Big data meets interactive virtual reality.
Being an advisor to several medical imaging publications, requires one to provide a prognosis of what the key dynamics in medical imaging might be in the following year.
At this point in time, I am personally involved in several areas: big data (BD) and interactive virtual reality (IVR). Both areas are beginning to take hold in terms of impacting patient outcomes (PO). This discussion is focused on the synergy between BD and IVR, and the resulting potential for significant gains in PO – an important dynamic for medical imaging.
The news about BD is increasing as IBM’s efforts with Watson are coming to fruition. It is most noteworthy that Virginia Rometty, IBM CEO, characterizes Watson as a cognitive-based system that represents supervised learning using BD techniques. Cognition is indeed a critical element in that it impacts knowledge, which is dependent on both cognition and intuition. Knowledge, in turn, represents a fundamental factor in driving PO.
The other critical element in the knowledge equation, intuition, has been shown to be driven by IVR. Hence, the power of the BD/IVR intersection.
Consider IVR as the ability to view an object in open 3D space and directly interact with the object (eg, removing a tumor electronically).
Radiologists have noted, that IVR provides a way to communicate more effectively with surgeons. Surgeons have noted that IVR allows them to finally achieve surgical visualization, the ability to view anatomy in a manner that corresponds to their 3D world view – they never open up patients and see 2D views.
Essentially, IVR represents a new paradigm, or “language,” with which different specialists discover an enhanced ability for communicating more effectively with one another.
Why might 2017 be the key year to realize the potential of the BD/IVR intersection? Based on several years of clinical trials, significant improvement in the core areas of PO, clinical efficacy (CE), and workflow (WF), have been demonstrated in a number of applications, due to IVR driven increases in knowledge.
We might think of IVR as focused on “doing the right things” and BD as focused on “doing things right.” A case in point would be a Protocol for optimizing both CE and WF for virtual colonoscopy. Based on the intuitive properties of IVR, a concept of dividing the colon into linear segments emerged with each segment separately analyzed for polyps. This breakthrough led to significant gains in both clinical efficacy and workflow.
BD has already been effectively applied to virtual colonoscopy. BD could also be applied to the analysis of all users of the above protocol to establish best practices from data representing all user motions (head, stylus, etc.). In this manner, BD is a key to “doing things right.” This direction was intimated by Shrestha.
The intersection of BD and IVR therefore provides a significant opportunity for achieving improvements in PO. We could think of this activity as knowledge modeling. Today, leading organizations in health care are establishing knowledge modeling as the core of effective data management. What could be better than to apply these principles to increasing PO?
Leading Breast Radiologists Discuss the USPSTF Breast Cancer Screening Recommendations
May 17th 2024In recognition of National Women’s Health Month, Dana Bonaminio, MD, Amy Patel, MD, and Stacy Smith-Foley, MD, shared their thoughts and perspectives on the recently updated breast cancer screening recommendations from the United States Preventive Services Task Force (USPSTF).
Multicenter CT Study Shows Benefits of Emerging Diagnostic Model for Clear Cell Renal Cell Carcinoma
May 15th 2024Combining clinical and CT features, adjunctive use of a classification and regression tree (CART) diagnostic model demonstrated AUCs for detecting clear cell renal cell carcinoma (ccRCC) that were 15 to 22 percent higher than unassisted radiologist assessments.
CT Study: AI Algorithm Comparable to Radiologists in Differentiating Small Renal Masses
May 14th 2024An emerging deep learning algorithm had a lower AUC and sensitivity than urological radiologists for differentiating between small renal masses on computed tomography (CT) scans but had a 21 percent higher sensitivity rate than non-urological radiologists, according to new research.