Dr. Merel Huisman, PhD

AI
AI and radiology: The younger generation's perspective
Radiologists must embrace artificial intelligence (AI), collaborate, be visible, and make digital innovation central to their work, writes resident Dr. Merel Huisman, PhD. As long as they do this, they will never be "mostly unnecessary" -- as Dutch Finance Minister Wopke Hoekstra predicted recently.
October 14, 2020
2020 10 14 17 28 8143 Computer Future Hologram 400
Page 1 of 1
Top Stories
Pexels Cottonbro 5723883
Molecular Imaging
How AI can help with PET/CT guideline deviations
Researchers have found a gap between what international PET/CT guidelines recommend and what actually happens in clinical practice.
Fat Tissue
MRI
MRI reveals how hidden muscle fat increases risk to heart, metabolism
Ean Mcongress
Molecular Imaging
The EANM joins EMUC26 and pushes its policy agenda in Brussels
Overview of the study design. (A) The fully automated deep learning framework was developed to estimate body composition (BC) (defined as subcutaneous adipose tissue [SAT] in liters; visceral adipose tissue [VAT] in liters; skeletal muscle [SM] in liters; SM fat fraction [SMFF] as a percentage; and intramuscular adipose tissue [IMAT] in deciliters) from MRI. The fully automated framework comprised one model (model 1) to quantify different BC measures (SAT, VAT, SM, SMFF, and IMAT) as three-dimensional (3D) measures from whole-body MRI scans. The second model (model 2) was trained to identify standardized anatomic landmarks along the craniocaudal body axis (z coordinate field), which allowed for subdividing the whole-body measures into different subregions typically examined on clinical routine MRI scans (chest, abdomen, and pelvis). (B) BC was quantified from whole-body MRI in over 66,000 individuals from two large population-based cohort studies, the UK Biobank (UKB) (36,317 individuals) and the German National Cohort (NAKO) (30,291 individuals). Bar graphs show age distribution by sex and cohort. BMI = body mass index. (C) After the performance assessment of the fully automated framework, the change in BC measures, distributions, and profiles across age decades were investigated. Age-, sex-, and height-adjusted body composition reference curves were calculated and made publicly available in a web-based z-score calculator (https://circ-ml.github.io).
MRI
Whole body MRI, deep-learning can 'map' distribution of fat and muscle
Turning Innovation into Everyday Efficiency
Sponsor Content
Turning Innovation into Everyday Efficiency
More in Home
How AI can help with PET/CT guideline deviations
By Claudia Tschabuschnig
Researchers have found a gap between what international PET/CT guidelines recommend and what actually happens in clinical practice.
May 6, 2026
Pexels Cottonbro 5723883
MRI reveals how hidden muscle fat increases risk to heart, metabolism
By Kate Madden Yee
The results suggest that MRI exams could "augment traditional risk factor screening," researchers noted.
May 5, 2026
Fat Tissue
The EANM joins EMUC26 and pushes its policy agenda in Brussels
By Claudia Tschabuschnig
Decisions shaping who gets access to theranostics in Europe have long been made mainly in the clinic. With EANM opening a Brussels office and joining EMUC26 as co-organizer, a full policy agenda arrives at the EU table.
May 5, 2026
Ean Mcongress
Whole body MRI, deep-learning can 'map' distribution of fat and muscle
By Kate Madden Yee
The map shows that the quality and amount of skeletal muscle, not just visceral fat, are strong predictors of disease.
May 5, 2026
Overview of the study design. (A) The fully automated deep learning framework was developed to estimate body composition (BC) (defined as subcutaneous adipose tissue [SAT] in liters; visceral adipose tissue [VAT] in liters; skeletal muscle [SM] in liters; SM fat fraction [SMFF] as a percentage; and intramuscular adipose tissue [IMAT] in deciliters) from MRI. The fully automated framework comprised one model (model 1) to quantify different BC measures (SAT, VAT, SM, SMFF, and IMAT) as three-dimensional (3D) measures from whole-body MRI scans. The second model (model 2) was trained to identify standardized anatomic landmarks along the craniocaudal body axis (z coordinate field), which allowed for subdividing the whole-body measures into different subregions typically examined on clinical routine MRI scans (chest, abdomen, and pelvis). (B) BC was quantified from whole-body MRI in over 66,000 individuals from two large population-based cohort studies, the UK Biobank (UKB) (36,317 individuals) and the German National Cohort (NAKO) (30,291 individuals). Bar graphs show age distribution by sex and cohort. BMI = body mass index. (C) After the performance assessment of the fully automated framework, the change in BC measures, distributions, and profiles across age decades were investigated. Age-, sex-, and height-adjusted body composition reference curves were calculated and made publicly available in a web-based z-score calculator (https://circ-ml.github.io).
First signals from Germany's lung cancer screening
By Claudia Tschabuschnig
Germany launched statutory LDCT lung cancer screening on 1 April 2026, marking one of Europe's most consequential screening rollouts. But at RÖKO Digital, experts made clear that the hard work of implementation from funding to infrastructure, local coordination, and AI integration, is only about to start.
May 4, 2026
'If you want to get this off the ground, coordinate locally with the cooperation partners that are necessary anyway, and set it up together. BDR and DRG are moving forward on this jointly,' said Prof. Dr. Hermann Helmberger, BDR president.
No two breasts are the same: Mammography's most common errors
By Claudia Tschabuschnig
The most anatomically variable organ in the body doesn't come with a manual. That's exactly the problem.
May 4, 2026
Pexels Tima Miroshnichenko 6234988
Will upright radiotherapy become a new standard?
By Will Morton
Multiple commercial upright systems have entered the market in recent years.
May 4, 2026
Rt Upright
Compartment-based image analysis will boost endometriosis detection
By Frances Rylands-Monk
Endometriosis management has changed radically over the last 20 years, according to a session at ECR 2026.
May 1, 2026
Dr. Miriam Dolciami
When gynecology runs out of answers, interventional radiology steps in
By Claudia Tschabuschnig
Chronic pelvic pain passed between specialties for years, and a fibroid procedure that preserves fertility. While IR has solutions, the referral culture is only catching up slowly.
April 30, 2026
'MRI is here essential as a pre- and post-interventional imaging tool,' said Dr. Geert Maleux, MD, PhD, of University Hospitals Leuven in Leuven, Belgium.
Blind spots in imaging: Dementia care in mammography and miscarriage prediction
By Claudia Tschabuschnig
Dementia in the mammography room and miscarriage in the first trimester, two blind spots that better technology alone won't fix.
April 29, 2026
Early detection depends on more than technology; it depends on whether the system is built for the patient who walks through the door.
4 CT signs help predict ischemia in small bowel obstruction
By Kate Madden Yee
The signs "could be prioritized when interpreting CT examinations in patients with SBO to help guide surgical decision-making."
April 29, 2026
Inflammatory Bowel Crohns
MRI reveals occurrence of placental contractions
By Kate Madden Yee
Characterizing these contractions could help clinicians better understand the placenta's function.
April 29, 2026
Uterine and placental changes during an example placental contraction. The top row shows axial MRI images at selected times points before, during and after a placental contraction (indicated by vertical lines on the graph below) with segmentations shown below. Changes in placental and non-placental volumes, wall areas and placental R2* (all measured across the whole volume of the uterus, not just the single slice shown) are plotted underneath. The legend indicates the colors used for the lines in the plots and the regions indicated in the segmentation.
Page 1 of 80
Next Page