View Presentation Video

Atita Suwannasak¹, Uten Yarach¹, and Prapatsorn Sangpin^2
1Chiang Mai university, Chiang Mai, Thailand, ²Philips Healthcare (Thailand), Bangkok, Thailand

Keywords: Machine Learning/Artificial Intelligence, Brain

For brain volume measurement (BVM), High-resolution (HR) MR images have shown to provide accurate results at small subcortical areas. However, prolonged scan time remains a classical challenge for 3D MRI. We implemented a combined technique, deep learning based super-resolution (DL-SR) and low-resolution Compressed Sensing (CS) 3D-TFE-T1W with acceleration factor 4 to generate Super-resolution (SR) images under one minute scan time. The results show that DL-SR model is able to improve image resolution, in which no significant differences (p>0.01) in quantitative volumetric measurement between reference and DL-SR at subcortical regions, except for caudate region.

View Presentation Video

Bryan Quah¹, Sreekanth Madhusoodhanan Nair¹, Jin Jin², Fei Han³, Brian Renner¹, Elaina Gombos¹, Ke Cheng Liu³, Sunil Patil³, John A. Derbyshire⁴, Ken Sakaie⁵, Emmanuel Obusez⁵, Jonathan Lee⁵, Mark Elliot⁶, Russell T. Shinohara⁷, Matthew K. Schindler⁸, Jae W. Song⁶, Michel Bilello⁶, Marwa Kaisey¹, Nader Binesh⁹, Marcel Maya⁹, Javier Galvan⁹, Hui Han¹⁰, Debiao Li¹⁰, Andrew Solomon¹¹, Daniel S. Reich¹², Nancy L. Sicotte¹, Mark Lowe⁵, Daniel Ontaneda¹³, Omar Al-Louzi¹, and Pascal Sati^1,10
1Department of Neurology, Cedars-Sinai Medical Center, Los Angeles, CA, United States, ²Siemens Healthcare Pty Ltd, Brisbane, Australia, ³Siemens Medical Solutions, PA, United States, ⁴Functional MRI Facility, National Institute of Mental Health, National Institutes of Health, Bethesda, MD, United States, ⁵Imaging Institute, Cleveland Clinic, Cleveland, OH, United States, ⁶Department of Radiology, University of Pennsylvania, Philadelphia, PA, United States, ⁷Department of Biostatistics, Epidemiology, and Informatics, Penn Statistics in Imaging and Visualization Center, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, United States, ⁸Department of Neurology, University of Pennsylvania, Philadelphia, PA, United States, ⁹Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, United States, ¹⁰Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, United States, ¹¹Larner College of Medicine, The University of Vermont, Burlington, VT, United States, ¹²Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, United States, ¹³Mellen Center, Department of Neurology, Neurological Institute, Cleveland Clinic, Cleveland, OH, United States

Keywords: Machine Learning/Artificial Intelligence, Data Processing, Denoising, Neuroimaging

The scan time of high-resolution T2*-weighted brain imaging using 3D echo-planar imaging (3D-EPI) can be significantly reduced by applying Controlled Aliasing In Parallel Imaging Results In Higher Acceleration (CAIPIRINHA). However, this comes at the expense of a significant reduction in image quality. In this study, we evaluated the feasibility of using a deep learning-based approach (DnCNN) to denoise highly accelerated 3D-EPI scans acquired at 3T. Our results show that DnCNN was able to efficiently denoise highly accelerated T2*-weighted brain scans while preserving anatomical and pathological details.

View Presentation Video

Cristiana Fiscone¹, Nico Curti², Matti Ceccarelli³, David Neil Manners¹, Gastone Castellani², Caterina Tonon^1,4, Daniel Remondini^5,6, Raffaele Lodi^1,4, and Claudia Testa^4,5
1Department of Biomedical and Neuromotor Sciences, University of Bologna, Bologna, Italy, ²Department of Experimental, Diagnostic and Specialty Medicine, University of Bologna, Bologna, Italy, ³Department of Agricultural and Food Sciences, University of Bologna, Bologna, Italy, ⁴Functional and Molecular Neuroimaging Unit, IRCCS Istituto delle Scienze Neurologiche di Bologna, Bologna, Italy, ⁵Department of Physics and Astronomy, University of Bologna, Bologna, Italy, ⁶INFN Bologna, Bologna, Italy

Keywords: Machine Learning/Artificial Intelligence, Visualization, Super Resolution, Generalization

Enhanced Deep Super Resolution (EDSR) is a machine learning model aimed to improve image spatial resolution. It was previously trained with general purpose figures and, in this work, directly tested on different MR images: T₁w, T₂w and Quantitative Susceptibility Mapping (QSM), a quantitative imaging technique. The studied cohort included 28 healthy subjects. Without needing fine-tuning, EDSR shows excellent ability of generalization over new kind of data, improving imaging visualization and outperforming the traditional bicubic upsampling. In future applications, images of patients will be considered to test EDSR reconstruction when there is pathological tissue.

View Presentation Video

Chun-Yuan Shin¹, Yi-Ping Chao², Li-Wei Kuo^3,4, Yi-Peng Eve Chang⁵, and Jun-Cheng Weng^1,6,7
1Department of Medical Imaging and Radiological Sciences, and Department of Artificial Intelligence, Chang Gung University, Taoyuan, Taiwan, ²Department of Computer Science and Information Engineering, and Graduate Institute of Artificial Intelligence, Chang Gung University, Taoyuan, Taiwan, ³Institute of Biomedical Engineering and Nanomedicine, National Health Research Institutes, Miaoli, Taiwan, ⁴Institute of Medical Device and Imaging, National Taiwan University College of Medicine, Taipei, Taiwan, ⁵Department of Counseling and Clinical Psychology, Columbia University, New York City, NY, United States, ⁶Medical Imaging Research Center, Institute for Radiological Research, Chang Gung University and Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan, ⁷Department of Psychiatry, Chang Gung Memorial Hospital, Chiayi, Taiwan

Keywords: Machine Learning/Artificial Intelligence, Diffusion/other diffusion imaging techniques

Understanding neural connections helps scientists conduct cognitive behavioral research. There are many nerve fiber intersections in the brain that need to be observed, and the size is between 30-50 nanometers. Improving image resolution has become an important issue. Generalized q-sampling imaging (GQI) was used to reveal the fiber geometry of straight and crossing. However, it is difficult to accurately describe fiber bending, fanning, and diverging with low-resolution imaging. In this work, we tried to achieve superresolution with a deep learning method on diffusion magnetic resonance imaging (MRI) images that has the potential to assess crossing, curving, and splaying fiber structures.

Dallas Turley^1,2, Pattana Wangaryattawanich², Jalal Andre², Majid Chailan², Johannes M. Peeters³, Kim Van de Ven³, and Orpheus Kolokythas^2
1Philips Healthcare, Seattle, WA, United States, ²Department of Radiology, University of Washington, Seattle, WA, United States, ³Philips Healthcare, Best, Netherlands

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence

Artificial intelligence in MR is a diverse and growing field. In this work, we apply convolutional neural networks (CNN) to accelerated routine clinical protocols to investigate potential image quality improvements. For moderate increase in reconstruction time, CNNs were judged by experienced radiologists to significantly improve image quality by reducing noise and artifact. 

View Presentation Video

Wei Xu¹, Jing Cheng¹, and Dong Liang^1
1Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, ShenZhen, China

Keywords: Machine Learning/Artificial Intelligence, Brain

The application of MRI has been limited due to the restriction of imaging time and spatial resolution. Super-resolution is an important strategy in clinics to speed up MR imaging. In this work, we propose a novel GAN-based super-resolution method which incorporates gradient features to improve the recovery of local structures of the super-resolution images. Experiments on 3D MR Vessel Wall imaging demonstrate the superior performance of the proposed method.

View Presentation Video

Atsuro Suzuki¹, Tomoki Amemiya¹, Yukio Kaneko¹, Suguru Yokosawa¹, and Toru Shirai^1
1Imaging Technology Center, FUJIFILM Corporation, Tokyo, Japan

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence, Noise reduction

To develop a convolutional neural network (CNN)-based denoiser for various noise levels, we propose the use of estimated noise-based normalization in denoising. When the CNN-based denoiser with estimated noise-based normalization was applied to brain FLAIR images with various noise levels, it  resulted in values closer to the normalized root mean square error (NRMSE) between the denoised and the target images compared with a conventional CNN-based denoiser trained with the same noise level as that in the input image. In conclusion, our method effectively reduced the noise in an image with various noise levels in terms of minimization of the NRMSE.

View Presentation Video

Qinyang Shou¹, Zechen Zhou², Kevin Blansit², Praveen Gulaka², Enhao Gong², Greg Zaharchuk², and Ajit Shankaranarayanan^2
1University of Southern California, Los Angeles, CA, United States, ²Subtle Medical Inc., Menlo Park, CA, United States

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence, Knowledge Distillation

In this work, knowledge distillation (KD) is investigated to improve model generalizability for image enhancement tasks. KD can allow a 35× faster convolutional network to achieve similar performance as a Transformer based model in image denoising tasks. In addition, KD can enable a single image enhancement model for both denoising and super-resolution tasks that outperforms the conventional multi-task model trained with mixed data. KD potentially allows efficient image enhancement models to achieve better generalization performance for clinical translation.

