Diagnostic Imaging brings you daily coverage of SIIM 2021 virtual annual meeting.

SIIM 2021 Virtual Annual Meeting: May 24 - 27, 2021

Assessing left atrium parameters through cardiac CTA before transcatheter aortic valve replacement may predict mortality in patients with severe aortic stenosis, a recent study found.

, included 175 patients with severe aortic stenosis who underwent cardiac CTA before transcatheter aortic valve replacement (TAVR). Reduced left atrium emptying fraction (LAEF) was associated with an increased risk of mortality within 24 months after TAVR.

“The CT scan performed routinely before every TAVR could be used more extensively than it is currently,” Gilberto Aquino, MD, of the Medical University of South Carolina told Diagnostic Imaging. “By extensively assessing a structure that is already included in the scan, such as the left atrium, we could improve pre-TAVR risk stratification and post-TAVR monitoring without added patient radiation exposure.”

The median age of study participants was 79 and 52.6% were men. Within 24 months after TAVR, 38 patients (21.7%) died. Investigators calculated maximum left atrium volumes (LAVImax) and minimum left atrium volumes (LAVImin). LAEF was automatically calculated. Cox regression was performed to determine which parameters were predictive of mortality.

Clinically, increased LAVImax and LAVImin and decreased LAEF -- most commonly assessed using transthoracic echocardiography -- are associated with a higher risk for heart failure, atrial fibrillation and stroke, the authors noted.

In univariable analysis, all three parameters were predictive of mortality. But only LAEF independently predicted mortality after adjusting for clinical parameters (hazard ratio 0.97 [0.94-0.99]; p=.02).

“We were surprised to find that only left atrial function, represented by left atrial emptying fraction (LAEF) in our study, was independently associated with mortality after TAVR, while volume parameters such as maximum and minimum left atrial volumes were not independently associated when adjusted for confounders,” Aquino said. “However, considering that our patient population had severe aortic stenosis, their baseline volumes might have been chronically increased at baseline, and thus, only functional impairment was able to effectively differentiate those at higher or lower risk for mortality after TAVR.”

The study evaluated left atrium parameters using predictive clinical variables and the Society of Thoracic Surgeons Predicted Risk for Mortality (STS-PROM). Adding the parameters to STS-PROM improved the ability of the model to predict mortality.

“The increasing popularity of TAVR should be met with improved risk stratification and post-treatment surveillance, and using a readily available CT scan beyond its typical use for valve sizing and peripheral access route evaluation could provide more information than is currently used in clinical practice,” Aquino said.

Limitations of the study include the limited temporal resolution of cardiac CTA-derived left atrium parameters. The advanced age of the participants also may have resulted in other causes of death confounding the assessment.

Ongoing advances in artificial intelligence-assisted assessment are anticipated.

“Ultimately, with the increasing frequency of TAVR, the goal is to maximize the use of imaging to improve pre-TAVR risk stratification by assessing multiple structures, such as the cardiac chambers, coronary arteries, pulmonary artery, muscle mass, and epicardial, subcutaneous and visceral fat,” Aquino said. “This could allow the creation of a comprehensive CT risk score for TAVR that would help determine which patients require closer monitoring.”

Articles

Cardiac CTA before transcatheter aortic valve replacement can be used to better determine risk by assessing left atrium functional parameters that are predictive of mortality.

Using Cardiac CTA Before TAVR to Assess Left Atrium Parameters May Predict Mortality

A couple Thursdays ago, I got an early-morning call from my radgroup: Don’t bother trying to log in for work, that day or indeed the next few. A nasty bit of hacking had occurred, and taken their entire computer-system down.

Working via teleradiology since 2011, and in facilities large and small before that, I’m no stranger to outages. Sometimes they’re a welcome break…especially if you’re salaried and getting paid the same whether you’re working all day or twiddling your thumbs. Not as much if you know that imaging-cases are still accumulating, and you’ll be frantically trying to catch up when your access to them is restored. 

 not if you’re “per click,” earning zippity-doo-dah while your employer pulls itself together.

Unlike other outages I’d seen, this one wasn’t over in a matter of hours, or even a couple of days. I still don’t know all the details; one of the other telerads theorized that it was on the level of ransomware/cyberterrorism, such that Federal entities were involved. Everything was down, even the group’s websites and email systems, and there was nary a guesstimate as to when we’d be back on our feet.

