More Like this

1. Lessons learned from the two largest Galaxy morphological classification catalogues built by convolutional neural networks

   https://doi.org/10.1093/mnras/stac3228  

   Cheng, T-Y ; Domínguez Sánchez, H. ; Vega-Ferrero, J. ; Conselice, C. J. ; Siudek, M. ; Aragón-Salamanca, A. ; Bernardi, M. ; Cooke, R. ; Ferreira, L. ; Huertas-Company, M. ; et al ( November 2022 , Monthly Notices of the Royal Astronomical Society)

   We compare the two largest galaxy morphology catalogues, which separate early- and late-type galaxies at intermediate redshift. The two catalogues were built by applying supervised deep learning (convolutional neural networks, CNNs) to the Dark Energy Survey data down to a magnitude limit of ∼21 mag. The methodologies used for the construction of the catalogues include differences such as the cutout sizes, the labels used for training, and the input to the CNN – monochromatic images versus gri-band normalized images. In addition, one catalogue is trained using bright galaxies observed with DES (i < 18), while the other is trained with bright galaxies (r < 17.5) and ‘emulated’ galaxies up to r-band magnitude 22.5. Despite the different approaches, the agreement between the two catalogues is excellent up to i < 19, demonstrating that CNN predictions are reliable for samples at least one magnitude fainter than the training sample limit. It also shows that morphological classifications based on monochromatic images are comparable to those based on gri-band images, at least in the bright regime. At fainter magnitudes, i > 19, the overall agreement is good (∼95 per cent), but is mostly driven by the large spiral fraction in the two catalogues. In contrast, the agreement within the elliptical population is not as good, especially at faint magnitudes. By studying the mismatched cases, we are able to identify lenticular galaxies (at least up to i < 19), which are difficult to distinguish using standard classification approaches. The synergy of both catalogues provides an unique opportunity to select a population of unusual galaxies.

    

   more » « less
2. Knee Osteoarthritis Classification Using 3D CNN and MRI

   https://doi.org/10.3390/app11115196  

   Guida, Carmine ; Zhang, Ming ; Shan, Juan ( June 2021 , Applied Sciences)

   null (Ed.)

   Osteoarthritis (OA) is the most common form of arthritis and can often occur in the knee. While convolutional neural networks (CNNs) have been widely used to study medical images, the application of a 3-dimensional (3D) CNN in knee OA diagnosis is limited. This study utilizes a 3D CNN model to analyze sequences of knee magnetic resonance (MR) images to perform knee OA classification. An advantage of using 3D CNNs is the ability to analyze the whole sequence of 3D MR images as a single unit as opposed to a traditional 2D CNN, which examines one image at a time. Therefore, 3D features could be extracted from adjacent slices, which may not be detectable from a single 2D image. The input data for each knee were a sequence of double-echo steady-state (DESS) MR images, and each knee was labeled by the Kellgren and Lawrence (KL) grade of severity at levels 0–4. In addition to the 5-category KL grade classification, we further examined a 2-category classification that distinguishes non-OA (KL ≤ 1) from OA (KL ≥ 2) knees. Clinically, diagnosing a patient with knee OA is the ultimate goal of assigning a KL grade. On a dataset with 1100 knees, the 3D CNN model that classifies knees with and without OA achieved an accuracy of 86.5% on the validation set and 83.0% on the testing set. We further conducted a comparative study between MRI and X-ray. Compared with a CNN model using X-ray images trained from the same group of patients, the proposed 3D model with MR images achieved higher accuracy in both the 5-category classification (54.0% vs. 50.0%) and the 2-category classification (83.0% vs. 77.0%). The result indicates that MRI, with the application of a 3D CNN model, has greater potential to improve diagnosis accuracy for knee OA clinically than the currently used X-ray methods. 

   more » « less
3. Cool interstellar medium as an evolutionary tracer in ALMA-observed local dusty early-type galaxies

   https://doi.org/10.1093/mnras/stac3001  

   Glass, David H. W. ; Sansom, Anne E. ; Davis, Timothy A. ; Popescu, Cristina C. ( October 2022 , Monthly Notices of the Royal Astronomical Society)

