Meta-learners for few-shot weakly-supervised medical image segmentation

Autor(es)

Oliveira, Hugo ; Gama, Pedro H. T. ; Bloch, Isabelle ; Cesar Jr, Roberto Marcondes

• Tipo de documento: Artigo Científico
• Fonte: PATTERN RECOGNITION; v. 153, p. 13-pg., 2024-04-24.

Resumo

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)

• Processo FAPESP: 20/06744-5 - Deep learning e representações intermediárias para análise de imagens pediátricas
• Beneficiário: Hugo Neves de Oliveira
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 15/22308-2 - Representações intermediárias em Ciência Computacional para descoberta de conhecimento
• Beneficiário: Roberto Marcondes Cesar Junior
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 22/15304-4 - Aprendizado de representações ricas em contexto para visão computacional
• Beneficiário: Nina Sumiko Tomita Hirata
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 17/50236-1 - Análise espaço-temporal de imagens de ressonância magnética
• Beneficiário: Roberto Marcondes Cesar Junior
• Modalidade de apoio: Auxílio à Pesquisa - Regular