Nadim Michel Daher

When it comes to non-invasively imaging the human body’s internal organs and tissues, we use all kinds of waves and radiations at our disposal. We use X-rays in radiographic or computed tomography (CT) imaging, acoustic waves in ultrasound imaging, magnetic fields in magnetic resonance (MR) imaging, and visible light in optical imaging, along with a few other types of modalities. As for the use of microwaves (or radio waves, or “radar”) in diagnostic imaging applications, it has been experimented with for many years, but has remained confined until recently to the research realm. Now, as it enters into commercialization stage, it’s time to take a closer look at the clinical potential of this new imaging modality.

It turns out that those same types of electromagnetic waves that our cellular phones use to transmit voice and data actually check all the marks for being used as a medical imaging modality: They can penetrate tissue in a non-ionizing and presumably harmless manner, get scattered based on the dielectric properties of tissue, and this scatter can be measured back by radio sensors in order to reconstruct an image.

Like every imaging modality, microwave imaging comes with its strengths and limitations. On the upside, microwave imaging is fast, safe, and can provide powerful functional imaging capabilities in real-time and in three dimensions. Its hardware components come in small sizes and at a low cost, since they benefit from the ongoing miniaturization and cost efficiencies of the large consumer electronics markets of wireless devices. On the downside, the modality provides rather low spatial resolution, and could use a broader body of clinical studies to understand it more fully.

That is about to change. Two startup companies, Micrima from the UK and EMTensor from Austria, were on the exhibit floor of the 2018 European Congress of Radiology to talk about new, largescale clinical studies that are nearing completion, and to showcase clinical imaging systems that are respectively ready, and about to be ready for prime time.

Digital mammography is the established mainstay in breast cancer screening and diagnosis, and the advent of 3D digital breast tomosynthesis over the last few years has been taking the modality to the next level. However, X-ray breast imaging has intrinsic limitations, which various other modalities such as breast ultrasound, breast MRI and molecular breast imaging have been seeking to address. Despite the advances in these various modalities, all of which still have important shortcomings, the position of an effective adjunct to digital mammography remains very much underserved. It is in this context that radio-wave breast imaging is evolving through multiple research and development efforts as detailed in the recent paper “Recent Advances in Microwave Imaging for Breast Cancer Detection”.

The most mature of these is Micrima’s MARIA® breast imaging system, in development for more than a decade and CE-marked since 2015. It uses radio-frequency waves to image the breast in 3D, while providing optimal patient comfort. It does not require breast compression, and the patient is lying down on a table in natural position. The resulting images provide a detailed view of the functional activity in breast tissue, which indicates the presence of lesions. Thanks to the deep penetration of radio-waves in breast tissue, unhampered by bones or air, the modality is effective in various types of breast but particularly effective in dense breasts, which has been a key area of breast imaging needing improvement. Continuing development work involving machine learning is expected to further improve the functional characterization of lesions provided by the system in the very near future. As the company’s new set of ongoing clinical trials in the UK near completion, this new modality is starting to deliver on its high promise for augmenting the breast imaging armamentarium.

Stroke imaging was a hot topic at ECR 2018. Since interventional treatment techniques of stroke have taken off (complementing the more mature intravenous therapy techniques), brain imaging of stroke patients has become a cornerstone of stroke patient management. Indeed, the key to managing stroke patients most effectively is the ability to differentiate between an ischemic or haemorrhagic stroke as quickly as possible, ideally during the critical first hour of crisis, and definitely under the three- to four-hour mark. This is how emergency clinicians can decide whether or not to administer tissue plasminogen activator (tPA) treatment, or whether to send the patient directly to a center equipped to perform endovascular thrombectomy interventions, neurosurgery and neuro-critical care.

