Gene Saragnese

AI
Where is AI making the difference in radiology today?
Artificial intelligence (AI) promises to reduce costs and improve clinical outcomes, and it can provide useful support tools that can be integrated into current workflow, PACS, medical imaging hardware, and healthcare clouds, writes industry expert Gene Saragnese.
January 3, 2019
2016 08 17 17 05 06 731 Computer Brain 400
Page 1 of 1
Top Stories
Mri Slide 400
MRI
How much surveillance imaging is needed for meningiomas?
Most surveillance MRI or CT exams did not result in intervention, and treatment rates remained stable during the study period.
Dr. Paul McCoubrie
Clinical News
The retiring radiologist
Shutterstock 2474798495
Digital X-Ray
Review charts path toward standardized chest x-ray optimization
Shutterstock 2743841919
Digital X-Ray
Fairness-aware training improves pneumonia AI performance across sexes
Low-quality axial T2-weighted MRI scans with gradient-weighted class activation mapping. The low-quality MRI scans (top row) show blurred structures and artifacts making zonal and capsule boundaries indistinguishable. On the same scans with gradient-weighted class activation map overlays (bottom row), red indicates regions that were most heavily weighted by the deep learning model toward the low-quality prediction.
MRI
AI framework could improve MRI quality control in prostate cancer
More in Home
How much surveillance imaging is needed for meningiomas?
By Amerigo Allegretto
Most surveillance MRI or CT exams did not result in intervention, and treatment rates remained stable during the study period.
August 21, 2026
Mri Slide 400
The retiring radiologist
By Paul McCoubrie, MBBS
In a new column, Dr. Paul McCoubrie reflects on aging and the prospect of retirement.
August 21, 2026
Dr. Paul McCoubrie
Review charts path toward standardized chest x-ray optimization
By Claudia Tschabuschnig
A 29-study review found no consensus on optimal beam quality for adult chest radiography, prompting calls for standardized research and safer, more consistent protocols.
August 19, 2026
Shutterstock 2474798495
Fairness-aware training improves pneumonia AI performance across sexes
By Claudia Tschabuschnig
Fairness-aware training reduced several sex-based disparities in pneumonia AI detection without compromising overall accuracy, but widened the sensitivity gap.
August 19, 2026
Shutterstock 2743841919
AI framework could improve MRI quality control in prostate cancer
By Amerigo Allegretto
The framework uses a DL model trained on low- and high-quality MR images and helped improve radiologist accuracy.
August 19, 2026
Low-quality axial T2-weighted MRI scans with gradient-weighted class activation mapping. The low-quality MRI scans (top row) show blurred structures and artifacts making zonal and capsule boundaries indistinguishable. On the same scans with gradient-weighted class activation map overlays (bottom row), red indicates regions that were most heavily weighted by the deep learning model toward the low-quality prediction.
AI fracture detection device validated across three European hospitals
By Will Morton
No differences in AI performance were observed across centers, and AI assistance was associated with higher reader sensitivity.
August 18, 2026
Artificial intelligence (AI) assistance facilitates correct fracture identification in cases initially missed by human readers. A representative case is shown using anteroposterior radiographs in a 29-year-old male patient with wrist trauma (suspected nondisplaced transverse scaphoid fracture). The reader’s initial unaided assessment (top) resulted in a missed fracture, whereas with AI assistance (bottom), the fracture was correctly identified. The green box represents the fracture location as predicted by the AI tool, the blue box represents the reference standard annotation, and the red dots represent individual reader annotations.
CT for breast radiotherapy detects ischemic heart disease risk
By Will Morton
As survival after early-stage breast cancer improves, cardiovascular disease has emerged as an increasingly prominent competing risk in older women.
August 17, 2026
Heart 1
Review highlights opportunities and risks of AI in pediatric imaging
By Claudia Tschabuschnig
Adult-trained AI tools may underperform in children, requiring pediatric-specific datasets, age-stratified validation, and stronger clinical oversight for safe deployment, researchers say.
August 17, 2026
Pexels Cottonbro 5867701 (1)
FAPI-PET/CT shows promise in hepatopancreatobiliary cancers
By Will Morton
FAPI-PET/CT could potentially improve noninvasive cancer staging, and, ultimately, clinical decision making.
August 13, 2026
Shown is a 69-year-old man with a cholangiocarcinoma in the distal common bile duct. F-18 FDG-PET/CT was negative where Ga-68 FAPI-46 PET/CT showed high focal FAPI uptake in the liver hilum and surrounding lymph nodes. a-d: F-18 FDG-PET/CT, e-h: Ga-68 FAPI-46 PET/CT. a, b, e, f: Maximum intensity projections, c, g: axial fusion images, d, h: non-contrast enhanced CT.
AI performs well in breast screening, but density complicates the picture
By Claudia Tschabuschnig
While AI can support breast cancer risk assessment, its performance declined as breast density increased, while variations related to equipment vendor and measurement level may complicate personalized screening.
August 13, 2026
Shutterstock 1918864388
Lviv hosts second cardiovascular forum: From imaging to wartime medicine
MCI Lviv 2026 brought Ukrainian and international specialists together for two days of practical education and scientific exchange.
August 12, 2026
Photo 2026 06 19 10 08 34
Are European pilot sites ready for organized prostate cancer screening?
By Claudia Tschabuschnig
European pilot sites have the clinical capacity for risk-stratified prostate cancer screening but lack the infrastructure needed for implementation, a study found.
August 11, 2026
Pexels Tara Winstead 7723619
Page 1 of 90
Next Page