View Presentation Video

Tiebao Meng¹, Haibin Liu¹, Haoqiang He¹, Jialu Zhang², and Long Qian^2
1Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, China, ²MR Research, GE Healthcare, Beijing, China

Keywords: Machine Learning/Artificial Intelligence, Diffusion/other diffusion imaging techniques

Deep Learning reconstruction (DLR) has the potential to reduce MRI scan time while improving signal-to-noise ratio (SNR) and maintaining spatial resolution. This study evaluated results of DLR in 66 patients undergoing clinical DWI of nasopharyngeal cancer (NPC). To assess the image quality of the DWI with DLR, each patient underwent three different protocols: conventional DWI without DLR, fast DWI without DLR and fast DWI with DLR. The image quality was evaluated among these groups. Preliminary results suggested the feasibility of fast DWI with DLR in the diagnosis of NPC with reduced scan time.

View Presentation Video

Florintina C¹, Sajith Rajamani¹, Preetham Shankpal¹, Suresh Joel¹, Sudhanya Chatterjee¹, Rohan Patil¹, Ramesh Venkatesan¹, Raja Sundaresan¹, and Harsh Agarwal^1
1GE Healthcare, Bengaluru, India

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence

SWI is a high resolution MRI sequence, particularly sensitive to compounds which distort the local magnetic field making it useful in detecting blood products, calcium, etc. 3 and is used as part of brain MR imaging. The phase images are high pass filtered to remove the slow varying susceptibility changes and this is important to differentiate between para and diamagnetic substances. When this filtered phase image is used to accentuate the directly observed signal loss in the magnitude image, it is raised to a higher power and  noise gets magnified as well, imparting undesirable effects in the SWI image. 

View Presentation Video

Hamed Yousefi¹, Chunwei Ying², Mahdjoub Hamdi², Richard Laforest², and Hongyu An^2
1Imaging Science, Washington University in St.Louis, St Louis, MO, United States, ²Washington University in St.Louis, St Louis, MO, United States

Keywords: Machine Learning/Artificial Intelligence, Brain

In this study, dynamic brain PET denoising was done using registered MRI and reconstructed PET images reconstructed by the OSEM method, while maintaining TACs that were quite near to the original noisy data. The fundamental challenge to using the supervised learning approach is the lack of ground truth. The resulting spatiotemporal images improved the image quality according to various CNR, SNR, and CRC parameters while maintaining TACs that were similar to the original raw PET. This method only needs one trained network, one set of matrices for a statistical temporal PCA model, and 4D dynamic PET data as input. 

View Presentation Video

Yuseoung Son¹, Sumin Roh¹, Jae-Kyun Ryu¹, Won Beom Jung¹, Seok-Mn Lee², A-Rim Lee², Chuluunbaatar Otgonbaatar³, Jaebin Lee⁴, Ho-Jung Choi², Young-Won Lee², and Hackjoon Shim^1,4
1Medical Imaging AI Research Center, Canon Medical Systems Korea, Seoul, Korea, Republic of, ²College of Veterinary Medicine, Chungnam National University, Daejeon, Korea, Republic of, ³College of Medicine, Seoul National University, Seoul, Korea, Republic of, ⁴Magnetic Resonance Business Unit, Canon Medical Systems Korea, Seoul, Korea, Republic of

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence

Most veterinary imaging has been achieved using human MRI scanners. Therefore, extensive averaging is required to obtain high-resolution images with high SNR for the animals, thereby leading to a long scan time. Veterinary MRI is typically performed under general anesthesia to minimize the level of stress and movement during image scanning. Therefore, long anesthetic conditions could affect animal normal physiology and be life-threatening, especially for patients in veterinary medical field. Here, we aimed to obtain higher image quality with short scanning time using super-resolution generative adversarial network (SRGAN) in the canine brain MRI.

View Presentation Video

Rokgi Hong¹, Juhyung Park¹, Hayeon Lee², Hongjun An¹, and Jongho Lee^1
1Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea, Republic of, ²School of Electrical Engineering, Korea University, Seoul, Korea, Republic of

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence

View Presentation Video

Hung Phi Do¹, Dawn Berkeley¹, Brian Tymkiw¹, Wissam AlGhuraibawi¹, and Mo Kadbi^1
1Canon Medical Systems USA, Inc., Tustin, CA, United States

Keywords: Prostate, Prostate

In prostate MRI, high SNR images are desired for a better depiction of anatomical and pathological structures; however, it often requires a longer scan time, especially at 1.5T. Deep Learning Denoising Reconstruction (DLR) has been shown to effectively remove noise, allowing high SNR with higher resolution and shortened scan time simultaneously. This study demonstrates that DLR enables the acquisition of high SNR images with 29.48% scan time reduction and 31.51% increase in spatial resolution at 1.5T.

