Skip to content

Radiological study for vascular anomalies using AI

Observational study to establish evaluation method for vascular abnormalities using deep learning

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
JPRN
Registry ID
JPRN-jRCT1040220052
Enrollment
20
Registered
2022-08-11
Start date
2022-08-11
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

Vascular anomalies hemangioma, vascular anomalies

Interventions

None listed

Sponsors

Michio Ozeki
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: 1, A multicenter phase III investigator-initiated clinical trial (NPC-12T-LM study) conducted from 2017 to 2019 to investigate the efficacy and safety of NPC-12T (sirolimus) for intractable lymphatic disease, Multi-center, open-label, uncontrolled study to investigate the safety and efficacy of sirolimus for refractory vascular and lymphatic diseases (SRL-CVA-01 study, jRCTs031180290) started in 2017, and Conducted from 2020 to 2022, a multicenter phase III investigator-initiated clinical trial (NPC -12T-CVA) 2) Patients with evaluable MRI images 3) Patients who agreed to participate in this study

Exclusion criteria

Exclusion criteria: 1) Patients with other than obvious vascular abnormalities 2) Patients with clearly different lesions and image artifacts such as bleeding and inflammation that are difficult to evaluate 3) Other patients who are judged to be inappropriate by the principal investigator or co-investigator

Design outcomes

Primary

MeasureTime frame
Correlation coefficient between "lesion volume of vascular abnormalities measured by deep learning" and "lesion volume independently measured by two radiologists"

Secondary

MeasureTime frame
Correlation coefficient (ICC(2,1)) of analysis results of area and volume measured independently by two radiologists and a trained doctor Differences in AI segmentation and correlation coefficients with different MRI images (fat-suppressed T2-weighted images, T1-weighted images, contrast-enhanced T1-weighted images, etc.)

Contacts

Public ContactOzeki Michio

Gifu University Hospital

michioo@gifu-u.ac.jp+81-58-230-6000

Outcome results

None listed

Source: JPRN (via WHO ICTRP) · Data processed: Jul 3, 2026