Imperial College London
Portrait Picture

DR BERNHARD KAINZ

Faculty of Engineering, Department of Computing

Reader in Medical Image Computing
 
 
 
//

Contact

 

+44 (0)20 7594 8349b.kainz Website CV

 
 
//

Location

 

372Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Day:2024:10.1002/uog.27577,
author = {Day, TG and Matthew, J and Budd, SF and Venturini, L and Wright, R and Farruggia, A and Vigneswaran, TV and Zidere, V and Hajnal, JV and Razavi, R and Simpson, JM and Kainz, B},
doi = {10.1002/uog.27577},
journal = {Ultrasound Obstet Gynecol},
title = {Interaction between clinicians and artificial intelligence to detect fetal atrioventricular septal defects on ultrasound: how can we optimize collaborative performance?},
url = {http://dx.doi.org/10.1002/uog.27577},
year = {2024}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - OBJECTIVES: Artificial intelligence (AI) has shown promise in improving the performance of fetal ultrasound screening in detecting congenital heart disease (CHD). The effect of giving AI advice to human operators has not been studied in this context. Giving additional information about AI model workings, such as confidence scores for AI predictions, may be a way of improving performance further. Our aims were to investigate whether AI advice improved overall diagnostic accuracy (using a single CHD lesion as an exemplar), and to see what, if any, additional information given to clinicians optimized the overall performance of the clinician-AI team. METHODS: An AI model was trained to classify a single fetal CHD lesion (atrioventricular septal defect, AVSD), using a retrospective cohort of 121,130 cardiac four chamber images extracted from 173 ultrasound scan videos (98 with normal hearts, 75 with AVSD). A ResNet50 model architecture was used. Temperature scaling of model prediction probability was performed on a validation set, and gradient-weighted class activation maps (grad-CAMs) produced. Ten clinicians (two consultant fetal cardiologists, three trainees in pediatric cardiology, and five fetal cardiac sonographers) were recruited from a center of fetal cardiology to participate. Each participant was shown 2000 fetal four chamber images in a random order (1,000 normal and 1,000 AVSD). The dataset was comprised of 500 images, each shown in four conditions: 1) image alone without AI output; 2) image with binary AI classification; 3) image with AI model confidence; 4) image with gradient-weighted class activation map image overlays. The clinicians were asked to classify each image as normal or AVSD. RESULTS: 20,000 image classifications were recorded from 10 clinicians. The AI model alone achieved an accuracy of 0.798 (95% CI 0.760 - 0.832), sensitivity of 0.868 (95% CI 0.834 - 0.902) and specificity of 0.728 (95% CI 0.702 - 0.754, and the clinicians without AI achiev
AU  - Day,TG
AU  - Matthew,J
AU  - Budd,SF
AU  - Venturini,L
AU  - Wright,R
AU  - Farruggia,A
AU  - Vigneswaran,TV
AU  - Zidere,V
AU  - Hajnal,JV
AU  - Razavi,R
AU  - Simpson,JM
AU  - Kainz,B
DO  - 10.1002/uog.27577
PY  - 2024///
TI  - Interaction between clinicians and artificial intelligence to detect fetal atrioventricular septal defects on ultrasound: how can we optimize collaborative performance?
T2  - Ultrasound Obstet Gynecol
UR  - http://dx.doi.org/10.1002/uog.27577
UR  - https://www.ncbi.nlm.nih.gov/pubmed/38197584
ER  -
Download