Radiologist’s Intro to Machine Learning – 1 of 10

Article 1 – Introduction to Our Series

In 2017, the Kaggle Data Science Bowl took aim at using machine learning and artificial intelligence to fight the leading cause of cancer death in the US among both men and women.  Entrants were challenged to use a dataset of thousands of high-resolution pulmonary CT images to create new lung cancer detection algorithms. These algorithms were made to improve diagnosis and reduce false positive rates.

Of the 394 competing teams, which team received the top prize?  A team combining members from both the Medicine and Computer Science Departments of Tsinghua University in China.

Competitions such as this are a great way to combine international talent with global problems. This style of teamwork is just scratching the surface of the infinite potential for advancement within our field through interactions between medical professionals and computer science.

During radiology training, we learn that a 3-cm, spiculated, soft-tissue attenuating lung mass has a very high probability of being cancer.  Likewise, a 5-mm, smooth, calcified nodule has a very low probability of being cancer.

However, we also know that many pulmonary nodules lay somewhere in between our ability to accurately predict malignancy.  The Fleischner Society worked very hard to offer a solution with its updated follow-up criteria in 2017, which included both size and density changes. However, we still can’t look at an 8-mm nodule with a slightly irregular border and say how likely it will be cancer.

To take the Kaggle Competition one step further, there is a very real possibility that Fleischner criteria (or its replacement) will be very customizable and lung nodule tracking will improve. We will dive more into this in Article 2.

—-

These Kaggle teams use similar technology behind Facebook’s facial recognition. Have you ever wondered how they can determine who is in your photos? This technology is called deep learning, a subset of machine learning and a subset of artificial intelligence, and we will also dive deeper into these topics in Articles 3, 5 and 6.

These sorts of efforts are a testament to the open-source community, and how people are determined to find novel solutions to important problems by working together and sharing data.

Let’s take the contrarian view, that machine learning and artificial intelligence may portent to the obsolescence of the radiology specialty.  Professor Geoffrey Hinton comes to mind.

—-

Geoffrey Hinton is a very smart guy, but his lack of medical training on the nuances of the radiology specialty, such as image-guided biopsies, tumor board and discussion with our surgical colleagues, etc., has perhaps given him only a superficial view of our profession.   Radiologists’ jobs will morph with new tools but will be around as long as we continue to assist our clinical colleagues.

The outcome of the Kaggle competition was also benefited by timing and available resources. Thanks to the huge video gaming market, for the first time we have cost effective high power computing called Graphical Processing Units (GPUs). More in Article 3. Another area we may take for granted is voice recognition. While we may or may not see day to day improvement, it has certainly improved over the past decade. More in Article 4.

Another very important piece to the puzzle is data. Lots of data. Lots of data that is properly labeled. The American College of Radiology (ACR) and Stanford are currently working on this.  More in Article 5. (or 7).

Collaborative teams of computer scientists and medical professionals have amazing potential for development of field-changing algorithms. But when we talk about inserting these technologies into our daily workflow, or in the context of privacy, or data management – cue the crickets.  More in article 8.

—-

Before we go any further, we would like to formally introduce ourselves.

Ty Vachon –

“This is the first of a series of 10 articles aimed to guide my colleagues. I have been tracking the growth of ML and medical applications since 2012 and following great mentors like Drs. Dreyer and Michalski. Informatics, particularly medical image utilization, has been a large part of my background. I received my radiology training in the US Navy after serving as a flight surgeon with the Marine Corps. My final Navy tour was in Okinawa, including a Radiology Department Head tour, before completing my Navy commitment and moving back to San Diego as an Angel Investor, entrepreneur, and informatics advisor and consultant. As of this writing, I have no relevant financial disclosures regarding this series.”

Danilo Pena –

“I have a background in chemical engineering, and worked as an engineer for two years. During the job, I realized that I needed to make a larger impact on society, and I also wanted to learn to code. Thus, I applied to school, got in, and quit my job. I am currently a Biomedical Informatics Master’s student at the University of Texas Health Science Center in Houston and an Albert-Schweitzer Fellow. I am always learning, and I am excited to help others learn what I know. I hope that through this series of articles, people from the medical field to the machine learning field to just the average person can use this information to understand the current landscape of radiology and its relationship with technology advancements in artificial intelligence.”

We believe that through our disparate, but complementary skill sets, we can educate others about this exciting field.

—-

Now that you know a little bit about us, you might be wondering why should you spend your time on our series.

During the series, we will start slow and review key terminology. We will also discuss enough recent historical progress to provide context and address new trends. If you are a little more advanced, please offer clarifying thoughts from personal experience in the comments. And of course, if you notice any erroneous text, we will humbly review those comments as well.

This series is not meant to be exhaustive, but these articles are meant to level the playing field when it comes to radiology and artificial intelligence. This field is rapidly changing, and there are a lot of moving parts. We are doing our part to educate and learn through this process.

