From the September 2022 issue of HealthCare Business News magazine
By Rich Mather
The complex physics at the heart of MR enables its greatest strength: the array of different image contrast mechanisms that make MR so versatile.
MR can detect changes to the local magnetic environment due to the presence of iron, calcium, or hemoglobin. It can trace the diffusion patterns of water along microscopic tissue architecture and even measure the chemical exchange of magnetization between free and bound water molecules to probe macromolecular content. Despite all of this technical capability and success, there are still two key issues that manufacturers can help solve to unlock MR’s full global potential: patient access, to drive healthcare equity among all communities; and better workflow, to streamline the diagnostic process.
The challenges of access to MR come from a range of causes. For some patients it is a matter of proximity, having to travel hundreds of miles to the nearest facility. For others, claustrophobia or physical size prevents them from being able to get an exam. Finally, exam cost can be prohibitive. Whatever the reason, limitations to access mean that many patients with a clinical need for MR are unable to get one. To improve access, we need to minimize system cost and, more importantly, total cost of ownership. This will lower the barrier to MR for smaller, more remote community clinics, increasing geographic coverage. New system designs will better accommodate more patient shapes, sizes, and movement limitations as well as minimizing claustrophobia. Finally, designing MR scanners around ubiquitous high-speed networks to build an ecosystem of interconnected components can help bridge healthcare informatics systems.
MIT labs, experts in Multi-Vendor component level repair of: MRI Coils, RF amplifiers, Gradient Amplifiers Contrast Media Injectors. System repairs, sub-assembly repairs, component level repairs, refurbish/calibrate. email@example.com/+1 (305) 470-8013
The other major challenge in MR is workflow. MR’s flexibility comes at the cost of generating large data sets capturing all the different possible contrast mechanisms. Acquisition speeds are slow compared to CT and ultrasound, making scheduling more challenging. Similarly, as access challenges are solved, scanner operation must be simpler and faster to enable high-quality images without the need for highly-trained technologists.
While there is a lot of hype around artificial intelligence (AI) in all industries, when applied correctly to the right problem, AI can manage complexity better than any conventional algorithm. In MR, several AI techniques are well suited to play a critical role in reducing cost and improving efficiency. Deep convolutional neural networks (DCNNs) do an excellent job of feature identification and discrimination. While a conventional algorithm might only use a few hand-selected features like edge detection over a small patch of the image, by training to a task, DCNNs can discover and combine millions of features over the entire dataspace. A deep learning reconstruction (DLR) network’s ability to discriminate between signal and noise in MR is a great example. The resulting noise-reduced images are far more natural-looking with higher resolution compared to conventional algorithms. DLR approaches reduce acquisition times and increase spatial resolution while preserving diagnostic quality. Other networks will recognize patient anatomy and automatically plan scan geometry and other acquisition parameters. Image artifacts will be automatically recognized and corrected or trigger data reacquisition as necessary. Combinations of sensor hardware and AI will detect and correct for magnetic field non-idealities to further accelerate acquisitions and allow for sitting in less restrictive environments. Furthermore, AI will help manage the overwhelming data volumes by detecting clinically relevant findings, triaging normal data sets, and prioritizing worklists. Ultimately, AI will streamline and simplify the entire MR workflow.
MR has the widest potential of any current imaging modality. Cost, speed, complexity, and availability have limited this potential. Future technologies will democratize MR, opening global access and simplifying the workflow to manage the increasing demand without compromising on quality or cost.
About the author: Rich Mather is the president of Canon Medical Research, USA.