Michael Allen

AI
AI tool needs more diverse skin types in datasets
A dermatology algorithm powered by artificial intelligence (AI) that can identify a range of skin conditions doesn't work effectively on black skin, according to researchers in Uganda and Sweden. The study highlights the potential risks of AI-based healthcare and the need to ensure diversity in datasets used to train algorithms.
November 28, 2019
2019 11 27 21 00 8965 Uganda Research Team 20191127214704
Clinical News
MRI reveals molecular composition of the brain
Researchers from Israel have developed a model that compares the water content of the brain with measures of physical properties obtained from MRI scans to calculate the molecular composition of lipids in the brain. The technique may help detect changes in the biological makeup of the brain over time and identify key changes associated with diseases like Alzheimer's.
August 21, 2019
2019 08 20 18 51 7221 Mezer Mri Brain Map Thumb
Page 1 of 1
Top Stories
Hospitals across Europe, here in Katowice, Poland, are deploying AI tools in clinical workflows, but the regulatory infrastructure to oversee them is still catching up.
AI
One tool, many rulebooks: How the world is and isn't regulating medical AI
AI is reshaping radiology faster than regulators can keep up. From Brussels to Dubai to Seoul, most are still writing their own rules.
PET/CT images performed at 10- and 60-minutes following injection of Ga-68 FAPI-46 (mean 181 MBq; range 143–225 MBq).
Molecular Imaging
Early FAPI-PET scans match 60-minute scans for lung cancer staging
Think more deeply about the structural, procedural, or operational bottlenecks stacking on top of one another, Dr. Rizwan Malik told UKIO delegates.
AI
The great AI debate: Expensive failure or vital prerequisite?
C-index for Cox regression and random survival forests models using two feature sets. Adding historical registry data decreases the C-index for Cox regression but increased it for the random survival forests model, consistent with the non-linear structure in the registry data.
MRI
AI gives a boost to cardiac MRI risk prediction
AI for CT & PET/CT Imaging
Sponsor Content
AI for CT & PET/CT Imaging
More in Home
One tool, many rulebooks: How the world is and isn't regulating medical AI
By Claudia Tschabuschnig
AI is reshaping radiology faster than regulators can keep up. From Brussels to Dubai to Seoul, most are still writing their own rules.
June 12, 2026
Hospitals across Europe, here in Katowice, Poland, are deploying AI tools in clinical workflows, but the regulatory infrastructure to oversee them is still catching up.
Early FAPI-PET scans match 60-minute scans for lung cancer staging
By Will Morton
By convention, most molecular imaging tracers such as F-18 FDG are injected one hour prior to PET scans to allow time for uptake of the tracer by tumors.
June 10, 2026
PET/CT images performed at 10- and 60-minutes following injection of Ga-68 FAPI-46 (mean 181 MBq; range 143–225 MBq).
The great AI debate: Expensive failure or vital prerequisite?
By Philip Ward
The spotlight fell brightly on AI at Tuesday's plenary session at the U.K. Imaging and Oncology Congress. The global expert panel scrutinized the current status of AI and the challenges ahead.
June 10, 2026
Think more deeply about the structural, procedural, or operational bottlenecks stacking on top of one another, Dr. Rizwan Malik told UKIO delegates.
AI gives a boost to cardiac MRI risk prediction
By Kate Madden Yee
Accurate risk prediction for coronary heart disease helps clinicians guide patient therapy and follow-up.
June 10, 2026
C-index for Cox regression and random survival forests models using two feature sets. Adding historical registry data decreases the C-index for Cox regression but increased it for the random survival forests model, consistent with the non-linear structure in the registry data.
MMA embolization for chronic subdural hematoma: Routine takes shape
By Claudia Tschabuschnig
MMA embolization for chronic subdural hematoma is becoming routine. After eight randomized trials, six positive results, German data now adds to the picture.
June 10, 2026
Flat-detector CT showing catheter position following contralateral middle meningeal artery embolization in a case where ipsilateral access was not possible.
ECIO 2026: interventional oncology's next step
By Claudia Tschabuschnig
At ECIO 2026 in Basel, experts highlighted how multidisciplinary collaboration, patient selection, and evidence generation are shaping the next phase of the specialty.
June 9, 2026
Experts gathered at the European Conference on Interventional Oncology ECIO 2026 in Basel to discuss the latest advances in minimally invasive cancer care.
What's the optimum approach for B3 breast lesions?
By Philip Ward
Certain B3 lesion types should be screened more often, researchers from a top London hospital have asserted at the U.K. Imaging and Oncology Congress (UKIO).
June 9, 2026
Breast Cancer Social
AI may provide early breast cancer alerts from mammograms
By Amerigo Allegretto
Commercial AI systems could provide early alerts for breast cancer by picking out early signs of the disease on mammograms.
June 9, 2026
Screening mammograms and AI score changes are depicted over time in two individuals with screen-detected cancer. Full-field digital mammograms show craniocaudal (top) and mediolateral (bottom) views of the left and right breast. The description below each mammogram indicates whether AI scores from three AI-based computer-aided detection systems (AI-1, AI-2, and AI-3) were above or below the 90th percentile. (A) Mammograms from three screening time points (in 2009, 2011, and 2014) in an individual who was diagnosed in February 2014 (at age 73 years) with a left-sided 25-mm grade 2 invasive breast carcinoma, no special type (arrow). Mammographic breast density was classified as BI-RADS B on all three mammograms. (B) Mammograms from four screening time points (in 2009, 2011, 2013, and 2015) in an individual who was diagnosed in October 2015 (at age 65 years) with a left-sided 45-mm grade 2 lobular carcinoma (arrow). Mammographic breast density was classified as BI-RADS C on all four mammograms. Screen-detected cancers were defined as those diagnosed within 90 days for individuals who were recalled at screening (*).
Tattoo pigments can have significant impact on imaging
By Philip Ward
Tattoos can appear as shadows or artifacts on an x-ray, causing confusion during interpretation. Research presented at the U.K. Imaging and Oncology congress has provided new data on which tattoo inks have the greatest impact.
June 8, 2026
2026 06 08 Tattoos Homepage Image
SERAM 2026: Biparametric MRI cuts time and costs in prostate cancer imaging
By Claudia Tschabuschnig
A study presented at SERAM 2026 suggests that biparametric MRI (bpMRI) can reduce exam time and costs in patients with clinically significant prostate cancer.
June 8, 2026
Biparametric prostate MRI identified clinically significant Gleason 3+4 prostate cancer using T2-weighted imaging, diffusion-weighted imaging, and ADC mapping alone.
SERAM 2026: AI chest triage cuts referrals without raising CT use
By Claudia Tschabuschnig
A real-world implementation study from a Spanish regional hospital suggests that AI-assisted chest radiograph triage may reduce specialist referrals without driving additional CT imaging.
June 4, 2026
An AI system highlights multiple abnormalities on a chest radiograph, including a pulmonary nodule (nódulo pulmonar), pleural effusion (derrame pleural), and alveolar syndrome/consolidation (síndrome alveolar).
AI detects lung cancer nodules well but shows low specificity
By Kate Madden Yee
The finding suggests the models offer “a potential role as adjunctive tools for ruling out malignancy” rather than classifying it.
June 4, 2026
Am 2020 06 26 16 29 2945 Cancer Lung 400
Page 1 of 85
Next Page