-
Generating intermediate slices with U-nets in craniofacial CT images medRxiv. Radiol. Imaging Pub Date : 2024-05-09 Soh Nishimoto, Kenichiro Kawai, Koyo Nakajima, Hisako Ishise, Masao Kakibuchi
Aim The Computer Tomography (CT) imaging equipment varies across facilities, leading to inconsistent image conditions. This poses challenges for deep learning analysis using collected CT images. To standardize the shape of the matrix, the creation of intermediate slice images with the same width is necessary. This study aimed to generate inter-slice images from two existing CT images.
-
Automatic Lymph Nodes Segmentation and Histological Status Classification on Computed Tomography Scans Using Convolutional Neural Network medRxiv. Radiol. Imaging Pub Date : 2024-05-09 Alexey Shevtsov, Iaroslav Tominin, Vladislav Tominin, Vsevolod Malevanniy, Yury Esakov, Zurab Tukvadze, Andrey Nefedov, Piotr Yablonskii, Pavel Gavrilov, Vadim Kozlov, Mariya Blokhina, Elena Nalivkina, Victor Gombolevskiy, Yuriy Vasilev, Mariya Dugova, Valeria Chernina, Olga Omelyanskaya, Roman Reshetnikov, Ivan Blokhin, Mikhail Belyaev
Lung cancer is the second most common type of cancer worldwide, making up about 20% of all cancer deaths with less than 10% 5-year survival rate for the very late stage. The recent guidelines for the most common non-small-cell lung cancer (NSCLC) type recommend performing staging based on the 8th edition of TNM classification, where the mediastinal lymph node involvement plays a key role. However,
-
Probing intratumoral metabolic compartmentalisation in fumarate hydratase-deficient renal cancer using clinical hyperpolarised 13C-MRI and mass spectrometry imaging medRxiv. Radiol. Imaging Pub Date : 2024-05-08 Ines Horvat-Menih, Ruth Casey, James Denholm, Gregory Hamm, Heather Hulme, John Gallon, Alixander S Khan, Joshua Kaggie, Andrew B Gill, Andrew N Priest, Joao A G Duarte, Cissy Yong, Cara Brodie, James Whitworth, Simon T Barry, Richard J A Goodwin, Shubha Anand, Marc Dodd, Katherine Honan, Sarah J Welsh, Anne Y Warren, Tevita Aho, Grant D Stewart, Thomas J Mitchell, Mary A McLean, Ferdia A Gallagher
Background Fumarate hydratase-deficient renal cell carcinoma (FHd-RCC) is a rare and aggressive renal cancer subtype characterised by increased fumarate accumulation and upregulated lactate production. Renal tumours demonstrate significant intratumoral metabolic heterogeneity, which may contribute to treatment failure. Emerging non-invasive metabolic imaging techniques have clinical potential to more
-
K-means clustering of hyperpolarised 13C-MRI identifies intratumoural perfusion/metabolism mismatch in renal cell carcinoma as best predictor of highest grade medRxiv. Radiol. Imaging Pub Date : 2024-05-08 Ines Horvat-Menih, Alixander S Khan, Mary A McLean, Joao Duarte, Eva Serrao, Stephan Ursprung, Joshua D Kaggie, Andrew B Gill, Andrew N Priest, Mireia Crispin-Ortuzar, Anne Y Warren, Sarah J Welsh, Thomas J Mitchell, Grant D Stewart, Ferdia A Gallagher
Purpose Conventional renal mass biopsy approaches are inaccurate, potentially leading to undergrading. This study explored using hyperpolarised [1-13C]pyruvate MRI (HP 13C-MRI) to identify the most aggressive areas within the tumour of patients with clear cell renal cell carcinoma (ccRCC).
-
ShapeMed-Knee: A Dataset and Neural Shape Model Benchmark for Modeling 3D Femurs medRxiv. Radiol. Imaging Pub Date : 2024-05-07 Anthony A. Gatti, Louis Blankemeier, Dave Van Veen, Brian Hargreaves, Scott L. Delp, Garry E. Gold, Feliks Kogan, Akshay S. Chaudhari
Analyzing anatomic shapes of tissues and organs is pivotal for accurate disease diagnostics and clinical decision-making. One prominent disease that depends on anatomic shape analysis is osteoarthritis, which affects 30 million Americans. To advance osteoarthritis diagnostics and prognostics, we introduce ShapeMed-Knee, a 3D shape dataset with 9,376 high-resolution, medical-imaging-based 3D shapes
-
Auto-segmentation of thoraco-abdominal organs in pediatric dynamic MRI medRxiv. Radiol. Imaging Pub Date : 2024-05-06 Yusuf Akhtar, Jayaram K. Udupa, Yubing Tong, Tiange Liu, Caiyun Wu, Rachel Kogan, Mostafa Al-noury, Mahdie Hosseini, Leihui Tong, Samarth Mannikeri, Dewey Odhner, Joseph M. Mcdonough, Carina Lott, Abigail Clark, Patrick J. Cahill, Jason B. Anari, Drew A. Torigian
Purpose Analysis of the abnormal motion of thoraco-abdominal organs in respiratory disorders such as the Thoracic Insufficiency Syndrome (TIS) and scoliosis such as adolescent idiopathic scoliosis (AIS) or early onset scoliosis (EOS) can lead to better surgical plans. We can use healthy subjects to find out the normal architecture and motion of a rib cage and associated organs and attempt to modify
-
Impact of Non-Contrast Enhanced Imaging Input Sequences on the Generation of Virtual Contrast-Enhanced Breast MRI Scans using Neural Networks medRxiv. Radiol. Imaging Pub Date : 2024-05-06 Andrzej Liebert, Hannes Schreiter, Lorenz A Kapsner, Jessica Eberle, Chris Ehring, Dominique Hadler, Luise Brock, Ramona Erber, Julius Emons, Frederik B. Laun, Michael Uder, Evelyn Wenkel, Sabine Ohlmeyer, Sebastian Bickelhaupt
Background Virtual contrast-enhanced (vCE) imaging techniques are an emerging topic of research in breast MRI.