View Presentation Video

Kang Wang¹, Matthew J. Middione¹, Andreas Markus Loening¹, Patricia Lan², Xinzeng Wang³, Daniel B Ennis¹, and Ryan Lennex Brunsing^1
1Radiology, Stanford University, Palo Alto, CA, United States, ²GE HealthCare, Menlo Park, CA, United States, ³GE HealthCare, Houston, TX, United States

Keywords: Pancreas, Diffusion/other diffusion imaging techniques, Diffusion Weighted Imaging, Denoising, M1-nulled, ADC

Multi-shot DWI (msDWI) may be improved by M1 motion-compensation, but at a penalty of longer TE and lower SNR. DL-based denoising has recently emerged as an option for DWI, which could help offset this TE penalty. Here we assess the impact of a commercially available DL-based denoising tool in the setting of motion-compensated msDWI.

View Presentation Video

Hung Phi Do¹, Dawn Berkeley¹, Brian Tymkiw¹, Wissam AlGhuraibawi¹, and Mo Kadbi^1
1Canon Medical Systems USA, Inc., Tustin, CA, United States

Keywords: MSK, MSK

Two-average (2NAQ) scans are often required to acquire high resolution images with adequate Signal-to-Noise Ratio (SNR). Deep Learning Denoising Reconstruction (DLR) effectively removes noise hence improving the SNR of reconstructed images. The SNR gain could be used to increase resolution and/or reduce scan time. This study demonstrates that the DLR-reconstructed one-average (1NAQ) images have similar image quality to those acquired with 2NAQ and reconstructed with conventional reconstruction. As a result, approximately 2X scan time reduction is achieved with DLR.

View Presentation Video

Jun Sun¹, Yiding Guo¹, Zhizheng Zhuo¹, Siyao Xu¹, Min Guo¹, Li Chai¹, Junjie Li¹, Liying Qu¹, Minghao Wu¹, Juan Wei², Mingna Li³, Tong Li³, Jinyuan Weng⁴, Xiaodong Gong⁵, Yunyun Duan¹, Dabiao Zhou¹, and Yaou Liu^1
1Capital Medical Universtiy, Beijing Tiantan Hospital, Beijing, China, ²MR Research, GE Healthcare, Beijing, China, ³BioMind Inc., Beijing, China, ⁴Department of Medical Imaging Product, Neusoft, Group Ltd., Shenyang, China, ⁵Department of Medical Imaging Product, Neusoft, Group Ltd., Beijing, China

Keywords: Tumors, Brain

Deep learning reconstruction (DLR) approach with denoising can improve image quality of magnetic resonance (MR) images. However, its applications on multi-modal glioma imaging have not been assessed.Multi-modal images of 107 glioma patients were evaluated by signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), edge sharpness, visual assessment, diagnosis accuracy and efficiency. Contrasted with conventionally reconstructed images, the DLR images showed higher tumor/residual tumor SNR, higher tumor to white/gray matter CNR, better results of the visual assessment, and a trend of improved diagnosis efficiency and comparable accuracy. DLR can improve image quality of multi-modal glioma images which should benefit the glioma diagnosis.

View Presentation Video

Takuya Aoike¹, Noriyuki Fujima², Jihun Kwon³, Masami Yoneyama³, Satonori Tsuneta², Kinya Ishizaka¹, and Kohsuke Kudo^4
1Department of Radiological Technology, Hokkaido University Hospital, Sapporo, Japan, ²Department of Diagnostic and Interventional Radiology, Hokkaido University Hospital, Sapporo, Japan, ³Philips Japan, Ltd., Tokyo, Japan, ⁴Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine, Sapporo, Japan; Global Center for Biomedical Science and Engineering, Faculty of Medicine, Hokkaido University, Sapporo, Japan

Keywords: Spinal Cord, Spinal Cord

SmartSpeed Precise Image (SSPI) is one of novel image reconstruction technique which combined the physics driven type deep learning-based denoising process and Super-Resolution techniques. We investigated the utility of SSPI-based single-shot turbo spin-echo sequence of the cervical spinal cord T2-weighted image with the short acquisition time. High quantitative signal-to-noise ratio and qualitative image sharpness were successfully demonstrated by using SSPI. This methodology can be useful for the better image quality and the short acquisition time in the assessment of patients with cervical spinal cord diseases.

View Presentation Video

Xiaofeng Yang¹, Sagar Mandava², Yang Lei¹, Huiqiao Xie¹, Tonghe Wang³, Justin Roper¹, Tian Liu⁴, and Hui Mao^1
1Emory University, Atlanta, GA, United States, ²GE Healthcare, Atlanta, GA, United States, ³Memorial Sloan Kettering Cancer Center, New York, NY, United States, ⁴Icahn School of Medicine at Mount Sinai, New York, NY, United States

Keywords: Quantitative Imaging, Data Processing

This study aims to develop an efficient and clinically applicable method using patient-specific self-supervised resolution-enhancing network to synthesize the high-resolution information of MR images in the low-resolution direction to generate respective high-resolution MRI.