Tag Archives: Radiology

The FDA has an Idea, or 10, on Good Machine Learning Practice

Good machine learning practices goes beyond the chip

The U.S. FDA, Health Canada, and the UK’s MHRA have unveiled 10 guiding principles for Good Machine Learning Practice (GMLP) in developing AI/ML medical devices. These principles aim to ensure safety, efficacy, and quality in healthcare innovation. Key focuses include leveraging multi-disciplinary expertise, implementing good software and security practices, ensuring representative clinical study participants and data sets, maintaining independence between training and test data sets, and emphasizing the performance of the human-AI team. These guidelines also highlight the importance of clear user information, robust testing, and ongoing monitoring of deployed models to manage re-training risks and maintain performance.

Read the full GMLP draft on the FDA website.

1-Minute Summary

Here are the ten principles of GMLP.

Continue reading

AI+Human Better than Human in Neurodegenerative Imaging

Recent research underscores a leap in neuroimaging accuracy for Alzheimer’s disease diagnosis, emphasizing the superior performance of AI-assisted radiologists over either AI or humans alone. This collaborative approach marries the meticulous precision of AI with the nuanced understanding of human experts, potentially setting a new standard in the detection of amyloid-related imaging abnormalities. Specifically, it demonstrated superior performance in detecting amyloid-related imaging abnormalities (ARIA), crucial for amyloid-β–directed antibody therapy. This synergy enhances diagnostic precision and underscores the potential of AI-enhanced radiological diagnostics to improve patient care significantly.

How will this synergy between AI and human intelligence redefine the future of medical diagnostics? Can this model be the blueprint for addressing other complex diseases? This breakthrough prompts us to envision a healthcare landscape where technology and human expertise converge to offer unparalleled patient care.

Detailed study can be found in JAMA Network Open.

Your Origin Story for Data Science

There’s an origin story for every superhero; even those without superpowers (like Batman – that’s right) got started somewhere. What we sometimes forget is that there is also an origin story for every regular person, every profession, every hobby.

Source: Wikimedia Commons

 

If you’re a radiologist looking to learn a few things in radiology data science, a simple web search will reveal a seemingly overwhelming amount of material you might have to know.

Fortunately, only a very small subset is necessary to start being productive.  Here are a few resources I used to get started.

Continue reading

The [machine learning] race is on – Don Dennison

Continue reading

Machine learning, real opportunites: Dr. Keith Dreyer’s keynote sets tone for ISC 2016

Dr. Keith Dreyer opens with a keynote during the Intersociety Summer Conference (ISC) with description of data science and overview of how machine learning have evolved over time.

He describes that machines and humans inherently see things differently. Humans are excellent at object classification, recognition of faces, understanding language, driving, and imaging diagnostics. Continue reading

Five way to keep up coding skills when you are a full time radiologist

Radiologists have a day job (or a night job, depending on your precise definition of “radiologist.”) Many people want to learn the syntax of a computer language, while some want to keep up on existing skills.

If your goals are similar to mine, these might help.  Now these are not ways to learn to write code (I’ll write about that later), but ways to brush up on existing skills.

Here are five things to help keeping up your coding skills:

Work on a Project

Most radiology practices can be improved by better use of technology  Continue reading

Think Outside the (View) Box

Twenty years ago, medicine and surgery rounds used to start in the reading room.  Sitting in a dark room with a viewbox and an alternator, a senior radiologist greeted visiting clinical teams every day and reviewed their patients’ films.

With the advent of digitization and picture archive and communication system (PACS), the last 20 years saw a rapid evolution of radiology.  We read studies faster than ever, and radiology workflow focused extensively on the interpretation of images and the associated diagnostic report.

Recently, there has been a revival patient-centered care and communication.  Communication is the new radiology workflow.

I had the pleasure of writing about the importance of communication in radiology in a previous post. Just this month, a group at Beth Israel Deaconess Medical Center writes in American Journal of Roentgenology that despite our focus on critical value communication, the bulk (52%) of errors in radiology communication actually occur outside of results.

While most communication errors did not cause patient harm, 37.9% did affect patient care.  The radiology value chain, of course, begins as early as the decision to image and extends well into appropriate follow-up imaging of identified lesions (Enzmann, Radiology 2012).

Maybe it’s time we as radiologists take ownership of the whole imaging process, from the decision to image all the way to follow-up.

[Tweet “New AJR paper finds a majority of communication errors in radiology occur outside of results notification.”]

Don’t Go to The RSNA for The Great Research

The Radiology Society of North America (RSNA) annual conference is one of the most popular and most well-attended conferences in radiology.  The deal is the same – you submit some academic work you completed, and if it is deemed worthy, you are offered a not-quite-golden ticket to attend the not-quite-chocolate-making conference center.

You spend upwards to one week in a place with 20,000 strangers pushing around, 4,000 some CME-worthy offerings, and another 700 vendors trying to decide whether you have money to buy a CT table.  Sometimes people say that you go to the RSNA conference to learn about the newest research, to get ideas from being bathed in the sheer high density of smartness that we assumed would somehow disperse by diffusion.  The research is great, the vendors are great, the city is amazing, but these aren’t the reasons to go to the RSNA conference. If the research is important enough you will see it in a journal, if you need a product you will find that vendor on the internet, and Chicago… is indeed amazing, but it would be more so in September than December.

The reason that tens of thousands of people come together on this one week is not for the great research.  It’s for each other.  Go for the great people.  The world-class research is just a bonus.

Registration Now Open

Radiology’s largest annual conference is held in Chicago this year from Nov 29 – Dec 4

Relaxing the Quality MOC Requirements – Good News or Bad Omen?

In September, the American Board of Radiology (ABR) released a set of expanded options for satisfying Part 4 Requirements for its maintenance of certification (MOC).

The biggest change includes the ABR’s willingness to include additional areas (16 of them) of involvement in departmental quality and safety other than Practice Quality Improvement (PQI) as qualifying requirement. Continue reading

4 Ways Radiology Resident Experience Determines the Quality of a Residency

You are a fourth year medical student.  You’ve worked hard for three years, passed the USMLE with flying colors, conducted some spectacular extracurricular work.  And you’ve decided to pursue diagnostic radiology.  Continue reading