Therefore, there is a very strong clinical rationale for an effective imaging modality that can triage stroke patients quickly, as soon as they reach emergency departments or even sooner, such as on board ambulances in mobile stroke units (MSU). EMTensor’s brain imaging system, now in its third-generation with the fourth already in the works, is extremely promising in this regard. The system has a much smaller footprint and considerably lower cost compared to the mobile CT units that are starting to equip ambulances. This makes it much more realistic to envision it as a standard equipment of ambulance fleets. Further, its safety profile makes it suitable for clinical use cases not possible with conventional MRI or CT brain imaging, such as 24/7 brain monitoring of patients with traumatic brain injury. EMTensor seems to be moving in these directions quickly, with two brain scanners used in ongoing clinical studies, and plans for CE-marking and FDA approval within three years.

It’s exciting to be able to witness the debut of a brand new imaging modality and watch it take its first steps into the clinical field. It makes one realize that there are always new avenues for bridging some of the gaps left open by the current spectrum of imaging modalities. The big imaging vendors should take notice of this new versatile, safe and cost-effective modality, which stands a good chance of establishing itself at the frontlines or as an adjunct across various care pathways-potentially disrupting places where ‘big-iron’ modalities are established today.

Articles

ECR 2018: Electromagnetic microwaves bring much-needed new weaponry to the arsenal of breast and stroke imaging.

Microwave Imaging Shows Great Potential

At the HIMSS17 show last March we announced 

the race for medical imaging analytics ecosystems

, and profiled seven vendors making early moves. Eight months later at RSNA 2017, this race continued to pick up steam in a big way.

With a momentum that seems to mirror the rapid proliferation of medical imaging artificial intelligence companies, more and more of the larger informatics vendors are looking to capitalize on these diverse applications to augment their own offerings. As more AI algorithms obtain regulatory approval, the big opportunity now is to channel them to market while delivering them as an integral part of the daily clinical workflows. Indeed, experience has shown that even the smartest computer-aided detection or diagnosis (CADx) algorithm, if not well integrated into the routine workflow, is likely to be ultimately ignored by most clinical end-users.

Therefore, while these algorithms may become validated for market use, they still need a pathway to market adoption and “a place to live” once in the field. It is not reasonable to think that their creators, often startups, have the wherewithal and the market access to channel them into the field. In fact, if they had to switch gears towards the marketing and sales function, they would quickly lose their technological edge and inevitably slow down their product portfolio development. Not counting the fact that, at a time when integrated delivery networks (IDN’s) and health systems are trying to consolidate their vendor relationships and standardize their procurement mechanisms, no one is going to enter into dozens of new vendor contracts to deploy various niche AI applications.[[{"type":"media","view_mode":"media_crop","fid":"64768","attributes":{"alt":"Nadim Michel Daher, Industry Principal Medical Imaging and Informatics, Frost & Sullivan","class":"media-image media-image-right","id":"media_crop_198633661643","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"8297","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 213px; width: 170px; float: right;","title":"Nadim Michel Daher, Industry Principal Medical Imaging and Informatics, Frost & Sullivan","typeof":"foaf:Image"}}]]

Deep learning frameworks provide an efficient way to develop software algorithms, at much higher speed than traditional coding methods. Therefore, the proliferation of medical imaging AI solutions that we saw at RSNA 2017, with a massive number of new players and new algorithms from existing players, is bound to continue. Whether these frameworks are utilized in a supervised or unsupervised (or hybrid) way, what it really boils down to is assembling a robust dataset of images, associated findings, annotations, and outcomes, then let the framework work its magic to identify the relationships between them, and derive the right software code.

That’s where few vendors have identified the opportunity to help AI developers gain cost- and time-efficient access to large, well-curated medical imaging datasets. DICOM Systems with their 

, and Medexprim with their now open-sourced 

, are two such vendors that promoted this value proposition at RSNA. This commercial data access is meant to complement the two strategies for accessing good quality image datasets that early-moving imaging AI vendors have had to rely on: the imaging resources and biobanks available for R&D projects such as 

 on one hand, and on the other hand, one-to-one R&D collaborations between individual hospital organizations and individual vendors.