-
Transcranial Blood–Brain Barrier Opening in Alzheimer’s Disease Patients Using a Portable Focused Ultrasound System with Real-Time 2-D Cavitation Mapping medRxiv. Radiol. Imaging Pub Date : 2024-05-06 Sua Bae, Keyu Liu, Antonios N. Pouliopoulos, Robin Ji, Sergio Jiménez-Gambín, Omid Yousefian, Alina R. Kline-Schoder, Alec J. Batts, Fotios N. Tsitsos, Danae Kokossis, Akiva Mintz, Lawrence S. Honig, Elisa E. Konofagou
Background Focused ultrasound (FUS) in combination with microbubbles has recently shown great promise in facilitating blood-brain barrier (BBB) opening for drug delivery and immunotherapy in Alzheimer’s disease (AD). However, it is currently limited to systems integrated within the MRI suites or requiring post-surgical implants, thus restricting its widespread clinical adoption. In this pilot study
-
Diffusion Tensor Phenomapping of the Healthy and Pressure-Overloaded Human Heart medRxiv. Radiol. Imaging Pub Date : 2024-05-05 Christopher A. Rock, Y. Iris Chen, Ruopeng Wang, Anne L. Philip, Boris Keil, Rory B. Weiner, Sammy Elmariah, Choukri Mekkaoui, Christopher T. Nguyen, David E. Sosnovik
Current techniques to image the microstructure of the heart with diffusion tensor MRI (DTI) are highly under-resolved. We present a technique to improve the spatial resolution of cardiac DTI by almost 10-fold and leverage this to measure local gradients in cardiomyocyte alignment or helix angle (HA). We further introduce a phenomapping approach based on voxel-wise hierarchical clustering of these gradients
-
An Anthropomorphic Diagnosis System of Pulmonary Nodules using Weak Annotation-Based Deep Learning medRxiv. Radiol. Imaging Pub Date : 2024-05-05 Lipeng Xie, Yongrui Xu, Mingfeng Zheng, Yundi Chen, Min Sun, Michael A. Archer, Yuan Wan, Wenjun Mao, Yubing Tong
Purpose To develop an anthropomorphic diagnosis system of pulmonary nodules (PN) based on Deep learning (DL) that is trained by weak annotation data and has comparable performance to full-annotation based diagnosis systems.
-
Investigation of the differential biology between benign and malignant renal masses using advanced magnetic resonance imaging techniques (IBM-Renal): a multi-arm, non-randomised feasibility study medRxiv. Radiol. Imaging Pub Date : 2024-05-05 Ines Horvat-Menih, Mary McLean, Maria Jesus Zamora-Morales, Marta Wylot, Joshua Kaggie, Alixander S Khan, Andrew B Gill, Joao Duarte, Matthew J Locke, Iosif A Mendichovszky, Hao Li, Andrew N Priest, Anne Y Warren, Sarah J Welsh, James O Jones, James N Armitage, Thomas J Mitchell, Grant D Stewart, Ferdia A Gallagher
Introduction Localised renal masses are an increasing burden on healthcare due to the rising number of cases. However, conventional imaging cannot reliably distinguish between benign and malignant renal masses, and renal mass biopsies are unable to characterise the entirety of the tumour due to sampling error, which may lead to delayed treatment or overtreatment. There is an unmet clinical need to
-
Interactive Segmentation of Lung Tissue and Lung Excursion in Thoracic Dynamic MRI Based on Shape-guided Convolutional Neural Networks medRxiv. Radiol. Imaging Pub Date : 2024-05-04 Lipeng Xie, Jayaram K. Udupa, Yubing Tong, Joseph M. McDonough, Patrick J. Cahill, Jason B. Anari, Drew A. Torigian
Purpose Lung tissue and lung excursion segmentation in thoracic dynamic magnetic resonance imaging (dMRI) is a critical step for quantitative analysis of thoracic structure and function in patients with respiratory disorders such as Thoracic Insufficiency Syndrome (TIS). However, the complex variability of intensity and shape of anatomical structures and the low contrast between the lung and surrounding
-
An Accelerated PETALUTE MRI Sequence for In Vivo Quantification of Sodium Content in Human Articular Cartilage at 3T medRxiv. Radiol. Imaging Pub Date : 2024-05-03 Cameron X. Villarreal, Xin Shen, Ahmad A. Alhulail, Nicholas M. Buffo, Xiaopeng Zhou, Evan Pogue, Armin Nagel, Ali Caglar Özen, Mark Chiew, Stephen Sawiak, Uzay Emir, Deva D. Chan
In this work, we demonstrate the sodium magnetic resonance imaging (MRI) capabilities of a three-dimensional (3D) dual-echo ultrashort echo time (UTE) sequence with a novel rosette petal trajectory (PETALUTE), in comparison to the 3D density-adapted (DA) radial spokes UTE sequence. We scanned five healthy subjects using a 3D dual-echo PETALUTE acquisition and two comparable implementations of 3D DA-radial
-
Assessment of 3D hemi-diaphragmatic motion via free-breathing dynamic MRI in pediatric thoracic insufficiency syndrome medRxiv. Radiol. Imaging Pub Date : 2024-05-03 Mahdie Hosseini, Jayaram K. Udupa, You Hao, Yubing Tong, Caiyun Wu, Yusuf Akhtar, Mostafa Al-Noury, Shiva Shaghaghi, Joseph M. McDonough, David M. Biko, Samantha Gogel, Oscar H. Mayer, Patrick J. Cahill, Drew A. Torigian, Jason B. Anari
