Chest X-ray can prospectively predict outcomes for a patient with COVID-19 in high pre-test probability settings or a quick turnaround of RT-PCR testing.

In a poster presented during the 2021 ARRS Virtual Annual Meeting, Russel Reeves, M.D., a radiology resident at Thomas Jefferson University in Philadelphia, described how this type of imaging can potentially help providers prepare for the type of care a patient will need.

For additional ARRS 2021 Virtual Annual Meeting conference coverage, click 

“We developed an accurate and reliable tool for classifying COVID-19 severity, which can be used both at the attending chest radiologist and junior resident level,” he said. “This study identifies the laboratory, clinical and radiographic data that predict important patient outcomes, such as death, intubation, and the need for chronic renal replacement therapy (CRRT).”

For their study, Reeves’ team identified 240 patients admitted to an urban multi-center health system between March 16, 2020, and April 13, 2020, who had RT-PCR-confirmed COVID-19, including 142 males and 98 females with an average age of 65.

Chest X-rays captured at the time of admission were evaluated by three cardiothoracic radiologists and three diagnostic radiology residents who scored the images based on extent and severity of COVID-19 pneumonia. In addition, they also collected information on demographics, clinical characteristics, as well as admission laboratory values and assessed the inter-rater reliability among attending providers, residents, and the combined group of readers.

Based on their analysis, inter-rater reliability for chest X-ray scoring was high among the attending, residents, and combination group (a 0.686 average). Their evaluation showed no difference in outcomes for gender, race, ethnicity, or among those who had lung cancer or chronic obstructive pulmonary disease histories.

The team did note that even though disease severity seen on chest X-ray was an independent predictor of death, it was a non-independent predictor of CRRT and intubation – but not extracorporeal membrane oxygenation.

These results, the team said, add to the existing knowledge base around the role chest X-ray can play in COVID-19 care.

“These findings are supported by prior work, validating the utility of [chest X-ray] for patient prognostication, while adding new insight into COVID-19 infection during the initial presentation,” they said.

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

Articles

In high pre-test probability and quick RT-PCR settings, chest X-ray scoring can be predictive. 

Chest X-ray Can Predict Outcomes for Patients With COVID-19

The push toward greater utilization of artificial intelligence in radiology (AI) shows no signs of slowing, so it would be a good idea to brush up on the legal aspects of using it, a group of industry experts said.

In an April 9 perspective article published in 

 legal and radiology experts from Harvard noted that the use of AI in diagnostic imaging is largely uncharted territory. Some risks to providers, practices, and technology developers have been identified, but more could be revealed over time.

To help you prepare, H. Benjamin Harvey, M.D., J.D., a neuroradiologist from Massachusetts General Hospital, and Vrushab Gowda, J.D., a Harvard Law School graduate who is also pursuing his medical degree from the University of North Carolina at Chapel Hill School of Medicine, discussed some specifics of the liabilities around AI use in musculoskeletal imaging.

These cases typically deal with medical malpractice, Harvey and Gowda said. While plaintiffs have the burden of showing four distinct occurrences of negligence, courts will also rely on professional society standards, as well as community practice and department protocols. Consequently, it is vital to create guidelines, complete sufficient user training, and correctly integration AI.

In addition, AI is extremely helpful, but if you rely on it alone – rather than using the tool and deciding to dismiss its findings and recommendations – your malpractice risk will be greater, they said.

When it comes to using AI with medical imaging, there are two main concerns, they said – do you let your patients know you’re using AI, and if you do, what do you need to tell them?

Given that AI is largely used for research investigations currently, this issue hasn’t crept up much. But, once the tools are implemented clinically, the story will be different, especially if the technology eventually becomes autonomous further downstream.

Ultimately, Harvey and Gowda said, proper handling of informed consent will likely require a patient-based or provider-based standard, and the difference between them can be unclear.

“The rub of the matter is that radiologists should be cognizant of their peers’ disclosures and anticipate the sorts of information patients would find important when deploying AI,” they said.

When mistakes happen, patients are going to look for someone to hold accountable, they said. If you’ve used an AI tool that results in a negative outcome, your hospital or radiology practice could end up as the defendant – not you.

This situation of “vicarious liability” can be sticky, they explained, because it puts your practice or facility leadership in the hot seat. Consequently, there is a need for clearly written protocols on how to handle these potential situations.

You aren’t the only one subjecting yourself to liability and risk when you use an AI tool. The developer also bears responsibility for when things go wrong, such as mislabeling findings or recommending a biopsy – or worse, not recommending one.

Under a strict liability framework, if a plaintiff can prove that the mistake is a result of a manufacturing problem – which could be tough to do – they could win their case. Conversely, negligence principles call for examining the features of the healthcare facility rather the product.

Either way, they said, radiologists need to be aware about these possibilities and stay current with what’s going on.

With a lack of clarity around liability and responsibility with the future use of artificial intelligence, Harvey and Gowda both said, as radiologists, you must make sure your voice is part of the discussion around developing stringent AI imaging standards.

“Looking forward, imaging departments should articulate clear protocols for their use, to include procedures in the event of human-AI discrepancy,” they said. “They can be aided by [American College of Radiology]- and [Society of Skeletal Radiology]-validated guidelines, training programs, and model practices for deploying AI technologies.”

Liability and responsibility concerns are not significant with AI use now, but as the tools enter clinical use, that will change. 



