Li, Yiwen;
Fu, Yunguan;
Yang, Qianye;
Min, Zhe;
Yan, Wen;
Huisman, Henkjan;
Prisacariu, Victor Adrian;
... Hu, Yipeng; + view all
(2022)
Few-shot image segmentation for cross-institution male pelvic organs using registration-assisted prototypical learning.
In:
Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI) 2022.
IEEE: Kolkata, India.
(In press).
Preview |
Text
2201.06358v1.pdf - Other Download (3MB) | Preview |
Abstract
The ability to adapt medical image segmentation networks for a novel class such as an unseen anatomical or pathological structure, when only a few labelled examples of this class are available from local healthcare providers, is sought-after. This potentially addresses two widely recognised limitations in deploying modern deep learning models to clinical practice, expertise-and-labour-intensive labelling and cross-institution generalisation. This work presents the first 3D few-shot interclass segmentation network for medical images, using a labelled multi-institution dataset from prostate cancer patients with eight regions of interest. We propose an image alignment module registering the predicted segmentation of both query and support data, in a standard prototypical learning algorithm, to a reference atlas space. The built-in registration mechanism can effectively utilise the prior knowledge of consistent anatomy between subjects, regardless whether they are from the same institution or not. Experimental results demonstrated that the proposed registration-assisted prototypical learning significantly improved segmentation accuracy (p-values<0.01) on query data from a holdout institution, with varying availability of support data from multiple institutions. We also report the additional benefits of the proposed 3D networks with 75% fewer parameters and an arguably simpler implementation, compared with existing 2D few-shot approaches that segment 2D slices of volumetric medical images.
| Type: | Proceedings paper |
|---|---|
| Title: | Few-shot image segmentation for cross-institution male pelvic organs using registration-assisted prototypical learning |
| Event: | IEEE International Symposium on Biomedical Imaging (ISBI) 2022 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/ISBI52829.2022.9761453 |
| Publisher version: | http://dx.doi.org/10.1109/ISBI52829.2022.9761453 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | eess.IV, eess.IV, cs.CV |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10146183 |
Archive Staff Only
 |
View Item |
