Embrace A Future with Artificial Intelligence

Tomblinson_DSC4809_PP_5x7This post was contributed by Courtney Tomblinson, MD, ACR Valerie P. Jackson Education Fellow and neuroradiology fellow at Vanderbilt University.

Artificial intelligence and augmented intelligence tools are not the enemy. At least not for radiologists. Rather, they are tools to help us build a better future for our patients and practices.

Media hype of inflated claims of AI performance has built mistrust that AI will soon replace radiologists. Perhaps it is a glass-half-full view, but I – and many other radiologists – don’t share this fear. In fact, as author and “futurologist” Mark Stevenson put it in his keynote address at the American Society for Radiation Oncology (ASTRO) Annual Meeting earlier this week, “You won’t be replaced by AI, you will be replaced by someone who knows how to use AI.” It was a quote shared frequently throughout the radiology Twitterverse – a place where you can often find me engaging in important discussions like this one.

Personally, I can’t wait to test some of these new AI tools. I would urge others to get excited about the possibilities these technologies can hold, as well.

This week, the ACR Data Science Institute (ACR DSI) released the first of its landmark AI use cases to help ensure that AI tools do what they say they can do, can be safely implemented into the radiology workflow, and enable quality improvement over time.

Medical imaging AI can now move from curiosities that sometimes appear in medical literature or sensationalized news stories, to the creation of tools that actually help us improve patient care. This is big.

The TOUCH-AI use cases were created to empower AI developers to produce algorithms that are clinically relevant, ethical and effective. Each use case provides narrative descriptions and flow charts which specify the health care goal of the algorithm, the required clinical input, how it should integrate into the clinical workflow and how it will interface with users and tools. The use cases are bringing radiologists and allied professionals together to solve some of healthcare’s biggest challenges.

One day, when AI tools are commonplace, when they have made us even more efficient and when patients are no longer suffering from disease or injury that will then be preventable or easily treatable – we will look back on this week and smile.

These are heady times. But don’t fear the days ahead. Revel in them.

Big things are coming. The future is now. And we, as radiology professionals, get to play a leading role.

Connecting the Dots: Where Priorities Like Mammography, Reporting and Data Systems and Artificial Intelligence Intersect

Dr.McGinty(updated)_andcroppedThis post was contributed by Geraldine McGinty, MD, MBA, FACR, chair of the ACR Board of Chancellors

We’re now more than halfway through Breast Cancer Awareness Month, and our Mammography Saves Lives campaign has been hard at work educating women and providers on the importance of annual mammograms starting at age 40 – something that we’re committed to all year long.

And if you’ve been practicing medicine for a while, you’re also likely familiar with the ACR Reporting and Data Systems (RADS), which provide a standardized framework for reporting on imaging findings with the goals of reducing the variability of terminology in reports and easing communication between radiologists and referring physicians.

Lastly, similar to Mark Twain, the rumors of radiology’s death at the hands of artificial intelligence (AI) are greatly exaggerated. As the work of the ACR Data Science Institute (ACR DSI) is demonstrating, collaboration between radiology professionals, industry leaders, government agencies, and patients is leading to the development and implementation of AI applications that will help radiology professionals improve medical care.

When viewing these efforts from a high level, it’s clear that they’re significant to radiology, but it may seem that they’re largely unrelated to one another, working in silos. But what makes an article we recently published in the JACR so exciting is seeing how these efforts converge.

The study’s authors used Breast Imaging Reporting and Data System (BI-RADS) data from the University of California, Irvine Machine Learning Repository and the Digital Database for Screening Mammography repository. Two sets of models were trained: M1 and M2. M1 used lesion shape, margin, density and patient age information from data set 1 and image texture parameters from data set 2. M2 used the same image parameters as M1, but also used BI-RADS classification provided by radiologists.

Overall, the model that used BI-RADS classification from radiologists (M2) outperformed the model that did not (M1). In simpler terms: AI algorithms perform significantly better when they include a radiologist’s opinion.

The study results demonstrate that a radiologist-augmented workflow is feasible in AI, allowing better management of patients and disease classification.

By educating women on the importance of starting mammography at age 40, leveraging the data available in BI-RADS and bringing radiologists and AI algorithms together, we can play a leading role in reducing breast cancer death rates nationwide.

  • Do you and/or your practice participate in any, or all, of the above efforts?
  • Have you heard that the ACR DSI is making a big announcement at the ACR Quality & Safety Conference next Friday, Oct. 26? What are you anticipating?

Please share your thoughts in the comments section below and join the discussion on Engage (login required).

Lung Cancer Screening’s Lifesaving Double Impact

Ella KazerooniThis post was contributed by Ella Kazerooni, MD, FACR, executive sponsor of the Lung Cancer Screening 2.0 Committee, chair of the American college of Radiology Lung Cancer Screening Resources Committee and chair of the ACR Lung-RADS® committee.

Evidence to support annual lung cancer screening  with low-dose computed tomography (LDCT) in high-risk patients received a double boost recently.

The Nelson Study , presented at the recent IASLC World Conference on Lung Cancer, showed that LDCT screening reduced lung cancer deaths by 26 percent in men and up to 61 percent in women (a 44 percent reduction overall if male and female cohort were evenly split).

And just this week, a paper in Annals of Internal Medicine predicted that lung cancer deaths would continue to drop in coming decades — in part due to LDCT. The authors stated that LDCT could not only reduce lung cancer deaths via early detection but also boost smoking cessation rates.

So, not only would LDCT cut older current and former smokers’ risk of dying from lung cancer nearly in half, but it also leads more people to stop smoking — which could save more lives.

Lung cancer kills more people each year than breast, colon and prostate cancers combined. Once implemented nationwide, this cost-efficient test would be the most effective cancer screening exam in history.

Yet, LDCT remains underutilized due to referring providers being uninformed or unaware of the benefits, and due to under coverage by Medicare. Let your referring providers know that they should consider these lifesaving exams for their high-risk patients.

  • The ACR Lung Cancer Screening resources page offers a number of materials to help us spread the word and learn how to start and maintain safe and effective lung cancer screening programs in our practices or hospitals.
  • I would also invite you to check out the American Lung Association® Saved by the Scan campaign. This may be a useful resource to link from your practice website.
  • RadiologyInfo.org is another tremendous resource for patients. The lung cancer screening section explains to patients what lung cancer screening exams are, how to prepare for them, benefits and risks, and more.
  • The National Lung Cancer Roundtable (NLCRT), a national coalition of public, private and voluntary organizations and invited individuals, dedicated to reducing the incidence of and mortality from lung cancer in the United States, offers a variety of resources as well.  

We have tools available to educate our referring providers and patients about lung cancer screening and how it can help many high-risk patients. I invite you to use them.

  • Does your practice or hospital offer lung cancer screening?
  • What have you found works well in informing patient and providers about lung cancer screening?

Please share your thoughts in the comments section below and join the discussion on Engage (login required).