Medical images are by far the largest and fastest-growing data source in the health care industry - IBM researchers estimate that they account for at least 90% of all medical data today - but they also present challenges that need to be addressed. The volume of medical images can be overwhelming to even the most sophisticated specialists; radiologists in some hospital emergency rooms are presented with thousands of images each day.
Tools to help clinicians extract insights from medical images remain limited, requiring most analysis to be done manually. This has created an opportunity to analyze and cross-reference medical images against a deep trove of lab results, electronic health records, genomic tests, clinical studies and other health-related data sources to enable providers to compare new medical images with a patient's image history as well as populations of similar patients to detect changes and anomalies.
"The breadth and depth of Watson-powered solutions on display at RSNA 2016 from Watson Health's imaging group and from Merge are unmatched among the AI community, and showcase how IBM is bringing cognitive computing to healthcare in clinically meaningful ways", stated Anne LeGrand, Vice President of Imaging for IBM Watson Health.
Watson Health showed:
Watson cognitive computing is ideally suited to support radiologists on their journey 'Beyond Imaging' to practices that address the needs of patient populations, deliver improved patient outcomes, and demonstrate real-world value", stated Nancy Koenig, General Manager of Merge Healthcare. "This week at RSNA, Merge is proud to unveil solutions for providers that enable the first steps on the cognitive care journey, addressing breast cancer, lung cancer, and trauma patients in the ER."
IBM Research showed physicians how Watson might reduce the time to diagnosis and increase efficiency in provider workflows. Radiologists select cases from a variety of imaging topics, make their diagnosis, and see how a Watson solution attempts to assist the same case as it understands, reasons and learns from text- and imaging data in real time.
The live demonstration showcased more than a decade of work by IBM Research's top medical imaging, text mining, and AI data scientists. The demo was able to analyze patient data culled from thousands of data sources and present insights in a compact summary report intended to help clinicians efficiently reach a differential diagnosis. For example, the technology featured in the demo, uses deep learning to recognize positions in the body for major anatomical structures - such as in a CT imaging study - and detects anomalies - such as dissections in the aorta, or embolisms in pulmonary arteries. Combining imaging and clinical data with clinical knowledge, it performs clinical inference on the patient's condition and its management, pre-assembling relevant information in a simple online format for a diagnosing physician to consider.
IBM was also showcasing at RSNA 2016 its ecosystem approach to innovation, including the global Watson Health medical imaging collaborative and work with Siemens Healthineers to introduce Population Health Management solutions worldwide.