Rethink Imaging

EP 9 • December 27, 2024

Rethinking Medical Imaging: Frame by Frame Holiday Special

Featured Guest

Multiple Guests (Compilation)

•

Listen Now37 min

Also on:

Let's Talk

Beyond dose

Ask us what your imaging data can actually show you.

Start a Conversation

Share This Episode

Subscribe to Rethink Imaging

To close out its first year, Rethink Imaging looks back at the most impactful moments from the show’s inaugural run. This holiday special pulls together segments from seven distinguished leaders in medical imaging, covering the topics that defined season one: AI integration, radiation safety, dose management, healthcare policy, and career advice for imaging professionals.

The featured segments are drawn from the show’s 2024 guest roster, which included Drs. Griglock, Samei, Armbruster, Siegel, Fleisher, Frush, Larson, and Goode. Each clip captures a standout moment from the guest’s full conversation with host Chris St. John, so listeners can revisit the highlights or discover episodes they missed the first time.

Host

Chris St. John

Host, Rethink Imaging • Imalogix

Featured Guest

Multiple Guests (Compilation)

•

Watch the Episode

Key Takeaways

AI integration was a recurring thread across year one, with guests weighing how new tools fit into real imaging workflows and clinical decision-making.
Radiation safety and dose management anchored several conversations, from optimization strategies to the data needed to manage dose across a department.
Healthcare policy came up repeatedly as guests discussed how regulation and industry trends shape imaging practice.
Guests shared career advice for imaging professionals, drawing on their own paths through clinical, academic, and industry roles.

Full Transcript

Christmas Episode Transcript

Chris St. John: [00:00:00] Welcome to Frame by Frame Rethink Imaging, a podcast by Imalogix. Here, we explore the intricate world of medical imaging, aiming to dissect the field and inspire both professionals and curious minds alike. I’m your host, Chris St. John. Welcome to a very special holiday edition of Frame by Frame Rethink Imaging.

Chris St. John: As the year draws to a close, we’re wrapping it up with a celebration of the luminaries we’ve spoken to this year. Grab your favorite holiday drink, get cozy, and join us as we journey through some of the highlights of Frame by Frame. Let’s dive into the magic of innovation and care.

Tom Griglock:

I’ve always thought of science as like a process, like elementary school education on the scientific method and like, yeah, you know, doing a science fair project where I put caffeine pills into like fast growing plants and I was like, look, science.

Chris St. John: But I don’t really [00:01:00] know what are the key differences between science and medicine? Like, where is the discrepancy kind of living,

Tom Griglock: right? I mean, that’s a great question. I don’t know the answer to that. I mean, it’s this blurry relationship, you know, again, if you ask a hundred different people that are in both of these fields are in this field, that question, you know, you might have overlap on some of those answers, but you’re going to get a hundred different answers to that question.

Tom Griglock: Yeah. So, yeah, I mean, it’s just an interesting thing to pay attention to. And it’s something, you know, none of it is easy. I guess that’s the thing that’s. Crazy, you know, and so we think, you know, when we’re teaching students, even medical physics students are, you know, obviously like radiology residents and different physician residents, like they spend more time in the hospital and everything else.

Tom Griglock: But like when we teach medical physicists as scientists about this stuff, you know, one of the things that we do is we get them in the clinic alongside technologists and alongside radiologists and radiation oncologists to see what it actually looks like to deal with the patient. Because like the idea of taking an x ray is very easy, right?

Tom Griglock: Okay. But the reality is that imaging somebody who’s in a lot of pain and is moving around, you know, like that’s [00:02:00] really freaking hard,

Chris St. John: right? Like we can show you how to do a phantom study, but the second you have a patient on the table, it’s like,

Tom Griglock: well, it’s, it’s theory. I mean, like, why didn’t it look bad?

Tom Griglock: Well, because the patient was in so much pain that they couldn’t stand, they couldn’t keep their foot. You know, they had a bone popping out of their skin, like it probably, yeah. So, I mean, I think, you know, the reality of, you know, and I don’t think it’s a secret, but I mean, I think being honest and transparent of this is really freaking hard work that these people do all the time.

Tom Griglock: And that’s why it is, you know, more of a nuanced practice or art or anything else and less of a science a lot of times is where that comes into.

Chris St. John: Yeah. So basically what you’re saying is just don’t trust anyone as I move through this show.

