FluidRegNet: Longitudinal registration of retinal OCT images with new pathological fluids

Julia Andresen, Jan Ehrhardt, Claus von der Burchard, Ayse Tatli, Johann Roider, Heinz Handels, Hristina Uzunova
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:48-60, 2024.

Abstract

Eye diseases such as the chronic central serous chorioretinopathy are characterized by fluid deposits that alter the retina and impair vision. These fluids occur at irregular intervals and may dissolve spontaneously or thanks to treatment. Accurately capturing this behavior within an image registration framework is challenging due to the resulting prominent tissue deformations and missing image correspondences between visits. This paper presents FluidRegNet, a convolutional neural network for the registration of successive optical coherence tomography images of the retina. The correspondence between time points is established by predicting the position of the origin of the fluids by creating a fluid seed in the form of sparse intensity offsets in the moving image and registering the fluid seed to the affected area in the follow-up image. We show that this leads to deformation fields that more accurately reflect the actual dynamics of retinal fluid growth compared to other image registration methods. In addition, the network outputs are used for unsupervised fluid segmentation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-andresen24a, title = {FluidRegNet: Longitudinal registration of retinal OCT images with new pathological fluids}, author = {Andresen, Julia and Ehrhardt, Jan and von der Burchard, Claus and Tatli, Ayse and Roider, Johann and Handels, Heinz and Uzunova, Hristina}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {48--60}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/andresen24a/andresen24a.pdf}, url = {https://proceedings.mlr.press/v250/andresen24a.html}, abstract = {Eye diseases such as the chronic central serous chorioretinopathy are characterized by fluid deposits that alter the retina and impair vision. These fluids occur at irregular intervals and may dissolve spontaneously or thanks to treatment. Accurately capturing this behavior within an image registration framework is challenging due to the resulting prominent tissue deformations and missing image correspondences between visits. This paper presents FluidRegNet, a convolutional neural network for the registration of successive optical coherence tomography images of the retina. The correspondence between time points is established by predicting the position of the origin of the fluids by creating a fluid seed in the form of sparse intensity offsets in the moving image and registering the fluid seed to the affected area in the follow-up image. We show that this leads to deformation fields that more accurately reflect the actual dynamics of retinal fluid growth compared to other image registration methods. In addition, the network outputs are used for unsupervised fluid segmentation.} }
Endnote
%0 Conference Paper %T FluidRegNet: Longitudinal registration of retinal OCT images with new pathological fluids %A Julia Andresen %A Jan Ehrhardt %A Claus von der Burchard %A Ayse Tatli %A Johann Roider %A Heinz Handels %A Hristina Uzunova %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-andresen24a %I PMLR %P 48--60 %U https://proceedings.mlr.press/v250/andresen24a.html %V 250 %X Eye diseases such as the chronic central serous chorioretinopathy are characterized by fluid deposits that alter the retina and impair vision. These fluids occur at irregular intervals and may dissolve spontaneously or thanks to treatment. Accurately capturing this behavior within an image registration framework is challenging due to the resulting prominent tissue deformations and missing image correspondences between visits. This paper presents FluidRegNet, a convolutional neural network for the registration of successive optical coherence tomography images of the retina. The correspondence between time points is established by predicting the position of the origin of the fluids by creating a fluid seed in the form of sparse intensity offsets in the moving image and registering the fluid seed to the affected area in the follow-up image. We show that this leads to deformation fields that more accurately reflect the actual dynamics of retinal fluid growth compared to other image registration methods. In addition, the network outputs are used for unsupervised fluid segmentation.
APA
Andresen, J., Ehrhardt, J., von der Burchard, C., Tatli, A., Roider, J., Handels, H. & Uzunova, H.. (2024). FluidRegNet: Longitudinal registration of retinal OCT images with new pathological fluids. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:48-60 Available from https://proceedings.mlr.press/v250/andresen24a.html.

Related Material