So far beyond the realm of anything that might have been planned for, this was tantamount to a “black swan” event for the group. I’ve referenced the term in this column before, and there’s a worthwhile book on the subject (“The Black Swan: The Impact of the Highly Improbable,” by Nassim Nicholas Taleb). I won’t rehash it here.

Just because you can’t predict such things, doesn’t mean you won’t have to deal with them if they happen. And even though you can’t thoroughly plan for the unknown (or it would be prohibitively costly to protect yourself against everything that’s less than 0.001% likely to ever occur), there are some things that can make you more resilient for when it comes busting down your door.

Developing and maintaining plans for more probable/predictable incidents is a good start. Some components of those plans might be useful when a “black swan” turns up. For instance, a contingency strategy dealing with more typical, briefer outages might provide a framework for when hackers hold your system hostage or terrorists detonate an EMP in the area. It’s a lot easier to modify a partially-relevant plan for your current situation than to create one from scratch.

Even if none of the plans you’ve formulated can be adapted, devising them in the first place has you in a better place than if you hadn’t. You (and, hopefully, your team) have already gone through the exercise of thinking about the various components that make your operation work, and what happens if one or more of them are taken out. What it might take to function in their absence, if any substitutes can be used, who to call for repairs/replacements, etc. The basic process of methodically sizing up a bad situation will come a lot more readily to you if you’re done it before.

Still, by its very nature a “black swan” event isn’t tidily handled by preparation. The best means of dealing with it is being ready to take, and roll with, its punches. Rather than panicking and going to pieces, you take stock of your troubles and what’s still intact. Then, you have an idea of what stands between your current situation and normalcy, and can start figuring how to get from hither to yon.

Facets of this need not be complex puzzles or massive undertakings. For instance, my radgroup’s usual means of communication (email and instant-message app) were down. Reestablishing contact began with simple phone-calls, followed by external email accounts. Those wanting to keep personal e-ddresses out of the mix simply created new Gmails for the purpose. Group-messages could then be used to relay marching orders and share updates as new information became available (also for offsite rads like myself to post questions).

Another important aspect of being able to roll with the punches is having flexibility and redundancy in your setup. If, under even the best of circumstances, your operation is stretched to its limit or liable to unravel if one tiny component falls out of place, it won’t take a black swan to create havoc…but such an event will be all the more devastating when it happens.

More robust by far is an organization whose members’ roles overlap. If one or more are taken out of commission for any reason (illness, equipment failure, whatever), others might have to stretch in compensation but the net is more capable of holding the burden than tearing under it. And if members of the team are used to having Operations “call an audible” to redirect their efforts when circumstances warrant, they’ll be that much more capable of shifting focus in times of crisis.

Individual members of the team can also make themselves more resilient for when black swans come a-calling. In a lot of ways, similar to the organizational-level stuff: Don’t panic, be ready to adapt as situations arise, etc. That’s especially important for per-click rads who might be facing a sudden cutoff of income for the duration of an outage. Having emergency funds in reserve, for instance, instead of living paycheck-to-paycheck. Some might even maintain separate sources of income, such as contacts with locums agencies.

Simply keeping an adaptive frame of mind can go a long way: Sure, it might be worrisome when your employer is down for the count and you don’t know when they’ll be back up. Maybe you nervously eyeball job-listings, just in case…but, in the meantime, you’ve suddenly got an unexpected bit of vacation. Even if it’s unpaid, try to make use and/or enjoyment of it. Sleep in, jumpstart your fitness regimen, get that stuff done around the house you’ve been putting off, meet up with some friends you haven’t seen.

That visit from the black swan, played the right way, might ultimately turn out to be something you look back on and realize you desperately needed.

Even though you can’t thoroughly plan for the unknown, there are some things that can make you more resilient for when it comes busting down your door.

Things Unforeseen

Dr. Gruen is the chief medical officer of IBM Watson Health Imaging.

If only we were as good at prevention and early detection as we are at treating complex disease in U.S. healthcare. Generally, people know what they should do, and in some cases, they do it. For example, many patients religiously go to the dentist for a cleaning every six months to prevent cavities. 

But screening women with consistent mammograms beginning at age 40 to detect breast cancer?

 Not so much. Just imagine how many lives we could save if we looked for breast cancer with the rigor and diligence with which we prevent tooth decay.

