Article
Radiology, Nuclear Medicine & Medical Imaging
Christof Boehm, Jonathan K. Stelter, Kilian Weiss, Jakob Meineke, Alexander Komenda, Tabea Borde, Marcus R. Makowski, Eva M. Fallenberg, Dimitrios C. Karampinos
Summary: A preconditioned water-fat-silicone total field inversion (wfsTFI) algorithm was developed to estimate susceptibility map in the breast with silicone, and its performance was evaluated in comparison with previously proposed methods. Numerical simulations and in vivo measurements demonstrated that the wfsTFI algorithm significantly reduced artifacts and improved the accuracy of susceptibility estimation in proximity to silicone breast implants.
MAGNETIC RESONANCE IN MEDICINE
(2023)
Article
Psychiatry
Marisleydis Garcia Saborit, Alejandro Jara, Nestor Munoz, Carlos Milovic, Angeles Tepper, Luz Maria Alliende, Carlos Mena, Barbara Iruretagoyena, Juan Pablo Ramirez-Mahaluf, Camila Diaz, Ruben Nachar, Carmen Paz Castaneda, Alfonso Gonzalez, Juan Undurraga, Nicolas Crossley, Cristian Tejos
Summary: The study used quantitative susceptibility mapping (QSM) to investigate magnetic susceptibility changes in deep-brain nuclei in patients with psychosis. The results showed a reduction in iron concentration in the globus pallidus externa of patients. The findings suggest that susceptibility reduction may be a trait marker of psychosis rather than a state marker.
SCHIZOPHRENIA BULLETIN
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ashley Wilton Stewart, Simon Daniel Robinson, Kieran O'Brien, Jin Jin, Georg Widhalm, Gilbert Hangel, Angela Walls, Jonathan Goodwin, Korbinian Eckstein, Monique Tourell, Catherine Morgan, Aswin Narayanan, Markus Barth, Steffen Bollmann
Summary: A robust masking technique and reconstruction procedure were developed to automatically separate reliable from less reliable phase regions, operating on two-pass reconstruction to extract more information and suppress streaking artifacts, leading to significant artifact and error reductions, greater anatomical detail, and minimal parameter tuning across a range of acquisitions.
MAGNETIC RESONANCE IN MEDICINE
(2022)
Article
Neurosciences
Atsushi Yoshida, Frank Q. Ye, David K. Yu, David A. Leopold, Okihide Hikosaka
Summary: Quantitative susceptibility mapping (QSM) is a valuable tool for visualizing subcortical structures in the macaque brain and provides enhanced contrast for important anatomical details. The method significantly improves the visualization of structures such as the ventral pallidum, globus pallidus, substantia nigra, subthalamic nucleus, and dentate nucleus. Additionally, QSM values of certain structures are correlated to the age of macaque subjects.
Article
Neurosciences
Zhuang Xiong, Yang Gao, Feng Liu, Hongfu Sun
Summary: Deep neural networks show great potential in solving dipole inversion for QSM. However, they perform poorly when there are mismatched sequence parameters. In this study, we propose the AFTER-QSM deep neural network, which is robust against arbitrary acquisition orientation and spatial resolution. The network achieves excellent generalizability and significantly improves image quality assessments and reduces artifacts and noise levels compared to other methods.
Review
Cardiac & Cardiovascular Systems
Alberto Aimo, Li Huang, Andrew Tyler, Andrea Barison, Nicola Martini, Luigi F. Saccaro, Sebastien Roujol, Pier-Giorgio Masci
Summary: Quantitative susceptibility mapping (QSM) is a non-invasive magnetic resonance imaging (MRI) technique that is used to study and evaluate cardiovascular diseases, providing valuable insights into their pathophysiological changes, disease progression, and treatment response.
JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE
(2022)
Article
Neurosciences
Hyungseok Jang, Sam Sedaghat, Jiyo S. Athertya, Dina Moazamian, Michael Carl, Yajun Ma, Xing Lu, Alicia Ji, Eric Y. Chang, Jiang Du
Summary: This study developed an ultrashort echo time quantitative susceptibility mapping technique with an efficient 3D cones trajectory and validated its effectiveness in the human brain. The results showed that this technique provides reliable estimation of magnetic susceptibility and offers a new biomarker for susceptibility mapping in the in vivo brain.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Gisela E. Hagberg, Korbinian Eckstein, Elisa Tuzzi, Jiazheng Zhou, Simon Robinson, Klaus Scheffler
Summary: The purpose of this study was to develop improved tissue masks for Quantitative Susceptibility Mapping (QSM). The study compared different methods of generating masks and evaluated their effects on QSM contrast and artifacts. The results showed that an automatic, phase-based masking method was able to mitigate artifacts and restore QSM contrast across different brain regions.
MAGNETIC RESONANCE IN MEDICINE
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Julia V. Velikina, Ruiyang Zhao, Collin J. Buelo, Alexey A. Samsonov, Scott B. Reeder, Diego Hernando
Summary: To improve repeatability and reproducibility in quantitative susceptibility mapping (QSM) of the liver, an optimized regularized reconstruction algorithm for abdominal QSM was developed. The algorithm incorporates estimates of data reliability and anatomical priors, resulting in higher quality susceptibility maps. Evaluations show that the proposed method outperforms the standard method in terms of linear correlation, test-retest repeatability, and reproducibility across different acquisition protocols.
MAGNETIC RESONANCE IN MEDICINE
(2023)
Article
Neurosciences
Zhenghao Li, Ruimin Feng, Qiangqiang Liu, Jie Feng, Guoyan Lao, Ming Zhang, Jun Li, Yuyao Zhang, Hongjiang Wei
Summary: The brain tissue phase contrast in MRI sequences reflects the spatial distributions of multiple substances. Advanced susceptibility imaging methods have been recently developed to distinguish the contributions of opposing susceptibility sources for QSM. The proposed method provides state-of-the-art performances for quantifying brain iron and myelin compared to previous QSM separation methods.
Article
Radiology, Nuclear Medicine & Medical Imaging
Nashwan Naji, Alan Wilman
Summary: This study proposes a new method to improve background field estimation and inversion-to-susceptibility process for high-resolution thin slab data by utilizing additional low-resolution data of extended spatial coverage. The proposed method enables focal QSM acquisitions at sub-millimeter resolution within a relatively short scan time.
MAGNETIC RESONANCE IN MEDICINE
(2023)
Article
Neurosciences
Jingwen Yao, Melanie A. Morrison, Angela Jakary, Sivakami Avadiappan, Yicheng Chen, Johanna Luitjens, Julia Glueck, Theresa Driscoll, Michael D. Geschwind, Alexandra B. Nelson, Javier E. Villanueva-Meyer, Christopher P. Hess, Janine M. Lupo
Summary: This study evaluated the performance of different dipole inversion algorithms for iron-sensitive susceptibility imaging using 7T on healthy subjects and Huntington's disease patients. The results showed that single-step QSM methods with either total variation or total generalized variation constraints (SSTV/SSTGV) and the single-step deep learning method iQSM provided the best performance in terms of correlation with iron deposition and differentiation between healthy controls and premanifest HD individuals, while deep learning QSM methods trained with multiple-orientation susceptibility data created QSM maps that were most similar to the multiple orientation reference and with the best visual scores.
Article
Neurosciences
Yang Gao, Martijn Cloos, Feng Liu, Stuart Crozier, G. Bruce Pike, Hongfu Sun
Summary: This study proposed a Deep Complex Residual Network (DCRNet) to accelerate QSM and R2* acquisition by recovering both magnitude and phase images from incoherently undersampled data. Compared with other methods, DCRNet substantially reduced artifacts and blurring, resulting in the highest PSNR, SSIM, and RMSE on various MRI maps. Additionally, DCRNet demonstrated a 3.2% to 9.1% accuracy improvement in deep grey matter susceptibility and significantly shortened the reconstruction time of single 2D brain images.
