Dataset Information

Data infrastructures for AI in medical imaging: a report on the experiences of five EU projects.

ABSTRACT: Artificial intelligence (AI) is transforming the field of medical imaging and has the potential to bring medicine from the era of 'sick-care' to the era of healthcare and prevention. The development of AI requires access to large, complete, and harmonized real-world datasets, representative of the population, and disease diversity. However, to date, efforts are fragmented, based on single-institution, size-limited, and annotation-limited datasets. Available public datasets (e.g., The Cancer Imaging Archive, TCIA, USA) are limited in scope, making model generalizability really difficult. In this direction, five European Union projects are currently working on the development of big data infrastructures that will enable European, ethically and General Data Protection Regulation-compliant, quality-controlled, cancer-related, medical imaging platforms, in which both large-scale data and AI algorithms will coexist. The vision is to create sustainable AI cloud-based platforms for the development, implementation, verification, and validation of trustable, usable, and reliable AI models for addressing specific unmet needs regarding cancer care provision. In this paper, we present an overview of the development efforts highlighting challenges and approaches selected providing valuable feedback to future attempts in the area.Key points• Artificial intelligence models for health imaging require access to large amounts of harmonized imaging data and metadata.• Main infrastructures adopted either collect centrally anonymized data or enable access to pseudonymized distributed data.• Developing a common data model for storing all relevant information is a challenge.• Trust of data providers in data sharing initiatives is essential.• An online European Union meta-tool-repository is a necessity minimizing effort duplication for the various projects in the area.

SUBMITTER: Kondylakis H

PROVIDER: S-EPMC10164664 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Data infrastructures for AI in medical imaging: a report on the experiences of five EU projects.

Kondylakis Haridimos H Kalokyri Varvara V Sfakianakis Stelios S Marias Kostas K Tsiknakis Manolis M Jimenez-Pastor Ana A Camacho-Ramos Eduardo E Blanquer Ignacio I Segrelles J Damian JD López-Huguet Sergio S Barelle Caroline C Kogut-Czarkowska Magdalena M Tsakou Gianna G Siopis Nikolaos N Sakellariou Zisis Z Bizopoulos Paschalis P Drossou Vicky V Lalas Antonios A Votis Konstantinos K Mallol Pedro P Marti-Bonmati Luis L Alberich Leonor Cerdá LC Seymour Karine K Boucher Samuel S Ciarrocchi Esther E Fromont Lauren L Rambla Jordi J Harms Alexander A Gutierrez Andrea A Starmans Martijn P A MPA Prior Fred F Gelpi Josep Ll JL Lekadir Karim K

European radiology experimental 20230508 1

Artificial intelligence (AI) is transforming the field of medical imaging and has the potential to bring medicine from the era of 'sick-care' to the era of healthcare and prevention. The development of AI requires access to large, complete, and harmonized real-world datasets, representative of the population, and disease diversity. However, to date, efforts are fragmented, based on single-institution, size-limited, and annotation-limited datasets. Available public datasets (e.g., The Cancer Imag ...[more]

PMID: 37150779

Similar Datasets

Project description:BackgroundPrevious studies in medical imaging have shown disparate abilities of artificial intelligence (AI) to detect a person's race, yet there is no known correlation for race on medical imaging that would be obvious to human experts when interpreting the images. We aimed to conduct a comprehensive evaluation of the ability of AI to recognise a patient's racial identity from medical images.MethodsUsing private (Emory CXR, Emory Chest CT, Emory Cervical Spine, and Emory Mammogram) and public (MIMIC-CXR, CheXpert, National Lung Cancer Screening Trial, RSNA Pulmonary Embolism CT, and Digital Hand Atlas) datasets, we evaluated, first, performance quantification of deep learning models in detecting race from medical images, including the ability of these models to generalise to external environments and across multiple imaging modalities. Second, we assessed possible confounding of anatomic and phenotypic population features by assessing the ability of these hypothesised confounders to detect race in isolation using regression models, and by re-evaluating the deep learning models by testing them on datasets stratified by these hypothesised confounding variables. Last, by exploring the effect of image corruptions on model performance, we investigated the underlying mechanism by which AI models can recognise race.FindingsIn our study, we show that standard AI deep learning models can be trained to predict race from medical images with high performance across multiple imaging modalities, which was sustained under external validation conditions (x-ray imaging [area under the receiver operating characteristics curve (AUC) range 0·91-0·99], CT chest imaging [0·87-0·96], and mammography [0·81]). We also showed that this detection is not due to proxies or imaging-related surrogate covariates for race (eg, performance of possible confounders: body-mass index [AUC 0·55], disease distribution [0·61], and breast density [0·61]). Finally, we provide evidence to show that the ability of AI deep learning models persisted over all anatomical regions and frequency spectrums of the images, suggesting the efforts to control this behaviour when it is undesirable will be challenging and demand further study.InterpretationThe results from our study emphasise that the ability of AI deep learning models to predict self-reported race is itself not the issue of importance. However, our finding that AI can accurately predict self-reported race, even from corrupted, cropped, and noised medical images, often when clinical experts cannot, creates an enormous risk for all model deployments in medical imaging.FundingNational Institute of Biomedical Imaging and Bioengineering, MIDRC grant of National Institutes of Health, US National Science Foundation, National Library of Medicine of the National Institutes of Health, and Taiwan Ministry of Science and Technology.

Project description:BackgroundThe European Commission supports the initiation of health information related projects and networks serving comparative population health monitoring and health system performance assessment. Many of these projects and networks have produced relevant data, standards, methods, indicators and knowledge that may be lost as these networks become inactive. The aim of this project retrieval and review was to identify health information projects and networks and their produced output; and subsequently facilitate systematic access to this information for policy makers, researchers and interested others via a web-based repository.MethodsThe scope of this article covers 1. population health oriented topics and 2. health system/health services oriented topics. Out of scope are specific infectious diseases; individual rare diseases; and the occurrence and effects of specific medical treatments, interventions and diagnostics; cohort studies; or studies focusing on research methods. We searched bibliographic databases and EU project databases for policy supporting projects and networks and selected those fulfilling our inclusion criteria after more in-depth inspection. We searched for their outputs. In addition, we reviewed country participation in these projects and networks.ResultsWe identified 36 projects and networks, 16 of which are population health oriented, 6 are health systems and services oriented and 14 cover both. Their total volume of output is not easily retrievable, as many project websites have been discontinued. Some networks and/or their outputs have found continuance within European agencies and/or national institutions. Others are struggling or have gone lost, despite their policy relevance. Participation in the projects was not evenly distributed across Europe. Project information was made available through the Health Information Portal.ConclusionsEU funded projects and networks have contributed greatly to the evidence-base for policy by providing comparative health information. However, more action is needed to evaluate and conserve their outputs and facilitate continued contribution to the field after project funding stops. The realization of a sustainable infrastructure for these projects and networks is urgent. The Health Information Portal can play an important role in conserving and reusing health information. Information inequalities may exist across Europe but need further investigating.

Dataset Information

Data infrastructures for AI in medical imaging: a report on the experiences of five EU projects.

Publications

Data infrastructures for AI in medical imaging: a report on the experiences of five EU projects.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets