Overcoming Data Scarcity in Biomedical Imaging with a Foundational Multi-Task Model
This addresses data scarcity for biomedical imaging researchers, offering a novel method to improve model performance with limited data.
The authors tackled data scarcity in biomedical imaging by proposing a multi-task learning strategy that decouples training tasks from memory requirements, resulting in a foundational model (UMedPT) that outperformed ImageNet pretraining and previous state-of-the-art models, maintaining performance with only 1% of original data for in-domain tasks and requiring no more than 50% for out-of-domain tasks.
Foundational models, pretrained on a large scale, have demonstrated substantial success across non-medical domains. However, training these models typically requires large, comprehensive datasets, which contrasts with the smaller and more heterogeneous datasets common in biomedical imaging. Here, we propose a multi-task learning strategy that decouples the number of training tasks from memory requirements. We trained a Universal bioMedical PreTrained model (UMedPT) on a multi-task database including tomographic, microscopic, and X-ray images, with various labelling strategies such as classification, segmentation, and object detection. The UMedPT foundational model outperformed ImageNet pretraining and the previous state-of-the-art models. For tasks related to the pretraining database, it maintained its performance with only 1% of the original training data and without fine-tuning. For out-of-domain tasks it required not more than 50% of the original training data. In an external independent validation imaging features extracted using UMedPT proved to be a new standard for cross-center transferability.