Article
Neurosciences
Ruimin Feng, Jiayi Zhao, He Wang, Baofeng Yang, Jie Feng, Yuting Shi, Ming Zhang, Chunlei Liu, Yuyao Zhang, Jie Zhuang, Hongjiang Wei
Summary: In this study, a model-based deep learning architecture called MoDL-QSM was proposed to improve accuracy in quantifying tissue susceptibility in various brain diseases by considering the impact of susceptibility tensors, reducing streaking artifacts. The model integrates convolutional neural networks and a physical model, using phase induced by X-33 and X-13, X-23 terms as network training labels. The results demonstrated superior performance compared to other deep learning QSM methods, showing potential for future applications.
Article
Neurosciences
Yang Gao, Zhuang Xiong, Amir Fazlollahi, Peter J. Nestor, Viktor Vegh, Fatima Nasrallah, Craig Winter, G. Bruce Pike, Stuart Crozier, Feng Liu, Hongfu Sun
Summary: This study developed a new deep neural network method to achieve near-instant quantitative field and susceptibility mapping from raw MRI phase data, eliminating the cumbersome steps of traditional QSM reconstruction process and achieving high reconstruction accuracy.
Article
Ophthalmology
Tin Yan Alvin Liu, Carlthan Ling, Leo Hahn, Craig K. Jones, Camiel J. F. Boon, Mandeep S. Singh
Summary: This study demonstrates the use of cSLO imaging and deep learning to estimate visual acuity in retinitis pigmentosa (RP) patients, showing promising performance in predicting visual impairment.
BRITISH JOURNAL OF OPHTHALMOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Craig K. Jones, Guoqing Wang, Vivek Yedavalli, Haris Sair
Summary: The study derived a multinomial probability function and quantitatively measured data and epistemic uncertainty using a 3D U-Net segmentation network. Uncertainty decreased with increasing training data, with the neural network trained with 898 volumes showing higher uncertainty maps primarily at tissue boundaries. Epistemic uncertainty decreased as expected with more training data, while aleatoric uncertainty showed a similar trend.
JOURNAL OF MEDICAL IMAGING
(2022)
Article
Astronomy & Astrophysics
Adrian M. Price-Whelan, Pey Lian Lim, Nicholas Earl, Nathaniel Starkman, Larry Bradley, David L. Shupe, Aarya A. Patil, Lia Corrales, C. E. Brasseur, Maximilian Noethe, Axel Donath, Erik Tollerud, Brett M. Morris, Adam Ginsburg, Eero Vaher, Benjamin A. Weaver, James Tocknell, William Jamieson, Marten H. van Kerkwijk, Thomas P. Robitaille, Bruce Merry, Matteo Bachetti, H. Moritz Gunther, Thomas L. Aldcroft, Jaime A. Alvarado-Montes, Anne M. Archibald, Attila Bodi, Shreyas Bapat, Geert Barentsen, Juanjo Bazan, Manish Biswas, Mederic Boquien, D. J. Burke, Daria Cara, Mihai Cara, Kyle E. Conroy, Simon Conseil, Matthew W. Craig, Robert M. Cross, Kelle L. Cruz, Francesco D'Eugenio, Nadia Dencheva, Hadrien A. R. Devillepoix, Jorg P. Dietrich, Arthur Davis Eigenbrot, Thomas Erben, Leonardo Ferreira, Daniel Foreman-Mackey, Ryan Fox, Nabil Freij, Suyog Garg, Robel Geda, Lauren Glattly, Yash Gondhalekar, Karl D. Gordon, David Grant, Perry Greenfield, Austen M. Groener, Steve Guest, Sebastian Gurovich, Rasmus Handberg, Akeem Hart, Zac Hatfield-Dodds, Derek Homeier, Griffin Hosseinzadeh, Tim Jenness, Craig K. Jones, Prajwel Joseph, J. Bryce Kalmbach, Emir Karamehmetoglu, Mikolaj Kaluszynski, Michael S. P. Kelley, Nicholas Kern, Wolfgang