4 Must-Knows about Future Radiologist Liabilities with AI

Currently, radiology practices face several challenges, such as decreased utilization during COVID-19, payer reimbursement policy changes, and consumerization of healthcare. A decrease in utilization has led to a reduction in staffing levels while payer reimbursement changes, such as increased prior authorization requirements, have added more work to the revenue cycle staff.

A recent statistic shows a 300-percent increase in previous authorization denials. Also, consumerization has required practices to overhaul their patient financial experience. Now more than ever, practices are required to adopt technologies like artificial intelligence (AI), machine learning (ML), and consumer-centric workflows to enable digital transformation in their workforce and practice.

Due to consumer expectations, there is a continuous shift toward digitally guiding the patient's financial experience. This, coupled with growing patient responsibilities due to high deductible plans, requires a new level of resources and focused efforts. Additionally, the lack of integrated technology between billing and electronic health record systems adds another layer of complexity to the existing revenue cycle workflow.

Revenue Cycle Management for the Pandemic

As imaging and radiology organizations continue to face increasing challenges in the financial exchange and reimbursement landscape, they are left with two distinct choices of adding more resources or automating key processes. It is crucial to adopt critical technologies capable of boosting efficiency throughout the revenue cycle. This allows employees to focus their time on value-added activities while addressing the historical challenges listed above.

After a year of reduced revenues due to the coronavirus, organizations are re-examining their administrative procedures to optimize efficiency and accuracy. With innovations, such as robotic process automation (RPA) and ML, organizations can improve the bottom line while scaling resources to focus on complex, value-added activities. Automating portions of the revenue cycle management system to a digital platform creates an opportunity for imaging/radiology groups to streamline even the most complex end-to-end processes and functions, allowing them to recapture lost revenue.

For example, a radiology group facing an increase in account receivables (AR) may begin to explore initial steps to automate several repetitive or mundane tasks to gain the most significant efficiency for improvements to their bottom line. Apart from the increase in AR, the radiology group would also face an average of a seven-day delay-in-claim submission.

With the implementation of ML algorithms, the radiology group can recognize patterns and suggest predictive actions for optimal claim follow-up and denial resolution. Predictive denial modeling and reporting can be performed in advance of the payor’s response. These cases suggest the correct fix for the denials using the past learning and underpayment analysis for out-of-network claims. Combining innovations, such as RPA and ML, makes it possible to automate even the most complex end-to-end processes and functions.

Due to the implementation of technology across the revenue cycle processes, a radiology group can successfully reduce a more than 90 insurance AR from 40 percent to 15 percent, in turn reducing the days in AR from 49 to 25, which is well within the industry benchmarks. It can also increase the percentage of clean claim rates by more than 99 percent. Additionally, the radiology group could obtain transparency into the root causes of the delay-in-claim submission. With the implementation of technology, it improved the delay in submission from seven to four days.

While each group has its unique challenges, the approach of automation implementation is the same. The first step is to identify the most critical challenges and inefficient processes to address.

Conducting a workflow analysis is crucial to identify where automation can drive efficiencies. Once an analysis is complete, they should re-engineer the key processes and prioritize which workflows to automate based on the ease of implementation and return on investment. Many organizations make the mistake of attempting to automate current inefficient manual processes without re-engineering them or accurately evaluating the workflow.

An automation solution does not replace existing technology investments but rather supplements the shortcomings of core and ancillary systems. Automation for administrative functions offers a layer that helps organizations improve their productivity and focus on more value-added tasks while minimizing time and costs that arise from repetitive tasks. This, in turn, helps accelerate cash flows and improve operating margins.

Teri Gatchel-Schmidt, MBA, CPC, has more than 28 years of experience in the healthcare industry as a practice administrator, operational leader, and revenue cycle optimization consultant to large health systems and physician organizations. Over the past 18 years, she has worked extensively with healthcare systems to enhance their financial performance in academic and physician ambulatory-based settings. Her extensive hands-on knowledge of end-to-end revenue cycle processes gives her the ability to identify workflow redesign and overall performance improvement opportunities with an eye towards financial improvement and increased efficiency.

Automated solutions can improve productivity while minimizing time and cost.

Improve Capturing Revenue within Radiology Groups

Patients who have metastatic kidney cancer could benefit from undergoing baseline brain imaging, according to a recently published study.

Journal of the National Comprehensive Cancer Network

investigators from both Memorial Sloan Kettering (MSK) Cancer Center and Gustave Roussy Institute, a leading academic cancer center in France, showed that incidental brain metastases can occur in a clinically significant percentage of patients who have newly diagnosed metastatic renal cell carcinoma.

Consequently, they said, implementing brain imaging – even in asymptomatic patients – could positively impact overall survival rates.

For their study, they included 1,689 patients with metastatic renal cell carcinoma who had been considered to participate in a clinical trial at either facility between 2001 and 2019. These individuals had no clinical suspicion of brain involvement, but they had undergone brain CT or MRI.

When researchers evaluated the patients' scans, they found 72 patients (4.3 percent of the group) had asymptomatic brain metastases. Of that group, 22 were diagnosed via screening for first-line studies, and 50 via screening in the treatment-refractory setting. For those patients, the median 1-year overall survival rate was 48 percent, and the median overall survival was 10.3 months.

Brain imaging is routinely implemented for kidney cancer patients who show evidence of central nervous system involvement, but that is not the case for patients who are symptomatic, they said. Given these results, it could be useful to conduct brain imaging in this patient population.

