Article
Neurosciences
Yang Hu, Qingfeng Li, Kaini Qiao, Xiaochen Zhang, Bing Chen, Zhi Yang
Summary: Magnetic resonance imaging (MRI) is a non-invasive tool widely used for measuring human brain properties. However, there is a lack of processing pipelines for multi-modal MRI data, and the reliability and validity measures are inadequate. To address this, PhiPipe, a multi-modal MRI processing pipeline, was developed and evaluated. PhiPipe showed comparable or better reliability and validity compared to two popular single-modality pipelines. It provides a user-friendly solution for multi-modal MRI data processing and includes reliability and validity assessments to aid researchers in experimental design and statistical analysis. This study also presents a framework for evaluating the reliability and validity of image processing pipelines.
HUMAN BRAIN MAPPING
(2023)
Article
Environmental Sciences
Pei Nie, Zhenqi Cui, Yaping Wan
Summary: This paper introduces a rapid parallel remote sensing image mosaicking algorithm utilizing read filtering. By dividing the target images into blocks and storing them in a distributed file system, and using asynchronous reading and processing methods, the algorithm reduces data I/O and computing overhead and improves the efficiency of parallel computing.
Article
Neurosciences
Chih-Chin Heather Hsu, Shin Tai Chong, Yi-Chia Kung, Kuan-Tsen Kuo, Chu-Chung Huang, Ching-Po Lin
Summary: This article presents a semi-automated pipeline tool called iDIO for preprocessing and analysis of diffusion magnetic resonance imaging (dMRI) data. The tool integrates features from various advanced dMRI software tools and provides a set of suggested processing steps based on the image header of the input data. Additionally, the pipeline offers post-processing options such as estimation of diffusion tensor metrics and whole-brain tractography-based connectomes reconstruction. iDIO also generates an easy-to-interpret quality control report for data assessment.
HUMAN BRAIN MAPPING
(2023)
Article
Engineering, Biomedical
Kamlesh Pawar, Gary F. Egan, Zhaolin Chen
Summary: A deep learning method incorporating domain knowledge of parallel magnetic resonance imaging is proposed for accelerated image reconstruction, achieving significant improvements in accuracy and robustness compared to state-of-the-art methods. The method utilizes a novel loss function and outperforms others in various contrasts, showing stability and robustness to perturbations. Comprehensive validation on large datasets demonstrates accurate and stable image enhancement through the regularization of deep learning-based reconstruction with domain knowledge.
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
(2021)
Article
Biology
Gayathri Mahalingam, Russel Torres, Daniel Kapner, Eric T. Trautman, Tim Fliss, Shamishtaa Seshamani, Eric Perlman, Rob Young, Samuel Kinn, JoAnn Buchanan, Marc M. Takeno, Wenjing Yin, Daniel J. Bumbarger, Ryder P. Gwinn, Julie Nyhus, Ed Lein, Steven J. Smith, R. Clay Reid, Khaled A. Khairy, Stephan Saalfeld, Forrest Collman, Nuno Macarico da Costa
Summary: Serial-section electron microscopy is a high-resolution method for studying biological samples, with applications in reconstructing neural wiring diagrams. We present ASAP, a software pipeline that can handle large datasets in a distributed computational environment, offering high throughput and modular design.
Article
Computer Science, Artificial Intelligence
Joel Jonsson, Bevan L. Cheeseman, Suryanarayana Maddu, Krzysztof Gonciarz, Ivo F. Sbalzarini
Summary: This paper presents data structures and algorithms for native implementations of discrete convolution operators over Adaptive Particle Representations (APR) of images on parallel computer architectures. The APR is a content-adaptive image representation that reduces memory and runtime costs. The study provides efficient algorithmic building blocks for processing APR images and demonstrates the speedup achieved with APR convolution compared to pixel-based algorithms.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Astronomy & Astrophysics
S. J. Brennan, M. Fraser
Summary: AutoPhOT is a novel automated pipeline for rapid, publication-quality photometry of astronomical transients. It is capable of aperture and point-spread-function photometry, template subtraction, and calculation of limiting magnitudes. AutoPhOT can also calibrate photometry and reproduce published light curves with minimal human intervention.
