Automatic detection of abnormal lesions in FDG-PET/CT screening using deep learning technology

Deep learning based automatic detection of pathological uptake in [18F] DG PET/CT screening - Deep learning based automatic detection of pathological uptake in [18F] DG PET/CT screening

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

JPRN

Registry ID

JPRN-UMIN000047885

Enrollment

6000

Registered

2022-07-01

Start date

2022-07-01

Completion date

Unknown

Last updated

2026-06-29

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Screening

Interventions

None listed

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: 1) Subjects who agreed on a written document 2) Subjects who underwent studies such as thyroid ultrasound or gastrointestinal endoscopy to be training data

Exclusion criteria

Exclusion criteria: 1) Subjects with artifacts on [18F] DG PET/CT 2) Subjects without complete [18F] DG PET/CT scanning 3) Subjects without any training data available such as ultrasound, blood test, fecal occult blood, or gastrointestinal endoscopy 4) Subjects who scored "E (diagnosed in other institutes)" with ultrasound or gastrointestinal endoscopy 5) Subjects who were considered as not eligible by investigators

Design outcomes

Primary

Measure	Time frame
FDG Uptake in thyroid, stomach, duodenum, and large intestine	—

Countries

Japan

Contacts

Public ContactTomomi Nobashi

Kyoto University Hospital Preemptive Medicine and Lifestyle Related Disease Research Center

nobaco@kuhp.kyoto-u.ac.jp075-751-3760

Outcome results