“With 4 percent overall incidence in this cohort, one might conclude that baseline brain imaging should be considered in all patients with metastatic kidney cancer, particularly those with multi-organ involvement and/or pulmonary metastases,” said lead MSK researcher Ritesh R. Kotecha, M.D.

The team also identified other areas of cancer spread in patients who had brain involvement. At initial kidney cancer diagnosis, 43 patients (60 percent) had metastatic disease, but by the time of brain metastasis diagnosis, 62 patients (86 percent) had metastatic disease in two or more additional organ systems. The most common was lung (66 patients, 92 percent), followed by liver and bone (18 patients each, 25 percent).

“In current practice, chest, abdomen, and pelvis are routinely imaged from the time that metastatic disease is first detected, yet many oncologists do not image the brain,” said senior researcher Martin H. Voss, M.D., medical oncologist with MSK.

According to Eric Jonasch, M.D., professor of genitourinary medical oncology at The University of Texas MD Anderson Cancer Center, the findings of this study are important for two main reasons.

“First, they show that the overall prognosis of patients with brain metastases is consistently worse than the broader population of patients with metastatic renal cell carcinoma. We need to develop a deeper scientific understanding of why this patient population has a worse outcome, and we need to include them in future clinical trials,” said Jonasch, who is the vice chair of the NCCN Clinical Practice Guidelines in Oncology Panel for Kidney Cancer. “Second, they underscore the utility for MRI imaging of all patients with metastatic renal cell carcinoma both at initial diagnosis, and at regular intervals, to detect occult brain metastases, since specific treatment strategies are required for this patient population.”

The team did note that their study did not elucidate how frequently brain imaging in these patients should be repeated, pointing to the need for further study.

Study finds clinically significant percentage of patients with metastatic renal cell carcinoma develop asymptomatic brain metastases. 

Brain MRI and CT Could Identify Metastasis in Patients with Kidney Cancer

Low-dose CT (LDCT) isn’t just for lung cancer screening. Data gathered from the scans can also help predict a patient’s five-year risk of death from cardiovascular disease.

investigators from The Netherlands detailed how implementing a deep learning algorithm that is fueled with information captured during a low-dose CT exam for lung cancer screening can offer valuable details about calcification in the heart and the aorta.

Using LDCT in this way is a two-for-one opportunity to screen patients for both potentially deadly conditions. The scan is used to detect lung cancer in high-risk individuals, including heavy smokers, but for those individuals, cardiovascular disease actually surpasses lung cancer as the leading cause of death. By picking up these areas of calcification that are linked to plaque build-up, the scan can give providers a strong predictor of heart attacks, stroke, and mortality from cardiovascular disease.

Given the recent recommendation update from the U.S Preventive Services Task Force that opened up LDCT lung cancer screening to high-risk individuals ages 50-to-80 who have at least a 20-pack year smoking history, it is possible that providers will be able to pick up on cardiovascular disease mortality risk in an even wider population of patients, the team said.

In the past, data pulled from CT images has been used in conjunction with other risk factors, such as cholesterol levels, blood pressure, and self-reported history of illness. But, for this study, the team, led by Bob D. de Vos, Ph.D., from Amsterdam University Medical Center and the Image Sciences Institute at the University Medical Center Utrecht, drew upon deep learning to create an automated method that can quickly predict five-year cardiovascular disease mortality without putting a heavier work burden on providers.

“We have shown that five-year cardiovascular disease mortality can be predicted for lung screening participants in less than half a second, using only site-specific calcium scores automatically derived from lung screening low-dose CT,” the team said. “Hence, the proposed image-based analysis could aid in identification of lung screening participants at risk for cardiovascular disease mortality, without relying on self-reported participant data.”

Figure 2: Projections of all aligned chest CT scans show feasibility of slab-based quantification of calcium, resulting in an average image. For alignment, only translation, rotation, and scaling were allowed, resulting in a blurry image, because not all anatomy is exactly the same across participants. From left to right, the center axial, sagittal, and coronal sections are shown. Note that field of view is similar to cardiac CT, which is a consequence of image alignment by the used automatic calcium scoring method. Image alignment allowed the determination of calcification distributions into slabs as a proxy measure for proximal and distal calcifications, of which the borders are indicated by the horizontal lines.

For the study, they pulled data from LDCT scans conducted between August 2002 and April 2004 on 4,451 participants with an average age of 61 who were part of the National Lung Screening Trial. Using those details, the team trained their deep learning method to quantify six types of vascular calcification: thoracic aorta calcification (TAC), aortic and mitral valve calcification, coronary artery calcification (CAC) of the left main, the left anterior descending, and the right coronary artery. After training, they tested their method on data gleaned from 1,113 participants.

The team compared the methods with semi-automatic baseline prediction using self-reported participant characteristics, such as age, smoking history, and history of illness. According to their analysis, the prediction model using calcium scores performed better than the baseline model.

Specifically, the prediction model that used calcium scores reached a C statistic of 0.74 while the baseline model that relied on only participant characteristics achieved 0.69. The model had the best results, they said, when all variables were combined – a 0.76 C statistic.

“The analysis shows we found predictors that are typically not described in a literature, possibly because we performed analysis in lung cancer screening participants we are already at high risk of cardiovascular disease from a history of heaving smoking and the presence of extensive arterial calcification,” de Vos explained.