Tom Griglock: That’s what I’m getting from this. Yeah. I mean, I think, you know, I was listening to something a couple of days ago when they started talking about, like, it was something about, you know, the election or politics or something else coming up.

Tom Griglock: And it was, you know, what happens with polls and all of this stuff. And the thing I was thinking [00:03:00] of was like, you know, when we think everybody’s the expert, you know, or when we trust everybody who’s like, says that they’re an expert or that you think is an expert as an expert and you don’t show any sort of like healthy.

Tom Griglock: I don’t want to say skepticism, but I’ll say skepticism. You know, I think it’s good to listen to these people and to take what they’re saying is, you know, they believe that it’s true. But sometimes what an expert thinks isn’t something that’s been proven. Sometimes what an expert thinks or says and they could say like, no, like this is definitely true.

Tom Griglock: It doesn’t have to be true. I mean it could be their informed opinion based on 20 years of this. Except for the fact that, you know, many things over time, especially in science, and I’m sure in medicine as well, have been proven wrong. Right. You know, and people were experts at the time, and then all this time later we go, oh, that wasn’t good.

Tom Griglock: That’s not what we should have done.

Chris St. John: That was Dr. Tom Griglock reflecting on the complex relationship between science and medicine. Emphasizing how scientific thinking and real world patient care often intersect but don’t always align. His insights remind us that even [00:04:00] in highly technical fields, human experience shapes every outcome.

Chris St. John: Continuing this exploration, Dr. Ahsan Sameh examines how data driven precision supports clinical decision making. Blending quantitative science with the qualitative art of patient care. So how do you balance the quantitative data with the qualitative insights in making decisions about patient care?

Ehsan Samei: So what if doctor says, well, it could be this or that or that or this?

Ehsan Samei: It’s like, okay, well, how good are you? Really? Right? Of course, you don’t want to be wrong to give you the wrong thing. So accuracy is important. I’m not saying accuracy of interpretation is not important, but reducing uncertainty is equally important. In fact, that’s probably most likely thing that we need to have to practice medicine proficiently and well.

Ehsan Samei: Reducing uncertainty. So you didn’t know many things before you saw the doctor, you’re more certain about your medical condition. So, in the same way, if I am able to provide the human interpreter a [00:05:00] little bit higher quality medical image that is quantified as being higher quality, so they can be more certain in their interpretation, then patient will be better served.

Chris St. John: I mean, it’s simple, but it kind of, that feels like a very effective way of thinking about it, especially for me. That’s like an easier way to think about something that has infinite nuance to it, I guess.

Ehsan Samei: So the way I think about this, it’s a good question, by the way, Chris, you’re asking brilliant questions.

Ehsan Samei: Right. I appreciate it. You asked me to think deeply about this thing. The way I frame this is that for the things that you do know, quantitate. For the things that you do not know, qualitate. best way of putting it, right? Right. I’ll give you another example. I love examples. Looking at the back of the package of the food, it says you have this much carbohydrates, this much fat, this much protein, and so much.

Ehsan Samei: They are very quantitative. So these are the things that we can quantitate. Is it useful to quantitate them? I would say yes. I’d [00:06:00] love to see how much protein is in this package, how much fat, and whatever. Does that mean that it tastes good? No. No. Taste is not quantitative. Right. This needs to be qualitated.

Ehsan Samei: Right. Right? Yeah. So here’s a good example. So quantitate the things that you do know, but don’t assume the stuff that you have quantitated and you do know is the end of the story.

Chris St. John: Oh, absolutely. Like, I mean, to just like build on this example, like I think about once again, former chef here, there’s going to be a lot of food references, but you know, I think like thinking about something as simple as like, it will take X amount of time to boil this amount of water was the water salted.

Chris St. John: Well, where are you relative to sea level? Right? Like all of a sudden, something that you think you have like pretty succinct data on, once again, it just kind of goes out the window as soon as you start thinking more and more deeply about it.

Ehsan Samei: Right. So as a result, you can think about that qualitative approach [00:07:00] towards reality is the sauce, is the space that fills the gap.

Ehsan Samei: That’s what makes all the difference. Well, I mean, what I just said is actually the irony. We feel like when we quantitate, we feel like we got it. We understood, you know, we know what that person is all about because we have quantitated that thing. But in reality There is more to that entity that we are after in the qualitative terms of that thing, right?

Ehsan Samei: Yeah. So in medicine, we quantitate. We measure the size of the tumors. We ask the question, you know, how much is tumor is growing and not growing? All those are quantitative. I can measure the resolution of an image. I measure the noise of an image. These are all quantitative measures of how good that image is.