An Ounce of Prevention: Weighing Evidence and Personal Risk Factors

Unfortunately, when it comes to breast cancer screening recommendations,

 there are multiple sets of guidelines, many of them different. Conflicting recommendations can breed confusion and, far worse, can potentially threaten lives. One study estimated that if women followed less stringent recommendations and started screening at age 50 (instead of 40), and women aged 50-74 only screened every other year (instead of annually), it could result in about 6,500 more deaths from breast cancer every year in the United States.

To further complicate matters, even the best evidence-based guidelines may not be the best approach for every patient. All patients need to make sure their complete history is part of their healthcare decision making, and that is particularly important for breast cancer patients. Each woman has a unique personal and family history which may impact her risk of getting breast cancer. There are many factors that women and their physicians should consider when determining the best approach to breast cancer screening, such as personal health history, family history, genetic profile and hormonal considerations, among many others.

Doctors don’t know their patients as well as patients know themselves. For example, who in the family has had cancer, especially breast, ovarian or cancer of the gastrointestinal tract? Has the patient ever had a breast biopsy that showed abnormal cells, or prior cancer? At what age did she have her first period? Go through menopause? How many pregnancies? How dense is the patient’s breast tissue? Women and their doctors must work through these issues together to pursue more effective prevention.

Where Artificial Intelligence (AI) Can Help With Breast Cancer Prevention Efforts

As a breast radiologist, I believe one of the keys to better outcomes will be a more personalized level of risk assessment for every patient. AI can help deliver this personalization. For example, women with the densest breast tissue have a higher risk of breast cancer.

 These women may benefit from more extensive screenings, such as ultrasound or breast MRI. AI can help conduct density assessments to identify higher-risk patients.

In addition to density assessment, AI can enhance breast cancer detection by helping clinicians identify abnormalities on a mammogram, including a 3D (tomosynthesis) mammogram, that might be overlooked by even the most experienced radiologist. 

There is some promising research around applying data and AI to identifying breast cancer. An IBM research team analyzed de-identified mammography images, linked to comprehensive clinical data and biomarkers, to create a new algorithm designed to predict breast cancer.

 The combined machine- and deep-learning model correctly predicted the development of breast cancer in 87 percent of the cases it analyzed – an accuracy comparable to radiologists.

There are many exciting possibilities that could result from this type of research. For example, this may be the first study to incorporate both mammograms and electronic health record data for the prediction of breast cancer, which shows the potential of one day harnessing multiple data sets and AI algorithms to tailor risk assessment to each patient. The research team 

 analyzing clinical risk elements to better understand their relationship to an individual’s personalized risk.

To be clear, AI will never replace the radiologist. Another large-scale IBM Research study found that no single AI algorithm could outperform radiologists, but the combination of AI with radiologist assessment improved overall accuracy.

And no matter how good the technology gets, there will never be a replacement for good, patient-centered care. I encourage women to know their risk and talk to their doctors about breast cancer screenings. I’d like to see all patients do for the rest of our bodies what we so willingly do to prevent dental disease. The benefits to our lives can be dramatic.

This article does not provide medical advice. For information on the benefits of breast cancer screening starting at age 40, visit the 

For a more detailed discussion of differences between recommendations, see 

“Clearing up confusion over breast cancer screening recommendations”

Hendrick and Helvie, “United States Preventive Services Task Force Screening Mammography Recommendations: Science Ignored.” 

 2011;196: W112-W116. 10.2214/AJR.10.5609

Source: NIH National Cancer Institute. https://www.cancer.gov/types/breast/breast-changes/dense-breasts

Akselrod-Ballin A, Chorev M, Shoshan Y, et al. Predicting breast cancer by applying deep learning to linked health records and mammograms. 

Schaffter T, Buist DSM, Lee CI, et al. Evaluation of combined artificial intelligence and radiologist assessment to interpret screening mammograms. 

Artificial intelligence can help seek out and identify high-risk patients who might benefit from more extensive screening. 

Personalizing Breast Cancer Risk Assessment 

Rob Fabrizio is Director of Strategic Marketing, Diagnostic Imaging, FUJIFILM Healthcare Americas Corporation

There’s a new epidemic out there and it’s a pesky problem on every professional athletic field, court and course: Sports injuries.

After months of relative inactivity during the COVID-19 pandemic, professional athletes are finding their bodies are being tested more than before. With gyms and even parks closed for everyone, resuming competitive sports after a lockdown is taking an unexpected toll on pro athletes—with sports injuries on the rise in virtually every league.

Consider America’s favorite pastime, baseball. Recently, while fans were singing “take me out to the ballgame,” athletes were literally being taken out of the ballgame! 

 from Major League Baseball found that in the abbreviated 2020 season, the overall injury incidence rate per 1000 athlete-exposures was almost twice the rate compared with the two seasons—2018 and 2019—before COVID-19.

Professional football didn’t fare much better. According to a 

 the rate of injury in NFL players during weeks 1-4 of the 2020-2021 regular seasons was significantly higher than during three recent past NFL preseasons and regular seasons.

And, for the 2020-2021 season, professional hoops may as well have been known as professional hurts. Numerous NBA stars have missed playoff games this past spring with a variety of impeding injuries. There were 

 lost to soft-tissue injuries, according to certified athletic trainer Jeff Stotts, who maintains the most authoritative public injury-tracking database that covers the NBA. It's the second-highest figure recorded since tracking began in 2005-06.

Simply put, COVID-19 lockdown has wreaked havoc on professional athletes. It’s a problem of athletes doing too much, too soon. Unlike an extended “off season” when pros continue to work out and train, the pandemic lockdown limited training—or nixed it altogether. 

Now that athletes are back on the playing fields, we are witnessing the fallout. But thankfully, when injuries do happen, professional teams have a way to quickly diagnose, treat and manage them. It all starts with the right diagnostic imaging.

From coaches to catcher’s mitts, every professional team understands the value of choosing the best personnel and equipment. It all plays a fundamental role in building a winning team. 

That same philosophy extends to how pro leagues take care of their athletes. While they may not be on the field, radiologists and X-ray techs have long been an essential part of a sports team’s medical team. Now, with the uptick in injuries due to COVID lockdown and lack of practice, medical teams have become more critical than ever. 

What’s more, imaging equipment really matters—it’s truly a team’s first line of defense in getting immediate and accurate diagnoses of injuries. 

The right technology can help diagnose an athlete quickly and get the right treatment promptly started. Most professional sports teams have traditional full size mobile imaging systems at their training facilities as well as at the stadium for ready access to X-rays on demand in the locker room.

In recent years, access to imaging has become even more convenient for teams. Today, new innovations in digital radiography (DR) allow the X-ray professionals associated with a team to take the equipment even more places— reaching injured players on the field. 

It’s all because today’s portables are smaller, lighter weight and have longer lasting battery power. For example, 

 a mini-sized portable with an unprecedented 12-hour battery life. Its compact size, lightweight and versatility make it a great option for remote uses. Add to that the fact that it is affordably priced, so a team can have multiple units if needed. Its image quality is excellent for an ultra-low powered, low dose system due to the combination of Fujifilm’s high sensitivity detectors and advanced image processing. 

For higher demands, power and budgets, the more common choice is the full size 

 which provides x-ray room image quality for every possible view and every size player, with 4 hour battery power.

The benefits of portable DR are many. For example, the injured athlete need not be moved because the equipment comes to them—helping prevent added pain and possible complications from being moved prior to understanding the scope of the injury. Moreover, the ability to obtain high quality images on-site during game time means a speedier diagnosis so the best possible treatment plan can begin immediately.

Presently, Fujifilm works with professional sports teams that use FDR Go PLUS mobile systems along with 

 detectors to provide immediate diagnostic images on injuries. 

Because of the lack of a gradual return to sports, less practice before the season, and overzealous practice schedules, teams are encountering more and more injuries.

Some of the common injuries athletes are experiencing at this time include sprains, fracture, dislocations, shin splints, ACL tears, groin pulls, hamstring strains, and knee, shoulder and elbow injuries.

Figuring out the precise nature of the injury begins with diagnostic imaging. Simply put, portable but powerful DR equipment on the field, court and course is making a decisive impact in the rapid assessment of a wide variety of professional sports injuries. 

Hopefully, we’ve all learned a lot from the COVID-19 pandemic, medically and otherwise. It has shined a spotlight on so much—and sports medicine is yet another area illuminated by this pandemic. Clearly, the isolation and inability to train and practice has led to greater numbers of sports injuries. 

Now more than ever, there is a real need for professional teams to include the latest advances in portable DR as critical gear for their medical staff in treating player’s injuries on the field and the court.

NFL season is starting now and NBA in October. In the NBA, the 

 of players sidelined per game due to injury, non-COVID-19 illness or the need for rest this last season was 5.1—the highest since the 2009-2010. NFL injuries 

 over the first half of the 2020 season. In tennis, we have just seen several players drop out of Wimbledon 2021 due to everything from ankle to abdominal injuries, and this past July, a number of Olympians saw their dreams dashed due to injuries that arose after being sidelined from practice during COVID-19. 

State-of-the-art portable imaging equipment is the first line of defense to address this new epidemic of sports injuries. The sooner injuries are diagnosed, the sooner effective treatment can begin and to help speed recovery. That’s a winning game plan for every team. 

The COVID-19 lockdown wreaked havoc on professional athletes, and now we are witnessing the fallout. But thankfully, when injuries do happen, professional teams have a way to quickly diagnose, treat and manage them. It all starts with the right diagnostic imaging.

Portable Digital Radiography: Tackling Today’s Sports Injury Epidemic 

Image IQ Quiz: Patient Presents With Ankle Pain

Last time around, I dwelled on the so-called “pay per click” model of radiology-compensation. As then mentioned, I’ve seen some love it, some loathe it, and a lot of folks scattered across the spectrum in-between.

Most of the non-polar sentiments include a recognition of tradeoffs: Yes, it can be a bean-counting, headache-making, quarrel-inducing mess, but what else are you going to do? Just pay people a set amount and hope they’ll do a reasonable amount of work? Not noticing/caring if they seem to be pulling harder than others on the team who earn just as much, if not more?

A “happy medium” system would be one in which rads knew they could go about their work without fretting over the daily vagaries of their RVU tally…but nevertheless assured that their productivity would be on the record. And that slackers on the team wouldn’t go undetected.

Leadership would, similarly, have an idea who was shouldering how much of the group’s burden…without having to constantly tinker with complex schemes of differing exam-values, deterrence-mechanisms for “cherrypicking” of easier or higher-value cases, etc.

Tracking RVUs, or even RVU-related “work units,” doesn’t really get at this. You certainly wind up with a bunch of numbers to apply to your rads, numbers which can be put on tables and charts for periodic review. You can make sophisticated-looking curves to show a rad’s productivity over time, and stack them up against other rads, throw in standard-deviation ranges, etc.

Most rads who’ve been working more than a little while have seen their performance tracked. Even if you’re not in a pay-per-click situation, the folks in charge need to know if you’ve been generating enough revenue to warrant whatever salary or hourly rate you receive. Also how to fairly apportion bonuses and consider requests for raises.

But as long as all of that is based on curves, bar-charts, etc. derived from your RVU total, the per-click issues are a big part of the picture. Somewhat paradoxically, I think adding a 

 curve would simplify things, for groups preferring to operate via salaries or hourly rates:

By all means, keep tracking RVUs. After all, if that’s how your group is receiving its revenue, it doesn’t make sense to pretend otherwise. Rads who are doing the heavy lifting to make that revenue happen should definitely be recognized, if not rewarded.

But alongside the RVU curve, have another measurement, truer to the simplicity that “per click” implies: A curve of the raw number of exams a rad has read.

This way, the rad(s) who are dealing with the neverending onslaught of low-paying studies like XR…work that has to get done one way or another…can be tracked for the service they are providing. One important facet of which is running interference so the RVU-sluggers can focus on their MR.

Maybe the rads who would look better on the second curve don’t have the skills to read many of the higher-ticket scans. Maybe they prefer lower-tech modalities. Or maybe their other responsibilities (fluoro, diagnostic mammos, fielding phone calls, etc.) interrupt them so much, it’s just easier to squeeze “bite-sized” studies like XR in between.

If such rads know that they will be valued for taking care of the mountain of XR—despite that mountain’s reimbursement-worth being unimpressive next to a reasonable daily haul of MR and CT—they can go about their work without constantly being tempted to sift through the list for brainscans to shore up their RVU-numbers.

When it’s time for performance reviews, each rad’s two curves can then be seen as equally-important parts of the big picture. Total exams in bottom quartile, but you’re tops RVU-wise? You did your part. RVUs low, but study-volume high? You get praise, not browbeating.

Sort of like being on a track-n-field team: A sprinter is used/valued for what he can do in the 100-meter dash. A distance-runner is regarded for his performance in the 5k. You wouldn’t put either guy in the other’s event and expect good results.

Of course, rads aren’t quite as pigeonholed as all that. Some might do well if told, each day they came into work, whether they should be going for case-volume or RVUs. Or self-select which suits them at any given moment, depending on their mood or circumstances around them.

Obviously, not everybody can be focused on the same curve; the work all needs to be done. Some coordination of efforts via assignment of roles might be needed to avoid all the XR getting gobbled up early in the day, lest there be dozens of RVU-heavy scans that only a fraction of the group can take care of. Or the opposite: Nothing but XR left on the lists at 4pm, and while some of the volume-centric rads industriously plug away, the “I wish I had some MR” rads reluctantly poke through a few cases at a snail’s pace.

 of a rad’s curves are relevant, rather than just choosing one to be his personal yardstick. A top-quartile RVU-rad with bottom-quartile volume, for instance, might be considered as being on the same level as a top-volume/bottom-RVU member of the team…as well as a rad who’s dead-center for both RVU and case-number.

Meanwhile, a rad in the 75th percentile on both of his curves might be considered something of a hero, and bonused appropriately. And a rad whose two curves were in the bottom 10% might be approached for remediation…unless, of course, that rad had other roles of value such as in administration.

Because not everything shows up on curves, no matter how many you’re willing to draw.

Clicks and Curves

Michelle Alexander has over 20 years experience as a registered sonographer and greater than 10 years in the development of strain elastography, point shear wave elastography and real-time shear wave elastography. Michelle has done extensive global scientific research with all types of elastography in the areas of liver, prostate, breast, thyroid, kidney, cervical and musculoskeletal applications alongside luminaries in Europe, China, Canada and the United States. In addition, she holds a patent in the United States and Europe for elastography visualization

Breast cancer is more common than most people would like to admit. In the U.S., a woman has a 1 in 8 chance of developing breast cancer during their lifetime.

That’s why the American Cancer Society recommends annual mammograms for women beginning at age 40, and even earlier for those with more risk factors.

 But scheduling and receiving a mammogram can be anxiety provoking, especially if a woman has a family history of breast cancer. If the medical professional should discover something during the exam that warrants further examination, the next step is usually an ultrasound of the breast to help clarify what is seen on mammography and if a biopsy is needed or not. The days spent waiting for biopsy results can be terrifying, so if it can be avoided it can greatly improve a patient’s wellbeing.

Luckily advancements in image quality and advanced technologies in ultrasound devices such as shearwave imaging can help. Shearwave elastographic features provide qualitative and quantitative information that can be added to mammographic BIRADS analysis, allowing sonographers and radiologists to improve specificity of breast ultrasound mass assessment.

 These tools provide the physician with additional information, and possibly eliminate the need for a biopsy.

I’ve seen these benefits first-hand. In my experience, patients will go straight from the first ultrasound scan to a biopsy if suspicious abnormalities are detected within the breast tissue on mammography and ultrasound. In order to change the patient care cycle, giving a patient a second ultrasound prior to a biopsy may help them avoid un-needed tests. I was once performing a pre-biopsy ultrasound with a Samsung RS85 Prestige® and the device’s 2D and S-Shearwave Imaging™ feature showed that the lump was just an intramammary lymph node. This meant there was no reason to biopsy it, so it was canceled.

Another imaging tool that simplifies and enhances the screening process is a feature called S-Detect™. The semi-automated reporting feature tool analyzes selected lesions and is able to define margins clearly so the user knows a more precise distance from the nipple and depth of the lesion. This is very helpful for documentation and provides clear information on follow-up visits. There is also an ergonomic benefit. In many cases, a sonographer is reaching across the patient’s body to perform a scan. The automated nature of S-Detect reduces the time a sonographer spends on the breast scanning, which therefore reduces time spent in a very uncomfortable position, causing shoulder and arm fatigue. Lastly, it may also give those who are questioning their judgement an extra layer of confidence.

As time goes on, ultrasound manufacturers are moving beyond 2D and 3D imaging, and into the world of advanced intelligence (AI) to construct new ways to display, interpret and understand what is going on inside the human body. S-Detect is a good example of this. Breast ultrasound has become an increasingly common and crucial tool used by medical professionals to determine abnormalities faster and with more confidence. In fact, because image quality and software has advanced to where it has, practitioners have even begun using ultrasound as a first modality to avoid exposing a woman to small amounts of radiation.

When choosing an ultrasound device, medical professionals should consider not only the image quality but also the software and hardware features available in order to improve both their own experience, but, more importantly, the experience of the patient.

https://www.cancer.org/cancer/breast-cancer/about/how-common-is-breast-cancer.html

 Recommendations for the Early Detection of Breast Cancer 

https://www.cancer.org/cancer/breast-cancer/screening-tests-and-early-detection/american-cancer-society-recommendations-for-the-early-detection-of-breast-cancer.html

3. Berg WA et. al; BE1 Investigators. Shear-Wave Elastography Improves the Specificity of Breast US: The BE1 Multinational Study of 939 Masses. 

. 2012 Feb;262(2). doi: 10.1148/radiol.11110640. PMID: 22282182.

Advancements in image quality and advanced technologies in ultrasound devices such as shearwave imaging can help.

The Importance of Ultrasound When Determining Suspicious Abnormalities in Breast Tissue

Deep learning improved accuracy of diagnosing interstitial lung disease with a proposed content-based image retrieval of similar chest CT images in a recent study.

, included 288 patients with confirmed interstitial lung disease and available CT images.

Investigators used a proposed content-based image retrieval (CBIR) search engine to pull CT images from a database of these cases, which included usual interstitial pneumonia (UIP), nonspecific interstitial pneumonia (NSIP), cryptogenic organizing pneumonia and chronic hypersensitivity pneumonitis.

Eighty of the cases were used as test cases and the CBIR pulled the top three similar CT images from the database using a deep learning algorithm that compared the extent and distribution of different disease patterns.

Investigators compared the diagnostic accuracy of eight physicians with varying levels of experience before and after the CBIR was applied.

“The proposed content-based image retrieval system for chest CT images by using deep learning can improve the diagnostic accuracy of interstitial lung disease (ILD) and interreader agreement in readers with different levels of experience,” the authors, led by Jooae Choe, MD, PhD, wrote. “This system can be expected to provide radiologic decision support to centers where thoracic imaging expertise is unavailable or cases of ILD are scarce.”

Overall, diagnostic accuracy improved from 46.1% before CBIR to 60.9% after CBIR. Diagnostic accuracy in UIP cases improved from 52.4% to 72.8%, and in NSIP cases from 42.9% to 61.6%.

CBIR also improved the agreement of CT interpretation between physicians (Fleiss k, 0.32 vs 0.47; P = .005).

Among non-radiology physicians, accuracy improved from 52% to 72% in cases with definite UIP CT pattern. For radiology residents, the change was 67% vs 85%.

“A major challenge of CBIR to be used as a decision-supporting tool is finding features and distance measures that match the clinicians’ requirements on the basis of a particular application,” the authors wrote. “By applying deep learning, structural characteristics (eg, reticulation and ground-glass opacity) inherent to a specific ILD pattern can be quantified on CT images with high accuracy and incorporated into CBIR.”

Mark O. Wielputz, MD, professor in the Department of Diagnostic and Interventional Radiology at Heidelberg University Medical Center, wrote in a related commentary that the database should be expanded into a continually growing system and multidisciplinary team discussion is still necessary for final diagnosis.

“Reference image retrieval is appealing because a decision regarding diagnosis is still made by a human reader provided with supporting image information,” Wielputz wrote. “This creates confidence in such systems compared with computational algorithms that provide only a list of differential diagnoses without explanation.”

He described the system as a shortcut in learning the patterns of diseases.

“A pattern-based and automated search should help radiologists and may be a game changer for computer-aided diagnosis,” Wielputz wrote.

A recent study showed how using artificial intelligence to retrieve reference images could improve diagnosis of interstitial lung disease with chest CT.

Deep Learning Can Improve the Diagnostic Accuracy of Interstitial Lung Disease 

Pranav Chitkara, M.D. is a Board Certified, Fellowship Trained Radiologist. Dr. Chitkara completed medical school at The University of Texas Southwestern and his radiology residency at State University of New York in Brooklyn. Dr. Chitkara also completed his fellowship in Musculoskeletal Imaging at Cleveland Clinic.

Young male with chest and right knee pain after injury

Case: Young male presents with chest and right knee pain post-injury. 

A young male presents with chest and right knee pain after injury. What most likely represents the imaging findings? ​ ​


Image IQ Quiz: Young Male With Chest and Right Knee Pain After Injury

Radiology has its ghosts. There’s ghosting-artifact (most commonly in MR, but the term has been used in other modalities). Ghost-reading: Someone without credentials or even a local license provides a low-cost interpretation, and then a legit rad signs that report with his own name. Plus various imaging-findings that got the word attached to them (“ghost meniscus,” “ghost vertebra,” etc.).

All of which might be interesting things, but not my focus today. Instead, another term that’s not specific to our field, but can be highly relevant: The social phenomenon of “ghosting.”

Most of us are familiar with the concept, even if we don’t know it by that name. I only learned this bit of slang a few years ago. It wouldn’t be the first time I’ve emerged from under a rock to join the rest of vernacular-society, but perhaps this column will serve to do the same for a few readers out there who are as unhip as I.

Ghosting refers to unilaterally ceasing communication with someone. Passively, without warning or declaration of intent. You just stop taking their calls, responding to messages, etc. You effectively become a ghost of the person they thought they had a relationship with. Most probably first experience this behavior during the breakup of a romance.

If you’re doing the ghosting, you might see nothing wrong with it. Or you feel some measure of guilt, like telling a “white lie.” Yes, maybe it would be nobler of you to stand up and tell the other party why you’re parting ways…but your reasons could be perceived as hurtful, might even spark a confrontation with worse consequences. Better to take the path of least resistance and hope they get the hint or have enough other stuff going on that they’ll hardly notice your absence.

Being ghosted, on the other hand, doesn’t leave you with much sympathy for your ghoster. Don’t they owe you more than that? Some measure of respect, an understanding of what you did (or didn’t do)? Or at least an “It’s not you, it’s me” story so you don’t indefinitely question yourself over the matter? It can be downright infuriating: They snuck away like a thief in the night, too lazy to give you the closure you deserved.

Folks might get introduced to ghosting during awkward breakups in gradeschool, but the practice of quietly retreating from an unwanted relationship is far more widespread. Healthcare included, despite what one might have hoped for regarding the behavior of “professionals.” Small wonder that the radiologist, a common poster-child for social ineptitude or avoidance, is no exception.

You might experience ghosting, for instance, if you’re supposedly in a partnership-track and ask about your status…but the current partners don’t intend to make you one (if they ever did). If the raise or end-of-year bonus you expected has failed to materialize. You might be ghosted by someone who’s not completing a task for you—a shared project, something you delegated, or even something you requested of a superior. Heck, you could be the one who completed the task, and whoever asked it of you might avoid responding because they don’t want to deal with the results.

You can be ghosted by folks with whom you have the most tenuous of connections; as long as there is a reasonable expectation of response, there’s the opportunity to ghost. I’ve previously written of the unfortunate prevalence of ghosting in the radiology-recruitment world: An awful lot of would-be employers fail to answer inquiries, leaving job-seekers in the dark about what happened to their applications: Being considered? Rejected? Lost in the ether?

Being ghosted professionally can be tougher to deal with than personally. At least with a vanishing social contact, you can work through your side of things and eventually shrug it off. Not so much if the individual ghosting you has something you want/need, or, worse, is someone you still have to work with; every time you see the perpetrator, it’s an annoying reminder. Especially if the ghost ever requests something of you.

Something I’ve come to understand in the fullness of time: Chase as few of those ghosts as you possibly can. It’s a waste of your time and energy, and even if you catch them it probably won’t be worthwhile. They’re scared of confronting you; in addition to whatever they originally didn’t want to discuss, if they face you now they do so as a coward. If you do wind up interacting, avoid referencing their ghosting-behavior (tempting as it may be to watch ‘em squirm more).

A ghost has tried in a very passive way to tell you “no” without actually saying the word. Trying to pry out a “yes” won’t generally get you what you want; they might speak affirmatively but their subsequent actions will rarely live up to it. They’ll do a halfhearted job if they do it at all. They might even resent you for cornering them, and find ways to punish you for it.

Accepting the unspoken “no” doesn’t get rid of all ghosts. Some come back to haunt you. Maybe testing the waters to see if they can continue the relationship without having to address whatever issue they were trying to avoid. Or maybe they just like playing head-games. I’d suggest keeping such folks at arm’s length; if they were comfortable ghosting you once, they’ll surely do it again. Why give them another chance to let you down?

 need that ghost to finish what it started, or you know that nobody else would fill its shoes as well. I’ve had success offering “bait” to come back. A useful bit of information, or some assistance I can provide. The sort of thing I can hold off on delivering, or parcel out, such that the ghost won’t get what it wants until it’s given me what I need. Not a maneuver you want to overuse: There are multiple ways it can go awry, and once a ghost learns you’ve got such tricks up your sleeve, it can become very circumspect about your offerings…or extra-clever about getting them without giving anything in return.

Chase as few of those ghosts as you can in an effort to save your time and energy.

Deep Learning Can Improve the Diagnostic Accuracy of Interstitial Lung Disease

Image IQ Quiz: Young Male With Chest and Right Knee Pain After Injury

Ghosts in Radiology