Purpose Thoracic insufficiency syndrome (TIS) affects ventilatory function due to spinal and thoracic deformities limiting lung space and diaphragmatic motion. Corrective orthopedic surgery can be used to help normalize skeletal anatomy, restoring lung space and diaphragmatic motion. This study employs free-breathing dynamic MRI (dMRI) and quantifies the 3D motion of each hemi-diaphragm surface in
-
MyoVision-US: an Artificial Intelligence-Powered Software for Automated Analysis of Skeletal Muscle Ultrasonography medRxiv. Radiol. Imaging Pub Date : 2024-04-30 Zoe Calulo Rivera, Felipe González-Seguel, Arimitsu Horikawa-Strakovsky, Catherine Granger, Aarti Sarwal, Sanjay Dhar, George Ntoumenopoulos, Jin Chen, V. K. Cody Bumgardner, Selina M. Parry, Kirby P. Mayer, Yuan Wen
Introduction/Aims Muscle ultrasound has high utility in clinical practice and research; however, the main challenges are the training and time required for manual analysis to achieve objective quantification of morphometry. This study aimed to develop and validate a software tool powered by artificial intelligence (AI) by measuring its consistency and predictability of expert manual analysis quantifying
-
Lowering The Acoustic Noise Burden in MRI with Predictive Noise Canceling medRxiv. Radiol. Imaging Pub Date : 2024-04-30 Paulina Šiurytė, Sebastian Weingärtner
Even though Magnetic Resonance Imaging (MRI) exams are performed up to 16 times per every 100 inhabitants each year, patient comfort and acceptance rates are strongly compromised by exposure to loud acoustic noise. Here we present a system for acoustic noise cancellation using anti-noise derived from predicted scanner sounds. In this approach, termed predictive noise canceling (PNC), the acoustic fingerprint
-
Histology-informed liver diffusion MRI: biophysical model design and demonstration in cancer immunotherapy medRxiv. Radiol. Imaging Pub Date : 2024-04-29 Francesco Grussu, Kinga Bernatowicz, Marco Palombo, Irene Casanova-Salas, Ignasi Barba, Sara Simonetti, Garazi Serna, Athanasios Grigoriou, Anna Voronova, Valezka Garay, Juan Francisco Corral, Marta Vidorreta, Pablo García-Polo García, Xavier Merino, Richard Mast, Núria Roson, Manuel Escobar, Maria Vieito, Rodrigo Toledo, Paolo Nuciforo, Joaquin Mateo, Elena Garralda, Raquel Perez-Lopez
Innovative diffusion Magnetic Resonance Imaging (dMRI) models enable in vivo mapping of biologically meaningful properties such as cell size, potential biomarkers in cancer. However, while cancers frequently spread to the liver, models tailored for liver applications and easy to deploy in the clinic are still sought. We tackle this unmet need by delivering a practical and clinically viable liver dMRI
-
How Do Neurotransmitter Pathways Contribute to Neuroimaging Phenotypes? medRxiv. Radiol. Imaging Pub Date : 2024-04-29 Amir Ebneabbasi, Mortaza Afshani, Arman Seyed-Ahmadi, Varun Warrier, Richard A.I. Bethlehem, Timothy Rittman
Neuroimaging could accurately reflect human behaviour in health and disease, but the mechanism by which image-derived phenotypes correspond to neurotransmitter systems remains uncertain. Prior studies have explored spatial correlations between neuroimaging phenotypes and positron emission tomography radiotracers. However, the influence of neurotransmitters goes beyond the receptors/transporters, influencing
-
Altered Brain Glucose Metabolism in COVID-19 disease: An activation likelihood estimation Meta-analysis medRxiv. Radiol. Imaging Pub Date : 2024-05-01 Dongju Kang, Hyunji Jung, Kyoungjune Pak
Purpose COVID-19, caused by the SARS-CoV-2 virus, has significantly altered modern society and lifestyles. We investigated its impact on brain glucose metabolism by meta-analyzing existing studies that utilized 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) scans of the brain.
-
Harmonizing multisite neonatal diffusion-weighted brain MRI data for developmental neuroscience medRxiv. Radiol. Imaging Pub Date : 2024-05-01 Alexandra F. Bonthrone, Manuel Blesa Cábez, A. David Edwards, Jo V. Hajnal, Serena J. Counsell, James P. Boardman
Large diffusion-weighted brain MRI (dMRI) studies in neonates are crucial for developmental neuroscience. Our aim was to investigate the utility of ComBat, and empirical Bayes tool for multisite harmonization, for removing site effects from white matter (WM) dMRI measures in healthy infants born 37-42+6 weeks from the Theirworld Edinburgh Birth Cohort (n=86) and Developing Human Connectome Project
-
Prompt Engineering Strategies Improve the Diagnostic Accuracy of GPT-4 Turbo in Neuroradiology Cases medRxiv. Radiol. Imaging Pub Date : 2024-05-01 Akihiko Wada, Toshiaki Akashi, George Shih, Akifumi Hagiwara, Mitsuo Nishizawa, Yayoi Hayakawa, Junko Kikuta, Keigo Shimoji, Katsuhiro Sano, Koji Kamagata, Atsushi Nakanishi, Shigeki Aoki
Background Large language models (LLMs) like GPT-4 demonstrate promising capabilities in medical image analysis, but their practical utility is hindered by substantial misdiagnosis rates ranging from 30-50%.
