Reducing Uncertainty in 3D Medical Image Segmentation under Limited Annotations through Contrastive Learning

Sanaz Jarimijafarbigloo, Reza Azad, Amirhossein Kazerouni, Dorit Merhof
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:694-707, 2024.

Abstract

Despite recent successes in semi-supervised learning for natural image segmentation, applying these methods to medical images presents challenges in obtaining discriminative representations from limited annotations. While contrastive learning frameworks excel in similarity measures for classification, their transferability to precise pixel-level segmentation in medical images is hindered, particularly when confronted with inherent prediction uncertainty.To overcome this issue, our approach incorporates two subnetworks to rectify erroneous predictions. The first network identifies uncertain predictions, generating an uncertainty attention map. The second network employs an uncertainty-aware descriptor to refine the representation of uncertain regions, enhancing the accuracy of predictions. Additionally, to adaptively recalibrate the representation of uncertain candidates, we define class prototypes based on reliable predictions. We then aim to minimize the discrepancy between class prototypes and uncertain predictions through a deep contrastive learning strategy.Our experimental results on organ segmentation from clinical MRI and CT scans demonstrate the effectiveness of our approach compared to state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-jarimijafarbigloo24a, title = {Reducing Uncertainty in 3D Medical Image Segmentation under Limited Annotations through Contrastive Learning}, author = {Jarimijafarbigloo, Sanaz and Azad, Reza and Kazerouni, Amirhossein and Merhof, Dorit}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {694--707}, 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/jarimijafarbigloo24a/jarimijafarbigloo24a.pdf}, url = {https://proceedings.mlr.press/v250/jarimijafarbigloo24a.html}, abstract = {Despite recent successes in semi-supervised learning for natural image segmentation, applying these methods to medical images presents challenges in obtaining discriminative representations from limited annotations. While contrastive learning frameworks excel in similarity measures for classification, their transferability to precise pixel-level segmentation in medical images is hindered, particularly when confronted with inherent prediction uncertainty.To overcome this issue, our approach incorporates two subnetworks to rectify erroneous predictions. The first network identifies uncertain predictions, generating an uncertainty attention map. The second network employs an uncertainty-aware descriptor to refine the representation of uncertain regions, enhancing the accuracy of predictions. Additionally, to adaptively recalibrate the representation of uncertain candidates, we define class prototypes based on reliable predictions. We then aim to minimize the discrepancy between class prototypes and uncertain predictions through a deep contrastive learning strategy.Our experimental results on organ segmentation from clinical MRI and CT scans demonstrate the effectiveness of our approach compared to state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Reducing Uncertainty in 3D Medical Image Segmentation under Limited Annotations through Contrastive Learning %A Sanaz Jarimijafarbigloo %A Reza Azad %A Amirhossein Kazerouni %A Dorit Merhof %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-jarimijafarbigloo24a %I PMLR %P 694--707 %U https://proceedings.mlr.press/v250/jarimijafarbigloo24a.html %V 250 %X Despite recent successes in semi-supervised learning for natural image segmentation, applying these methods to medical images presents challenges in obtaining discriminative representations from limited annotations. While contrastive learning frameworks excel in similarity measures for classification, their transferability to precise pixel-level segmentation in medical images is hindered, particularly when confronted with inherent prediction uncertainty.To overcome this issue, our approach incorporates two subnetworks to rectify erroneous predictions. The first network identifies uncertain predictions, generating an uncertainty attention map. The second network employs an uncertainty-aware descriptor to refine the representation of uncertain regions, enhancing the accuracy of predictions. Additionally, to adaptively recalibrate the representation of uncertain candidates, we define class prototypes based on reliable predictions. We then aim to minimize the discrepancy between class prototypes and uncertain predictions through a deep contrastive learning strategy.Our experimental results on organ segmentation from clinical MRI and CT scans demonstrate the effectiveness of our approach compared to state-of-the-art methods.
APA
Jarimijafarbigloo, S., Azad, R., Kazerouni, A. & Merhof, D.. (2024). Reducing Uncertainty in 3D Medical Image Segmentation under Limited Annotations through Contrastive Learning. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:694-707 Available from https://proceedings.mlr.press/v250/jarimijafarbigloo24a.html.

Related Material