Ehsan Samei: Is that the end of the story? No. Does that mean that therefore I need to throw all the numbers out? They don’t mean anything? No, that’s not the case. I still like to have those, how much sugar and carbohydrates in my [00:08:00] package. I still need to have it. That doesn’t mean that these are meaningless. They’re very meaningful that how much sugar is in that package for me.

Ehsan Samei: But that doesn’t mean that fully describes the reality of that thing. That’s where the human element comes in, using that example again, right? Right. So physician needs to have all the quantitative insight at his or her disposal, but should never assume that they got the final answer, because that’s the arrogance of sort of assuming that you got it.

Ehsan Samei: And when you got, you have that arrogance, you go wrong.

Chris St. John: Absolutely. And we’re also at this moment in time too, where At least from my perspective, it feels like the human element is not really taking a backseat yet, but as data analytics is becoming more advanced, as we start using more and more of these AI tools, like, how do you see the role of human judgment evolving with the application of all of this?

Ehsan Samei: I [00:09:00] think we will continue. I mean, there is no question that sort of data analytics, machine learning, artificial intelligence has been another disruptive technology at the human level for everything that we do as insightful and as impactful as they are. I think they don’t have the final answer in a sense that, you know, many things.

Ehsan Samei: Are is still unknown and uncertain. Like for example, people always think about, okay, we are gonna train all these algorithms and detect all the cancers that might be in the body, and humans need to ever, ever, you know, diagnose them, whatever. But all the examples that they provide are for types of cancers that, for which we have many examples, right?

Ehsan Samei: there are thousands of rare diseases. We don’t have good examples. So, for those examples, we don’t have enough data to be able to train an algorithm to figure out what is what. Dr.

Chris St. John: Ehsan Sameh emphasized the balance between data driven insights and [00:10:00] clinical interpretation, underscoring the value of reducing uncertainty in patient care.

Chris St. John: Expanding on this, Dr. Donald Frush delves into effective communication about radiation safety. Offering strategies for easing patient concerns while emphasizing the critical role of transparency and trust. What advice would you give to a young radiology tech or someone who’s considering the field, or someone who’s in residency or something?

Chris St. John: What advice would you give folks who are just starting?

Donald Frush: It’s a really good question, Chris, and it’s a little bit dependent on who that individual is and what their level of training is and so on. But as always, to validate that what they’re doing from a professional standpoint is appreciated, right?

Chris St. John: Yeah.

Donald Frush:And the value of that to the patient, right? Because fundamentally.

Donald Frush: What is healthcare? What is excellence in healthcare? It’s making sure that the patient is well [00:11:00] taken care of. Now there are multiple levels, you know, efficiency, effectiveness, you know, marketing, professional advancement. There are many things that are metrics for what someone might consider excellence, but if we talk about what is the fundamental of Part of why we’re here, it’s taking care of patients and it’s protecting them from harm and it’s also providing them a benefit.

Donald Frush:And, you know, medical imaging that uses ionizing radiation is, it’s like the poster child of that kind of thing of do good, but do no harm there. And so it’s sort of emphasizing the importance of what they’ve done from a professional standpoint and reiterating that radiation protection is an important part of that.

Donald Frush:And whatever level they’re at, whether it’s a radiology resident or an internist or a cardiology fellow or a radiology technologist or a health physicist, is to look at the domain of what you’re supposed to understand about [00:12:00] the use of ionizing radiation and be familiar with the types of conversations.

Donald Frush: that you might need to know. You know, what are you going to be dealing with? Providers, you’re going to be dealing with patients, you’re going to be dealing with other imaging experts, et cetera. And to sort of say, okay, what do I need to know? What kind of questions come up? What is the scope of what I need to know?

Donald Frush: Cause you can’t know everything. And, you know, talk to senior individuals, say, okay, you know, that’s part of the training here is what exactly they need to know about doses and risk and so on. And to get talking points, I think to develop The population based talking points depends on who you’re going to be speaking with, whether it’s a patient or a colleague or an administrator or a medical physicist related to that.

Donald Frush:And there is a variety of information available for individuals to do that and, you know, to always remember, you know, the tenets of radiation protection. which is, is it the right exam? How do I work towards making sure it’s the right exam? Technologists may say, hey, they ordered this just yesterday. What do [00:13:00] we need to do?