ASTRONOMY & ASTROPHYSICS
(2022)
Article
Agriculture, Multidisciplinary
Aijing Feng, Chin Nee Vong, Jing Zhou, Lance S. Conway, Jianfeng Zhou, Earl D. Vories, Kenneth A. Sudduth, Newell R. Kitchen
Summary: Unmanned aerial vehicle (UAV) based remote sensing has been widely used in precision agriculture, and a near-real time image processing pipeline has been developed to improve the positioning accuracy of single UAV images. The pipeline eliminates the need for ground control points and image postprocessing steps, allowing for near-real time processing and potential real-time implementation using an onboard edge computing system.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Engineering, Electrical & Electronic
Yahui Tang, Kan Chang, Mengyuan Huang, Baoxin Li
Summary: This paper proposes a framework based on convolutional neural networks for mapping nonlinear sRGB images back to a linear color space. The framework models the ISP pipeline in both reverse and forward directions, achieving accurate mapping.
Article
Radiology, Nuclear Medicine & Medical Imaging
Marie-Judith Saint Martin, Fanny Orlhac, Pia Akl, Fahad Khalid, Christophe Nioche, Irene Buvat, Caroline Malhaire, Frederique Frouin
Summary: This paper describes a dedicated pipeline to increase reproducibility in breast MRI radiomic studies. The pipeline effectively reduces intra and inter-acquisition variabilities, harmonising radiomic features between coils and improving lesion classification performance. More work is needed to assess this pipeline on patient data for robust multi-scanner radiomic studies.
MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE
(2021)
Article
Engineering, Multidisciplinary
Yasheng Chang, Jianmin Gao
Summary: This study introduces a novel method for measuring the similarity of DR images from pressure pipeline welds. By proposing algorithms for tilt angle detection, weld area extraction, and local entropy enhancement, the method achieves an accurate calculation of image similarity.
Article
Engineering, Ocean
Yupeng Zhang, Hongwei Zhang, Jun Liu, Shitong Zhang, Zhi Liu, Enmou Lyu, Weiyu Chen
Summary: Submarine pipelines are a simple and efficient approach for transporting marine oil and gas resources. However, pipeline damage caused by natural or man-made causes can result in resource wastage and environmental pollution. This study proposes a tracking algorithm using forward-looking sonar to accurately track submarine pipelines. The algorithm combines the integrated navigation system and image processing techniques to achieve accurate and stable pipeline tracking.
APPLIED OCEAN RESEARCH
(2022)
Article
Astronomy & Astrophysics
E. Savary, K. Rojas, M. Maus, B. Clement, F. Courbin, R. Gavazzi, J. H. H. Chan, C. Lemon, G. Vernardos, R. Canameras, S. Schuldt, S. H. Suyu, J-C Cuillandre, S. Fabbro, S. Gwyn, M. J. Hudson, M. Kilbinger, D. Scott, C. Stone
Summary: In this study, a search for galaxy-scale strong gravitational lenses was conducted in the initial 2500 square degrees of the Canada-France Imaging Survey. A convolutional neural network committee was designed and applied to a selection of 2,344,002 r-band images of color-selected luminous red galaxies. A total of 133 lens candidates were found, of which 104 were completely new. The candidates were analyzed using an automated modeling step, providing distributions of properties for both sources and lenses.
ASTRONOMY & ASTROPHYSICS
(2022)
Article
Astronomy & Astrophysics
Jing-Hang Shi, Bo Qiu, A-Li Luo, Zhen-Dong He, Xiao Kong, Xia Jiang
Summary: The paper proposes a CNN-based photometric pipeline for SDSS images, which consists of target source detection and target source classification. The experiments show that the pipeline outperforms other networks in terms of accuracy, recall, and F1-score, and the target source classification network has higher accuracy, fewer parameters, and faster inference speed.
MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
(2022)
Article
Nanoscience & Nanotechnology
Scott C. McCormick, Namid Stillman, Matthew Hockley, Adam W. Perriman, Sabine Hauert
Summary: This study presents a new method for observing the transport dynamics of nanoparticles through tissue-mimetic microfluidic chips, demonstrating the size-dependence of nanoparticle penetration depth and the impact of the presence of microparticles on this process.
INTERNATIONAL JOURNAL OF NANOMEDICINE
(2021)
Article
Psychology, Developmental
Ekomobong E. Eyoh, Michelle D. Failla, Zachary J. Williams, Kyle L. Schwartz, Laurie E. Cutting, Bennett A. Landman, Carissa J. Cascio
Summary: In this study, researchers analyzed electronic medical records to find potential predictive markers for autism spectrum disorder (ASD) by comparing the medical conditions of 579 autistic individuals and 1897 matched controls before the age of 2. They found that Generalized convulsive epilepsy, nystagmus, lack of normal physiological development, delayed milestones, and strabismus were more likely in those later diagnosed with ASD, while perinatal jaundice was less likely to be associated. Strabismus and nystagmus, which are lesser-known conditions, could potentially improve screening practices for ASD.
