It isn’t a secret to any radiologist that the bulk of his or her day is spent in the reading room, pouring over scans, looking for critical findings that can help detect disease or change the course of a patient’s treatment. Those interpretive skills are highly valuable throughout all aspects of healthcare.

But, what about the non-interpretive skills. The ones that don’t go directly into analyzing a CT scan or MRI image? They are equally as vital to successful radiology practice. They can help providers create the most impactful and useful radiology reports, they can create collegial work environments, and they can help a radiologist and his or her colleagues avoid burnout. 

In a session during this year’s Radiological Society of North America annual meeting, Dr. Diane Strollo, associate professor of cardiothoracic surgery at the University of Pittsburgh led a panel specifically dedicated to discussing the importance of and implementation of non-interpretive skills. This week, 

 talked with her about the skills that are most important and the impact they can have.

Videos

RSNA

They might not be used for diagnosis, but pay attention to -- and sharpen -- your non-interpretive skills. They can create a much better work environment.

Pay Attention to Non-Interpretive Skills

The RadXX awards are less than five years old, but they have become a focal point of the Radiological Society of North America annual meeting in that short time, drawing attention to and recognizing the significant contributions that women have made to the field of medical imaging informatics.

This year, Cheryl Petersilge, M.D., founder and chief executive officer of the consulting firm Vidagos received the RadXX Trailblazer award for her pioneering and innovative work in the field. Not only was Petersilge on the front lines of implementing enterprise imaging during her tenure at the Cleveland Clinic, but she now leads efforts to help both healthcare organizations and vendor develop and implementing imaging informatics strategies.

 about her journey into imaging informatics and how her efforts have changed the field not only for women, but also overall.

Explain what initially led you to be interested in the field of imaging informatics.

 I really become interested in informatics toward the mid-portion of my career, and I saw it as something that was becoming more and more important in healthcare. It was something I really wanted to learn about, and I actually started my informatics experience in clinical informatics. I was a physician champion for computerized physician order entry in my local hospital, and, then, I was the Regional Medical Director for the East Side for the implementation of electronic documentation in the regional hospitals at the Cleveland Clinic. As those efforts were underway, enterprise imaging was being established at the Cleveland Clinic. It was prompted by the changeover in our PACS system, and it was a really great fit for a radiologist to become a medical director.

I started working with the team that was implementing that initiative and became the first medical director. It gave me the opportunity to really shape the direction and establish the strategy for how we were going to go implementing that throughout the Cleveland Clinic. It was a great fit for me because my passion really lies in strategy developments. I really liked having the opportunity to establish something new. The great thing was it wasn’t just establishing something new at the Cleveland Clinic, it was helping establish something new for all of healthcare since we were really one of the first enterprise imaging programs. We became one of the most comprehensive enterprise imaging programs during my tenure there.

 You received this year’s RadXX Trailblazer award largely due to your experience and innovative efforts. What are some of the main accomplishments you can point to that led to your earning this accolade?

I think of two different things. One is helping to lead the enterprise imaging program at the Cleveland Clinic and uncovering some of the challenges that actually continue today. For example, how do we label photographs as they go into the electronic medical record? And, what are the challenges around that? When we were having discussion with our clinicians about what we were doing, we realized there was a disconnect. We kept calling things orders, and they kept saying they didn’t give orders – to us, orders meant how you label things in the electronic medical record. So, we had to uncover those challenges.

Some of that work set the stage for establishing the encounters-based workflow which is now an HIS standard. I’m not going to claim that we drove that, but I think we helped uncover the problem and played a role in defining the problem statement. Also, with surgical imaging, we were exploring how do you implement surgical imaging programs into your enterprise imaging program? What all needs to go into the consideration of that program? Those programs are still in their infancy in most organizations.

Other than that, one of the avenues of work that I’ve done is in photo documentation – incorporating medical photographs into the enterprise imaging program. I alluded to some of the challenges we had at the Cleveland Clinic. Through that, we were able to establish the photo documentation workgroup for the HIMSS and SIIM enterprise imaging community that is working to bring together multiple disciplines that are engaged in photo documentation. This is an area that radiologists don’t play in, so we’re getting a lot of other fields together to try and coordinate what has been very specific work into a unified process.

 How did that get you to founding Vidagos, and what role does the company play in medical imaging informatics?

As I mentioned, strategy is really what I enjoy – it’s what makes me happiest. As the Cleveland Clinic program matured and the roadmap was established, we did a lot of strategy and defining work. I would say it’s now turning over to more of an operational and implementation type job. I established a new radiology group for the Cleveland Clinic and a place where I used to work in private practice, but after a few years, that was when my interest in imaging informatics started. I was looking for other opportunities to engage my passion for learning and developing strategy.