Donald Frush: And technologists have said this to me and I said, well, maybe they made a mistake. Maybe they didn’t know. And so that conversation comes up with the provider and say, you know, we did this yesterday or something similar. I think I can answer your question. So it’s for them to always be an advocate for the radiation protection.

Donald Frush: Is it the right exam? Be sure that it’s done appropriately and that everyone, you know, needs to develop in their own regard and role this collective radiation protection program for wherever they’re working. So it does echo a lot of what we’ve talked about before, but it’s identifying a champion, right?

Donald Frush:The group that’s really invested in this, it’s providing the proper resources and it’s supporting those individuals because radiation protection is sort of an odd bird because it doesn’t bring in revenue, right? Right. It doesn’t. It doesn’t reduce costs. You know, unless you’re not going to get an exam and you don’t use it, but then you’re talking about the rest.

Donald Frush: So it doesn’t bring in revenue. It doesn’t reduce costs. And it’s actually costly because you do need to [00:14:00] provide, you do need to put together the team to do this. Of course, it takes time,

Donald Frush:And if you think about it, if you step back and say, okay, radiation protection or any safety in medicine, what is the measure of success?

Donald Frush: And the problem with radiation protection and any element of quality is no one comes home after being a champion of safety or radiation protection and say, gosh, all my patients were really protected today, right? There was a hundred percent protection. Why? Because that’s expected. What do people come home with?

Donald Frush: Oh my gosh, this CT, we’ve drifted and we’re using too much dose, or this patient got a procedure and didn’t need to do it. Or, you know, the chair is calling me and saying, what happened with this procedure? This, you know, patient is complaining that it took too long and they got too much radiation. So those individuals who are invested in this just have to understand, lobby for what they do, but realize that it is somewhat of a thankless task in that.

Donald Frush: you know, those, all the measures of what we consider, you know, what do we want to do? We want [00:15:00] to, you know, have a beneficial practice, which actually can support itself. We want to make sure costs are reduced. We want to come home and be, you know, happy about what we’ve succeeded in. And, you know, a lot of the quality people, a lot of radiation protection is, you know, the success is perfection and that’s what’s expected.

Donald Frush:So if people remember that real respect of what you’re in a health physicist, medical physicists, et cetera, is to understand that domain, but Also, go back to some of those earlier things that I talked about in terms of defining what you need to do, developing talking points, working with the stakeholders, being a champion, and just knowing that you’re responsible for radiation protection.

Donald Frush:You know, if you think about it for yourself, you know, what would you want for you and your family? Is that what you’re doing for your patients and the colleagues that you work with?

Chris St. John: Dr. Fresh’s thoughtful guidance on communicating radiation risks highlights how patient understanding supports better healthcare experiences.

Chris St. John: Wrapping up, Dr. David Larson explores dose optimization, emphasizing the value of precise teamwork and consistent protocols in delivering safer, more

David Larson: [00:16:00] effective imaging.

The challenge is that, well, I’ll say, first of all, a CT is miraculous. I mean, it has transformed medical care. I mean, it really is. What we’re able to see with CT is phenomenal.

David Larson: So we wouldn’t want to ever, you Downplay the transformational nature of the technology, but at the same time it does use radiation and radiation is associated with increased risk of cancer. It uses low dose radiation, but we want to minimize that risk in any way we can. So there is a core principle in radiology.

David Larson: As low as reasonably achievable, we use dose as low as we can. We need to use some dose, but we don’t want to use any more than is necessary. The problem with CT is that the more dose you use, the better the images look. You know, the thing that is your limit is pretty visible to everybody. If you’re not using enough radiation, then it kind of jumps out at you, say, Hey, I can’t, you know, it’s very noisy is how it looks grainy kind of images.

David Larson: Like you’re not gonna be able to make the diagnosis. On the other end of the spectrum, there’s nothing that jumps [00:17:00] out at you that says, Hey, you’re using too much dose, right? So it’s kind of like if there’s a threshold and the threshold isn’t exact point, but there is a threshold below which if you go, it’s going to be too noisy.

David Larson: But if you go above it, it’s not necessarily a problem that you can see. So then the goal is to kind of get to hug that lower threshold as closely as you can. But it’s tough because you don’t know where that threshold is innately unless you’ve gone over it, right? So that’s one problem, or it’s one challenge.