-
Radiomic analysis of patient and inter-organ heterogeneity in response to immunotherapies and BRAF targeted therapy in metastatic melanoma medRxiv. Radiol. Imaging Pub Date : 2024-04-27 Alexandra Tompkins, Zane N. Gray, Rebekah E. Dadey, Serafettin Zenkin, Nasim Batavani, Sarah Newman, Afsaneh Amouzegar, Murat Ak, Nursima Ak, Taha Yasin Pak, Vishal Peddagangireddy, Priyadarshini Mamindla, Sarah Behr, Amy Goodman, Darcy L. Ploucha, John M. Kirkwood, Hassane M. Zarour, Yana G. Najjar, Diwakar Davar, Rivka Colen, Jason J. Luke, Riyue Bao
Background Variability in treatment response may be attributable to organ-level heterogeneity in tumor lesions. Radiomic analysis of medical images can elucidate non-invasive biomarkers of clinical outcome. Organ-specific radiomic comparison across immunotherapies and targeted therapies has not been previously reported.
-
No-code machine learning in radiology: implementation and validation of a platform that allows clinicians to train their own models medRxiv. Radiol. Imaging Pub Date : 2024-04-26 Daniel C. Elton, Giridhar Dasegowda, James Y. Sato, Emiliano G. Frias, Christopher P. Bridge, Artem B. Mamonov, Mark Walters, Martynas Ziemelis, Thomas J. Schultz, Bernardo C. Bizzo, Keith J. Dreyer, Mannudeep K. Kalra
Machine learning models can assist clinicians and researchers in many tasks within radiology such as diagnosis, triage, segmentation/measurement, and quality assurance. To better leverage machine learning we have developed a platform that allows users to label data and train models without requiring any programming knowledge. The technology stack consists of a TypeScript web application running on
-
Advanced MRI Prediction Model for Anatomical Site Identification in Uterine Carcinoma: Enhancing Diagnostic Accuracy and Treatment Planning medRxiv. Radiol. Imaging Pub Date : 2024-04-26 Mahrooz Malek, Moneereh moayeri, Setareh Akhavan, Shahrzad Sheikh Hasani, Fatemeh Nili, Zahra Mahboubi-Fooladi
Introduction The uterine carcinoma is the most commonly diagnosed malignancy in female pelvis. Accurate identification of tumor origin is crucial for determining appropriate treatment approaches. This study aims to develop a prediction model using multiple MRI parameters to accurately diagnose uterine cancer with an indistinctive origin and those involving both the endometrium and cervix prior to treatment
-
Holistic AI analysis of hybrid cardiac perfusion images for mortality prediction medRxiv. Radiol. Imaging Pub Date : 2024-04-24 Anna M Michalowska, Wenhao Zhang, Aakash Shanbhag, Robert JH Miller, Mark Lemley, Giselle Ramirez, Mikolaj Buchwald, Aditya Killekar, Paul B Kavanagh, Attila Feher, Edward J Miller, Andrew J Einstein, Terrence D Ruddy, Joanna X Liang, Valerie Builoff, David Ouyang, Daniel S Berman, Damini Dey, Piotr J Slomka
Background While low-dose computed tomography scans are traditionally used for attenuation correction in hybrid myocardial perfusion imaging (MPI), they also contain additional anatomic and pathologic information not utilized in clinical assessment. We seek to uncover the full potential of these scans utilizing a holistic artificial intelligence (AI)-driven image framework for image assessment.
-
Complex Regulation of Protocadherin Epigenetics on Aging-Related Brain Health medRxiv. Radiol. Imaging Pub Date : 2024-04-22 Vanessa Schmithorst, Abha Bais, Daryaneh Badaly, Kylia Williams, George Gabriel, Rafael Ceschin, Julia Wallace, Vince Lee, Oscar Lopez, Annie Cohen, Lisa J. Martin, Cecilia Lo, Ashok Panigrahy
Life expectancy continues to increase in the high-income world due to advances in medical care; however, quality of life declines with increasing age due to normal aging processes. Current research suggests that various aspects of aging are genetically modulated and thus may be slowed via genetic modification. Here, we show evidence for epigenetic modulation of the aging process in the brain from over
-
Development and Validation of a Paralimbic Related Subcortical Brain Dysmaturation MRI Score in Infants with Congenital Heart Disease medRxiv. Radiol. Imaging Pub Date : 2024-04-22 William T. Reynolds, Jodie K. Votava-Smith, George Gabriel, Vince Lee, Vidya Rajagopalan, Yijen Wu, XiaoQin Liu, Hisato Yagi, Ruby Slabicki, Brian Gibbs, Nhu N. Tran, Molly Weisert, Laura Cabral, Subramanian Subramanian, Julia Wallace, Sylvia del Castillo, Tracy Baust, Jacqueline Weinberg, Lauren Lorenzi Quigley, Jenna Gaesser, Sharon H. O’Neil, Vanessa Schmithorst, Rafael Ceschin, Cecilia Lo, Ashok
Background Brain magnetic resonance imaging (MRI) of infants with congenital heart disease (CHD) shows brain immaturity assessed via a cortical-based semi-quantitative score. Our primary aim was to develop an infant paralimbic-related subcortical-based semi-quantitative dysmaturation score, a brain dysplasia score (BDS), to detect abnormalities in CHD infants and predict clinical outcomes. Our secondary
-
SCIseg: Automatic Segmentation of T2-weighted Intramedullary Lesions in Spinal Cord Injury medRxiv. Radiol. Imaging Pub Date : 2024-04-21 Enamundram Naga Karthik, Jan Valosek, Andrew C. Smith, Dario Pfyffer, Simon Schading-Sassenhausen, Lynn Farner, Kenneth A. Weber, Patrick Freund, Julien Cohen-Adad
Purpose To develop a deep learning tool for the automatic segmentation of T2-weighted intramedullary lesions in spinal cord injury (SCI).