E. Kerzendorf, Eric W. Koch, Shankar Kulumani, Antony Lee, Chun Ly, Zhiyuan Ma, Conor MacBride, Jakob M. Maljaars, Demitri Muna, N. A. Murphy, Henrik Norman, Richard O'Steen, Kyle A. Oman, Camilla Pacifici, Sergio Pascual, J. Pascual-Granado, Rohit R. Patil, Gabriel Perren, Timothy E. Pickering, Tanuj Rastogi, Benjamin R. Roulston, Daniel F. Ryan, Eli S. Rykoff, Jose Sabater, Parikshit Sakurikar, Jesus Salgado, Aniket Sanghi, Nicholas Saunders, Volodymyr Savchenko, Ludwig Schwardt, Michael Seifert-Eckert, Albert Y. Shih, Anany Shrey Jain, Gyanendra Shukla, Jonathan Sick, Chris Simpson, Sudheesh Singanamalla, Leo P. Singer, Jaladh Singhal, Manodeep Sinha, Brigitta M. Sipocz, Lee R. Spitler, David Stansby, Ole Streicher, Jani Sumak, John D. Swinbank, Dan S. Taranu, Nikita Tewary, Grant R. Tremblay, Miguel De Val-Borro, Zlatan Vasovic, Samuel J. Van Kooten, Shresth Verma, Jose Vinicius de Miranda Cardoso, Peter K. G. Williams, Tom J. Wilson, Benjamin Winkel, W. M. Wood-Vasey, Rui Xue, Peter Yoachim, Chen Zhang, Andrea Zonca
Summary: The Astropy Project is an open-source Python package that provides commonly needed functionality to the astronomical community. Its core package, astropy, serves as the foundation for specialized projects and packages. This article summarizes the key features of the core package and provides updates on the project. It also discusses the connections with astronomical observatories and missions, and the future outlook and challenges of the Astropy Project.
ASTROPHYSICAL JOURNAL
(2022)
Article
Engineering, Biomedical
Yuxuan Liu, Mitsuki Ota, Runze Han, Jeffrey H. Siewerdsen, T. Y. Alvin Liu, Craig K. Jones
Summary: The purpose of this study is to use a statistical shape model and an active shape model for globe segmentation and to differentiate between normal globes and globe injuries. The results show that the active shape model segmentation is consistent with manual segmentation, and the segmented globes with injuries differ from normal globes in terms of structural deformation.
PHYSICS IN MEDICINE AND BIOLOGY
(2022)
Article
Computer Science, Interdisciplinary Applications
Y. Huang, C. K. Jones, X. Zhang, A. Johnston, S. Waktola, N. Aygun, T. F. Witham, A. Bydon, N. Theodore, P. A. Helm, J. H. Siewerdsen, A. Uneri
Summary: This study proposes a multi-perspective region-based neural network for automatic vertebrae labeling in intraoperative spine images. The network leverages knowledge of imaging geometry and aggregation of multiple view-angle images to improve labeling accuracy. Experimental results demonstrate excellent performance of the network on multiple metrics.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Patrick M. Lehmann, Anina Seidemo, Mads Andersen, Xiang Xu, Xu Li, Nirbhay N. Yadav, Ronnie Wirestam, Patrick Liebig, Frederik Testud, Pia Sundgren, Peter C. M. van Zijl, Linda Knutsson
Summary: This study presents the design of a numerical human brain phantom to simulate realistic dynamic glucose-enhanced (DGE) MRI at 3T. The influence of head movement on the signal before and after retrospective motion correction was evaluated. Results showed that motion artifacts can mimic DGE effects, and motion correction can alter the true signal effects. Therefore, post-processing methods using retrospective motion correction including B-0 correction will be crucial for clinical implementation.
