Video from ISMRM: The last mile to clinical AI deployment

Erik L. Ridley
May 11, 2025

HONOLULU – In a video interview at the annual meeting of the International Society for Magnetic Resonance in Medicine (ISMRM), Dania Daye, MD, PhD, of the University of Wisconsin, discussed challenges in bringing AI into clinical practice and shared tips for success.

 

 

Latest in ISMRM 2025
Yuhei Takado, MD, PhD
ISMRM: MRI is an 'indispensable' tool for AD diagnosis and staging
May 11, 2025
Katja Interview
Video from ISMRM: Katja Pinker lauds the many benefits of breast MRI
May 11, 2025
A lollipop plots showing the most important nodes by RF-MLA selected by Mean decrease in Gini for a 7 tesla fMRI dataset, with longer sticks meaning greater importance. Each group of networks’ nodes has its own color matching the same network’s color in the brain map. Nodes' names preceded by a red asterisk are repeated among different networks, matching the red nodes in the brain map, which appear in multiple networks.
ISMRM: fMRI identifies key brain regions in superagers
May 11, 2025
Workflow for FTD, AD, and CN classification using automated brain volumetry. Graphic and caption courtesy of Seung Hyun Lee and the ISMRM.
ISMRM: Deep-learning tool shows promise in diagnosing frontotemporal dementia
May 11, 2025
Related Stories
Yuhei Takado, MD, PhD
ISMRM 2025
ISMRM: MRI is an 'indispensable' tool for AD diagnosis and staging
Katja Interview
ISMRM 2025
Video from ISMRM: Katja Pinker lauds the many benefits of breast MRI
A lollipop plots showing the most important nodes by RF-MLA selected by Mean decrease in Gini for a 7 tesla fMRI dataset, with longer sticks meaning greater importance. Each group of networks’ nodes has its own color matching the same network’s color in the brain map. Nodes' names preceded by a red asterisk are repeated among different networks, matching the red nodes in the brain map, which appear in multiple networks.
ISMRM 2025
ISMRM: fMRI identifies key brain regions in superagers
Workflow for FTD, AD, and CN classification using automated brain volumetry. Graphic and caption courtesy of Seung Hyun Lee and the ISMRM.
ISMRM 2025
ISMRM: Deep-learning tool shows promise in diagnosing frontotemporal dementia
More in ISMRM 2025
ISMRM: MRI is an 'indispensable' tool for AD diagnosis and staging
By Kate Madden Yee
May 11, 2025
Yuhei Takado, MD, PhD
Video from ISMRM: Katja Pinker lauds the many benefits of breast MRI
By Kate Madden Yee
In an interview with AuntMinnie, Katja Pinker, MD, PhD, offered an overview of current techniques and protocols for breast MRI.
May 11, 2025
Katja Interview
ISMRM: fMRI identifies key brain regions in superagers
By Will Morton
Functional MRI (fMRI) has shed new light on brain areas that differentiate superagers from cognitively average older adults.
May 11, 2025
A lollipop plots showing the most important nodes by RF-MLA selected by Mean decrease in Gini for a 7 tesla fMRI dataset, with longer sticks meaning greater importance. Each group of networks’ nodes has its own color matching the same network’s color in the brain map. Nodes' names preceded by a red asterisk are repeated among different networks, matching the red nodes in the brain map, which appear in multiple networks.
ISMRM: Deep-learning tool shows promise in diagnosing frontotemporal dementia
By Maryam Payne
An automated brain volumetry model for MRI shows promising accuracy in diagnosing FTD, according to research presented at ISMRM 2025.
May 11, 2025
Workflow for FTD, AD, and CN classification using automated brain volumetry. Graphic and caption courtesy of Seung Hyun Lee and the ISMRM.
ISMRM: Novel MRI technique identifies changes in brain entropy
By Kate Madden Yee
A novel MRI technique called quantitative magnetization transfer (qMT) identifies changes in brain entropy due to normal aging.
May 11, 2025
Regions of interest depicted in colors: cerebrospinal fluid (blue), cortical gray matter (dark green), and white matter (yellow). Scatter plots present significant correlations between (b) [semi-solid spin pool size, or ms0m0s] entropy and age in cerebrospinal fluid and cortical gray matter, and (c) [longitudinal relaxation rates, or Rf1R1f] entropy and age in cortical gray matter and white matter (p < 0.05). Images, graphics, and caption courtesy of Sohae Chung, PhD, and the ISMRM.