Just as interesting to see in this context of capitalizing on data, is the growing vendor interest for delivering ways for academic researchers themselves to collaborate, promote and validate their own home-grown advanced algorithms. 

, with a focus on neuroimaging, was created to do just that.

 are all making some good progress, either by adding native applications to their advanced imaging analytics ecosystem, or by expanding their portfolio through new partnerships with  independent software vendors (ISV’s). Notably, Google Health made it as a first-time exhibitor at this year’s RSNA, while NTT Data augmented its AI partner portfolio by integrating

. In parallel, few imaging AI vendors that started out with a single niche application are gradually expanding organically by adding new native modules. A good case in point is Arterys who announced at RSNA it had received FDA approval for its 

, where it will soon roll out its new clearance-pending oncology lung CT and liver CT and MR applications, complementing the FDA-cleared cardiac MR application.

Meanwhile, much of the attention on the RSNA showfloor was drawn towards few new contenders setting out to build their own AI marketplace or “app store”, the top two of which would be:

: Nuance is probably the highest-profile new entrant in this playing field, due to the vast market footprint of the radiology reporting giant. 

Nuance launched its imaging AI Marketplace at RSNA

, dubbed the first “open” marketplace which brings on-board a number of imaging AI algorithms. Concurrently, Nuance also announced two new significant related partnerships, with Philips Healthcare, and with the GPU market leader NVIDIA, both of which strengthen its market entry. Things have shaped up very nicely for Nuance in the imaging analytics area since its 2014 acquisition of image sharing vendor Accelarad (re-branded PowerShare Network).

In fact, Nuance was able to capitalize on two other related acquisitions that were much less promoted publicly, both radiology analytics vendors: that of Montage Healthcare Solutions (re-branded as PowerScribe 360 MONTAGE and mPower), and that of 

. Now, the combination of these image management and analytics capabilities, along with the new partnerships, put Nuance in an ideal position to power-up, populate and operationalize its new imaging AI marketplace.

: EnvoyAI is the new name for McCoy Medical Technologies, which advanced visualization vendor 

 last June but decided to maintain as an independent entity. EnvoyAI’s new Exchange platform is an 

, with over 15 partner ‘apps’ and 35 algorithms, and counting, already accessible through the platform. EnvoyAI also acts as a channel for some native TeraRecon ‘apps’ it contributes to the platform, since two are already part of EnvoyAI’s offering. Synergies could also work the other way for the two companies, since on its side TeraRecon also pre-launched its new Northstar viewer, dubbed the ‘world’s first AI-results viewer’, which will allow for closer interaction between image viewing and these advanced imaging analysis tools.

The company is dedicated to making the use of medical imaging AI algorithms practical for end-users, which means they will be able to experiment with the various algorithms and pay per-use. These prices, determined by each AI vendor, already vary widely across the portfolio. For example, few algorithms are priced under $1 per study, while others, which can be billed for against a CPT reimbursement code, at over $40 per study.

As of the RSNA 2017 timeframe, only a handful of imaging AI algorithms seeking regulated use cases, already have U.S. FDA market approval. While the process is time- and cost-intensive, most vendors seem to have the ball rolling on the process, yet everyone is eagerly waiting for FDA regulation on how to deal with the continuous learning of algorithms, rather than having to re-submit regular “Maintenance 510k” applications for new algorithm versions, as is being done by some right now.

The marketplaces offering access to both FDA-approved and non-FDA approved algorithms raises the question of whether we are bound to enter an interim phase of off-label, experimental use of the regulated yet non-approved ones, as has been largely the case, for example, with image study interpretations in non-diagnostic grade mobile viewers.

RSNA 2017: The Race for Medical Imaging Analytics Ecosystems Takes New Turns

About ten years ago, in what could have been an ordinary 

post, a doctor from Connecticut, Richard L. Reece, wrote these lines:



“If […] you regard patients and doctors as intelligent consumers of care and providers of integrity, who give that care, you may believe they are perfectly capable of fending for themselves.”