MAGNETIC RESONANCE IN MEDICINE
(2023)
Correction
Multidisciplinary Sciences
Sarthak Pati, Ujjwal Baid, Brandon Edwards, Micah Sheller, Shih-Han Wang, G. Anthony Reina, Patrick Foley, Alexey Gruzdev, Deepthi Karkada, Christos Davatzikos, Chiharu Sako, Satyam Ghodasara, Michel Bilello, Suyash Mohan, Philipp Vollmuth, Gianluca Brugnara, Chandrakanth J. Preetha, Felix Sahm, Klaus Maier-Hein, Maximilian Zenk, Martin Bendszus, Wolfgang Wick, Evan Calabrese, Jeffrey Rudie, Javier Villanueva-Meyer, Soonmee Cha, Madhura Ingalhalikar, Manali Jadhav, Umang Pandey, Jitender Saini, John Garrett, Matthew Larson, Robert Jeraj, Stuart Currie, Russell Frood, Kavi Fatania, Raymond Y. Huang, Ken Chang, Carmen Balana, Jaume Capellades, Josep Puig, Johannes Trenkler, Josef Pichler, Georg Necker, Andreas Haunschmidt, Stephan Meckel, Gaurav Shukla, Spencer Liem, Gregory S. Alexander, Joseph Lombardo, Joshua D. Palmer, Adam E. Flanders, Adam P. Dicker, Haris I. Sair, Craig K. Jones, Archana Venkataraman, Meirui Jiang, Tiffany Y. So, Cheng Chen, Pheng Ann Heng, Qi Dou, Michal Kozubek, Filip Lux, Jan Michalek, Petr Matula, Milos Kerkovsky, Tereza Koprivova, Marek Dostal, Vaclav Vybihal, Michael A. Vogelbaum, J. Ross Mitchell, Joaquim Farinhas, Joseph A. Maldjian, Chandan Ganesh Bangalore Yogananda, Marco C. Pinho, Divya Reddy, James Holcomb, Benjamin C. Wagner, Benjamin M. Ellingson, Timothy F. Cloughesy, Catalina Raymond, Talia Oughourlian, Akifumi Hagiwara, Chencai Wang, Minh-Son To, Sargam Bhardwaj, Chee Chong, Marc Agzarian, Alexandre Xavier Falcao, Samuel B. Martins, Bernardo C. A. Teixeira, Flavia Sprenger, David Menotti, Diego R. Lucio, Pamela LaMontagne, Daniel Marcus, Benedikt Wiestler, Florian Kofler, Ivan Ezhov, Marie Metz, Rajan Jain, Matthew Lee, Yvonne W. Lui, Richard McKinley, Johannes Slotboom, Piotr Radojewski, Raphael Meier, Roland Wiest, Derrick Murcia, Eric Fu, Rourke Haas, John Thompson, David Ryan Ormond, Chaitra Badve, Andrew E. Sloan, Vachan Vadmal, Kristin Waite, Rivka R. Colen, Linmin Pei, Murat Ak, Ashok Srinivasan, J. Rajiv Bapuraj, Arvind Rao, Nicholas Wang, Ota Yoshiaki, Toshio Moritani, Sevcan Turk, Joonsang Lee, Snehal Prabhudesai, Fanny Moron, Jacob Mandel, Konstantinos Kamnitsas, Ben Glocker, Luke V. M. Dixon, Matthew Williams, Peter Zampakis, Vasileios Panagiotopoulos, Panagiotis Tsiganos, Sotiris Alexiou, Ilias Haliassos, Evangelia I. Zacharaki, Konstantinos Moustakas, Christina Kalogeropoulou, Dimitrios M. Kardamakis, Yoon Seong Choi, Seung-Koo Lee, Jong Hee Chang, Sung Soo Ahn, Bing Luo, Laila Poisson, Ning Wen, Pallavi Tiwari, Ruchika Verma, Rohan Bareja, Ipsa Yadav, Jonathan Chen, Neeraj Kumar, Marion