Open access image repositories: high-quality data to enable machine learning research

Prior, Fred; Almeida, Jonas S.; Kathiravelu, Pradeeban; Kurç, Tahsin; Smith, Kirk E.; Fitzgerald, Thomas J.; Saltz, J. H.

doi:10.1016/j.crad.2019.04.002

Cited by 44 publications

(33 citation statements)

References 69 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radiation therapy treatment plans will need to be fused with images that define targets and correlate to images that review the pattern of failure. It will be through these mechanisms we will all mature in our understanding of disease processes and the success/failure of our applied therapies [23,24].…”

Section: The Cancer Imaging Archive (Tcia)mentioning

confidence: 99%

Acquisition and Management of Data for Translational Science in Oncology

Fitzgerald¹,

Bishop–Jodoin²,

Laurie³

et al. 2021

Translational Research in Cancer

View full text Add to dashboard Cite

Oncology clinical trials provide opportunity to advance care for patients with cancer. Bridging basic science with bedside care, cancer clinical trials have brought new and updated scientific knowledge at a rapid pace. Managing subject data in translation science requires a sophisticated informatics infrastructure that will enable harmonized datasets across all areas that could influence outcomes. Successful translational science requires that all relevant information be made readily available in a digital format that can be queried in a facile manner. Through a translational science prism, we look at past issues in cancer clinical trials and the

show abstract

Section: The Cancer Imaging Archive (Tcia)mentioning

confidence: 99%

Acquisition and Management of Data for Translational Science in Oncology

Fitzgerald¹,

Bishop–Jodoin²,

Laurie³

et al. 2021

Translational Research in Cancer

View full text Add to dashboard Cite

show abstract

“…The development of AI solutions that are reproducible as well as transferable to clinical practice will require access to large scale data for model training and optimisation [16][17][18] (otherwise known as big data, and also referred to as the "oil" of the 21st century [19]). However, despite the acquisition of large volumes of imaging data routinely in clinical settings, access to big data in medical imaging poses significant challenges in practice.…”

Section: Introductionmentioning

confidence: 99%

Data preparation for artificial intelligence in medical imaging: A comprehensive guide to open-access platforms and tools

et al. 2021

View full text Add to dashboard Cite

The vast amount of data produced by today's medical imaging systems has led medical professionals to turn to novel technologies in order to efficiently handle their data and exploit the rich information present in them. In this context, artificial intelligence (AI) is emerging as one of the most prominent solutions, promising to revolutionise every day clinical practice and medical research. The pillar supporting the development of reliable and robust AI algorithms is the appropriate preparation of the medical images to be used by the AI-driven solutions. Here, we provide a comprehensive guide for the necessary steps to prepare medical images prior to developing or applying AI algorithms. The main steps involved in a typical medical image preparation pipeline include: (i) image acquisition at clinical sites, (ii) image de-identification to remove personal information and protect patient privacy, (iii) data curation to control for image and associated information quality, (iv) image storage, and (v) image annotation. There exists a plethora of open access tools to perform each of the aforementioned tasks and are hereby reviewed. Furthermore, we detail medical image repositories covering different organs and diseases. Such repositories are constantly increasing and enriched with the advent of big data. Lastly, we offer directions for future work in this rapidly evolving field.

show abstract

“…Secondly, unsupervised learning methods can be used to search for new radiomic features that might be very different from what would be noticed by a human observer. The AI can take on the discovery and find new and useful patterns within the existing imaging data ( Miles, 2020 ; Prior et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence for the Future Radiology Diagnostic Service

Mun

Wong

et al. 2021

Front. Mol. Biosci.

View full text Add to dashboard Cite

Radiology historically has been a leader of digital transformation in healthcare. The introduction of digital imaging systems, picture archiving and communication systems (PACS), and teleradiology transformed radiology services over the past 30 years. Radiology is again at the crossroad for the next generation of transformation, possibly evolving as a one-stop integrated diagnostic service. Artificial intelligence and machine learning promise to offer radiology new powerful new digital tools to facilitate the next transformation. The radiology community has been developing computer-aided diagnosis (CAD) tools based on machine learning (ML) over the past 20 years. Among various AI techniques, deep-learning convolutional neural networks (CNN) and its variants have been widely used in medical image pattern recognition. Since the 1990s, many CAD tools and products have been developed. However, clinical adoption has been slow due to a lack of substantial clinical advantages, difficulties integrating into existing workflow, and uncertain business models. This paper proposes three pathways for AI's role in radiology beyond current CNN based capabilities 1) improve the performance of CAD, 2) improve the productivity of radiology service by AI-assisted workflow, and 3) develop radiomics that integrate the data from radiology, pathology, and genomics to facilitate the emergence of a new integrated diagnostic service.

show abstract

Open access image repositories: high-quality data to enable machine learning research

Cited by 44 publications

References 69 publications

Acquisition and Management of Data for Translational Science in Oncology

Acquisition and Management of Data for Translational Science in Oncology

Data preparation for artificial intelligence in medical imaging: A comprehensive guide to open-access platforms and tools

Artificial Intelligence for the Future Radiology Diagnostic Service

Contact Info

Product

Resources

About