Tracer-agnostic diffusion model-based CT-free attenuation correction for brain PET: Comprehensive evaluation… | ScholarDeck

Paper

Tracer-agnostic diffusion model-based CT-free attenuation correction for brain PET: Comprehensive evaluation across 14 tracers.

New research · Nuclear Medicine

Physics in medicine and biology · 3w

AI / informaticsPhysics in medicine and biology· Jun 2026

Tracer-agnostic diffusion model-based CT-free attenuation correction for brain PET: Comprehensive evaluation across 14 tracers.

Yuya Onishi, Kibo Ote, Masanori Ito … Yasuomi Ouchi

Read paper

Neurologic ImagingAI / informaticsClinical practiceQ2IF 3.2

Diffusion model-based CT-free attenuation correction kept regional bias under 10% across 14 PET tracers.

Tracer-agnostic diffusion model-based CT-free attenuation correction for brain PET: Comprehensive evaluation across 14 tracers.

Yuya Onishi … Yasuomi Ouchi

Physics in medicine and biology · Jun 2026 · Q2 in Radiology

Background

Accurate attenuation correction (attenuation correction) is critical in quantitative brain PET imaging.

Purpose

This study aimed to develop a tracer-agnostic deep-learning approach for a CT-free attenuation correction framework.

10%

Results

10%

off-target error stayed low across every tracer tested

More results

Robust generalizability was demonstrated in tracers with diverse uptake patterns and acquisition protocols.

SIGNIFICANCE: This CT-free attenuation correction approach achieves quantitative accuracy comparable to that of CT-based correction while eliminating additional scans, reducing radiation exposure, and simplifying the workflow.

“

Conclusion

This tracer-independent design supports the early evaluation of novel tracers and their broad clinical adoption in brain-PET imaging.

Read paper

0 comments

No comments yet. Be the first.

ScholarDeck.

Join the discussion on this paper

Create your profile

Related papers

Latest Foundational

Cohort Study

AUC 0.940 vs 0.892

p-tau217 diagnoses AD more accurately in early-onset than late-onset patients

Study

>0.65

predicted and actual delivered radiation doses to liver and tumor track closely

Cohort Study

HR 5.2

bigger tracer uptake rise after therapy meant over 5 times higher progression risk

Cohort Study

HR 0.34

high tumor dose cut progression or death risk by two thirds

Case-control

AUC, 0.88

higher plasma p-tau217 tracks with amyloid PET positivity, close to cerebrospinal fluid markers

AI / Informatics

1.17 per SD

higher resting right ventricular uptake means greater risk of death or heart attack

Cohort Study

rho = 0.81

Higher plasma p-tau217 strongly correlated with higher tau PET binding in memory regions.

Animal / Preclinical

>98%

over 98% pure, ready for reliable imaging and therapy