David Larson: And the other challenge is it’s very, very sensitive to size. Because as you create a shadow on the detector, some of those x rays are absorbed, And if you have greater size, more of those x rays have to be absorbed in order to create that shadow. So, it involves a lot of math, and involves a lot of thorough understanding of how the machine actually works at every size.

David Larson: And that understanding is not really well, I would say, developed and well implemented. At least not to the level of sophistication that we really need to fully optimize DOS. [00:18:00]

Chris St. John: Right. And so is that, so you’re saying obviously, like I hear the term size adjusted dose being thrown around as well, it’s my assumption.

Chris St. John: Is that some sort of automatic calculation? Is that something that people are doing? Like, how do you end up with a size adjusted dose?

David Larson: Yeah. So one thing I’ll say about optimization before I address that specifically, it’s important to remember that optimization of dose is based on image quality. Right, so it’s not actually about the, the dose that the organs receive.

David Larson: I mean, you want to minimize the dose that the organs receive, but as long as you get adequate image quality and use the most dose efficient parameters on your scanner, then you have to assume that’s the lowest dose your organs can receive. That image quality ends up being the driver.

Chris St. John: How do you go about optimizing then?

David Larson: Yeah. So really what it comes down to is set a target and consistently hit that target. Right. The shift in mindset and this happened in manufacturing really about, and it’s now about 60 to 70 years ago where [00:19:00] across the world, you know, this was the kind of lean Six Sigma quality transformation, you know, really kind of focused in Japan where the mindset used to be.

David Larson: You know, you just keep, you have specification limits. And as long as you’re somewhere within the limits, then you’re fine. It’s, it can been termed the goalpost mentality. And so this approach is now a target based approach. And so that’s what true optimization is, is you say, I want to specifically hit this target.

David Larson: And I’m going to continuously work to make it so I am very precisely hitting that target. And so to do that, you have to start with the target. In our research, we started, we use estimated image noise as a function of patient size. And But that’s a bit more complicated and probably more than is necessary.

David Larson: So, we’re now looking at using what’s called a CTDI VOL, CT Dose Index, or a volume, right, the CT Dose Index. So, if you can set a target for your CT Dose Index over a range of patient sizes, You start there, then it’s a matter of setting the parameters on your scanner to hit that and then have a [00:20:00] monitoring application to make sure that you do so on a regular basis.

Chris St. John: Right, right. And so you’re saying that like the dose monitoring stuff is adjusting dose in real time. Is that correct?

David Larson: Kind of. So I think what you’re referring to is called automated tube current modulation. Sure.

Chris St. John: I was going to say automatic tube current modulation, but you know,

David Larson: exactly. You did. Yeah. You, that’s what you described.

David Larson: Yeah. Tube current is basically a proxy for the amount of radiation that’s going out. And so from the x ray tube, you put a certain amount of tube current in and you get a proportionate amount of radiation out. So it’s kind of like you could saying it’s like automatic radiation modulation, right? And modulation just means it adjusts as it goes around.

David Larson: So tube current modulation is a technology that’s been around for about 20 years. And as it goes around the patient, it recognizes how far it has to penetrate, how thick the patient [00:21:00] is at each angle. And so whether if the gantry is front to back, Um, then it’s usually thinner. And if it’s side to side, then it’s usually larger, right?

David Larson: So it automatically adjusts. It’s radiation as it goes around, and it’s great technology works really well. The main downside to it is that even if though it adjusts, it doesn’t clarify what it needs to adjust to. So it adjusts. And so what we tend to see is there’s still a lot of variation still used too much radiation more than was necessary to hit that target dose or that target image quality.

David Larson: And so you have to really nail down what is that target image quality, and then on the backside, confirm that you hit that target. And that’s what a tube current modulation algorithm does not necessarily do for you. That’s why we’re still facing this problem. Yes, it adjusts as it goes around. So it’s, you know, it’s a great technology.

David Larson: It’s just, they didn’t quite finish it. It has to be accompanied by a monitoring system, and that monitoring, you have to be fully confident that you’ve nailed that [00:22:00] target dose based on image quality.

Chris St. John: Dr. Larson’s exploration of dose optimization revealed the power of collaborative efforts in creating safer imaging environments.

Chris St. John: Building on this operational focus, James Armbruster discusses how real time collaboration and clear protocols keep complex radiology departments running smoothly. Let’s get into workflows a little bit, right? If me saying workflow is all it takes to get you to go, you should go.

James Armbruster: No, I mean, I think workflow is a big deal.