Smits, Sebastian R. van der Voort, Ahmed Alafandi, Fatih Incekara, Maarten M. J. Wijnenga, Georgios Kapsas, Renske Gahrmann, Joost W. Schouten, Hendrikus J. Dubbink, Arnaud J. P. E. Vincent, Martin J. van den Bent, Pim J. French, Stefan Klein, Yading Yuan, Sonam Sharma, Tzu-Chi Tseng, Saba Adabi, Simone P. Niclou, Olivier Keunen, Ann-Christin Hau, Martin Vallieres, David Fortin, Martin Lepage, Bennett Landman, Karthik Ramadass, Kaiwen Xu, Silky Chotai, Lola B. Chambless, Akshitkumar Mistry, Reid C. Thompson, Yuriy Gusev, Krithika Bhuvaneshwar, Anousheh Sayah, Camelia Bencheqroun, Anas Belouali, Subha Madhavan, Thomas C. Booth, Alysha Chelliah, Marc Modat, Haris Shuaib, Carmen Dragos, Aly Abayazeed, Kenneth Kolodziej, Michael Hill, Ahmed Abbassy, Shady Gamal, Mahmoud Mekhaimar, Mohamed Qayati, Mauricio Reyes, Ji Eun Park, Jihye Yun, Ho Sung Kim, Abhishek Mahajan, Mark Muzi, Sean Benson, Regina G. H. Beets-Tan, Jonas Teuwen, Alejandro Herrera-Trujillo, Maria Trujillo, William Escobar, Ana Abello, Jose Bernal, Jhon Gomez, Joseph Choi, Stephen Baek, Yusung Kim, Heba Ismael, Bryan Allen, John M. Buatti, Aikaterini Kotrotsou, Hongwei Li, Tobias Weiss, Michael Weller, Andrea Bink, Bertrand Pouymayou, Hassan F. Shaykh, Joel Saltz, Prateek Prasanna, Sampurna Shrestha, Kartik M. Mani, David Payne, Tahsin Kurc, Enrique Pelaez, Heydy Franco-Maldonado, Francis Loayza, Sebastian Quevedo, Pamela Guevara, Esteban Torche, Cristobal Mendoza, Franco Vera, Elvis Rios, Eduardo Lopez, Sergio A. Velastin, Godwin Ogbole, Mayowa Soneye, Dotun Oyekunle, Olubunmi Odafe-Oyibotha, Babatunde Osobu, Mustapha Shu'aibu, Adeleye Dorcas, Farouk Dako, Amber L. Simpson, Mohammad Hamghalam, Jacob J. Peoples, Ricky Hu, Anh Tran, Danielle Cutler, Fabio Y. Moraes, Michael A. Boss, James Gimpel, Deepak Kattil Veettil, Kendall Schmidt, Brian Bialecki, Sailaja Marella, Cynthia Price, Lisa Cimino, Charles Apgar, Prashant Shah, Bjoern Menze, Jill S. Barnholtz-Sloan, Jason Martin, Spyridon Bakas
NATURE COMMUNICATIONS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiaoxuan Zhang, Alejandro Sisniega, Wojciech B. B. Zbijewski, Junghoon Lee, Craig K. K. Jones, Pengwei Wu, Runze Han, Ali Uneri, Prasad Vagdargi, Patrick A. A. Helm, Mark Luciano, William S. S. Anderson, Jeffrey H. H. Siewerdsen
Summary: A 3D deep learning reconstruction framework called DL-Recon was proposed for improved intraoperative cone-beam CT (CBCT) image quality. It combines physics-based models with deep learning CT synthesis and leverages uncertainty information to promote robustness. The DL-Recon approach showed substantial improvements in the accuracy and quality of intraoperative CBCT.
