| Full text | |
| Author(s): |
Oliveira, Hugo
;
Gama, Pedro H. T.
;
Bloch, Isabelle
;
Cesar Jr, Roberto Marcondes
Total Authors: 4
|
| Document type: | Journal article |
| Source: | PATTERN RECOGNITION; v. 153, p. 13-pg., 2024-04-24. |
| Abstract | |
Most uses of Meta -Learning in visual recognition are very often applied to image classification, with a relative lack of work in other tasks such as segmentation and detection. We propose a new generic Meta -Learning framework for few -shot weakly supervised segmentation in medical imaging domains. The proposed approach includes a meta -training phase that uses a meta-dataset. It is deployed on an out -of -distribution few -shot target task, where a single highly generalizable model, trained via a selective supervised loss function, is used as a predictor. The model can be trained in several distinct ways, such as second -order optimization, metric learning, and late fusion. Some relevant improvements of existing methods that are part of the proposed approach are presented. We conduct a comparative analysis of meta -learners from distinct paradigms adapted to few -shot image segmentation in different sparsely annotated radiological tasks. The imaging modalities include 2D chest, mammographic, and dental X-rays, as well as 2D slices of volumetric tomography and resonance images. Our experiments consider in total 9 meta -learners, 4 backbones, and multiple target organ segmentation tasks. We explore small -data scenarios in radiology with varying weak annotation styles and densities. Our analysis shows that metric -based meta -learning approaches achieve better segmentation results in tasks with smaller domain shifts compared to the meta -training datasets, while some gradient- and fusionbased meta -learners are more generalizable to larger domain shifts. Guidelines learned from the comparative performance assessment of the analyzed methods are summarized to support those readers interested in the field. (AU) | |
| FAPESP's process: | 20/06744-5 - Deep learning and intermediate representations for pediatric image analysis |
| Grantee: | Hugo Neves de Oliveira |
| Support Opportunities: | Scholarships in Brazil - Post-Doctoral |
| FAPESP's process: | 15/22308-2 - Intermediate representations in Computational Science for knowledge discovery |
| Grantee: | Roberto Marcondes Cesar Junior |
| Support Opportunities: | Research Projects - Thematic Grants |
| FAPESP's process: | 22/15304-4 - Learning context rich representations for computer vision |
| Grantee: | Nina Sumiko Tomita Hirata |
| Support Opportunities: | Research Projects - Thematic Grants |
| FAPESP's process: | 17/50236-1 - Spatio temporal analysis of pediatric magnetic resonance images |
| Grantee: | Roberto Marcondes Cesar Junior |
| Support Opportunities: | Regular Research Grants |