JOURNAL OF AUTISM AND DEVELOPMENTAL DISORDERS
(2023)
Article
Clinical Neurology
Olwen C. Murphy, Elias S. Sotirchos, Grigorios Kalaitzidis, Elena Vasileiou, Henrik Ehrhardt, Jeffrey Lambe, Ohemaa Kwakyi, James Nguyen, Alexandra Zambriczki Lee, Julia Button, Blake E. Dewey, Scott D. Newsome, Ellen M. Mowry, Kathryn C. Fitzgerald, Jerry L. Prince, Peter A. Calabresi, Shiv Saidha
Summary: This study investigated longitudinal changes in brain volumetric measures and retinal layer thicknesses following acute optic neuritis in people with multiple sclerosis. The results suggest that there is anterograde trans-synaptic degeneration after acute optic neuritis, which may have clinical relevance to visual outcomes.
ANNALS OF NEUROLOGY
(2023)
Article
Clinical Neurology
Lori L. Beason-Held, Cailey I. Kerley, Shikha Chaganti, Abhay Moghekar, Madhav Thambisetty, Luigi Ferrucci, Susan M. Resnick, Bennett A. Landman
Summary: By examining medical records, this study identified health conditions associated with dementia, both shared and distinctive, and found that some conditions can be detected at least 5 years before dementia diagnosis. These findings emphasize the importance of medical intervention and treatment to minimize the impact of health comorbidities in the aging population.
ANNALS OF NEUROLOGY
(2023)
Article
Neurosciences
Katherine S. Aboud, Tin Q. Nguyen, Stephanie N. Del Tufo, Catie Chang, David H. Zald, Alexandra P. Key, Gavin R. Price, Bennett A. Landman, Laurie E. Cutting
Summary: In this study, a neurobiological model for real-time semantic cognition in the context of language comprehension is elucidated using fused functional magnetic resonance imaging and electroencephalography analysis. It is found that semantic cognition is supported by trade-offs between widespread neural networks over milliseconds. Moreover, mediatory relationships among these networks significantly predict language comprehension ability.
JOURNAL OF NEUROSCIENCE
(2023)
Article
Geriatrics & Gerontology
Corey W. Bown, Omair A. Khan, Dandan Liu, Samuel W. Remedios, Kimberly R. Pechman, James G. Terry, Sangeeta Nair, L. Taylor Davis, Bennett A. Landman, Katherine A. Gifford, Timothy J. Hohman, John Jeffrey Carr, Angela L. Jefferson
Summary: This study found that enlarged perivascular spaces (ePVS) are difficult to quantify and their etiologies and consequences are unclear. The results suggest that higher aortic stiffness is associated with greater basal ganglia ePVS burden, and ePVS burden is associated with adverse cognitive trajectory, highlighting the clinical relevance of ePVS.
NEUROBIOLOGY OF AGING
(2023)
Article
Neurosciences
Kurt G. Schilling, Shreyas Fadnavis, Joshua Batson, Mereze Visagie, Anna J. E. Combes, Samantha By, Colin D. McKnight, Francesca Bagnato, Eleftherios Garyfallidis, Bennett A. Landman, Seth A. Smith, Kristin P. O'Grady
Summary: This study evaluates several denoising approaches for quantitative diffusion MRI of the spinal cord. The findings show that all methods improve signal-to-noise ratio and lesion visibility, and MPPCA and Patch2Self methods excel at improving image quality and intra-cord contrast. These denoising approaches have the potential to facilitate reliable diffusion observations and measurements in the spinal cord.
Article
Psychology, Clinical
Ryan Ahmed, Brian D. Boyd, Damian Elson, Kimberly Albert, Patrick Begnoche, Hakmook Kang, Bennett A. Landman, Sarah M. Szymkowicz, Patricia Andrews, Jennifer Vega, Warren D. Taylor
Summary: This study found that clinical improvement in late-life depression is associated with functional connectivity in intrinsic brain networks, particularly in the default mode, cognitive control, and limbic networks. Future research should focus on clinical markers of network connectivity informing prognosis.
PSYCHOLOGICAL MEDICINE
(2023)
Article
Multidisciplinary Sciences
Rafael Paez, Michael N. Kammer, Aneri Balar, Dhairya A. Lakhani, Michael Knight, Dianna Rowe, David Xiao, Brent E. Heideman, Sanja L. Antic, Heidi Chen, Sheau-Chiann Chen, Tobias Peikert, Kim L. Sandler, Bennett A. Landman, Stephen A. Deppen, Eric L. Grogan, Fabien Maldonado
Summary: A deep learning model (LCP CNN) showed better discrimination than clinical prediction models for the stratification of indeterminate pulmonary nodules (IPNs). However, the model's score is based on a single timepoint and does not consider longitudinal information. Investigating the change in LCP CNN scores over time, it was found that malignant and benign nodules have distinctive trends, which may improve the prediction of lung cancer.