Fending for our own selves. This seems to be the impression that the ongoing regulatory debates in the U.S. about concerns surrounding gadolinium retention, is leaving patients with for now. The U.S. FDA has deemed the current clinical evidence as inconclusive of an adverse effect of gadolinium retention in the brain and body, thereby recommending that further research studies be conducted by pharmaceutical vendors, academia, FDA, and federal research centers.  This provisional stance is leaving patients hanging in their decision-making, while everyone waits for more conclusive studies. [[{"type":"media","view_mode":"media_crop","fid":"64768","attributes":{"alt":"Nadim Michel Daher, Medical Imaging Industry Principal at Frost & Sullivan","class":"media-image media-image-right","id":"media_crop_127147805794","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"8297","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 188px; width: 150px; float: right;","title":"Nadim Michel Daher, Medical Imaging Industry Principal at Frost & Sullivan","typeof":"foaf:Image"}}]]

RSNA 2017 did ease some concerns.  The results of a 

by Robert J. McDonald, et al, were released, which finds that gadolinium deposits in the brain are not associated with adverse neurologic outcomes. That’s great news indeed, but it’s only one type of potential adverse outcome. In fact, the same researcher team, in a preclinical study of rodents, is now investigating the infiltration of gadolinium from blood into the cerebrospinal fluid (CSF) as the potential initial pathway entry into the brain.

It’s an uneasy situation for patients right now. We are exposed to an ever-growing body of clinical 

that confirm retention is indeed occurring after multiple injections of gadolinium-based contrast agents (GBCA), even in patients with normal kidney function. We already know that secondary effects could exist (that would be called Gadolinium Deposition Disease [GDD]), and that they have not been documented well enough. And yet, we are being told to wait – hoping the next time we need a contrast-enhanced MRI won’t be too soon.

The actor Chuck Norris deciding to sue GBCA manufacturers and distributors because he and his actor wife are convinced the acute strange symptoms she suffered are secondary effects tied to the three injections of linear GBCAs that she received in a very short time period, now comes in as the cherry on top of this raging issue. As this ad hoc lawsuit starts turning into a wider class action, it is becoming widely publicized that there could also be an acute immune reaction to gadolinium injections in addition to the issue of gadolinium retention, all occurring in patients with normal renal function.

The Evolving GBCA Safety Profile: a Ten-Year Recap


A few months before Dr. Reece’s 2006 post,  the FDA issued a major Black Box warning guiding physicians and patients with renal insufficiency that remains in effect today: these patients risk contracting a potentially fatal disease called nephrogenic systemic fibrosis (NSF). Almost immediately, this led the medical community to cease gadolinium injections in this patient group. The almost overwhelming cases of NSF were associated with the linear (aka open-chain) GBCA agents which bind the gadolinium agent the least tightly, making the binding less stable.

Now, 10 years later, the issue has surfaced for patients with normal renal function that GBCAs, at least the less stable (linear or open-chain) ones, actually leave residual deposits in the brain. So far, most of the clinical studies have demonstrated a potential safety risk profile of gadolinium deposition in the brain with the linear GBCAs, while alluding to a seemingly safer profile of macrocyclic or closed-chained GBCAs having no or less deposition. But just recently, the results of a new 

from Norway were publicized, that may shake-up the soft consensus that seemed to have been reached. That study shows that even the macrocyclic GBCAs that were studied did leave gadolinium residues in the brain of patients that had many (over 20) injections.


This summary only reflects our side of the Atlantic. Europe, where a similar debate about GBCA safety risk occurred about gadolinium retention in the brain, concurrently to the one in the U.S., has taken a radically different stance on the issue. Following an extensive 17-month review of all available and unpublished research, a recommendation by the European PRAC (Pharmacovigilance Risk Assessment Committee) –the European equivalent to our U.S. FDA – was followed by an actionable decision by the CHMR (Committee for Medicinal Products for Human Use), to pull from the market all linear GBCAs, namely Bracco’s MultiHance, GE’s Omniscan, Bayer’s Magnevist, and Mallinckrodt’s (now Guerbet) OptiMARK.