Editorial Material
Ophthalmology
Amir H. H. Kashani, T. Y. Alvin Liu, Craig Jones
JAMA OPHTHALMOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Zhenghan Fang, Kuo-Wei Lai, Peter van Zijl, Xu Li, Jeremias Sulam
Summary: STI is a promising magnetic resonance imaging technique that characterizes tissue magnetic susceptibility using a second-order tensor model. However, its application has been hindered by the requirement of measuring susceptibility-induced MR phase changes at multiple head orientations. In this work, we propose a data-driven image reconstruction algorithm called DeepSTI, which leverages a deep neural network to learn the data prior and solve the dipole inversion problem iteratively. Our method achieves significant improvement over state-of-the-art algorithms in reconstructing tensor images, principal eigenvector maps, and tractography results, while allowing for tensor reconstruction with MR phase measured at much less than six orientations.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Clinical Neurology
Andrew M. Hersh, Anika Zahoor, Danielle Livingston, Anthony Galinato, Hannah Recht, Jason Hostetter, Craig K. Jones, Daniel Lubelski, Haris I. Sair
Summary: This study presents a technique for generating splayed slices that show the bilateral neuroforamina simultaneously and evaluates its reliability compared with traditional axial slices in assessing cervical neural foraminal stenosis (CNFS). The results show that the interrater agreement is higher for the splayed slices compared with the axial slices, suggesting that splayed reconstructions can improve the consistency of CNFS evaluation.
WORLD NEUROSURGERY
(2023)
Article
Ophthalmology
Craig K. Jones, Bochong Li, Jo-Hsuan Wu, Toshiya Nakaguchi, Ping Xuan, T. Y. Alvin Liu
Summary: Optical Coherence Tomography (OCT) is an essential imaging modality in ophthalmology, especially for the diagnosis and management of macular diseases. This study evaluated and compared the effectiveness of five registration algorithms using OCT B-scans from 48 age-related macular degeneration (AMD) patients and 50 normal controls. The results showed that B-scan alignment significantly improved the smoothness of the surface map and enhanced the performance of the 3D CNN model in detecting AMD.
INTERNATIONAL JOURNAL OF RETINA AND VITREOUS
(2023)
Article
Engineering, Biomedical
Prasad Vagdargi, Ali Uneri, Xiaoxuan Zhang, Craig K. Jones, Pengwei Wu, Runze Han, Alejandro Sisniega, Junghoon Lee, Patrick Helm, Mark Luciano, William S. Anderson, Gregory D. Hager, Jeffrey H. Siewerdsen
Summary: We developed a 3D endoscopic reconstruction and registration method using simultaneous localization and mapping (SLAM) for real-time guidance in deep-brain surgery. The method allows augmented video overlay of preoperative or intraoperative 3D images to improve targeting accuracy. Phantom studies demonstrated the method's geometric accuracy and uncertainty in challenging scenarios and showed that it maintained accuracy even with limited data or scene occlusion.
IEEE TRANSACTIONS ON MEDICAL ROBOTICS AND BIONICS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xue Feng, Kanchan Ghimire, Daniel D. Kim, Rajat S. Chandra, Helen Zhang, Jian Peng, Binghong Han, Gaofeng Huang, Quan Chen, Sohil Patel, Chetan Bettagowda, Haris I. Sair, Craig Jones, Zhicheng Jiao, Li Yang, Harrison Bai
Summary: This paper proposes a deep convolutional neural network-based framework for brain tumor segmentation, incorporating a novel sequence dropout technique to improve the robustness of the network in the presence of missing MRI sequences. Experimental results demonstrate that sequence dropout can effectively enhance segmentation performance when key sequences are unavailable.
JOURNAL OF DIGITAL IMAGING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Lin Chen, Hyeong-Geol Shin, Peter C. M. van Zijl, Xu Li
Summary: A hollow-cylinder fiber model (HCFM) with two fiber populations was used to investigate the microstructure-induced frequency shift in white matter (WM) with crossing fibers. The frequency fitting method based on HCFM outperformed other multi-echo combination methods in estimating the bulk susceptibility-induced frequency shift (Cf) in simulations. The results showed that the microstructure-related frequency difference parameter (Δf), Cf, and QSM can be improved further by navigator-based B0 fluctuation correction.
MAGNETIC RESONANCE IN MEDICINE
(2023)