The method works in two stages, he said, first using deep learning to pinpoint the amount and location of arterial calcification in the coronary arteries and aorta. The second stage relies on a more conventional statistical approach to mortality prediction and identifies features that are most predictive of five-year mortality.

Incorporating the deep learning method into lung cancer screening would be simple, de Vos said, because it requires no special equipment and does not tack on any exam time. And, the benefits to providers and patients could be immense.

“The method uses only image information, it is fully automatic, and it is fast. The method obtains calcium scores in a complete chest CT in less than half a second. This means that the method should be easy to implement to routine patient work ups and screening,” he said. “Lung screening studies show that heavy smokers die from cardiovascular disease as much as from lung cancer. But, we also see that some people with very high calcium scores survive, while others with low scores do suffer from major cardiac events.”

Their results point to a need for additional research that can more specifically point to calcifications that are dangerous. To date, they have developed several automatic scoring methods that can use varied types of data, but they are continuing on with development. Now, de Vos said, they are concentrating on creating a calcium-scoring method that can use low-quality data, such as data affected by cardiac motion, low image resolution, and high noise level, to detect arterial calcification.

“We developed a method, for example, that can detect coronary calcification even when the lesions are below the clinically used threshold,” he said. “This way, we hope to increase the reproducibility of calcium scoring and enable more accurate prediction.”

But, for now, he said, their work has shown that it is possible to achieve real-time mortality prediction with lung screening chest CT by using only data from automatic deep learning-quantified arterial calcium.

A low-dose CT for lung cancer screening can also predict a five-year cardiovascular disease risk of death when using a deep learning algorithm.

Add Predicting Heart Disease Mortality Risk to LDCT Capabilities

Take a look at this CTA -- what's your diagnosis?

Focal narrowing of the descending aorta distal to the great vessels as visualized on this sagittal view of the aorta on CTA.

CTA and MRA can enable clear cross-sectional visualization of the aortic coarctation. One can also look for collateralization of vessels most commonly involving the subclavian artery to internal mammary artery to intercostal arteries and, then, to the aorta, distal to the coarctation. Rib notching can be seen. Treatment can surgical or balloon angioplasty.

What's the diagnosis for this image captured with CTA?

Image IQ Quiz: What's the Diagnosis for this CTA?

59-Year-Old Patient Presents with Abdominal Pain

Small bowel obstruction secondary to adhesions

Large bowel obstruction secondary to malignancy

- Complication of chronic cholecystitis with formation of cholecystoenteric fistula
- Gallstone passage through fistula, which ultimately becomes impacted within the small bowel (most commonly at ileocecal valve).
- Uncommon cause of small bowel obstruction

What is your diagnosis for this 59-year-old patient who presents with abdominal pain?

Image IQ Quiz: 59-Year-Old Patient Presents with Abdominal Pain

When it comes to breast cancer, imaging and preventive efforts go hand-in-hand. This year, through its Honorary Fellow Award, the Society of Breast Imaging recognized a provider who collaborates closely with imaging colleagues to bring the best level of care to women facing or receiving a breast cancer diagnosis.

Therese Bevers, M.D., is professor of clinical cancer prevention and medical director of the Cancer Prevention Center and prevention outreach programs at MD Anderson Cancer Center. In addition to overseeing the first comprehensive clinical cancer prevention service program that opened in 1996, she concentrates her efforts of breast cancer prevention, screening, and diagnosis.

For additional Society of Breast Imaging conference coverage, click 

 spoke with Bevers about what she sees as the main priorities in the fields surrounding breast cancer, as well as the main challenges that exist and what the future brings with imaging.

 How did you become interested in breast cancer prevention and screening? What was in your background or your education that led you to want that to be your focus?

Therese Bevers, M.D.
MD Anderson Cancer Center

 Interestingly, my background and my board certification is in family medicine. Prevention is a big component of primary care, and I eventually went into preventive medicine as a field of practice. Then, I was hired by MD Anderson to run the newly opened Cancer Prevention Center in 1996. That's when I really focused my career on cancer prevention, screening, and diagnosis. The natural area for me was breast cancer prevention and screening and diagnosis. I quickly became involved in the breast cancer prevention trial, which was the trial of tamoxifen versus placebo, that showed that tamoxifen reduced the risk of developing breast cancer by one-half. That just naturally led to expanding my career in the field of breast cancer prevention, screening, and diagnosis. I don't do any treatment – my background is primary care. Although, I have become a specialist in the field of preventive medicine and cancer diagnosis.

 What do you consider to be your most significant contributions to the field surrounding breast cancer?

 I think my biggest contribution has been in a leadership role largely through the National Comprehensive Cancer Network (NCCN), but through other entities, as well. That's my biggest area where I have led the breast cancer screening and diagnosis guideline panel that talks about how we should screen women at average and increased risk, and how we make the right diagnosis. Then, I also chaired the breast cancer risk reduction guideline panel, which talks about how to reduce a woman's risk of developing breast cancer, not only through tamoxifen and Raloxifene and aromatase inhibitors, but also through healthy lifestyle changes and for very high-risk women through prophylactic mastectomy.

I feel that my biggest contribution has been through that arena because I feel that as far as breast cancer risk reduction, I have helped to lead practice-changing guidelines there in the field of breast cancer screening. I, along with SBI and the American College of Radiology, have really endorsed, strongly supported, and being very vocal about the importance of beginning annual mammograms at age 40. The U.S. Preventive Services Task Force really recommends biennial or every other year mammograms beginning at age 50. I think if COVID-19 does nothing else, it shows us the error of going to every other year. Many women have not gotten their screening during COVID-19. So, some of their intervals have stretched out two years, and we are seeing more advanced diagnosis of breast cancer. I feel very strongly that the data supports getting an annual mammogram beginning at age 40.