On the Vendor Side: Wishful Thinking and Proactive Moves


Perhaps the most insightful part of the recent September 8,2017 Open Public Hearing 

of the FDA’s Medical Imaging Drugs Advisory Committee (MIDAC) was the timeslot allocated to the GBCA vendors. It is interesting to note that in this utmost situation of public health, the vendors did not reach a consensual opinion. Each vendor seemed to be taking the stance that best matches their own GBCA product(s) profile, based on their individual adoption level in the U.S. marketplace. This gave the perception of bias depending on whether their GBCA uses a closed-chain or macrocyclic (more stable) or open-chain or linear (less stable) chelate, and whether their product is profiled specifically in the clinical studies under evaluation, or not.

For example, GE Healthcare continues to argue that the benefits of administering a GBCA far outweigh any risks for Omniscan, which remains its dominant product in the U.S. and one that has been studied extensively. But at the same time, in Europe, GE is actively launching Clariscan, a macrocyclic and ionic (and therefore more stable and, presumably, safer) GBCA which they introduced at ECR 2017, with marketing authorization already in place, at least in Norway.

For Bayer, who operates two strong GBCA products in the U.S., one linear open chain and one macrocyclic closed chain, the position seemed naturally in evolution as their marketplace shifts from the linear to the macrocyclic.

As for Guerbet, who feels comforted by the presumably better stability and safety profile of its flagship macrocyclic GBCA Dotarem, it is acknowledging the fact that it is proactively phasing out from all markets the linear GBCA OptiMARK that came with its 2015 acquisition of Mallinckrodt’s contrast media and delivery systems (CMDS) business, independent of any decision in the U.S. about this product family.

People Moves: Awareness, Concern, and Angst


In this context of uncertainty, keeping abreast of a constantly growing body of scientific evidence, an engaged community decided not to wait and see what will come out of federal rulings from the FDA or other regulatory bodies. The web site 

 established by the Lighthouse Project has, since 2014, set out on its mission to “shed light on the effects of retained gadolinium from Contrast MRI”. In essence, here is a civic or social media movement that has taken ownership of an ostensibly medical issue, of which it wants the public more informed.


Big questions still remain unanswered. More ongoing clinical studies may soon unfold, with some possibly proving a causal link between gadolinium retention and various adverse secondary effects. This could be demonstrated even in healthy kidney patients and even in patients undergoing a not-so-high number of contrast-enhanced MRIs. Other studies, like the latest one out of Norway, may show that even macrocyclic GBCAs are not that much safer after all.

But while the controversy will probably not taper off anytime soon, can we contemplate a future without Gadolinium at all? This will require substantial validation and will take time, but a recent study published in 

shows promising works-in-progress towards a manganese-based contrast agent (MBCA) that could offer an equally effective but possibly much safer alternative to GBCAs.
 

Recent FDA review process of inconclusive clinical studies creates a potentially unhealthy decision-making environment for patients needing gadolinium-enhanced MRIs.

