CT Takeaways From RSNA 2017
The past few weeks have been a whirlwind, with the excitement of the Thanksgiving holiday followed by the even more exciting hustle and bustle of one of our favorite meetings: RSNA 2017. From the vendors to the speakers to the broad variety of topics that touch on every aspect of radiology, there’s always a lot to love about the RSNA meeting, and inevitably a lot to learn. This year was no exception, and we couldn’t help but walk away from RSNA 2017 excited about the future of radiology.
Changes are happening across every facet of the industry, but unsurprisingly it was the discussions related to innovation within Computed Tomography that we were the most excited to be a part of. It would take countless hours and likely hundreds of pages to detail everything from RSNA17, but these were two CT-specific advances worth sharing.
Deep Learning Can Quantify CAC On Low-Dose CT
It wouldn’t be a 2017 conference of note if deep learning and AI weren’t top points of conversation! On Tuesday Nikolas Lessmann, from the University Medical Center Utrecht, presented on a deep-learning algorithm Dutch researchers have worked to develop that can automatically calculate CAC scores from lung cancer screening CT exams and facilitate risk stratification in these patients.
Although there are already automatic methods available for CAC scoring that can achieve a close to human level of performance, the downside is that these techniques can’t be run on workstations and require dedicated servers and a high computational load. Lessmann’s team sought to overcome this challenge by creating an algorithm that can quantify the Agatston score directly from the input CT image. There’s still some work to be done, but the accuracy results are incredibly promising
Radiologists Aid Mass Disaster Recovery With Mobile CT
In recent years there’s been a shift in the way that the practical use of CT technology is viewed. More and more we’re seeing the technology used not only in a traditional diagnostic sense, but also implemented in broader applications as a solution or aid to problems within other industries. History and a number of sciences have utilized CT technology to aid in discovery and problem-solving, and researchers from various Italian universities are using CT to aid in mass disasters.
The team developed a CT protocol to help examine cadavers in large-scale catastrophes, using qualities like age, sex, stature, pre-existing pathological conditions, dental profile, and personal belongings to help identify the deceased. The high volume of cadavers in mass disasters makes it impossible to examine all of the bodies at once or store them for later identification. Coroners often don’t have time to analyze all this detailed information during the rescue, and in many cases this leaves family members and friends waiting and wondering whether their relatives are among the deceased. This is where the efficient imaging of cadavers with CT comes into play, the goal is for radiologists to use CT technology to aid coroners in more quickly and efficiently identifying victims of mass disaster.
“A lot still has to be done,” researchers noted, “and it is mandatory for radiologists to work with the coroners to improve our job in these events. The long-term effects of this effort can be huge.”
Radiology has evolved so much over the years, a fact that was evidenced at RSNA 2017, and CT is no exception. The technology itself, but more importantly how we use it, is continuing to change in ways that are incredibly exciting. It’s a great time to be in the industry, and we look forward how CT, and its applications, continue to grow in the upcoming years.