Video from ISMRM 2019: Jong Chul Ye on machine learning and data reconstruction

May 14, 2019
2019 05 14 20 16 6958 Ismrm 2019 Ye Jong Chul 400

MONTREAL - While most of the focus on machine learning in radiology has been image interpretation, Jong Chul Ye, PhD, of the Korea Advanced Institute of Science and Technology (KAIST) in South Korea believes that data reconstruction is also a fertile area for deep learning. He explains in this video from the International Society for Magnetic Resonance in Medicine (ISMRM) conference.

Jong Chul Ye, PhD, of KAIST.

Latest in MRI
Fat Tissue Adipocytes
T2-weighted MRI shows promise for body composition analysis
February 21, 2025
Echelon Synergy 1.5T MRI with MotionClear Comprehensive Motion Correction Suite
Sponsored
Echelon Synergy 1.5T MRI with MotionClear Comprehensive Motion Correction Suite
January 1, 2025
Images in an 18-year-old man with recurrent dislocations of the right shoulder. (A, B) Unenhanced coronal, (C) axial, and (D, E) sagittal deep learning super-resolution threefold parallel imaging -- accelerated turbo spin-echo MRI scans were obtained at 3-tesla field strength. (A) Coronal T2-weighted fat-suppressed (FS) and (B) coronal proton density (PD)-weighted MRI scans show a nondisplaced superior labral tear (arrows). (C) Axial proton density-weighted fat-suppressed, (D) sagittal T2-weighted fat-suppressed, and (E) sagittal T1-weighted MRI scans show continuation into a nondisplaced anteroinferior labral tear (arrows). All seven readers correctly diagnosed the arthroscopy-validated findings. (F) An arthroscopic photograph shows the anteroinferior labral tear (arrow). Image and caption courtesy of the RSNA.
7-minute shoulder MRI scans are feasible
February 18, 2025
2025 02 18 Radiology D Antonoli Figure1 Thumbnail
New AI model successfully segments anatomic structures in MR images
February 18, 2025
Related Stories
Ismrm Logo
Companies
ISMRM
2019 06 11 23 04 1990 Ai 400
CT
AI converts low-dose CT scans to high-quality studies
2019 05 14 20 16 6958 Ismrm 2019 Wald Larry 400
MRI
Video from ISMRM 2019: Larry Wald on new portable MRI designs
Echelon Synergy 1.5T MRI with MotionClear Comprehensive Motion Correction Suite
Sponsor Content
Echelon Synergy 1.5T MRI with MotionClear Comprehensive Motion Correction Suite
More in MRI
T2-weighted MRI shows promise for body composition analysis
By Kate Madden Yee
Using deep learning with T2-weighted MR imaging is a feasible way to assess patients' body composition, researchers have reported.
February 21, 2025
Fat Tissue Adipocytes
Are white-matter hyperintensities found on MRI biomarkers for TBI?
By Kate Madden Yee
White-matter hyperintensities found on high-resolution FLAIR images on 3-tesla MRI aren't necessarily biomarkers for mild traumatic brain injury (TBI).
February 19, 2025
2025 02 19 Ajr Tanwar Figure2 Thumbnail
7-minute shoulder MRI scans are feasible
By Will Morton
A commercially available deep-learning (DL) algorithm can enable high quality seven-minute shoulder MRI exams.
February 18, 2025
Images in an 18-year-old man with recurrent dislocations of the right shoulder. (A, B) Unenhanced coronal, (C) axial, and (D, E) sagittal deep learning super-resolution threefold parallel imaging -- accelerated turbo spin-echo MRI scans were obtained at 3-tesla field strength. (A) Coronal T2-weighted fat-suppressed (FS) and (B) coronal proton density (PD)-weighted MRI scans show a nondisplaced superior labral tear (arrows). (C) Axial proton density-weighted fat-suppressed, (D) sagittal T2-weighted fat-suppressed, and (E) sagittal T1-weighted MRI scans show continuation into a nondisplaced anteroinferior labral tear (arrows). All seven readers correctly diagnosed the arthroscopy-validated findings. (F) An arthroscopic photograph shows the anteroinferior labral tear (arrow). Image and caption courtesy of the RSNA.
New AI model successfully segments anatomic structures in MR images
By Kate Madden Yee
A Swiss research team has developed and tested an AI model that automatically segments anatomic structures on MR images independent of sequence.
February 18, 2025
2025 02 18 Radiology D Antonoli Figure1 Thumbnail
Are low-field MRI units effective for neuroradiologic imaging?
By Kate Madden Yee
Are low-field MRI units effective for neuroradiologic imaging? Perhaps, say researchers from the University of Michigan in Ann Arbor.
February 14, 2025
2025 02 13 Radio Graphics Kelsey Figure1 Thumbnail
fMRI reveals a brain circuit for creativity
By Kate Madden Yee
Functional MRI (fMRI) has revealed a brain circuit for creativity, researchers from Mass General Brigham in Boston have reported.
February 13, 2025
Brain Abstract
MRI model predicts pathologic features of liver cancer
By Will Morton
A new scoring model for MRI exams shows potential for improving the assessment of early recurrence in patients with hepatocellular carcinoma.
February 11, 2025
2025 02 11 I Score Thumbnail
Wash. bill would loosen supervision rules for RTs, MRI techs
By AuntMinnie.com staff writers
The state of Washington is considering a bill authorizing diagnostic radiologic technologists (RTs), therapeutic RTs, and MRI technologists to perform intravenous contrast procedures under "general supervision."
February 7, 2025
Signing Contract Legislation
Race influences headache diagnosis in children presenting to the ED
By Kate Madden Yee
Black or Hispanic children are less likely than their white peers to be diagnosed with migraine via MR imaging in pediatric emergency departments (ED).
February 5, 2025
Am 2016 09 27 14 38 54 774 Diverse Children 400
IMV: MRI exam mix shifts from outpatient to hospital settings
By Davin Korstjens
In 2024, the percentage of MRI procedures performed in an outpatient setting decreased by five percentage points to 66% of total MR procedures.
February 3, 2025
Mri Machine Screens
Ferumoxytol-enhanced MRA is safe for chronic kidney disease patients
By Kate Madden Yee
Ferumoxytol-enhanced MR angiography (MRA) appears to be safe for chronic kidney disease patients, researchers have reported.
January 29, 2025
Contrast Injector
Ultrafast MRI exam bests standard MRI for classifying breast cancers
By Amerigo Allegretto
An ultrafast MRI-based radiomics exam performs just as well as standard MRI and isn’t dependent on radiologist experience.
January 28, 2025
Ultrafast and standard MRI in a 30-year-old woman with triple-negative invasive ductal carcinoma. (A) Ultrafast MRI taken 16.8 seconds after contrast agent injection. (B) Standard MRI taken 58.8 seconds after contrast agent injection. Both images show an oval-shaped, irregular marginated, rim-enhancing mass in the left outer breast. For 3D tumor segmentation, the entire enhanced tumor margins were drawn from top to bottom of each tumor in axial views of U2 phase postcontrast ultrafast MRI and the initial phase postcontrast standard MRI. Among the 14 ultrafast images, U1 is the first phase in which the signal intensity of the hotspot region of interest of the tumor is 10% higher than the average signal intensity of unenhanced images. U2 is the immediate next phase of U1 and the well-established tumor enhancement time.
Page 1 of 613
Next Page