Search terms
Search terms
We know AI* can aid radiologists in image processing and interpretation. But what impact can it have at the point of image acquisition?
In this article we’ll look at how automated and AI-enabled “smart workflows” can support radiology technologists and streamline their workflow related to patient setup, parameter selection, image acquisition and image processing. These smart workflows hold promise in every major imaging modality – MR, CT, ultrasound and X-ray – and are all about boosting efficiency and clinical confidence for system operators, so they can focus more on the patient and less on the technology.
Challenge
The increasing use of MR to diagnose a variety of conditions and illnesses--even as imaging operations face staff shortages and variations in staff experience--puts pressure on MR teams to find new efficiencies that also allow for quality time with the patient.
Solutions
Philips SmartWorkflow for MR
Results
A 2019 Philips study of 254 radiology staff across four countries found that, while radiology staff consider communication with their patients to be extremely important to their job satisfaction, in real life these priorities fall short. Respondents gave “quality time with patients” a 4.3 out of 5 importance rating for their job satisfaction – but only 3 out of 5 in how satisfied they were in that respect of their current job.1
In a similar study of the patient experience of imaging, Philips learned that imaging patients have a strong desire to engage with caring staff that will be responsive to their concerns prior to and throughout the procedure.2 Indeed, the ability to engage with an undistracted technologist may help mitigate stress and encourage compliance – both of which can affect imaging outcomes.
If I could change one thing to improve my overall job satisfaction, it would be to have more communication with the patients themselves.”
J., Radiology technologist, U.S.
I wish the nurses [imaging staff] would be more compassionate.”
Imaging patient, U.S.
...Time per exam is very tight, which affects the quality of the images as everybody is stressed...”
S, Radiology Technologist, Germany
If we are in the middle of an exam and there are 10 patients waiting, we will be in a hurry, and errors may occur.”
A, Radiology Technologist, France
Often techs don’t have lunch because they’re so busy during the day...”
C, Imaging Director, U.S.
As a corollary, respondents said they felt that almost a quarter of their work could be automated. Their response underscores the great opportunity that exists to make system operators’ work more streamlined and less stressful. Needless to say, the productivity gain can be utilized not only for patient engagement, but also to meet the new standards of care and disinfection necessitated by COVID-19. This is where AI-enabled* “smart workflows” at the point of image acquisition can help provide a more confident, efficient, patient-centered experience.
Let’s take a look at the acquisition workflow in MR.
Workflow efficiency and ease of use contribute more than 25% to getting an image right the first time.1
What if you had a way to achieve high productivity while enabling your staff to focus on what matters most, the patient? Reduce and simplify the number of steps needed in a conventional MR exam workflow? Use technology to guide and coach where required, and even automate where possible? That kind of end-to-end workflow solution could directly boost efficiency through reduced variability and task automation, which in turn could support a better experience for patients and staff, resulting in patient-centered productivity.
That’s where Philips MR SmartWorkflow comes in. By reducing and simplifying the number of steps needed for patient preparation, even new operators who have never worked with the scanner can proceed with confidence – and keep focused on engaging with their patients.
As soon as the patient is placed on the system, the VitalEye is trying to look at the respiratory rate, and already tagging that. As soon as you close the door, it can start scanning. We’re able to manipulate these segments to lower breath-holds. This has made a significant improvement in our image quality.”
Dr. Constantino Peña
Miami Cardiac & Vascular Institute, Baptist Health South Florida, U.S.
The entire workflow is smooth: Patient positioning and set-up; launching the scan as soon as we leave the exam room; the intuitive touchscreen on the gantry; touchless patient sensing... All of these things are much better than on our old system."
Laura Barlow, RTMR
MRI Technologist Supervisor, University of British Columbia - Vancouver, BC, Canada
We don’t have to manually direct the patient to breathe and not breathe. We can go ahead and let the machine do the work of the breathing instructions while we continue our planning of the exam."
Carlos Avila, RT
Technologist at Miami Cardiac & Vascular Institute
Are you intrigued by what smarter workflows could do for you and your team? We are, which is why we’re so focused on improving them! From MR to CT to X-ray and ultrasound, we’re innovating smart workflows that help you get the right image first time, every time.
Challenge
The increasing use of MR to diagnose a variety of conditions and illnesses–even as imaging operations face staff shortages and variations in staff experience–puts pressure on MR teams to find new efficiencies that also allow for quality time with the patient.
Solutions
Results
*We embrace the following formal definition of AI (source: HLEG definition AI)
Artificial intelligence (AI) systems are software (and possibly also hardware) systems designed by humans that, given a complex goal, act in the physical or digital dimension by perceiving their environment through data acquisition, interpreting the collected structured or unstructured data, reasoning on the knowledge, or processing the information, derived from this data and deciding the best action(s) to take to achieve the given goal.
AI systems can either use symbolic rules or learn a numeric model, and they can also adapt their behavior by analyzing how the environment is affected by their previous actions.
As a scientific discipline, AI includes several approaches and techniques, such as machine learning (of which deep learning and reinforcement learning are specific examples), machine reasoning (which includes planning, scheduling, knowledge representation and reasoning, search, and optimization), and robotics (which includes control, perception, sensors and actuators, as well as the integration of all other techniques into cyber-physical systems).
Results presented are for illustrative purposes only and are not predictive of actual results for your business.
**Based on in-house testing.