James Armbruster: I think workflow is where it begins and where the emphasis needs to be put. Because workflow is, the term workflow gets thrown around a lot. in every industry, right? But I think in radiology specifically, it’s extremely, extremely important because it is unique, right? And, you know, workflow, I’ve mentioned this a lot.

James Armbruster: I stand behind the statement that workflow is a living, breathing thing, right? That is very unique and specific. Not only to hospitals, but the departments, right? [00:23:00] And workflow is not just, Hey, these are our processes, right? These are our policies and procedures. And this is what we do on a day to day basis.

James Armbruster: Workflow is much more, right? Workflow is relationships that the technologists have with one another. workflow is what my day to day steps are, what are my responsibilities when I walk into the to the radiology suite. You know, in a lot of cases in advanced imaging, advanced imaging being, you know, CT, MRI, fluoroscopy to a certain degree, there’s more than one technologist involved with the process, right?

James Armbruster: And that’s one of the, I think, things that have changed the most since I was a clinician versus today, right? When I was a clinician, you say, oh, back in my day, I’m aging myself a little bit. But, you know, back when I was practicing, You know, you were by yourself to a certain degree in a lot of cases, not every case, but in a lot of cases, you were by yourself as a technologist.

James Armbruster: So you were responsible for getting your patient in an MRI scenario, clearing your patient from metal, making sure that they get on the table, scan them, validate that the scans are great, get them off the table and then prepare your next patient. Whereas today, in most cases, there’s [00:24:00] multiple individuals in the radiology suite, right?

James Armbruster: So from a workflow perspective, it’s good to know what you’re doing as a team, right, and say, okay, you know, you’re going to scan today, I’m going to run the patients, I’m going to get the lines set up, and then there’s also, you know, what’s a lot more prevalent today, which is documentation, right, making sure that you’re entering information into the RIS or the HIS system.

James Armbruster: You know, validating that the metal implants in the patient are clear in MRI scenarios. There’s a lot more steps involved in the process, but there’s also more individuals involved in the process. So you have to make sure that everyone’s on the same page with what you’re going to do that day. So that I can continue, if I got a patient on the table.

James Armbruster: And the other person is responsible for getting the next patient set up, get a line in that patient if they need be, that that, you know, whole workflow just runs like a well oiled machine. Because what benefits from that, the patients will benefit from that, because, you know, things are moving, nobody’s late, nobody’s delayed getting on the table, [00:25:00] you know, the organization benefits from that, right?

James Armbruster: We’re actually able to move our patients through the system strategically, like based on what our workflow is. And the technologists benefit, right? We don’t get backed up. Everybody knows what they’re supposed to be doing that day with regards to what my responsibilities are, whether it’s scanning or running or what have you.

James Armbruster: And things work smoothly, right? But again, that has to be communicated. That has to be consistent. And, you know, it’s tough these days when, you know, there’s obviously a shortage in technologists, right? When there’s a shortage in technologists, what happens is you engage with know, agency technologists or techs that, you know, are coming in that aren’t necessarily part of your organization and they know things a certain way and aren’t familiar with how things are done at your facility, right?

James Armbruster: Those types of disruptions in workflow can be expensive, expensive in the terms of time and fruit, right? So that’s where workflow is really critical, making sure things are consistent.

Chris St. John: James Armbruster’s reflections on radiology workflows highlighted the constant need for adaptation and [00:26:00] teamwork in dynamic healthcare settings.

Chris St. John: Expanding on this theme of efficiency, Dr. Elliot Siegel explores how artificial intelligence can optimize clinical workflows while still relying on human expertise for critical decision making. Speaking of skepticism, as we’re starting to wrap up here today, as I think I mentioned to you, this whole field is all quite new to me still.

Chris St. John: So as a podcast host, as someone who is getting educated on all of this, AI or not, Do you have any recommendations for me as I’m continuing to talk to folks or do you have any tips on a healthy skepticism that I should be having as I’m progressing and learning more and more about this field?

Eliot Siegel: Yeah, I think part of the healthy skepticism that you should have is we’re all kind of, we all grow up, we’re all programmed, we all learn as time goes on to be skeptical about other human beings.

Eliot Siegel: You know, you meet somebody and You know, maybe they’re [00:27:00] being 100 percent honest. Maybe they’re not. Maybe they know what they’re talking about. Maybe they don’t know what they’re talking about. And as time goes on, you kind of get to know them and essentially learn that. And I think people tend to think because something is based on a neural network or it’s called AI or it’s FDA cleared.