ISMRM: Diffusion MRI predicts progression to Alzheimer's
By Amerigo Allegretto
A presentation at ISMRM 2025 suggests diffusion MRI could predict progression from mild cognitive impairment to Alzheimer's.
May 11, 2025
The hazard ratio for mean diffusivity and reciprocal of the hazard ratio for fractional anisotropy. Increases in mean diffusivity and decreases in fractional anisotropy are associated with a higher risk of conversion.
ISMRM: Exercise may reduce structural brain changes
By Liz Carey
Researchers examine the relationship between exercise intensity, brain volume changes, and depression.
May 11, 2025
Boxplot showing significantly larger brain volumes in individuals engaging in vigorous daily exercise compared to those with sedentary or moderate activity levels. The exercise intensity-brain volume pattern is similar across both depressed and nondepressed individuals.
ISMRM: Contrast-free MR angiography comparable to CT for PE detection
By Liz Carey
University of Michigan researchers investigate detectability of pulmonary embolism by noncontrast MR angiography at 0.55 tesla.
May 10, 2025
Axial (A) and Coronal (B) CTPA show multiple partial intraluminal filling defects along the course of the right middle lobar segmental branches (medial segment) (yellow arrow) and lower lobar and postero-medial segmental branches (green arrow). Note the low-signal filling defects on the axial and coronal 0.55T MRI sequence.
ISMRM: Insulin resistance in women associated with less myelin, changes in brain
By Maryam Payne
ISMRM research indicates that higher insulin resistance is associated with less myelin in women.
May 10, 2025
Associations between insulin resistance and MWF. (A) Distribution of insulin resistance, stratified by sex. (B) Regression analysis of whole-brain MWF vs. log (HOMA-IR), adjusted for age and age². Shaded regions indicate 95% confidence intervals. (C) Regression analysis of whole-brain MWF vs. log (HOMA-IR), adjusted for age, age², sex, and log (HOMA-IR) sex. Graphics and caption courtesy of Nathan Zhang, PhD, and the ISMRM.
ISMRM: Brain’s waste-clearing system accelerates brain aging after stroke
By Will Morton
The brain’s glymphatic system appears to accelerate brain aging in patients after ischemic stroke.
May 10, 2025
Representative T2-FLAIR, CBF maps, choroid plexus segment, free-water maps, ALPS ROI, and 3D T1BRAVO from a stroke patient, and a healthy control. Both individuals are 64 years old in chronological age. The patient displays an evident ischemic lesion in the basal ganglia region on T2-FLAIR imaging. The distinctions between the patient and the healthy control are as follows: CBF (32.22 ml/100g/min vs. 47.70 ml/100g/min), CPVF (1.47 vs. 0.84), VCSFVF (32.50 vs. 11.00), MSFW (0.0455 vs. 0.0313), ALPS (1.04 vs. 1.54), and BPAD (13.21 vs. -1.60).
ISMRM: Trimodal PET-MR-FUS may be feasible therapy monitoring option
By Amerigo Allegretto
Researchers at ISMRM 2025 touted the success of a trimodal MR-PET-FUS system that could have applications for therapy monitoring.
May 10, 2025
Researchers at ISMRM highlighted the success of a trimodal MR-PET-FUS system built around a low-field MRI scanner. MR (top) and PET (bottom) images were acquired simultaneously before and after FUS heating.
ISMRM: Switching between full and short breast MRI reduces recalls
By Kate Madden Yee
Switching between abbreviated and full protocols for breast MRI can reduce exam time and lower recall rates.
May 10, 2025
Protocol time and recall bounds as a function of AI specificity and sensitivity. On the top, the bounds are shown as a function of the specificity of the AI algorithm, for a fixed value of the sensitivity of that same AI model. On the bottom, the bounds are shown as a function of the sensitivity, for a fixed specificity. Graphics and caption courtesy of the ISMRM.
Page 1 of 2
Next Page