So, the SBI and ACR are very vocal about that, along with my co-chair of the NCCN panel. Having said that, I would like to note that I think it is the members, many members of SBI, who have really taught me all that I know about screening mammography and the data supporting annual beginning at age 40.

What are the most significant challenges you see facing efforts for breast cancer prevention, screening, and detection?

 For screening, it's that there are a number of different recommendations out there that just simply confuse women. Women don't know what to do, and when you don't know what to do, many people take the action of not doing anything. That concerns me, and I wish that we had a more unified voice for breast cancer screening, unfortunately, we don't.

I am very blessed in the institution that I work in that I get to work literally across the hallway from our breast imagers. I get to have daily one-on-one interactions with them about the symptoms a woman presents with the clinical findings that I identify and what their imaging findings are. We get to approach it collaboratively. Unfortunately, in the real world, out in the community, that doesn't get to happen often. That’s the biggest challenges for many clinicians who are trying to do the best that they can for women in making appropriate recommendations and making an accurate diagnosis. They just don't have that one-on-one collaboration with their breast imager.

What do you see as the main priorities in the field today or 5-to-10 years out?

Looking at new ways of screening for breast cancer, we have seen huge advances. I remember when I started at MD Anderson, there was a huge film library dedicated just to mammograms and breast imaging studies. Now, that film library has gone to the wayside and we have digital images. We now have expanded into tomosynthesis – in street lingo called 3D mammography – where we're actually getting images of the breast in slices like a CT scan would do. One other modality that has come since I started practicing 25 years ago is being able to offer women breast MRI if they're at high risk of developing breast cancer. That wasn't something we offered when I started in the field in 1996. But, now, it's codified in the NCCN and American Cancer Society recommendations for women at increased risk of breast cancer.

We’ve already made great strides that helped us to improve imaging. But, there are so many new modalities out there that are coming down the pipe. Areas I think that we will see continue to grow, at least in the field of imaging, would be contrast enhanced mammography where not only do we get the images, but we get functional information if contrast is injected. Is there a role for molecular breast imaging in screening? Maybe, maybe not. It has a higher dose of radiation. So, that's a bit of a concern. Certainly, it is an opportunity in the diagnosis of breast cancer because it gives functional information, especially for women that can't do MRI whether due to claustrophobia or body habitus. we're seeing more and more imaging modalities.

There's a lot of interest in identifying the Holy Grail of tumor markers in the blood that would identify women at risk for developing breast cancer or women that actually have breast cancer. If we had a tumor marker in the blood or saliva or whatever body fluid that we use, that allows us to move away from mobile mammography vans and brick-and-mortar buildings out to maybe a mall or a health fair where we could draw blood or get the saliva specimen. Then, we could circle back to that woman and say, “Hey, you're okay,” or the next woman and say, “We're a little concerned with what we saw. We need to get you in now for the imaging and do a workup to see if there is actually something going on.”

For you, in your career, what’s on the horizon? What is your next endeavor or area of focus?

I intend to continue with NCCN and leading those two guideline panels. I think there's a lot of opportunity. I have seen our NCCN and breast cancer screening and diagnosis guideline panel grow from a few pages to now close to 30 pages, We encompass not just the straightforward screening of average risk women and the diagnosis of just breast masses and nipple discharge, etc., but to encompassing more rare conditions like anaplastic large cell lymphoma (LCL), breast implant associated LCL, as well as breast cancer in men and breast pain imaging in the pregnant and lactating woman. That’s a big interest for me – being able to take what experts know and what the data has shown and being able to put it in a recommendation or a guideline such that community physicians can easily access it and say, “Ah, I should do that. I didn't think of that.”

MD Anderson Cancer Center medical director shares her thoughts the priorities and challenges facing breast cancer detection and screening.

For SBI Awardee: Face-to-Face Collaborations, a Challenge; New Modalities, Exciting Possibilities

Lung cancer remains the leading cause of cancer death in the United States, with more than half of all cases (57 percent) being diagnosed at a late stage with an average five-year survival rate of 22.6 percent

 However, there are signs of progress, with the rate of new cases going down 9 percent nationally and an increase in the five-year survival rate by 13.1 percent over the past five years

. This is likely due to reduced smoking rates, increased radon testing, more stringent air pollution regulations, and improvements in treatment

. However, the implementation of lung cancer screening to detect the deadly disease at an earlier stage has undoubtedly played a role in these gains, as well.

In 2011, the National Lung Screening Trial reported a 20-percent relative reduction in lung cancer amongst adults who smoked heavily and received low-dose CT (LDCT) annual screening compared to those who received annual chest radiographs

. Based on this evidence, the United States Preventive Services Task Force recommended annual lung cancer screening (LCS) with LDCT for high-risk adults (defined as 55-to-80-year-old persons who have a 30-plus pack year smoking history and quit less than 15 years ago).