Eliot Siegel: that, you know, it really is going to do what it claims to do. We don’t put AI through the same board examination and same testing program that we do humans. And I think as you’re looking at the use of AI, it’s really important to kind of get to know it and to be able to sort of test it in routine use and kind of at the edges also.

Eliot Siegel: And I think maintaining that healthy skepticism is important. And I think You know, having it essentially, we’re exploring the edges of what it does and what it can’t do, and trying to see, you know, where it works, where it breaks, where it doesn’t, is really important. The other thing that I think is important is that we look at its [00:28:00] impact on performance.

Eliot Siegel: And so, you know, is it making us less efficient or more efficient? One of the concerns I had when we created the world’s first digital radiology department was, Was maybe people spend all day adjusting the brightness and contrast of the images and zooming and roaming image because you can do that infinitely.

Eliot Siegel: And what we found is that it actually increased efficiency and productivity. And so I believe that now. In general, AI is actually slowing radiologists down for the most part with most applications. I think in the future we’re going to learn how to use it more efficiently, how to trust it, and how to have it do things that are essentially mundane and repetitive.

Eliot Siegel: Like bringing images up, arranging the images, bringing the prior reports, extracting information from those reports, communicating findings, generating a report, you know, in studies that we did early on at the Baltimore VA, we found that [00:29:00] radiologists only spend about 15 percent of the time it takes to interpret a study, making up their minds about it.

Eliot Siegel: What the findings are and what they’re going to say the rest of the time is waiting for things to happen and all sorts of other efficiencies in the process of arranging images, extracting information, reporting, communicating, and then waiting for the computer to do something else. And I believe there’s tremendous potential to increase that 15 percent to 70, 75 percent or so.

Eliot Siegel: which could create enormous improvements. People are looking at the question of how do you pay for and justify AI, and having AI as a spell checker or grammar checker or background checker is really helpful. It could increase confidence, it could decrease the difference between experts and you know, less expert folks.

Eliot Siegel: But what people will really pay for is something that increases their efficiency and productivity while improving their relative accuracy. And at that point, it really becomes super [00:30:00] cost effective.

Chris St. John: Breaking from the strict conversation on imaging, Dr. Lee Fleischer discussed how healthcare policy and patient advocacy drive systemic improvements.

Chris St. John: Can you just tell me a little bit more about, like, CMS’s overall mission in healthcare and how the clinical quality measures fit into that vision?

Lee Fleischer: I always talked about the fact that CMS is a payer, but because it’s a payer for Over 60 million Medicare beneficiaries and jointly with the states for Medicaid.

Lee Fleischer: So, and then through the marketplace, some of the rules that governs, and since every hospital takes money from Medicare, it can actually deploy quality measures. Congress gave CMS the authority and minimum standards. So those minimum standards are really what’s called the conditions of participation.

Lee Fleischer: Many people are surveyed by the joint commission or the states or DNV, [00:31:00] which is another accrediting organization. But that’s saying every hospital has to meet a minimum standard of safety where they shouldn’t be open and spend a lot of time in that space, making sure. And in fact, when hospitals couldn’t meet that, and we did have.

Lee Fleischer: Few in nursing homes. We had even more, they would be briefed up to me. I would make a decision. I would brief the administrator and she, since I had two female administrators during my tenure, two administrations, I was a career official and they wanted somebody who was not political to say, this is really the decision of minimum standards.

Lee Fleischer: Now, how do we tell the public and how do we drive care above that minimum? Cause if you go into a hospital, if you’re going to provider, you don’t want the base, you want to know you’re up here and that’s quality measurement and, and payment programs, which is in the innovation center, but trying to say the higher the quality as [00:32:00] measured by these measurement and they are publicly reported, the better you can do by going to that provider type and doctors and hospitals like to get A’s.

Lee Fleischer: So. Although there’s payment attached to it. So in many of the programs, if you don’t report, you lose your cost of living or your update and your annual update in some of the programs, they take the top. amount of money, the top 25 percent and the bottom 25%. And they take money away from the bottom and they give it to the top.

Lee Fleischer: So if you’re in the middle, it’s neutral to how much you would normally get paid. But if you are a poor performer, you’re going to lose to a

Chris St. John: high performer. Can you just tell me a little bit more about like CMS’s overall mission in healthcare? And how the clinical quality measures fit into that vision.

