Abstract
Combining imaging biomarkers with genomic and clinical phenotype data is the foundation of precision medicine research efforts. Yet, biomedical imaging research requires unique infrastructure compared with principally text-driven clinical electronic medical record (EMR) data. The issues are related to the binary nature of the file format and transport mechanism for medical images as well as the post-processing image segmentation and registration needed to combine anatomical and physiological imaging data sources. The SiiM Machine Learning Committee was formed to analyze the gaps and challenges surrounding research into machine learning in medical imaging and to find ways to mitigate these issues. At the 2017 annual meeting, a whiteboard session was held to rank the most pressing issues and develop strategies to meet them. The results, and further reflections, are summarized in this paper.
Highlights
The mission of the SiiM Machine Learning Committee (SiiMMLC) is to educate, promote, and advance the state of the art in medical imaging research
There are many issues to be addressed in the arena of machine learning (ML) applications in medical imaging, and many of them are not unique to the field
The learning curve of starting up a runtime platform and locating initial image sets has been significantly reduced by the MLC github site
Summary
The mission of the SiiM Machine Learning Committee (SiiMMLC) is to educate, promote, and advance the state of the art in medical imaging research. The MLC seeks to partner with industry and academic sites to identify new datasets, crowdsource curation and meta-tagging using existing (or to be developed) tools, and share these data set locations back on the github site [24]. To deliver the functions outlined above, there are numerous implied capabilities: a) capable de-identification algorithms b) crowdsourcing tools that interfaces with the Orchestrator to enable the work of human (or AI based) annotators to meta-tag data c) a well-defined API for investigators to query and find relevant studies for their algorithm d) well-defined APIs to fetch studies to the runtime environment, and pass outputs from one processing block to the in the workflows hosted by the Orchestrator
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