Insurance companies and Medicare/Medicaid began to cover LCS in 2014-2015. Despite these guidelines and financial reimbursement, patient and physician uptake to the guideline has been slow. Less than 4 percent of eligible adults received screenings in 2015, and that figure had a marginal increase to 5.7 percent in 2020

. However even with the lagging adoption, early diagnosis rates have increased 33 percent over the past five years

. Of all cases, 23 percent are caught at an early stage, which has a much higher five-year survival rate at 59 percent

Why have the rates for LCS with LDCT remained low? There are many potential factors at play, such as healthcare providers not collecting a sufficiently detailed smoking history to identify eligible patients, smokers being a demographic with a predisposition to have less contact with primary care providers (PCP), PCPs not recommending screening due to lack of time and other priorities, lack of insurance incentivization, high rate of false positives on LDCT, perhaps even the perception that smoking is a lifestyle choice and that resources should not be spent on this population.

Cancer Screening Challenges in the Face of COVID-19

As for the argument of the unacceptable number of false positives, there is, indeed, a 20-percent rate of over-diagnosis of lung cancer, which is consistent with the rate of over-diagnosis in breast cancer

. However, it also prevents one death for every 250 screens, which far exceeds the number needed to treat (NNT) of 2,000 for screening mammography

. According to one meta-analysis of annual LCS with LDCT, all-cause mortality was not reduced in a significant manner, which is reassuring that the increased amount of screening and over-diagnosis of lung cancer did not increase other causes of mortality

What can we do to increase adherence to this useful screening tool? Many possible obstacles can be targeted, such as using clinical navigators to assist patients in following up appropriately, implementing algorithms to better identify eligible patients by using existing electronic health care data. There are two reports that attempted to increase it in two different manners, one more clinically, one involving more of the community.

In the first scenario, within the Kaiser Northern California system, they implemented a reporting system in 2015 that standardized radiology reports of pulmonary findings with tags. Tags that were indicative of lung cancer were automatically forwarded to a coordinator who sent a list of cases to a triage physician. The physician, then, either sent the case to a multidisciplinary committee or the patient's primary care physician (PCP) with management recommendations.

For additional columns by Mina Makary, M.D., click

The committee was composed of a care coordinator, pulmonologist, thoracic surgeon, and often a radiologist and oncologist, and the group met weekly to discuss cases. They would, then, either manage the case or send recommendations to the PCP. From the data that was collected pre- and post-implementation from nearly 100,000 patients, they found that lung cancer was detected at the early stage 26 percent of the time pre-intervention, and 30 percent of the time post-intervention. 

The intervention was associated with a 24-percent increase in odds of early-stage lung cancer diagnosis within 120 days, with a quicker time to surgical intervention (46 days vs 41 days) without biopsies. It appears that standardization of the radiologic reporting coupled with the multi-disciplinary committee increased the rate of detection of early-stage cancer which ultimately leads to improved long-term outcomes

The other instance is the state Kentucky which has one of the highest LCS rates in the country. Kentucky has expanded the Medicaid program, which removes the need for preauthorization for LCS. The government supports the cause with the governor publicly committing to reduce lung cancer mortality. In 2013, the Kentucky Lung Cancer Education Awareness Detection Survivorship Collaborative was created and implemented two LCS projects.

The first one educated hundreds of PCPs on lung cancer prevention, early detection, treatment, and survivorship. The second project gave feedback to LCS programs on how to best deliver screening and engage healthcare providers. Due to this combined effort from the community with government support, Kentucky has the third highest screening rate in the nation, leading to more lung cancer survivors. They have provided a framework for other states with high lung cancer burdens to follow

As evidence continues to grow that LDCT is an effective tool at increasing lung cancer survivorship – and awareness increases amongst the public – LCS rates will likely increase in the following years. However, there is still much work to be done to achieve the rates that would benefit the most vulnerable populations. 

As demonstrated by these two cases, there are issues that can be improved at every level of the system – educating patients about the benefits of annual LDCT, promoting the value of LCS to PCPs, standardization of lung cancer findings and templates within an electronic medical record, improved coordination of care, and further research into how to refine screening populations and screening modalities. With widespread adoption by healthcare providers, this intervention will surely improve both the longevity and quality-of-life for increased numbers of at-risk individuals who receive the diagnosis of lung cancer.

State of Lung Cancer 2020 Report (Rep.). (2020, November 17). Retrieved https://www.lung.org/getmedia/381ca407-a4e9-4069-b24b-195811f29a00/solc-2020-report-final.pdf

Stacey A Fedewa, PhD, Ella A Kazerooni, MD, MS, Jamie L Studts, PhD, Robert A Smith, PhD, Priti Bandi, PhD, Ann Goding Sauer, MSPH, Megan Cotter, MPH, Helmneh M Sineshaw, MD, MPH, Ahmedin Jemal, DVM, PhD, Gerard A Silvestri, MD, MS, State Variation in Low-Dose Computed Tomography Scanning for Lung Cancer Screening in the United States, JNCI: Journal of the National Cancer Institute, 2020;, djaa170, https://doi.org/10.1093/jnci/djaa170

Urbania, T. H., Dusendang, J. R., Herrinton, L. J., Alexeeff, S., Corley, D. A., Ely, S., . . . Sakoda, L. C. (2020). Standardized reporting and management of suspicious findings on chest ct imaging is associated with improved lung cancer diagnosis in an observational study. Chest, 158(5), 2211-2220. doi:10.1016/j.chest.2020.05.595

Gøtzsche, P. C., & Nielsen, M. (2006). Screening for breast cancer with mammography. The Cochrane database of systematic reviews, (4), CD001877. https://doi.org/10.1002/14651858.CD001877.pub2

Ebell, M. H., Bentivegna, M., &amp; Hulme, C. (2020). Cancer-Specific mortality, all-cause mortality, and overdiagnosis in lung cancer Screening Trials: A meta-analysis. The Annals of Family Medicine, 18(6), 545-552. doi:10.1370/afm.2582

Two interventions to increase lung cancer screening rates from the clinical and community perspectives. 