-
Functional network organization is locally atypical in children and adolescents with congenital heart disease medRxiv. Radiol. Imaging Pub Date : 2024-04-20 Joy Roy, William Reynolds, Ashok Panigrahy, Rafael Ceschin
Children and adolescents with congenital heart disease (CHD) frequently experience neurodevelopmental impairments that can impact academic performance, memory, attention, and behavioral function, ultimately affecting overall quality of life. This study aims to investigate the impact of CHD on functional brain network connectivity and cognitive function. Using resting-state fMRI data, we examined several
-
Quantitative Magnetic Resonance Cerebral Spinal Fluid Flow Properties and Executive Function Cognitive Outcomes in Congenital Heart Disease medRxiv. Radiol. Imaging Pub Date : 2024-04-20 Vincent Kyu Lee, William T. Reynolds, Julia Wallace, Nancy Beluk, Daryaneh Badaly, Cecilia W Lo, Rafael Ceschin, Ashok Panigrahy
Cerebrospinal fluid (CSF) circulation has recently been shown to be important in nutrient distribution, waste removal, and neurogenesis. Increased CSF volumes are frequently observed in congenital heart disease (CHD) and are associated with neurodevelopmental deficits. This suggests prolonged perturbation to the CSF system and possible interference to its homeostatic function, which may contribute
-
Fully automatic segmentation of brain lacunas resulting from resective surgery using a 3D deep learning model medRxiv. Radiol. Imaging Pub Date : 2024-04-17 Raphael Fernandes Casseb, Brunno Machado de Campos, Wallace Souza Loos, Marcelo Eduardo Ramos Barbosa, Marina Koutsodontis Machado Alvim, Gabriel Chagas Lutfala Paulino, Francesco Pucci, Samuel Worrell, Roberto Medeiros de Souza, Lara Jehi, Fernando Cendes
The rapid and constant development of deep learning (DL) strategies is pushing forward the quality of object segmentation in images from diverse fields of interest. In particular, these algorithms can be very helpful in delineating brain abnormalities (lesions, tumors, lacunas, etc), enabling the extraction of information such as volume and location, that can inform doctors or feed predictive models
-
Validation of Left Ventricular High Frame Rate Echo-Particle Image Velocimetry against 4D Flow MRI in Patients medRxiv. Radiol. Imaging Pub Date : 2024-04-16 Yichuang Han, Daniel J. Bowen, Bernardo Loff Barreto, Robert. R. Zwaan, Mihai Strachinaru, Rob J. van der Geest, Alexander Hirsch, Annemien E. van den Bosch, Johan G. Bosch, Jason Voorneveld
Aims Accurately measuring intracardiac flow patterns could provide insights into cardiac disease pathophysiology, potentially enhancing diagnostic and prognostic capabilities. This study aims to validate Echo-Particle Image Velocimetry (echoPIV) for in-vivo left ventricular intracardiac flow imaging against 4D flow MRI.
-
Automated quality control of T1-weighted brain MRI scans for clinical research: methods comparison and design of a quality prediction classifier medRxiv. Radiol. Imaging Pub Date : 2024-04-15 Gaurav Bhalerao, Grace Gillis, Mohamed Dembele, Sana Suri, Klaus Ebmeier, Johannes Klein, Michele Hu, Clare Mackay, Ludovica Griffanti
Introduction T1-weighted MRI is widely used in clinical neuroimaging for studying brain structure and its changes, including those related to neurodegenerative diseases, and as anatomical reference for analysing other modalities. Ensuring high-quality T1-weighted scans is vital as image quality affects reliability of outcome measures. However, visual inspection can be subjective and time-consuming
-
Multimodal surface coils for low field MR imaging medRxiv. Radiol. Imaging Pub Date : 2024-04-15 Yunkun Zhao, Aditya A Bhosale, Xiaoliang Zhang
Low field MRI is safer and more cost effective than the high field MRI. One of the inherent problems of low field MRI is its low signal-to-noise ratio or sensitivity. In this work, we introduce a multimodal surface coil technique for signal excitation and reception to improve the RF magnetic field (B1) efficiency and potentially improve MR sensitivity. The proposed multimodal surface coil consists
-
Explainable AI in Deep Learning-based Detection of Aortic Elongation on Chest X-ray Images medRxiv. Radiol. Imaging Pub Date : 2024-04-15 Estela Ribeiro, Diego A. C. Cardenas, Felipe M. Dias, Jose E. Krieger, Marco A. Gutierrez
Aim Aortic Elongation can result from age-related changes, congenital factors, aneurysms, or conditions affecting blood vessel elasticity. It is associated with cardiovascular diseases and severe complications like aortic aneurysms and dissection. We aim to assess qualitatively and quantitatively explainable methods in order to understand the decisions of a deep learning model for Aortic Elongation
-
The application of deep learning in lung cancerous lesion detection medRxiv. Radiol. Imaging Pub Date : 2024-04-15 Phuong Thi Minh Chu, Tram Pham Bich Ha, Ngoc Minh Vu, Hoang Ha, Thu Minh Doan
Background Characterized by rapid metastasis and a significant death rate, lung cancer presents a formidable challenge, which underscores the critical role of early detection in combating the disease. This study addresses the urgent need for early lung cancer detection using deep learning models applied to computed tomography (CT) images.
-
Diagnostic Performance of Claude 3 from Patient History and Key Images in Diagnosis Please Cases medRxiv. Radiol. Imaging Pub Date : 2024-04-14 Ryo Kurokawa, Yuji Ohizumi, Jun Kanzawa, Mariko Kurokawa, Takao Kiguchi, Wataru Gonoi, Osamu Abe
Backgrounds Large language artificial intelligence models have showed its diagnostic performance based solely on textual information from clinical history and imaging findings. However, the extent of their performance when utilizing radiological images and providing differential diagnoses has yet to be investigated.
-
Exploratory Study on COPD Phenotypes and their Progression: Integrating SPECT and qCT Imaging Analysis medRxiv. Radiol. Imaging Pub Date : 2024-04-13 Frank Li, Xuan Zhang, Alejandro P. Comellas, Eric A. Hoffman, Michael M. Graham, Ching-Long Lin
Background The objective of this study is to understand chronic obstructive pulmonary disease (COPD) phenotypes and their progressions by quantifying heterogeneities of lung ventilation from the single photon emission computed tomography (SPECT) images and establishing associations with the quantitative computed tomography (qCT) imaging-based clusters and variables.
-
Deep learning models to predict mammographic density jointly on standard dose and low dose images medRxiv. Radiol. Imaging Pub Date : 2024-04-12 Steven Squires, Alistair Mackenzie, D. Gareth Evans, Sacha J Howell, Susan M Astley
Objectives Mammographic density is associated with increased risk of developing breast cancer. Automated estimation of density in women below normal screening age would enable earlier risk stratification. We are piloting the use of low dose mammograms combined with models that can make accurate mammographic density estimates.
-
Optimization of 1H MR spectroscopy methods for large volume acquisition of low concentration downfield resonances at 3T and 7T medRxiv. Radiol. Imaging Pub Date : 2024-04-12 Neil E. Wilson, Mark A. Elliott, Ravi Prakash Reddy Nanga, Sophia Swago, Walter R. Witschey, Ravinder Reddy
Purpose This goal of this study was to optimize spectrally selective 1H MRS methods for large volume acquisition of low concentration metabolites with downfield resonances at 7T and 3T, with particular attention paid to detection of nicotinamide adenine dinucleotide (NAD+) and tryptophan.
-
Sensitivity of unconstrained quantitative magnetization transfer MRI to Amyloid burden in preclinical Alzheimer’s disease medRxiv. Radiol. Imaging Pub Date : 2024-04-16 Andrew Mao, Sebastian Flassbeck, Elisa Marchetto, Arjun V. Masurkar, Henry Rusinek, Jakob Assländer
Introduction Magnetization transfer MRI is sensitive to semi-solid macromolecules, including amyloid beta, and has been used to discriminate Alzheimer’s disease (AD) patients from controls. Here, we utilize an unconstrained 2-pool quantitative MT (qMT) approach that quantifies the longitudinal relaxation rates of free water and semi-solids separately, and investigate its sensitivity to amyloid accumulation
-
Enhanced Classification Performance using Deep Learning Based Segmentation for Pulmonary Embolism Detection in CT Angiography medRxiv. Radiol. Imaging Pub Date : 2024-04-11 Ali Teymur Kahraman, Tomas Fröding, Dimitris Toumpanakis, Christian Jamtheim Gustafsson, Tobias Sjöblom
Purpose To develop a deep learning-based algorithm that automatically and accurately classifies patients as either having pulmonary emboli or not in CT pulmonary angiography (CTPA) examinations.
-
Utility of quantitative measurement of T2 using Restriction Spectrum Imaging for detection of clinically significant prostate cancer medRxiv. Radiol. Imaging Pub Date : 2024-04-09 Mariluz Rojo Domingo, Christopher C Conlin, Roshan A Karunamuni, Courtney Ollison, Madison T Baxter, Karoline Kallis, Deondre D Do, Yuze Song, Joshua M Kuperman, Ahmed S Shabaik, Michael E Hahn, Paul M Murphy, Rebecca Rakow-Penner, Anders M Dale, Tyler M Seibert
Background The Restriction Spectrum Imaging restriction score (RSIrs) has demonstrated higher diagnostic accuracy for clinically significant prostate cancer (csPCa) than conventional DWI. Both diffusion and T2 properties of prostate tissue inform the RSI signal, and studies have shown that each may be valuable for csPCa discrimination.
-
Intracranial aneurysm stiffness assessment using 4D flow MRI medRxiv. Radiol. Imaging Pub Date : 2024-04-09 Satoshi Koizumi, Taichi Kin, Tetsuro Sekine, Satoshi Kiyofuji, Motoyuki Umekawa, Nobuhito Saito
Background Although arterial stiffness is a known biomarker for cardiovascular events and stroke, there is limited information in the literature regarding the stiffness of intracranial aneurysms. This study aimed to assess intracranial aneurysm stiffness using four-dimensional flow magnetic resonance imaging (4D flow MRI).
