Building Flexible, Scalable, and Machine Learning-ready Multimodal Oncology Datasets

TL;DR

This paper introduces MINDS, a flexible and scalable metadata framework that integrates diverse oncology data sources to facilitate large-scale multimodal machine learning and personalized cancer treatment research.

Contribution

The work presents MINDS, a novel metadata system enabling efficient, reproducible, and secure integration of heterogeneous oncology data for advanced analysis and modeling.

Findings

MINDS successfully integrates multiple data types from public sources.

The framework enhances data exploration and cohort building for machine learning.

MINDS ensures data provenance, reproducibility, and scalability in cloud environments.

Abstract

The advancements in data acquisition, storage, and processing techniques have resulted in the rapid growth of heterogeneous medical data. Integrating radiological scans, histopathology images, and molecular information with clinical data is essential for developing a holistic understanding of the disease and optimizing treatment. The need for integrating data from multiple sources is further pronounced in complex diseases such as cancer for enabling precision medicine and personalized treatments. This work proposes Multimodal Integration of Oncology Data System (MINDS) - a flexible, scalable, and cost-effective metadata framework for efficiently fusing disparate data from public sources such as the Cancer Research Data Commons (CRDC) into an interconnected, patient-centric framework. MINDS offers an interface for exploring relationships across data types and building cohorts for developing large-scale multimodal machine learning models. By harmonizing multimodal data, MINDS aims to potentially empower researchers with greater analytical ability to uncover diagnostic and prognostic insights and enable evidence-based personalized care. MINDS tracks granular end-to-end data provenance, ensuring reproducibility and transparency. The cloud-native architecture of MINDS can handle exponential data growth in a secure, cost-optimized manner while ensuring substantial storage optimization, replication avoidance, and dynamic access capabilities. Auto-scaling, access controls, and other mechanisms guarantee pipelines' scalability and security. MINDS overcomes the limitations of existing biomedical data silos via an interoperable metadata-driven approach that represents a pivotal step toward the future of oncology data integration.