A self-supervised learning approach for registration agnostic imaging models with 3D brain CTA
Year: 2024
Type: article
Abstract: Deep learning-based neuroimaging pipelines for acute stroke typically rely on image registration, which not only increases computation but also introduces a point of failure. In this paper, we propose a general-purpose contrastive self-supervised learning method that converts a convolutional deep neural network designed for registered images to work on a different input domain, i.e., with unregistered images. This is accomplished by using a self-supervised strategy that does not rely on labels, where the original model acts as a teacher and a new network as a student. Large vessel occlusion (LVO) detection experiments using computed tomographic angiography (CTA) data from 402 CTA patients show the student model achieving competitive LVO detection performance (area under the receiver operating characteristic curve [AUC] = 0.88 vs. AUC = 0.81) compared to the teacher model, even with unregistered images. The student model trained directly on unregistered images using standard supervised learning achieves an AUC = 0.63, highlighting the proposed method's efficacy in adapting models to different pipelines and domains.
Source: iScience
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,150
Awards: Fine-grained spatial information extraction for radiology reports, Genetics of deep-learning-derived neuroimaging endophenotypes for Alzheimer's Disease, Addressing the paradox of poor outcomes despite successful recanalization in stroke, Deep Learning Enabled Endovascular Stroke Therapy Screening in Community Hospitals
OpenAlex ID: W4391450968