Lee Fleischer: I always talked about the [00:33:00] fact that CMS is a payer, but because it’s a payer for over 60 million Medicare beneficiaries and jointly with the states for Medicaid, so, and then through the marketplace, some of the rules it governs, and since every hospital takes money from Medicare, it can actually deploy quality measures.

Lee Fleischer: Congress gave CMS the authority and minimum standards. So those minimum standards are really what’s called the conditions of participation. Many people are surveyed by the joint commission or the states or DNB, which is another accrediting organization, but that’s saying every hospital has to meet a minimum standard of safety or they shouldn’t be open and spend a lot of time in that space, making sure.

Lee Fleischer: And in fact, when hospitals couldn’t meet that, and we did have. Few in nursing homes. We had even more, they would be briefed up to me. I would make a decision. I would brief the [00:34:00] administrator and she, since I had two female administrators during my tenure, two administrations, I was a career official and they wanted somebody who was not political to say, this is really the decision of minimum standards.

Lee Fleischer: Now, how do we tell the public and how do we drive care above that minimum? Cause if you go into a hospital, if you’re going to a provider, you don’t want the base, you want to know you’re up here and that’s quality measurement and, and payment programs, which is in the innovation center, but trying to say the higher the quality as measured by these measurement and they are publicly reported, the better you can do by going to that provider and doctors and hospitals like to get A’s.

Lee Fleischer: So Although there’s payment attached to it. So in many of the programs, if you don’t report, you lose your cost of living or your update and your annual update [00:35:00] in some of the programs, they take the top amount of money, the top 25 percent and the bottom 25%. And they take money away from the bottom and they give it to the top.

Lee Fleischer: So if you’re in the middle, It’s neutral to how much you would normally get paid. But if you are a poor performer, you’re going to lose to a high performer.

Chris St. John: I can only imagine with a million moving pieces and then having to provide healthcare on top of organizing it. Like there’s a lot

Lee Fleischer: going on.

Lee Fleischer: Absolutely. That’s why it’s important. The comment letters, I did not understand how seriously CMS took them. And that’s why I just like to say it really is important for your listeners to really think if there’s something that they see. That really would help improve it if there was a change, they should say it.

Lee Fleischer: In fact, one of the interesting things is [00:36:00] there’s actually something called the Administrative Procedures Act. If between a proposed and a final rule, there’s a better way to do something. Only if somebody said it, can you make that change. It’s called logical outgrowth. And therefore proposing things is really important.

Lee Fleischer: That’s the key. We did that frequently during my three years in the government.

Chris St. John: Yes, just participation, right? Keeping your finger on the pulse. And if you have a disagreement or a concern or something to say, just hit. I love that kind of transparency and communication. Lee, this is exactly what I was hoping for, right?

Chris St. John: Just like, clear understanding of how and why, I think just makes such a big difference. And so, we need to start wrapping up here, but just before we finish up, what are you most excited about in seeing the direction that these quality measures are moving? That brings us to the end of this festive look back at frame by frame rethink imaging in 2024.

Chris St. John: We hope these conversations have brought some warmth [00:37:00] and inspiration to your holiday season. Thank you for joining us throughout the past few months and making this journey so meaningful. From all of us here at Frame by Frame and at Imalogix, we wish you a happy holiday and a wonderful new year. Frame by Frame Rethink Imaging is brought to you by Imalogix.

Chris St. John: Here, you’ll find engaging interviews with thought leaders, experts, and patients, sharing stories that showcase the transformative power of medical imaging. To discover how Imalogix is rethinking imaging in healthcare, visit Imalogix. com. Be sure to subscribe to Frame by Frame Rethink Imaging on Apple Podcasts, Spotify, or wherever you listen.

Chris St. John: And from all of us here at Imalogix, thanks for tuning in.

Questions from This Episode

What does this holiday special cover?
It is a year-in-review compilation of the most impactful moments from Rethink Imaging’s first year. Segments cover AI integration, radiation safety, dose management, healthcare policy, and career advice for imaging professionals.
Who is featured in this episode?
The episode features segments from seven distinguished leaders in medical imaging, drawn from the show’s 2024 guest roster: Drs. Griglock, Samei, Armbruster, Siegel, Fleisher, Frush, Larson, and Goode. Host Chris St. John guides the retrospective.
Where can I hear the full interviews?
Every segment comes from a full episode published during 2024. Visit the All Episodes page at /podcast to find each guest’s complete conversation, or start with the related episodes linked below.