-
Test-retest repeatability of intravoxel incoherent motion (IVIM) measurements in the cervical cord medRxiv. Radiol. Imaging Pub Date : 2024-04-07 Anna Lebret, Simon Lévy, Patrick Freund, Virginie Callot, Maryam Seif
This work aimed at assessing the reliability of intravoxel incoherent motion (IVIM) parameters sensitive to perfusion changes in the cervical cord by determining the test-retest variability across subjects and different post-processing fitting algorithms. IVIM test-retest scans were acquired in the cervical cord (C1-C3) of 10 healthy subjects on a 3T MRI scanner, with a 15-minute break in-between.
-
A Siamese U-Transformer for change detection on MRI brain for multiple sclerosis, a model development and external validation study medRxiv. Radiol. Imaging Pub Date : 2024-04-06 Brendan S Kelly, Prateek Mathur, Ronan P Killeen, Aonghus Lawlor
Background Multiple Sclerosis (MS), is a chronic idiopathic demyelinating disorder of the CNS. Imaging plays a central role in diagnosis and monitoring. Monitoring for progression however, can be repetitive for neuroradiologists, and this has led to interest in automated lesion detection. Simultaneously, in the computer science field of Remote Sensing, Change Detection (CD), the identification of change
-
White matter lesion volumes on 3-T MRI in people with MS who had followed a diet- and lifestyle program for more than 10 years medRxiv. Radiol. Imaging Pub Date : 2024-04-06 Mariaan Jaftha, Frances Robertson, Susan J van Rensburg, Martin Kidd, Ronald van Toorn, Merlisa C. Kemp, Clint Johannes, Kelebogile E. Moremi, Lindiwe Whati, Maritha J Kotze, Penelope Engel-Hills
Background Cerebral white matter lesions (WMLs) in people with multiple sclerosis (pwMS) are associated with the death of myelin-producing oligodendrocytes. MS treatment strategies aim to limit WML accumulation and disability progression. It is commonly accepted that nutrition is one of the possible environmental factors involved in the pathogenesis of MS, but its role as a complementary MS treatment
-
Breast imaging with an ultra-low field MRI scanner: a pilot study medRxiv. Radiol. Imaging Pub Date : 2024-04-04 Sheng Shen, Neha Koonjoo, Friderike K. Longarino, Leslie R. Lamb, Juan C. Villa Hornung, Torben P.P. Camacho, Stephen E. Ogier, Susu Yan, Thomas R. Bortfeld, Mansi A. Saksena, Kathryn E. Keenan, Matthew S. Rosen
Breast cancer screening is necessary to reduce mortality due to undetected breast cancer. Current methods have limitations, and as a result many women forego regular screening. Magnetic resonance imaging (MRI) can overcome most of these limitations, but access to conventional MRI is not widely available for routine annual screening. Here, we used an MRI scanner operating at ultra-low field (ULF) to
-
SIENNA: Lightweight Generalizable Machine Learning Platform for Brain Tumor Diagnostics medRxiv. Radiol. Imaging Pub Date : 2024-04-04 Sreya Sunil, Rahul S. Rajeev, Ayan Chatterjee, Julie Pilitsis, Amitava Mukherjee, Janet L. Paluh
The transformative integration of Machine Learning (ML) for Artificial General Intelligence (AGI)-enhanced clinical imaging diagnostics, is itself in development. In brain tumor pathologies, magnetic resonance imaging (MRI) is a critical step that impacts the decision for invasive surgery, yet expert MRI tumor typing is inconsistent and misdiagnosis can reach levels as high as 85%. Current state-of-the-art
-
Generative Modeling of the Circle of Willis Using 3D-StyleGAN medRxiv. Radiol. Imaging Pub Date : 2024-04-03 Orhun Utku Aydin, Adam Hilbert, Alexander Koch, Felix Lohrke, Jana Rieger, Satoru Tanioka, Dietmar Frey
The circle of Willis (CoW) is a network of cerebral arteries with significant inter-individual anatomical variations. Deep learning has been used to characterize and quantify the status of the CoW in various applications for the diagnosis and treatment of cerebrovascular disease. In medical imaging, the performance of deep learning models is limited by the diversity and size of training datasets. To
-
DeepQCT: Predicting fragility fracture from high-resolution peripheral quantitative CT using deep learning medRxiv. Radiol. Imaging Pub Date : 2024-04-03 Fangyuan Chen, Lijia Cui, Qiao Jin, Yushuo Wu, Jiaqi Li, Yan Jiang, Yue Chi, Ruizhi Jiajue, Wei Liu, Wei Yu, Qianqian Pang, Ou Wang, Mei Li, Xiaoping Xing, Xuegong Zhang, Weibo Xia
Background Osteoporosis is prevalent in elderly women, which causes fragility fracture and hence increased mortality and morbidity. Predicting osteoporotic fracture risk is both clinically-beneficial and cost-effective. However, traditional tools using clinical factors and bone mineral density (BMD) fail to reflect bone microstructure. Here we aim to use high-resolution peripheral quantitative CT (HR-pQCT)
-
Deep Conformal Supervision: a comparative study medRxiv. Radiol. Imaging Pub Date : 2024-03-28 Amir Mohammad Vahdani, Shahriar Faghani
Background: Trustability is crucial for AI models in clinical settings. Conformal prediction as a robust uncertainty quantification framework has been receiving increasing attention as a valuable tool in improving model trustability. An area of active research is the method of non-conformity score calculation for conformal prediction. Method: We propose deep conformal supervision (DCS) which leverages
-
MRI assessment of adipose tissue fatty acid composition in the UK Biobank and its association with diet and disease medRxiv. Radiol. Imaging Pub Date : 2024-03-28 Marjola Thanaj, Nicolas Basty, Brandon Whitcher, Jimmy D Bell, E Louise Thomas