Lung Cancer Screening: Challenges and Opportunities

The days of relying on the radiology report to be your main communication with patients are gone. As the push for radiologists to become more active members of the patient care team continues to gain strength, its incumbent upon you and your trainees to learn how to effectively communicate with your referring providers, as well as patients.

a five-member team of experts laid out several tips for improving your communication skills – techniques that can benefit you as the healthcare climate tips further to value-based care.

“Communication requires the formulation of a message which is then shared with, and ultimately interpreted by, the receiving party. Importantly, absent or ineffective communication can lead to wasted time, increased healthcare expenditures, increased patient anxiety, and patient harm,” said the team led by Judah Burns, M.D., director of the diagnostic residency program at Montefiore Medical Center. “Effective communication, on the other hand, has been shown to improve health outcomes.”

But, despite efforts from the American Board of Radiology, the American College of Radiology (ACR), and the Accreditation Council for Graduate Medical Education, radiology residents are not getting the communication guidance they need, the team said.

To help trainees – and practicing providers – communicate better with patients, the team offered several suggestions:

Keep your reports clear and concise, using clinically relevant information. For example, if you don’t see anything alarming, say the results are “normal” rather than “unremarkable.” Structured reports, disease-specific reports, and templates can help clarify any uncertainty.

“From a patient’s perspective, conclusions and summary recommendations are the most impactful and notable sections of the written report,” they said. “These portions of the report should be most carefully considered to avoid simple repetition of findings, and to make reports actionable and understandable.”

Radiologists are often thought of as being removed from or not as invested in a patient’s care. To dispel that thought, include patient-specific information that shows you are an integrated member of the healthcare team. Remember to be respectful and non-judgmental in your tone when discussing sensitive topics, such as alcohol use or body habitus.

Using these templates can help trainees better learn how to organize their patient communications, giving patients easily understandable, organ-specific information that can help guide their future healthcare decisions. It can also help them develop greater clarity in their communications.

“Communicating uncertainty in radiological imaging is a critical reporting element,” the team said. “Clarifying the nature and extent of potential uncertainty allows physicians and patients to understand the degree of confidence and conveys diagnostic certainty in clinical decision-making.”

When possible, use pictures, tables, graphs, and images with hyperlinks to help illustrate findings.

“From the patient’s perspective, enhanced reporting is akin to story-telling. In many cases, a picture is more visually descriptive or impactful than a detailed or nuanced narrative,” they said. “The radiologist must aim to communicate important findings using written and illustrative tools in a manner that is precise, impactful, and relatable, maintaining focus on using those tools that help to best convey and contextualize imaging results.”

Communication Critical to Providers Adhering to Follow-Up Recommendations

Patient portals are growing in popularity with the number of patients using them rising from 35 percent in 2006 to 51 percent in 2016. But, giving patients direct access to images is still somewhat controversial as it can lead to confusion. It could be possible to mitigate this problem by including a summary statement in the report that provide context, such as letting a patient know that while images are available immediately, the care team needs time to interpret the results and will contact them for a discussion. If you choose, you can also include your contact information, as well as information for web consultations.

Participating in clinical imaging rounds or embedding reading rooms in clinical areas are two good ways to bolster the amount of face-to-face time radiologist trainees have to perfect their oral communication skills. In addition, attending multi-disciplinary meetings or participating in virtual consults can also be helpful. It would also be a good idea to increase training in telehealth consultations.

Encourage your trainees to make eye contact, nod their heads, and gesture – it’s a way to deepen the discussion and show patients that their radiologist is actively engaged.

“Particularly in brief interactions, such as those commonly occurring during radiologist consultations, the opportunity to establish and maintain relationships is limited,” the team said. “Effective non-verbal communication can decrease patient anxiety, reinforce patient discussions, and improve patient accordance with medication and follow-up recommendations.”

 Approach these situations carefully. Don’t use jargon – instead, focus on using simple terms. Be sure to be an active listener, and choose a supporting environment and atmosphere for relaying bad news.

By actively engaging in more patient interactions, the team said, radiology residents have more opportunities to identify barriers to care and existing health disparities. It provides them with the knowledge needed to combat any potential internal biases. Mastering these skills is critical, the team said, for trainees to be able to offer the highest level of care possible.

“Radiology trainees must gain skills in all forms of communication to fully engage with their patients,” they concluded. “Residency and fellowship programs and teaching faculty must model effective, professional communication in all forms and seek constant improvements in the work and clinical learning environments.”

Clear communication with referring providers and patients is critical. Following these steps can help.

8 Tips to Improve Radiologist Communication

MRI has grown in popularity as a tool to image the brain for various diseases or damage, leading to a heavy volume of scans for radiologists to interpret. Using an artificial intelligence (AI)-based system could help automate those interpretations to quickly identify the patients who need the most emergent care.

“MRI is increasingly used clinically for the detection and diagnosis of abnormalities. The resulting image overload presents an urgent need for improved radiologic workflow,” said a team of investigators from Massachusetts General Hospital (MGH) and Brigham and Women’s Hospital Center for Clinical Data Science. “Automatically identifying abnormal findings in medical images could improve the way worklists are prioritized, enabling improved patient care and accelerated patient discharge.”