SCIENTIFIC REPORTS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Praitayini Kanakaraj, Leon Y. Cai, Tianyuan Yao, Francois Rheault, Baxter P. Rogers, Adam Anderson, Kurt G. Schilling, Bennett A. Landman
Summary: In diffusion-weighted MRI, hardware nonlinearities cause spatial variations in diffusion weighting. This study proposes a two-step signal approximation method for correcting gradient nonlinearities in DW-MRI. The method scales the diffusion signal and resamples the gradient orientations, resulting in uniform gradients and easy integration into existing diffusion workflows. The technique was validated using a NODDI model and showed no significant differences compared to voxel-wise correction. The two-step signal approximation provides an efficient solution for correcting gradient nonlinearities in DW-MRI.
MAGNETIC RESONANCE IMAGING
(2023)
Article
Computer Science, Information Systems
Ho Hin Lee, Yucheng Tang, Qi Yang, Xin Yu, Leon Y. Cai, Lucas W. Remedios, Shunxing Bao, Bennett A. Landman, Yuankai Huo
Summary: This article proposes a simple semantic-aware contrastive learning approach for multi-object semantic segmentation in medical imaging. The method utilizes attention masks and image-wise labels to improve the performance. Experimental results demonstrate a significant improvement in medical image segmentation.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Review
Anatomy & Morphology
Anneke Alkemade, Rosa Grossmann, Pierre-Louis Bazin, Birte U. Forstmann
Summary: Postmortem MRI can bridge histological observations and in vivo brain anatomy. Co-registration of data from the two techniques is gaining interest, but requires understanding of tissue properties and the effects of fixation on imaging quality. This review discusses existing studies and challenges in postmortem research, providing insight for understanding the human brain and promoting interdisciplinary discussions.
BRAIN STRUCTURE & FUNCTION
(2023)
Article
Clinical Neurology
Yisu Yang, Kurt Schilling, Niranjana Shashikumar, Varuna Jasodanand, Elizabeth E. Moore, Kimberly R. Pechman, Murat Bilgel, Lori L. Beason-Held, Yang An, Andrea Shafer, Shannon L. Risacher, Bennett A. Landman, Angela L. Jefferson, Andrew J. Saykin, Susan M. Resnick, Timothy J. Hohman, Derek B. Archer
Summary: This study examines white matter microstructure abnormalities along the AD continuum using DMRI data. The findings suggest that FW correction can provide further insights into the neurodegenerative process of white matter in AD.
ALZHEIMER'S & DEMENTIA: DIAGNOSIS, ASSESSMENT & DISEASE MONITORING
(2023)
Article
Anatomy & Morphology
Kurt G. Schilling, Derek Archer, Francois Rheault, Ilwoo Lyu, Yuankai Huo, Leon Y. Cai, Silvia A. Bunge, Kevin S. Weiner, John C. Gore, Adam W. Anderson, Bennett A. Landman
Summary: This study provides a comprehensive characterization of superficial white matter (SWM) in the human brain, revealing its features and mechanisms associated with brain development and aging. SWM thickness and volume vary across brain regions and change with age, showing associations with cortical thickness and curvature. SWM volume peaks in adolescence, stabilizes throughout adulthood, and decreases with age. This study represents the first description of SWM features across the lifespan and provides insights into normal aging.
BRAIN STRUCTURE & FUNCTION
(2023)
Review
Engineering, Biomedical
Can Cui, Haichun Yang, Yaohong Wang, Shilin Zhao, Zuhayr Asad, Lori A. Coburn, Keith T. Wilson, Bennett A. Landman, Yuankai Huo
Summary: The rapid development of diagnostic technologies in healthcare requires physicians to handle and integrate heterogeneous yet complementary data. Recent studies have focused on using multimodal deep learning technologies to extract and aggregate such data for more objective and quantitative computer-aided clinical decision making.
PROGRESS IN BIOMEDICAL ENGINEERING
(2023)
Article
Health Care Sciences & Services
Cailey Kerley, Tin Q. Nguyen, Karthik Ramadass, Laurie E. Cutting, Bennett A. Landman, Matthew Berger
Summary: pyPheWAS Explorer is a graphical interface that allows users to design, execute, and analyze PheWAS experiments. It provides visualizations of demographic variables and model results, increasing transparency. A case study of attention deficit hyperactivity disorder patients and matched controls demonstrates the utility of pyPheWAS Explorer.