Developing Imaging Informatics Strategic Plans

As I was ending the process for enterprise imaging at the Cleveland Clinic, I knew that informatics was really something that I truly enjoyed. I had fulfilled my course at the Cleveland Clinic and was looking for new opportunities. Couple that with the fact that I got my MBA several years ago and the fact that I was always an entrepreneur at heart. So, I decided that it was time to go out and establish my own business. Frankly, I even looked into leaving healthcare to engage that passion, but after exploring a lot of things, I realized that informatics and healthcare was really where I belong – where I had the most to contribute.

I decided to start Vidagos consulting firm. There, my goal was the help organizations develop their enterprise imaging strategy and really bring them my experience because there are a lot of people out there that have built a program when no roadmap exists for how to do it. I knew that I could really help healthcare organizations. One of my goals was also to work with the vendors to help them understand what the healthcare organizations need, to be a voice for enterprise imaging to the government and to talk to and educate the government. I’ve really been able to fulfill all of those obligations. I work with many different healthcare organizations, educating them on what enterprise imaging and helping them assess their current state. For many organizations, that’s a daunting task. They don’t even know where to begin, so I walk them through what they want their enterprise imaging program to look like and what their guidelines should be. I develop their roadmap with them. Similarly, I’m doing the same thing for vendors, helping them understand what organizations need and how the field is evolving.

But, I’m not one to let moss grow, and I have expanded beyond enterprise imaging and am becoming more involved with general healthcare information exchange, data governance, standardization, and data commercialization. That’s primarily through my vendor relationships right now, but I also know that it will feed what I bring to healthcare organizations.

 With that as a backdrop, how do you feel your work has changed the field of imaging informatics – what would you point to as being the impact you have made?

Driving photo documentation and the consolidation or coordination of medical photography across the entire organization, as well as the recognition of the importance of metadata. One initiative I am deeply involved with – but I’m not leading – is selecting standards for body parts so we can unify al medical imaging through body part identification. So, whether it is a photograph of a wound, MRI of the wound, or the pathology of the wound, all of that would be unified by the body part. You could look at the full concept of that patient’s disease process. I think raising awareness of that has been one of the ways I’ve changed the field of imaging informatics.

One of my goals for this year, sort of one of my two messages, is to really stress the importance of the electronic health record and the difference between the electronic health record and the electronic medical record. I think many organizations are focused on their electronic medical record, and, certainly, there’s a lot of work to do there. But, we need to understand that there is so much information in the electronic health record and that includes patient generated data, even expanding the social determinants of health. That’s one of the new messages that I’m out there really trying to drive education for.

How do you feel what you’ve been able to accomplish has potentially impacted the field of imaging informatics for women who are interested in the specialty?

One of the most important things is for early-career people to see people that look like them be successful. Two of my mentors in imaging informatics have been women. For women to see women be successful, it is a huge influence on the field, so I think more and more women feel comfortable in the field. Also, to have people that they talk to about how they’ve dealt with some of the challenges might be unique to whatever part of the population you belong to. So, for RadXX, that would definitely be women.

For women to see these close relationships among women, to see women helping women is very important because women don’t always help women.I think to set the example of women supporting and developing other women is very, very important.

What is your hope for imaging informatics as it moves into the future as a specialty?

I really want to see imaging informatics become an enterprise priority. It needs to move beyond radiology, but radiology definitely needs to be a leader and a mentor. Radiology plays a critical role in imaging informatics. But, as we try to coordinate healthcare, we have to coordinate imaging. It has to be a cooperation among all of the different imaging specialties. I really want to get healthcare informaticists to understand that there is a wealth of information held in all of these images.

We also have to get the message out about the role imaging informatics can and will play in population health. In fact, one presentation at RSNA this past week talked about information that’s hidden in images that can be used to understand the health of your population. I think we’ve only begun to scratch the surface on that.

One of my hopes for the coming year is to start to reveal the role that imaging informatics should be playing.

For more coverage based on industry expert insights and research, subscribe to the Diagnostic Imaging e-newsletter

Articles

A desire to shape and help healthcare organizations direct their imaging informatics strategy is what drives award-winner Cheryl Petersilge, M.D., founder and chief executive officer of consulting firm Vidagos.

For RadXX Trailblazer, Imaging Informatics Passion Comes from Strategy

The use of artificial intelligence (AI) in medical imaging is not new – in fact, it has been a topic of conversation at the Radiological Society of North America (RSNA) annual meeting for at least the past five years. And, with that continued growth comes the obligation among radiologists to approach its use in medical imaging in the most ethical ways possible.

On Monday, radiology ethics expert David Larson, M.D., professor radiology at Stanford University, discussed how data used in AI tools are now being applied to clinical care. That information holds tremendous value, but the industry does not yet have the ethical, regulatory, and legal constructs in place to ensure the data is handled in the most proper fashion.

