TY - GEN
T1 - DeepBrainPrint
T2 - 6th International Conference on Medical Imaging with Deep Learning, MIDL 2023
AU - Puglisi, Lemuel
AU - The Alzheimer's Disease Neuroimaging Initiative
AU - Barkhof, Frederik
AU - Alexander, Daniel C.
AU - Parker, Geoffrey J. M.
AU - Eshaghi, Arman
AU - Ravì, Daniele
PY - 2023
Y1 - 2023
N2 - Recent advances in MRI have led to the creation of large datasets. With the increase in data volume, it has become difficult to locate previous scans of the same patient within these datasets (a process known as re-identification). To address this issue, we propose an AI-powered medical imaging retrieval framework called DeepBrainPrint, which is designed to retrieve brain MRI scans of the same patient. Our framework is a semi-self-supervised contrastive deep learning approach with three main innovations. First, we use a combination of self-supervised and supervised paradigms to create an effective brain fingerprint from MRI scans that can be used for real-time image retrieval. Second, we use a special weighting function to guide the training and improve model convergence. Third, we introduce new imaging transformations to improve retrieval robustness in the presence of intensity variations (i.e. different scan contrasts), and to account for age and disease progression in patients. We tested DeepBrainPrint on a large dataset of T1-weighted brain MRIs from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and on a synthetic dataset designed to evaluate retrieval performance with different image modalities. Our results show that DeepBrainPrint outperforms previous methods, including simple similarity metrics and more advanced contrastive deep learning frameworks.
AB - Recent advances in MRI have led to the creation of large datasets. With the increase in data volume, it has become difficult to locate previous scans of the same patient within these datasets (a process known as re-identification). To address this issue, we propose an AI-powered medical imaging retrieval framework called DeepBrainPrint, which is designed to retrieve brain MRI scans of the same patient. Our framework is a semi-self-supervised contrastive deep learning approach with three main innovations. First, we use a combination of self-supervised and supervised paradigms to create an effective brain fingerprint from MRI scans that can be used for real-time image retrieval. Second, we use a special weighting function to guide the training and improve model convergence. Third, we introduce new imaging transformations to improve retrieval robustness in the presence of intensity variations (i.e. different scan contrasts), and to account for age and disease progression in patients. We tested DeepBrainPrint on a large dataset of T1-weighted brain MRIs from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and on a synthetic dataset designed to evaluate retrieval performance with different image modalities. Our results show that DeepBrainPrint outperforms previous methods, including simple similarity metrics and more advanced contrastive deep learning frameworks.
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85189346547&origin=inward
M3 - Conference contribution
VL - 227
T3 - Proceedings of Machine Learning Research
SP - 716
EP - 729
BT - Medical Imaging with Deep Learning 2023, MIDL 2023
A2 - Oguz, Ipek
A2 - Noble, Jack
A2 - Li, Xiaoxiao
A2 - Styner, Martin
A2 - Baumgartner, Christian
A2 - Rusu, Mirabela
A2 - Heinmann, Tobias
A2 - Kontos, Despina
A2 - Landman, Bennett
A2 - Dawant, Benoit
PB - ML Research Press
Y2 - 10 July 2023 through 12 July 2023
ER -