   The content and distribution of cool interstellar medium (<30 K) can indicate the evolutionary mechanisms that transform late-type to early-type galaxies (ETGs). To investigate this, ALMA observations of 12CO[2-1] line emission were obtained for five dusty ETGs from a complete sample in low-density environments. Four of the ETGs have massive (∼109 M⊙), extended molecular gas reservoirs with effective radii ∼3–5 kpc. This work provides a kinematic and structural analysis of these observations, to explore possible evolutionary mechanisms. Axisymmetric or bisymmetric kinematic models were fitted to observations of molecular gas discs, to quantify the dominant structures present and highlight additional structures or asymmetries. Integral field unit observations of these ETGs were also examined where available. Two of the ETGs, GAMA64646 and 622305, appear to have undergone tidal disturbance leading to molecular gas discs and/or star-forming inner rings. GAMA272990 may have undergone a merger, leading to an elliptical galaxy with an embedded star-forming molecular gas disc. GAMA622429 has probably undergone a minor merger, indicated by asymmetry in molecular gas distribution and disturbance in optical images. The remaining ETG, GAMA177186, was affected by source confusion from an offset source which could be a high-mass dust- and gas-rich object at high redshift. Overall, it appears that a high proportion of dusty ETGs in low-density environments have massive, extended molecular gas reservoirs, and have undergone some kind of interaction as part of their recent evolution. Secular evolution can then (re-)transform the ETGs from star-forming to passive galaxies.

    

   more » « less
4. The ultraviolet upturn in field luminous red galaxies at 0.3 < z < 0.7

   https://doi.org/10.1093/mnras/stac609  

   De Propris, R. ; Ali, S. S. ; Chung, C. ; Bremer, M. N. ; Phillipps, S. ( March 2022 , Monthly Notices of the Royal Astronomical Society)

   We derive the evolution of the ultraviolet upturn colour from a sample of field luminous red galaxies at 0.3 < z < 0.7 with −24 < Mr < −21.5. No individual objects are securely detected, so we stack several hundred galaxies within absolute magnitude and redshift intervals. We find that the colour of the ultraviolet upturn (in observed NUV − i which is approximately equivalent to the classical FUV − V at the redshifts of our targets) does not change strongly with redshift to z = 0.7. This behaviour is similar to that observed in cluster ellipticals over this same mass range and at similar redshifts, and we speculate that the processes involved in the origin of the UV upturn are the same. The observations are most consistent with spectral synthesis models containing a fraction of a helium rich stellar population with abundances between 37 per cent and 42 per cent, although we cannot formally exclude a contribution due to residual star formation at the $\sim 0.5\, \mathrm{ per\,cent}$ level (however, this appears unlikely for cluster galaxies that are believed to be more quenched). This suggests that the ultraviolet upturn is a primordial characteristic of early-type galaxies at all redshifts and that an unexpected nucleosynthesis channel may lead to nearly complete chemical evolution at early times.

    

   more » « less
5. Transfer learning for galaxy feature detection: Finding giant star-forming clumps in low-redshift galaxies using Faster Region-based Convolutional Neural Network

   https://doi.org/10.1093/rasti/rzae013  

   Popp, Jürgen J. ; Dickinson, Hugh ; Serjeant, Stephen ; Walmsley, Mike ; Adams, Dominic ; Fortson, Lucy ; Mantha, Kameswara ; Mehta, Vihang ; Dawson, James M. ; Kruk, Sandor ; et al ( April 2024 , RAS Techniques and Instruments)

   Giant star-forming clumps (GSFCs) are areas of intensive star-formation that are commonly observed in high-redshift (z ≳ 1) galaxies but their formation and role in galaxy evolution remain unclear. Observations of low-redshift clumpy galaxy analogues are rare but the availability of wide-field galaxy survey data makes the detection of large clumpy galaxy samples much more feasible. Deep Learning (DL), and in particular Convolutional Neural Networks (CNNs), have been successfully applied to image classification tasks in astrophysical data analysis. However, one application of DL that remains relatively unexplored is that of automatically identifying and localizing specific objects or features in astrophysical imaging data. In this paper, we demonstrate the use of DL-based object detection models to localize GSFCs in astrophysical imaging data. We apply the Faster Region-based Convolutional Neural Network object detection framework (FRCNN) to identify GSFCs in low-redshift (z ≲ 0.3) galaxies. Unlike other studies, we train different FRCNN models on observational data that was collected by the Sloan Digital Sky Survey and labelled by volunteers from the citizen science project ‘Galaxy Zoo: Clump Scout’. The FRCNN model relies on a CNN component as a ‘backbone’ feature extractor. We show that CNNs, that have been pre-trained for image classification using astrophysical images, outperform those that have been pre-trained on terrestrial images. In particular, we compare a domain-specific CNN – ‘Zoobot’ – with a generic classification backbone and find that Zoobot achieves higher detection performance. Our final model is capable of producing GSFC detections with a completeness and purity of ≥0.8 while only being trained on ∼5000 galaxy images.

    

   more » « less