Join us for an interesting set of articles curated by a seasoned radiologist who is technology focused and a student interested in understanding how ML and AI will affect the next generation of healthcare.

Next week:

Article 2 – How Radiology and AI Will Come Together

Editor: Michael Doxey, M.D.

What is Informatics?

Clinical informatics is the implementation and evaluation of communication systems that improve patients’ health and care, as well as the relationship between patients and their physicians. It links information technology, communications and healthcare to improve the quality and safety of patient care.

Data and information technology can improve health care.

Patients CAN receive higher quality, more efficient and cost effective healthcare.

Profit driven industries have utilized data mining for decades and health care is slowly embracing the value of sifting through the vast amounts of collected information.

There are powerful concepts in various stages of development to include clinician decision support (computer programs that help doctors order the right labs, CT scans, MRI’s and ask all of the right questions), bidirectional electronic medical records (think online banking but with your doctor to check labs, radiology reports, make appointments, send home blood pressure or monthly weight from Bluetooth-enabled products), Apple Health Kit and genetically designed pharmaceuticals.

As a result of the exponential incorporation of technology and subsequent enormous amount of data that is generated and stored, the field of informatics is developing. Useful examples are already in place: curetogether.com or patientslikeme.com

Breast biopsy matrix – helpful guide to navigate the pathology report for radiologists

I wasn’t expecting a check in a box that said cancer, but the first time I looked at a breast biopsy pathology report I was surprised. I shouldn’t have been, but I was.

This is a guide we put together with the help of our surgeons. Consider saving/printing it out and discuss with your surgeons to standardize care in your institution.

Please let me know what you think and post feedback below or email if you like: ty@orainformatics.com

Dr. Vachon Dr. Miller
Dr. Vachon
Dr. Miller
Dr. Vachon Dr. Miller
Dr. Vachon
Dr. Miller
Dr. Vachon Dr. Miller
Dr. Vachon
Dr. Miller

Printable PDF: breast biopsy matrix

Dr. Miller, Primary Author
Dr. Vachon, Attending

 

Sign up for my email list here!

Vomiting infant – imaging needed? Bilious? X-ray or Ultrasound?

Vomiting infant – imaging needed? Bilious? X-ray or Ultrasound?

Vomiting In Infants Up To 3 Months Of Age?
Bilious vomiting in neonate up to 1 week old = abdomen radiograph and possibly upper GI or contrast enema
Bilious vomiting in infant 1 week to 3 months old = upper GI
Intermittent non-bilious vomiting since birth = possibly upper GI

New onset  projectile non-bilious vomiting = abdominal ultrasound 

As always, please refer to the source Appropriateness Criteria created by the American College of Radiology, here.

Educational purposes for licensed providers.

Note to Patients:

Radiology is a very large and ever changing field and this post is to help your provider.  When combined with a thorough history and physical exam, this information can be very useful.  Your provider is best suited to answer specific questions regarding this post.

A provider is usually a Nurse Practitioner, Physician Assistant or Medical Doctor.

Of course, this is not a substitute for medical care.

Osteomyelitis in diabetic foot?

Osteomyelitis in diabetic foot?

Imaging of suspected osteomyelitis in diabetic foot?

Summary
Soft tissue swelling with or without neuropathic arthropathy or with or without ulcer = foot X-ray AND MRI foot without and with contrast
If imaging is indeterminate, biopsy or aspiration is warranted

As always, please refer to the source Appropriateness Criteria created by the American College of Radiology, here.

Educational purposes for licensed providers. 

Note to Patients:Radiology is a very large and ever changing field and this post is to help your provider.  When combined with a thorough history and physical exam, this information can be very useful.  Your provider is best suited to answer specific questions regarding this post.

A provider is usually a Nurse Practitioner, Physician Assistant or Medical Doctor.Of course, this is not a substitute for medical care.

What is appropriate medical imaging?

What is appropriate medical imaging?

Having been in radiology a number of years, I know it can be difficult to decide what is the best study, if any, for each patient. Radiation? Cost? Wait time? Contrast or not? MRI vs CT scan?

The American College of Radiology teamed up with many specialist to create the Appropriateness Criteria. It has the goal of helping providers better choose which study is best for their patients.

There is terrific information in this project, however it can be intimidating to navigate.

I will summarize a few per week, with links to the source documentation, as a primer for my friends who are not necessarily radiologists.

Fellow providers, please leave comments and I will address them to the best of my ability. Patients please see below.

This is the entire Appropriateness Criteria:

http://www.acr.org/Quality-Safety/Appropriateness-Criteria

This is also accessible from here:

http://www.guideline.gov/search/search.aspx?term=acr+appropriateness

Radiologists in training may benefit from these posts as well as the ABR Core Exam asks specific question from the ACR AC.

