiments in 2015, 2017, 2019, and 2020 for grain yield, grain moisture, and ear height. The two-stage approach improved heritability, model fit, and genotypic effect estimation compared to baseline models. Electrical conductance and elevation from a 2019 soil survey significantly improved model fit, while 2D spline permanent environment were most strongly correlated with the soil parameters. Simulation of field effects demonstrated improved specificity for random regression models. In summary, the use of longitudinal normalized difference vegetation index measurements increased experimental accuracy and understanding of field spatio-temporal heterogeneity. [ABSTRACT FROM AUTHOR]

Objective To evaluate the associations between analytical methods, such as microarray and enzyme-linked immunosorbent assay (ELISA); expedient cutoffs; and the lowest possible number of microarrays in analysis for target biomarker estimation in case-control studies. Methods This study included 321 serum specimens, gathered in different case-control studies to test for atherosclerosis and atrial fibrillation. Among them, 48 serum specimens were analyzed using microarray technology. We used ELISA and commercial kits for confirmation of the results. Results Three proteins—cadherin-P, neuronal nitric oxide synthase, and adenovirus fiber—were shown to have distinctly different values in the case group vs the control group. As a result, we used those proteins as the target for confirmation using our alternative analytical method. Also, these protein values represented the limiting range between the highest and lowest differences in case-control groups. The results of microarray assay were confirmed using ELISA and commercial kits in the same specimens, in which microarray profiling was performed, and also in separate large case-control groups. Conclusions A 1.5-fold difference in the protein content, as measured using microarray technology, was shown to be sufficient for further investigation of the candidate proteins. As few as 3 microarrays were considered sufficient for perspective evaluation of the target proteins. Microarray serum profiling, therefore, provides semiquantitative determination of protein in serum. [ABSTRACT FROM AUTHOR]