In part three of this video series, Larson talks with 

about the other ethical questions that exist, along with potential safeguards that can be implemented, as well as what the future holds if these ethical questions are not answered appropriately.

What other ethical questions exist, and what the future holds.



AI & Medical Imaging: The Ethical Issues, Pt. 3

Using dual-energy CT (DECT) with an electron density (ED) measurement can improve the diagnosis of metastatic lymph nodes in patients who have non-small cell lung cancer (NSCLC) when compared to FDG PET/CT, new research has pointed out.

During this year’s Radiological Society of North America (RSNA) annual meeting, investigators from Kagoshima University in Japan shared the results of their study that showed a DECT-ED combination greatly augments the specificity of lymph node diagnosis.

Currently, conventional CT and FDG PET/CT are used for diagnosis in these situations, but their performance has been unsatisfactory, said Hiroaki Nagano, an associate professor at Kagoshima with an expertise in radiation science. Consequently, providers need an imaging modality that can be more accurate.

“We hypothesized that DECT-derived parameters, including ED, can help diagnose metastatic lymph nodes in patients with non-small cell lung cancer and may have additive diagnostic value to PET/CT,” he said.

By measuring ED, DECT has already proven useful in differentiating between high-grade and low-grade central nervous system gliomas. To see if it could do the same thing for lymph nodes with this patient population, Nagano’s team examined studies from 57 patients with pathologically confirmed NSCLC who underwent pre-operative DECT and FDG PET/CT.

“To our knowledge, this is the first report demonstrating that usefulness of ED in diagnostic metastatic lymph nodes in patients with non-small cell lung cancer,” he said.

Of the group, 37 had adenocarcinomas, 19 had squamous cell carcinomas, and 1 had pleomorphic carcinoma. Among the 117 lymph nodes visualized, 84 were non-metastatic, and 33 were metastatic – 57 in the N1 region, and 60 in N2. The team assessed the nodes for size, necrosis, calcification, margin clarity, and shape, then they compared CT features, PET/CT positive findings, CT value, and ED value between the non-metastatic and metastatic lymph nodes.

Based on their analysis, 15 percent of metastatic lymph nodes were necrotic, but only 1 percent of non-metastatic ones were. In addition, ED measurements for metastatic and non-metastatic lymph nodes were 3.47 and 3.50, respectively, and 65 percent of metastatic nodes were PET/CT positive, while only 25 percent of non-metastatic nodes were.

According to these results, Nagano said, metastatic nodes can be associated with necrosis and interstitial fibrous change. This can result in lower ED values on metastatic nodes than non-metastatic nodes. Their findings of ED being significantly lower with metastatic lymph nodes falls in line with this existing evidence.

When compared to PET/CT positive alone, PET/CT positive and ED outperformed in almost every way. PET/CT positive alone only performed better with sensitivity, 66.7 percent to 60.6 percent with PET/CT positive and ED.

Nagano noted that the study population used was small so additional research with larger groups is warranted. But, overall, he said, these findings indicate that the combination of PET/CT and ED performs with higher accuracy that PET/CT alone. It is, therefore, more useful in differentiating between non-metastatic and metastatic lymph nodes.

DECT and electron density offers more accurate differentiation between metastatic and non-metastatic lymph nodes when compared to FDG PET/CT.

Dual-Energy CT Improves Diagnosis of Metastatic Lymph Nodes with Non-Small Cell Lung Cancer

In part two of this video series, Larson talks with 

about how far down the road providers are in approaching AI in medical imaging as ethically as possible and what challenges stand in the way to reaching that goal.

Are radiologists approaching AI ethically, and what challenges exist.



AI & Medical Imaging: The Ethical Issues, Pt. 2

Artificial intelligence has been a mainstay of the Radiological Society of North America (RSNA) annual meeting for nearly a decade. Each year brings new developments, reveals new capabilities and algorithms, and furthers the conversation about how these tools can help radiologists provide care.

This year, the conversation began to turn to what steps could come next for AI. Conversations about deployment, consolidation, and U.S. Food & Drug Administration clearance are now the norm as the technology becomes less of a novelty and more of a mainstay.

 speaks with Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, about her reaction to what this year’s conference offered about these tools and what she sees on the horizon in 2021.

Podcasts

Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, discusses, during RSNA 2020, what new developments the annual meeting provided about these technologies, sessions to access, and what to expect in the coming year.

The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring

There is a correlation between the brain differences seen in children with at-risk genetics and their differences in cognitive performance, according to MRI imaging.

As part of this year’s Radiological Society of North America (RSNA) annual meeting, investigators from the University of California at San Francisco shared these results from the first study to examine the role of cortical development as a mediator between catechol-O-methyltransferase (COMT) genotype and cognitive performance. The team also examined the possibility that it could be a mediator for schizophrenia and psychosis onset.