U.S. Patients Left Fending For Themselves with Gadolinium Safety Risks

It’s one of the perks of working out of Paris, France: to be living in one of the world’s capitals of art. When time is short, it’s hard to think of a better mental escape from work matters, than visiting a nice art exhibition.  I used to expect the world I work in – the medical imaging industry – would not intrude on that of my free time, in which beaux-arts getaways are supposed to offer a complete change of scene. Ironically, it happened a few times in the last two years that medical imaging matters just bluntly intruded on a few of these arty escapes.   I stumbled on this wall sculpture at the 2015 edition of the renowned Paris Art Fair. There, twice a year, the latest creations of hundreds of artists and designers are displayed in one of Paris’ most amazing venues, under the huge barrel-vaulted glass roof of the Grand Palais. [[{"type":"media","view_mode":"media_crop","fid":"57939","attributes":{"alt":"","class":"media-image media-image-right","id":"media_crop_4105259646434","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"7304","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 473px; width: 630px; float: right; margin: 1px;","title":" ","typeof":"foaf:Image"}}]]It took me a minute or so to realize, two hours into an inspiring art stroll, that the reason this strange form I was staring at looked familiar, was because it was actually a green-painted scanner gantry cover. It could be from a CT or an MR scanner, I still can’t tell, but the fact that it was elevated here as an object of art made me think that we, who work in the medical imaging field and see these machines every day, tend to forget sometimes what amazing pieces of design work these objects really are. A few months later, I found myself one day in the basement of the Fondation Cartier watching a video installation made on the occasion of a retrospective exhibition of Daido Moriyama’s work. He’s a contemporary Japanese photographer who, throughout his career, worked extensively on the topic of market consumerism. In this 10-minute film, random images were rolling on two large screens, meant to represent the mix-and-match of random sights and visual memories we experience in our daily lives.[[{"type":"media","view_mode":"media_crop","fid":"57940","attributes":{"alt":"","class":"media-image media-image-right","id":"media_crop_2187328269079","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"7305","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 473px; width: 631px; float: right; border-width: 0px; border-style: solid; margin: 1px;","title":" ","typeof":"foaf:Image"}}]] The picture I snapped caught the moment when an X-ray image came up right next to the brand of a mass-market drink, which also happens to be one of the major pop-art symbols of our consumer society. At a time when healthcare consumerism is becoming a big topic, this coincidence felt ironic indeed. This also made me reflect on the extent to which our medical images, which patients bring back home along with the “good news” or “bad news” of their diagnosis, can create a lasting visual memory in people’s minds. The art intrusion struck again recently, when I came across, in a museum, a series of photographs called Mein Gehirn (German for “My Brain”), work from the late 1980s of a German artist called Isa Genzken. A hospitalization episode led the artist into a creative process whereby she felt the urge to look “inside herself.” With this introspective work, Genzken reminds us how fascinating our medical images can appear to the untrained eye, as we all struggle to understand how our minds and bodies really function. She also makes it a point that medical images can very much be looked at, as the curator puts it, a “unique variation of the self-portrait.”[[{"type":"media","view_mode":"media_crop","fid":"57943","attributes":{"alt":"","class":"media-image media-image-right","id":"media_crop_5956298627460","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"7308","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 191px; width: 630px; float: right; border-width: 0px; border-style: solid; margin: 1px;","title":" ","typeof":"foaf:Image"}}]] Closing out with another sight of increased romance lately between medical imaging and art, this week I learned about a new visualization technology called “cinematic rendering” that looks like it could well be right there, at the intersection of the two. Its inventors, Siemens Healthineers, released the 

 created with the innovative algorithm. Geared right now at research, teaching, or at better physician-patient communication, the technology is “A Journey Inside the Human Body” that may, down the line, become a valuable interventional planning tool when it develops into clinical use cases. The novel rendering technique, inspired by the animation work that we’re used to coming out of the movie industry, produces medical images that look more “photorealistic” than ever before. As I contemplate these images, there are some I find so esthetical that it becomes hard to draw the line between where medical imaging stops, and where artistic imagery starts. But why try to force down that line, anyway?  [[{"type":"media","view_mode":"media_crop","fid":"57942","attributes":{"alt":"","class":"media-image media-image-right","id":"media_crop_7481222734328","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"7307","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 840px; width: 630px; float: right; border-width: 0px; border-style: solid; margin: 1px;","title":" ","typeof":"foaf:Image"}}]]Photo credit: healthcare.siemens.com

The beauty of medical imaging is easy to overlook, but it's still there. 

Author | Nadim Michel Daher

Articles

Microwave Imaging Shows Great Potential

RSNA 2017: The Race for Medical Imaging Analytics Ecosystems Takes New Turns

U.S. Patients Left Fending For Themselves with Gadolinium Safety Risks

When Medical Imaging Meets Art