IMS machine learning prioritises medical images
February 7, 2019
Google Cloud technology partner International Medical Solutions (IMS) is helping radiologists and other healthcare clinicians use machine learning (ML) modelling to triage studies focusing on medical images that need immediate attention.
The Canadian company will unveil a prototype of the technology using the Google Cloud ML engine at next week’s HIMSS Conference in Orlando.
The platform uses a standard file format, enabling any AI company to add their own model to the workflow.
“This prototype is the next logical step in our evolution to create scalable, medical imaging that improves clinician workflows while quickly addressing the needs of patients,” said Vittorio Accomazzi, CTO of IMS.
The prototype will feature two common use cases. The first uses the Google Cloud ML engine to provide an indicator for prioritisation. Using the example of a radiologist who has several hundred chest cases to review, the study list will leverage machine learning to provide an indicator of the cases that are most likely to have a pathology. This will enable the radiologist to focus on those cases quickly and expedite the results.
The second scenario uses the Google Cloud ML engine to provide better decision support. In situations where there is no urgency involved with a diagnosis, such as determining breast density, machine learning modelling can be used for clinical decision support.
IMS is a partner to several healthcare organisations, including the American Society of Emergency Radiology (ASER) and the American College of Radiology (ACR).
"IMS is proud to partner with organisations who want to make a positive difference in the healthcare industry," said Accomazzi. "In our experience, healthcare professionals are hyper-focused on using flexible solutions that give them the ability to improve their workflow, reduce costs and provide an accurate diagnosis for their patients. We believe our new platform using the Google Cloud ML engine will transform the way medical images are read and interpreted for many years to come."
IMS designs and implements custom, scalable, medical imaging technology for multi-national modality OEMs, EMR companies and cloud-based radiology organisations. Founded in 2012, its team has more than 90 years of collective experience developing secure, low bandwidth, image distribution platforms with deep learning and artificial intelligence, providing its partners with the latest imaging technology.