“MRI in children with abnormal COMT genetics offers insight into neuroanatomical differences that manifest before clinical symptoms and might represent a window of intervention,” said lead study author, presenter, and UCSF radiology resident Justin M. Remer, M.D.

COMT is an enzyme that plays a critical role in frontal and temporal lobe dopamine metabolism. Existing research has shown that if an individual has the rs4680 Valine 108/158: Methionine polymorphism, he or she is at increased risk for schizophrenia. This variant can be identified via convergent functional genomics.

According to the team’s results, differences in cortical thickness development can be used to explain the differences in longitudinal cognitive development seen in children who have the COMT genotype. They reached this conclusion by examining T1 MRI brain images from 88 children between ages 1 years to 6 years.

Not only did Remer’s team group the children by COMT rs4680 genotype, but they also collected the children’s learning composite scores – a surrogate for IQ measurement. Using imaging, the team pinpointed areas of the brain that revealed developmental differences in children with the genetic make-up that put them at high risk for psychiatric disease.

Ultimately, using these findings, the team was able to connect the brain differences to variance in cognitive performance.

Differences in cortical thickness development correlates to cognitive differences and could be involved in increased risk for mental illness.

MRI Reveals At-Risk Genetics Can Affect Cognitive Performance

Radiology is not unlike any other medical specialty – biases exist even in the face of the strongest efforts to eliminate them. And, some of the most difficult to handle are the ones providers do not even know they have – the unconscious biases that largely go unrecognized.

But, the industry is beginning to talk about this issue more and more, educating radiology professionals about how unconscious biases appear and how they can best combat it. During this year’s Radiological Society of North America (RSNA) annual meeting, Jorge Soto, M.D., chief of radiology for Boston Medical Center, and Maureen Kohi, M.D., associate professor of clinical radiology at the University of California at San Francisco, led a session focusing on these biases that fly under the radar.

 spoke with them about the importance of shining a light on this problem and what radiology can do.

Jorge Soto, M.D., and Maureen Kohi, M.D., discuss how unconscious bias presents in radiology and the tools that providers can use to recognize and minimize the biases when they appear.

Unconscious Bias: Handling What You Don’t Know You Have

Work has been ongoing for years to decrease the presence and impact of disparities throughout healthcare, including in radiology. But, problems still exist, and there are new challenges on the horizon that could make it more difficult for radiologists to make it easier for patients to get the imaging services they need.

During this year's Radiological Society of North America (RSNA) annual meeting, Richard Heller, M.D., associate chief medical officer and national director of pediatric radiology with Radiology Partners, and Lucy Spalluto, M.D., associate professor of radiology and radiological sciences at Vanderbilt University School of Medicine, participated in a session dedicated to addressing the continued existence of health disparities. 

 about the underlying factors that result in healthcare disparities, as well as the challenges providers and facilities face to improving access to care.

Rich Heller, M.D., with Radiology Partners, and Lucy Spalluto, M.D., with Vanderbilt University School of Medicine, discuss the highlights of their RSNA 2020 session on health disparities, focusing on the underlying factors and challenges radiologists face to providing greater access to care.

RSNA 2020: Addressing Healthcare Disparities and Access to Care

Alzheimer’s disease can be diagnosed earlier with multi-modal imaging by using a novel machine learning model even when some modalities are missing, according to a new study.

Researchers from a multi-institutional team developed a model that outperforms others that are currently available, and they presented their work during this year’s Radiological Society of North America (RSNA) annual meeting.

Developing tools for early detection of Alzheimer’s disease is critical because early identification can help slow progression of the disease. So far, healthcare has looked to neuroimaging as an avenue to catch the signs of this condition. But, more data is needed for scan to be successful.

To meet this need, the team, led by Fleming Y. Lure, Ph.D., created a novel transfer learning-based machine learning model that can diagnose and prognose mild cognitive impairment due to Alzheimer’s with varying availability of imaging modalities, such as MRI, FDG-PET, and amyloid-PET.

“Our research provides a clinical tool to assist physicians in diagnosis and prognosis of Alzheimer’s disease when disease is still early for their patients, which has tremendous clinical benefits,” Lure said.

For the study, Lure’s team included 241 patients with mild cognitive impairment from the Alzheimer’s Disease Neuroimaging Initiative Database. Of the group, 97 had mild cognitive impairment due to Alzheimer’s disease. Within two years, 26 individuals with mild cognitive impairment had converted to Alzheimer’s disease, and another 46 had converted to Alzheimer’s within six years. The team divided the patients into four sub-cohorts based on imaging available: MRI only; MRI and FDG-PET; MRI and amyloid-PET; and all three modalities.

Based on their analysis, the team determined the machine learning model achieved much better accuracy than the competing model, using each cohort for prognosis and diagnosis.

Novel deep learning model can provide needed information from multi-modal imaging even when some modalities are absent.



Latest Conference Articles