The team, co-led by Romane Gauriau, Ph.D., former machine learning scientist from MGH, and Bernardo C. Bizzo, M.D., Ph.D., an MGH radiologist, published their findings Wednesday in 

 Their efforts resulted in a triaging system for brain MRIs that can detect multiple abnormalities from 3D volumetric imaging using a convolutional neural network and categorize the findings as “likely normal” and “likely abnormal.”

This is the first investigation to use a large, clinically relevant dataset and full-volume MRI data to identify overall brain abnormalities, they said.

Examples of axial FLAIR sequences from studies within dataset A. From left

to right: a patient with a ‘likely normal’ brain; a patient presenting an intraparenchymal

hemorrhage within the right temporal lobe; a patient presenting an acute infarct of the

inferior division of the right middle cerebral artery; and a patient with known

neurocysticercosis presenting a rounded cystic lesion in the left middle frontal gyrus.

For their retrospective study, the team used three large datasets that included more than 9,000 brain MRI scans culled from various institutions across two continents. They randomly split these datasets into training, validation, and test sets. All images were annotated by four radiologists who collated the studies into 10 categories: likely normal, almost normal, neoplasm, hemorrhage, infarct, infection or inflammatory disease, demyelination disease, vascular lesions, congenital, and other. In addition, FLAIR sequences were reviewed and categorized as “likely normal” and “likely abnormal.”

Based on their preliminary results, the team said, the model demonstrated relatively good performance in its ability to distinguish between “likely normal” and “likely abnormal” exams. Specifically, model A, trained on a dataset of axial FLAIR sequence exams conducted on adults and tested on a similar dataset that also included children, reached an F1-score of 0.72 and an area under the curve of 0.78 when compared with radiologic reports.

“Our experiments reveal reasonable performance for triaging purposes of a neural network for classification of likely normal or abnormal brain MRIs based on axial FLAIR sequences,” the team said. “Such a system could enable the creation of a ‘likely abnormal’ worklist which could be used to improve radiology workflow.”

With such a tool, they said, experienced radiologists and neuroradiologists could concentrate on the scans that were more urgent and time-consuming, and trainees and junior attendings could use it as a learning opportunity.

Their results also pointed to the generalizability of the model. They tested it on a validation set that was acquired during a different time period from a different institution than the data used the train the algorithm.

“The problem we are trying to tackle is very, very complex because there are a huge variety of abnormalities on MRI,” Gauriau said. “We showed that this model is promising enough to start evaluating if it can be used in a clinical environment.”

Like similar models that have been used to pinpoint abnormalities with CT scans and chest X-rays, this model has the potential to significantly improve turnaround time, as well as identifying incidental findings in outpatient settings.

“Say you fell and hit your head, then went to the hospital and they ordered a brain MRI,” she said. “This algorithm could detect if you have brain injury from the fall, but it may also detect an unexpected finding, such as a brain tumor. Having the ability could really help improve patient care.”

These findings point to the need for continued work, the team said. The next steps involve evaluating the model’s clinical utility and potential value for radiologist. Ultimately, they said, they wanted to be able further develop the model to provide the binary outputs “likely normal” and “likely abnormal.”

Using a model trained on three data sets could lead to automated categorization of “likely normal” and “likely abnormal” brain MRI results.

Triage Brain MRIs with AI-Based System

Case submitted by Elie Goulding, M.D., via

 Large partially thrombosed pseudoaneurysm is identified in the region of graft and surgery related to CABG along ascending aorta.

 Pseudoaneurysms can arise proximally or distally along grafts most commonly at the anastomotic sites. CTA can evaluate extent of any partial thrombosis. If there is continued increase in size or if it is large enough, it would require surgical correction. 

Pseudoaneurysms are associated with infection or leak. Coil occlusion or covered stents are common interventions to treat, as well, especially in high-risk patients.

What is this seen post bypass surgery along the aorta?

Image IQ Quiz: What's the Diagnosis of Post-Bypass CTA?

Leaving residency and starting your radiology career is stressful enough. Add in the need to protect yourself from unexpected or hidden perils, and the angst factor only rises.

In a session during the American Roentgen Ray Society (ARRS) 2021 Virtual Annual meeting, Sherwin Chan, M.D., Ph.D., associate professor and vice chair of radiology research at Children’s Mercy Hospital in Kansas City, discussed the types of insurance residents and attending providers should consider to best protect their financial stability.

For more ARRS 2021 Virtual Annual Meeting conference coverage, click 

“We really get insurance for black swan events. We get insurance because if this certain low-probability thing happens to us, it would be catastrophic and would really mess up our financial lives,” he said. “But, how do you decide what you want to insure? It comes down to a risk-versus-cost ratio.”

Overall, he said, you need to concentrate on four types of insurance: malpractice, life, disability, and umbrella.

Mistakes do happen, so carrying malpractice insurance is a must, Chan said. Both current malpractice and claims-made malpractice insurance offer you protection, but they differ based upon your time of employment.

Current malpractice insurance will cover you if a claim is brought against you for an error made during the time you worked at a facility even if you no longer work there. Claims-made malpractice policies will not cover you if you are no longer employed at the institution – if a suit is filed after you leave, you bear responsibility alone.

To successfully protect yourself from unforeseen circumstances, insurance – malpractice, life, disability, and umbrella – is vital.

