Standardizing digital biobanks: integrating imaging, genomic, and clinical data for precision medicine

Abstract

Advancements in data acquisition and computational methods are generating a large amount of heterogeneous biomedical data from diagnostic domains such as clinical imaging, pathology, and next-generation sequencing (NGS), which help characterize individual differences in patients. However, this information needs to be available and suitable to promote and support scientific research and technological development, supporting the effective adoption of the precision medicine approach in clinical practice. Digital biobanks can catalyze this process, facilitating the sharing of curated and standardized imaging data, clinical, pathological and molecular data, crucial to enable the development of a comprehensive and personalized data-driven diagnostic approach in disease management and fostering the development of computational predictive models. This work aims to frame this perspective, first by evaluating the state of standardization of individual diagnostic domains and then by identifying challenges and proposing a possible solution towards an integrative approach that can guarantee the suitability of information that can be shared through a digital biobank. Our analysis of the state of the art shows the presence and use of reference standards in biobanks and, generally, digital repositories for each specific domain. Despite this, standardization to guarantee the integration and reproducibility of the numerical descriptors generated by each domain, e.g. radiomic, pathomic and -omic features, is still an open challenge. Based on specific use cases and scenarios, an integration model, based on the JSON format, is proposed that can help address this problem. Ultimately, this work shows how, with specific standardization and promotion efforts, the digital biobank model can become an enabling technology for the comprehensive study of diseases and the effective development of data-driven technologies at the service of precision medicine.

Keywords: Big data; Biobanking; Clinical decision support systems (CDSS); Data integration; Imaging; NGS; Pathomics; Precision medicine; Radiomics; Standardization.

Fig. 1

Overview of data included in a comprehensive digital biobank according to the generation of numerical descriptors (e.g. radiomic features extracted from radiological images [16], pathomic features from digital pathology images [17], as well as molecular features from molecular profiling [18]) during the sample lifecycle (horizontal increasing arrow) and to the integration of different domains (vertical descending arrow)

Fig. 2

Use case diagram representing an external user (clinician/researcher) with the aim of performing a comprehensive analysis involving genomic, radiomic, and pathomic features of a specific tumor type or reproducing or integrating an already performed study. The figure also depicts the ways to interface with the digital biobank (e.g. “Data Catalog” or “Data Access” mode). CNN Convolutional Neural Networks; DL Deep- Learning; WES Whole Exome Sequencing; WGS Whole Genome Sequencing; SNP  Single Nucleotide Polymorphism; miRNA  MicroRNA.

Fig. 3

Proposed integrative approach accounting for standardization/harmonization of each diagnostic domain and integration among multidisciplinary domains, together with the harmonization/standardization concerning the generation of numerical descriptors associated with each single domain. The approach involved the use of MIABIS, DICOM and FASTQ as they are established standards in the common practice to describe raw and derived data from clinical imaging, pathology, and next-generation sequencing domains. JSON format was proposed to store and interchange domain-specific numerical descriptors. MIABIS Minimum Information About BIobank data Sharing; DCM (DICOM) Digital Imaging and Communications in Medicine; WSI Whole Slide Imaging; SR Structured Report; SEG Segmentation; JSON JavaScript Object Notation