Despite the breakthroughs of machine learning in biomedical image analysis, adoption in practice is slow due to several bottlenecks: scarcity of annotated training data, limited reliability of those annotations, and insufficient generalization of the models. This dissertation aims at addressing these bottlenecks by developing efficient training strategies for models that generalize well and appreciate the imperfection of labels along three use cases: cancer metastasis detection down to single cancer cells, transfer learning across biomedical domains, and whole-body organ segmentation.
«
Despite the breakthroughs of machine learning in biomedical image analysis, adoption in practice is slow due to several bottlenecks: scarcity of annotated training data, limited reliability of those annotations, and insufficient generalization of the models. This dissertation aims at addressing these bottlenecks by developing efficient training strategies for models that generalize well and appreciate the imperfection of labels along three use cases: cancer metastasis detection down to single ca...
»