Diffusion Models for Implicit Image Segmentation Ensembles

Julia Wolleb, Robin Sandkühler, Florentin Bieder, Philippe Valmaggia, Philippe C. Cattin
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1336-1348, 2022.

Abstract

Diffusion models have shown impressive performance for generative modelling of images. In this paper, we present a novel semantic segmentation method based on diffusion models. By modifying the training and sampling scheme, we show that diffusion models can perform lesion segmentation of medical images. To generate an image-specific segmentation, we train the model on the ground truth segmentation, and use the image as a prior during training and in every step during the sampling process. With the given stochastic sampling process, we can generate a distribution of segmentation masks. This property allows us to compute pixel-wise uncertainty maps of the segmentation, and allows an implicit ensemble of segmentations that increases the segmentation performance. We evaluate our method on the BRATS2020 dataset for brain tumor segmentation. Compared to state-of-the-art segmentation models, our approach yields good segmentation results and, additionally, detailed uncertainty maps.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-wolleb22a, title = {Diffusion Models for Implicit Image Segmentation Ensembles}, author = {Wolleb, Julia and Sandk\"uhler, Robin and Bieder, Florentin and Valmaggia, Philippe and Cattin, Philippe C.}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1336--1348}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/wolleb22a/wolleb22a.pdf}, url = {https://proceedings.mlr.press/v172/wolleb22a.html}, abstract = {Diffusion models have shown impressive performance for generative modelling of images. In this paper, we present a novel semantic segmentation method based on diffusion models. By modifying the training and sampling scheme, we show that diffusion models can perform lesion segmentation of medical images. To generate an image-specific segmentation, we train the model on the ground truth segmentation, and use the image as a prior during training and in every step during the sampling process. With the given stochastic sampling process, we can generate a distribution of segmentation masks. This property allows us to compute pixel-wise uncertainty maps of the segmentation, and allows an implicit ensemble of segmentations that increases the segmentation performance. We evaluate our method on the BRATS2020 dataset for brain tumor segmentation. Compared to state-of-the-art segmentation models, our approach yields good segmentation results and, additionally, detailed uncertainty maps.} }
Endnote
%0 Conference Paper %T Diffusion Models for Implicit Image Segmentation Ensembles %A Julia Wolleb %A Robin Sandkühler %A Florentin Bieder %A Philippe Valmaggia %A Philippe C. Cattin %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-wolleb22a %I PMLR %P 1336--1348 %U https://proceedings.mlr.press/v172/wolleb22a.html %V 172 %X Diffusion models have shown impressive performance for generative modelling of images. In this paper, we present a novel semantic segmentation method based on diffusion models. By modifying the training and sampling scheme, we show that diffusion models can perform lesion segmentation of medical images. To generate an image-specific segmentation, we train the model on the ground truth segmentation, and use the image as a prior during training and in every step during the sampling process. With the given stochastic sampling process, we can generate a distribution of segmentation masks. This property allows us to compute pixel-wise uncertainty maps of the segmentation, and allows an implicit ensemble of segmentations that increases the segmentation performance. We evaluate our method on the BRATS2020 dataset for brain tumor segmentation. Compared to state-of-the-art segmentation models, our approach yields good segmentation results and, additionally, detailed uncertainty maps.
APA
Wolleb, J., Sandkühler, R., Bieder, F., Valmaggia, P. & Cattin, P.C.. (2022). Diffusion Models for Implicit Image Segmentation Ensembles. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1336-1348 Available from https://proceedings.mlr.press/v172/wolleb22a.html.

Related Material