Objectives: This study aimed to assess the fatty acid (FA) composition of abdominal subcutaneous (ASAT) and visceral (VAT) adipose tissue in the UK Biobank imaging cohort (N = 33,823) using magnetic resonance imaging (MRI). Methods: We measured the fractions of saturated (fSFA), monounsaturated (fMUFA), and polyunsaturated (fPUFA) in ASAT and VAT from multi-echo MRI scans. We selected a sub-cohort
-
Improved correction of B0 inhomogeneity-induced distortions in diffusion-weighted images of the prostate medRxiv. Radiol. Imaging Pub Date : 2024-03-28 Christopher C Conlin, Aditya Bagrodia, Tristan Barrett, Madison T Baxter, Deondre D Do, Michael E Hahn, Mukesh G Harisinghani, Juan F Javier-DesLoges, Karoline Kallis, Christopher J Kane, Joshua M Kuperman, Michael A Liss, Daniel JA Margolis, Paul M Murphy, Michael Ohliger, Courtney Ollison, Rebecca Rakow-Penner, Mariluz Rojo Domingo, Yuze Song, Natasha Wehrli, Sean Woolen, Tyler M Seibert, Anders
Background: Conventional distortion correction techniques include the Reversed Polarity Gradient (RPG) method and FSL-topup, which estimate tissue displacement from EPI images of opposite phase-encoding polarity, and scale image intensity by the Jacobian of the estimated displacement. Purpose: To demonstrate that Jacobian intensity correction (JIC) can cause misleading improvement of EPI image distortion
-
Proton Free Induction Decay MRSI at 7T in the Human Brain Using an Egg-Shaped Modified Rosette K-Space Trajectory medRxiv. Radiol. Imaging Pub Date : 2024-03-26 Simon Blömer, Lukas Hingerl, Małgorzata Marjańska, Wolfgang Bogner, Stanislav Motyka, Gilbert Hangel, Antoine Klauser, Ovidiu C Andronesi, Bernhard Strasser
Purpose Proton (1H)-MRSI via spatial-spectral encoding poses high demands on gradient hardware at ultra-high fields and high-resolutions. Rosette trajectories help alleviate these problems, but at reduced SNR-efficiency due to their k-space densities not matching any desired k-space filter. We propose modified rosette trajectories, which more closely match a Hamming filter, and thereby improve SNR
-
Can motion capture improve task-based fMRI studies of motor function post-stroke? A systematic review medRxiv. Radiol. Imaging Pub Date : 2024-03-26 Zakaria Belkacemi, Liesjet E. H. van Dokkum, Andon Tchechmedjiev, Matthieu Lepetit-Coiffe, Denis Mottet, Emmanuelle Le Bars
Background: Variability in motor recovery after stroke represents a major challenge in its understanding and management. While functional MRI has traditionally been used to address post-stroke motor function in relation to clinical outcome, it lacks details about movement characteristics linked to observed brain activations. Combining fMRI with detailed information of motor function by using motion
-
Percutaneous Nephrostomy Guidance by a Convolutional Neural Network Based Endoscopic Optical Coherence Tomography System medRxiv. Radiol. Imaging Pub Date : 2024-03-21 Chen Wang, Paul Calle, Feng Yan, Qinghao Zhang, Kar-Ming A. Fung, Chongle Pan, Qinggong Tang
Percutaneous nephrostomy (PCN) is a commonly used procedure for kidney surgeries. However, difficulties persist in precisely locating the PCN needle tip during its insertion into the kidney. Challenges for PCN needle guidance exist in two aspects: 1) Accurate tissue recognition, and 2) Renal blood vessel detection. In this study, we demonstrated an endoscopic optical coherence tomography (OCT) system
-
Developing a deep learning model to predict the breast implant texture types with ultrasonography image: feasibility study medRxiv. Radiol. Imaging Pub Date : 2024-03-19 Ho Heon Kim, Won Chan Jeong, Kyungran Pi, Angela Soeun Lee, Min Soo Kim, Hye Jin Kim, Jae Hong Kim
Introduction Breast implants, including textured variants, have been widely used in aesthetic and reconstructive mammoplasty. However, the textured type, which is one of the shell types of breast implants, has been identified as a possible carcinogenic factor for lymphoma, specifically breast implant-associated anaplastic large cell lymphoma (BIA-ALCL). Identifying the texture type of the implant is
-
Quantitative transport mapping of multi-delay arterial spin labeling MRI detects early blood perfusion alteration in Alzheimer's disease medRxiv. Radiol. Imaging Pub Date : 2024-03-19 Yihao Guo, Liangdong Zhou, Yi Li, Gloria C Chiang, Tao Liu, Huijuan Chen, Weiyuan Huang, Mony J de Leon, Yi Wang, Feng Chen
Background Quantitative transport mapping (QTM) of blood velocity, based on the transport equation has been demonstrated higher accuracy and sensitivity of perfusion quantification than the traditional Kety's method-based blood flow (Kety flow). This study aimed to investigate the associations between QTM velocity and cognitive function in Alzheimer's disease (AD) using multiple post-labeling delay
-
Patient Preferences for Diagnostic Imaging Services: Decentralize or not? medRxiv. Radiol. Imaging Pub Date : 2024-03-19 Eline van den Broek-Altenburg, Jamie S. Benson, Adam Atherly, Kristen K. DeStigter
The objective of this study was to identify patient preferences for outpatient diagnostic imaging services and analyze how patients make trade-offs between attributes of these services using a discrete choice experiment (DCE). We used a DCE with 14 choice questions asking which imaging locations patients would prefer. We used latent class analysis to analyze preference heterogeneity between different