Medical imaging analysis has become a vital technology in patient care since it provides detailed anatomical information in all different types of tissue. These technologies are essential to patient customized therapy planning, therapy monitoring, and follow-up of disease progression, as well as targeting for non-invasive or minimally invasive treatments.
Recent advances in magnetic resonance (MRI) imaging machines published by Hyperfine and the digitization of the Xray source by NanoX shed light on a question that motivates this blogpost, what if imaging didn’t require, high capital expenditure, a dedicated suite, extensive training, or expensive upkeep? How would it impact the on-time diagnosis and accurate therapy?. Would there be an advantage in delivering care at potentially reduced costs to the population at large?. Would it help to address social and ethical issues related to access to and affordability of healthcare?.
The cost of MRI and CT accounts for less than 3% of Medicare spending in the US and very often these modalities replace more invasive and expensive tests [3] but it is still around 10 times more expensive than a 2D X-Ray. With the growth presented by 3D surgical planning and customized treatment the number of patients where a CT or MRI will provide added value vs an X-Ray will rise dramatically, and delivering the right treatment to the right patient at the right time is the key to the future of medicine.
It has been demonstrated that in many diseases ‘one size fits all’ no longer applies, with that in mind, medical imaging is changing treatment management to a patient-specific approach, with both health and economic benefits. Treatment monitoring helps avoid both unnecessary drug toxicities and ineffective treatments, with resultant reduction in healthcare costs and significant reduction of invasive testing, such as exploratory surgery.
In general, costs of delivering MR scans or CT scans are easier to capture, but vary globally across different healthcare systems. Costs are borne by different groups in different societies, varying from the government through employers to individuals, but this is largely irrelevant when discussing cost control. Costs may be fixed (such as the cost of MRI systems [capex, depreciation, and upgrades, service contracts, staff costs] or variable [eg, contrast and consumables]). Further, the “costs” will also vary depending on perspective, eg, reducing exam time may reduce the healthcare system cost, but the patient charge may remain unaltered. The cost will even vary depending on the setting where the test is performed, the same CT scan that can cost a couple hundred dollars in an imaging cabinet, will cost tens of thousands in an emergency room (ER).
However, the discussion about the costs becomes a discussion about the value, and the “value” is difficult to measure. Usually, value is defined as outcome over cost. In medicine, the usual way to demonstrate “value” is to demonstrate a positive impact on the late effects of treatment, like morbidity, mortality, and quality of life and these late outcomes are not often linked with imaging to the naked eye.
Advances in healthcare IT technologies, computing power, faster networks, and cheaper storage have revolutionized medical imaging over the recent past, allowing doctors to manage, analyze, and interpret images more easily and flexibly than in the last decade. This opens up new possibilities to measure imaging value. Additionally, thanks to the increasing use of Patient-Specific solutions, digital surgical planning, navigators, and 3D printing, imaging value is no longer just diagnostic. Today, it has become the source for the personalized treatment plan.
After the image has been acquired in digital form, medical imaging analysis software tools help with the analysis of the acquired image and are able to extract medically or clinically relevant information using image processing applications such as segmentation, contouring, and thresholding to make the region of interest more prominent and obvious as compared to the surrounding regions.
Computerized medical imaging analysis is an advancement that has been the central focus in medical imaging in the last few years. For instance, machine learning, especially with regard to deep learning, is helping to identify, classify, and quantify patterns in medical images. However, there are still unanswered challenges to the universal implementation of imaging analysis solutions, with the need to establish quality standards, reduction of errors, and interpretation guidelines.
The requirement to address the unsustainable rise in healthcare costs is both a tremendous challenge and a matter of critical importance, both for society in general, and for medical imaging in particular. Payers want evidence that an imaging study adds clinical value for the patient, or avoids unnecessary surgery or other costs. Hospitals want to know that their equipment is utilized efficiently, especially if the MRI examination is performed in the setting of an accountable care organization or cost-center. The imperative to prove the value of medical images, moreover, goes beyond economics alone. Patients certainly want to know that any imaging test they undergo is necessary and helpful for their care.
There is no general guideline or benchmark regarding the ideal number of CT scanners or MRI units or exams per population. However, the costs of imaging have to be controlled and rationalized to avoid overdiagnosis, when diseases that are so stable or indolent that they would not have become clinically relevant during the subject’s life are identified.
The challenge for personalized medicine is to recognize when the burdens of treatment outweigh the benefits for a given patient, taking into account the individual characteristics of the subject, including his or her personal values and preferences.
There are still unanswered challenges to the universal implementation of image analysis solutions, with the need to establish quality standards, reduction of errors, and interpretation guidelines, and it is known that It requires a global effort to increase accessibility, value for money, and impact on patient management. Demonstrating and increasing “Medical image Value” is a global necessity that will help Making custom the new standard.
Reducing the cost of MRI and CT imaging is the key to customizing treatment, programming robots and running the AI algorithms that will give more and more people around the globe the opportunity to access improved, digitally enabled therapeutics. This is why we at TECHFIT Digital Surgery salute and admire the work being done by Hyperfine and NanoX and wish them the best success in democratizing imaging, as many other things, like custom treatment will be democratized in the back of their success, resulting in better healthcare for millions.
Reference
[1] Medical imaging in personalised medicine: a white paper of the research committee of the European Society of Radiology (ESR). (2011). Insights into Imaging, 2(6), 621–630. https://doi.org/10.1007/s13244-011-0125-0
[2] Top Neuroradiology Thought Leader Edmond Knopp, M.D. Joins as Senior Medical Director. (2021, January 26). Hyperfine.
https://hyperfine.io/news/neuroradiology-thought-leader-edmond-knopp-joins-hyperfine/