Please Link In! www.linkedin.com/in/tyvachon

Educational purposes for licensed providers.

Note to Patients:

Radiology is a very large and ever changing field and this post is to help your provider.  When combined with a thorough history and physical exam, this information can be very useful.  Your provider is best suited to answer specific questions regarding this post.

A provider is usually a Nurse Practitioner, Physician Assistant or Medical Doctor.

Of course, this is not a substitute for medical care.

Pulmonary hypertension?

Pulmonary hypertension?

Suspected pulmonary hypertension?
Summary

Suspected pulmonary hypertension =

Both echocardiography and right heart catheterization, next chest radiograph and CTA chest with contrast, if needed

Educational purposes for licensed providers.

Note to Patients:

Radiology is a very large and ever changing field and this post is to help your provider.  When combined with a thorough history and physical exam, this information can be very useful.  Your provider is best suited to answer specific questions regarding this post.

A provider is usually a Nurse Practitioner, Physician Assistant or Medical Doctor.

Of course, this is not a substitute for medical care.

Acute pancreatitis? Ultrasound or CT? When?

Acute pancreatitis? Ultrasound or CT? When?

Imaging for acute pancreatitis
 
First time presentation, abdominal pain, and increased amylase and lipase with high clinical certainty of diagnosis; 
LESS THAN 48–72 hours after onset of symptoms; clinical score irrelevant; 
Suspected cause
unknown cause  => US abdomen to assess for gall stones
 
 
 
Everything else, probably => CT abdomen with contrast, see below.  
 
Critically ill, systemic inflammatory response syndrome (SIRS), severe clinical scores (eg, acute physiology and chronic health evaluation [APACHE], bedside index of severity in acute pancreatitis score (BISAPS), and/or Marshall); GREATER THAN 48–72 hours after onset of symptoms. => CT abdomen with contrast
 
Continued SIRS, severe clinical scores, leukocytosis, and fever; >7–21 days after onset of symptoms. => CT abdomen with contrast
Initial presentation with atypical signs and symptoms, including equivocal amylase and lipase values (possibly confounded by AKI or chronic kidney disease) and when diagnoses other than pancreatitis may be possible (bowel perforation, bowel ischemia, etc). => CT abdomen with contrast
 
Known necrotizing pancreatic and peripancreatic pancreatitis, significant deterioration in clinical status, including abrupt decrease in hemoglobin/hematocrit, hypotension, tachycardia, tachypnea, abrupt change in fever curve, or increase in white blood cells; time
after symptom onset irrelevant. 
=> CT abdomen with contrast
Educational purposes for licensed providers.
Note to Patients:

Radiology is a very large and ever changing field and this post is to help your provider.  When combined with a thorough history and physical exam, this information can be very useful.  Your provider is best suited to answer specific questions regarding this post.

A provider is usually a Nurse Practitioner, Physician Assistant or Medical Doctor.

Of course, this is not a substitute for medical care.

#orderwhat #pancreatitis @AFPjournal @PCareProgress @AANP_NEWS @AAPAorg #choosingwisely

Foot trauma? Foreign body? X-ray needed?

Foot trauma? Foreign body? X-ray needed?

Acute foot trauma? – #orderwhat #footpain @AFPjournal @PCareProgress @AANP_NEWS @AAPAorg
Meet Ottawa Rules or not neurologically intact  => Xray
Concern for Lisfranc injury => Weight bearing Xray, if able or MRI foot
Does not meet Ottawa Rules => No study indicated
X-rays negative and concern for tendon injury or dislocation => MRI foot

Penetrating trauma and concern for foreign body => X-ray, then US if needed 

Educational purposes for licensed providers.

Note to Patients:

Radiology is a very large and ever changing field and this post is to help your provider.  When combined with a thorough history and physical exam, this information can be very useful.  Your provider is best suited to answer specific questions regarding this post.

A provider is usually a Nurse Practitioner, Physician Assistant or Medical Doctor.

Of course, this is not a substitute for medical care.

Pyelonephritis?

Pyelonephritis?

Acute pyelonephritis?
Uncomplicated patient = no imaging indicated

Complicated patient such as: diabetes, immunocompromised, prior renal surgery, prior stones or not responding to therapy = CT abdomen with, and possibly without, contrast (e.g. if history of stone), possibly renal ultrasound or MRI abdomen with contrast 

As always, please refer to the source Appropriateness Criteria created by the American College of Radiology, here.

Educational purposes for licensed providers.

Note to Patients:

Radiology is a very large and ever changing field and this post is to help your provider.  When combined with a thorough history and physical exam, this information can be very useful.  Your provider is best suited to answer specific questions regarding this post.

A provider is usually a Nurse Practitioner, Physician Assistant or Medical Doctor.

Of course, this is not a substitute for medical care.