Rapid MRI

1356971 - Waiting list backlog reduction with rapid scanning and AI-enabled reporting

Friday, January 27, 2023

9:50 AM – 10:00 AM

Location: Silver Pearl 2

Presenting Author(s)

JA

Jessica Artico, MD

Clinical Research Fellow
St Bartholomew's Hospital, England, United Kingdom

Primary Author(s)

JA

Jessica Artico, MD

Clinical Research Fellow
St Bartholomew's Hospital, England, United Kingdom

Co-Author(s)

RL

Reem Laymouna, PhD, MSc

Cardiology Fellow
Barts Heart Centre at St Bartholomew's Hospital
Bristol, United Kingdom
PF

Paige Fox

Superintendent Radiographer
Barts Heart Centre, United Kingdom
HK

Hibba Kurdi, MD, BSc

Cardiology Fellow
Barts Health NHS Trust, London, UK
London, United Kingdom
AA

Aderonke T. Abiodun, MBChB

Clinical Research Fellow
University College London, United Kingdom
HS

Hunain Shiwani, MD

Clinical Research Fellow
University College London and Barts Heart Centre, United Kingdom
IP

Iain Pierce, PhD

Scientist
Barts Heart Centre at St Bartholomew's Hospital, United Kingdom
HX

Hui Xue, PhD

Director, Imaging AI Program
National Institutes of Health
Bethesda, Maryland, United States
PK

Peter Kellman, PhD

Senior Scientist
National Institutes of Health, Maryland, United States
RW

Roshan Weerackody

Consultant Cardiologist
Barts Heart Centre at St Bartholomew's Hospital, United Kingdom
Mark Westwood, MD

Consultant Cardiologist
Barts Heart Centre at St Bartholomew's Hospital, United Kingdom
Thomas A. Treibel, MD, PhD

Consultant Cardiologist
University College London, England, United Kingdom
James C. Moon, MD

Clinical Director, Imaging
Barts Heart Centre and UCL
London, England, United Kingdom
Rhodri Davies, MD, PhD

Associate clinical professor
University College London
London, Wales, United Kingdom

Disclosure(s):

Mark Westwood, MD: No relevant disclosure to display

Thomas A. Treibel, MD, PhD: No relevant disclosure to display

Background:

The need for rapid, focused protocols to increase throughput, improve cost-effectiveness and reduce waiting lists is now essential. We designed and implemented a rapid perfusion CMR protocol incorporating AI approaches in daily clinical practice and measured its impact.

Methods:

215 patients with suspect ischaemic heart disease were consecutively recruited and allocated to rapid (130) or conventional (85) perfusion CMR protocols. These protocols used inline perfusion mapping with AI inline super-human analysis^1,2.

Scanning times (first to last image timestamp), quality (consensus of 2 observers, scale of 3) and reporting times of standard reporting vs AI driven reporting by 3 experts in CMR (Level 3 Certification) were assessed.

Results:

Scanning time: Overall, the average scanning time was 36.0 (min 24, max 52) minutes for normal protocol and 22.5 (min 14, max 31) minutes for the rapid protocol, reducing scanning time by 13 minutes (p< 0.001). For both the rapid and the conventional protocol, the scan quality was considered similar (125/132 vs 80/85 scored as good).

Reporting time: Mean reporting times was 21.2(min 5, max 50) minutes for standard reporting, and 10.2(min 3, max 23) minutes for AI-driven reporting, reducing reporting times by 10 minutes (p< 0.01).

Conclusion:

Rapid CMR protocols incorporating AI approaches save 13.5 minutes scanning and 10 minutes reporting. Scans can consistently be performed in less than 25 minutes and reporting in less than 10 minutes. These can be implemented in NHS clinical services.

Sequelae: Following this trial, rapid CMR approaches have become routine for ~1/4 patients at our site and booking slots have been reduced to 50 minutes (from 1 hour) on all CMR booking diaries with a daily increase in activity of +3 patients a day with consequent benefits to waiting lists.