Overcoming Data Scarcity in Biomedical Imaging with a Foundational Multi-Task Model

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.

The NCI Imaging Data Commons as a platform for reproducible research in computational pathology

Objective: Reproducibility is critical for translating machine learning-based (ML) solutions in computational pathology (CompPath) into practice. However, an increasing number of studies report difficulties in reproducing ML results. The NCI Imaging Data Commons (IDC) is a public repository of >120 cancer image collections, including >38,000 whole-slide images (WSIs), that is designed to be used with cloud-based ML services. Here, we explore the potential of the IDC to facilitate reproducibility of CompPath research. Materials and Methods: The IDC realizes the FAIR principles: All images are encoded according to the DICOM standard, persistently identified, discoverable via rich metadata, and accessible via open tools. Taking advantage of this, we implemented two experiments in which a representative ML-based method for classifying lung tumor tissue was trained and/or evaluated on different datasets from the IDC. To assess reproducibility, the experiments were run multiple times with independent but identically configured sessions of common ML services. Results: The AUC values of different runs of the same experiment were generally consistent and in the same order of magnitude as a similar, previously published study. However, there were occasional small variations in AUC values of up to 0.044, indicating a practical limit to reproducibility. Discussion and conclusion: By realizing the FAIR principles, the IDC enables other researchers to reuse exactly the same datasets. Cloud-based ML services enable others to run CompPath experiments in an identically configured computing environment without having to own high-performance hardware. The combination of both makes it possible to approach the reproducibility limit.