Subscribe today for more stories, tips, and updates.

Cincinnati Children's Blog
  • Subscribe
  • CincinnatiChildrens.org
  • Contact Us
  • Blog
  • Healthy Living
  • Rare and Complex Conditions
  • Safety and Prevention
  • Heart Conditions
  • Learning and Growing
  • Research and Discoveries
  • ?
  • Blog
  • Healthy Living
  • Rare and Complex Conditions
  • Safety and Prevention
  • Heart Conditions
  • Learning and Growing
  • Research and Discoveries
  • ?
  • Subscribe
  • CincinnatiChildrens.org
  • Contact Us
HOME/Radiology/Richard Lui Collaborates with Radiology Faculty to Develop a Machine Learning Model to Predict Small Bowel Crohn’s Disease 

Richard Lui Collaborates with Radiology Faculty to Develop a Machine Learning Model to Predict Small Bowel Crohn’s Disease 

Richard Lui Collaborates with Radiology Faculty to Develop a Machine Learning Model to Predict Small Bowel Crohn’s Disease 
November 28, 2022
0 Comments
By: Glenn Miñano

This year I had the opportunity to develop a machine learning model to predict small bowel Crohn’s disease using magnetic resonance images (MRI) under the guidance of Jonathan Dillman, MD, Hailong Li, PhD, and Lili He, PhD, at Cincinnati Children’s Radiology. I would love to share our work with you.  

Crohn’s disease is a chronic inflammation of the intestines that can come and go over time. Crohn’s affects an estimated 750,000 children and adults in the United States and is becoming more common1.  Timely diagnosis in children helps lead to earlier treatment and fewer complications, such as malnutrition and impaired growth2. 

While MRI is widely used to evaluate patients with suspected Crohn’s, research has demonstrated variability in MRI interpretations, even among expert radiologists3,4. Furthermore, due to the limited availability of expert pediatric abdominal radiologists, not all MRI for Crohn’s in children is interpreted by experts. When interpreted by non-experts, there is an increased chance of making the wrong diagnosis. 

There is increasing research that machine learning evaluation of medical images can improve how well we diagnose many diseases. We aimed to develop a machine learning model to predict Crohn’s in pediatric patients using non-contrast MRI images. Our study included 135 patients that had a previous MRI for suspected Crohn’s. Their average age was 15 years; 50% were girls, and 70 had Crohn’s while 65 did not.  

For our models, I worked with Dr. Dillman to first identify particular bowel loops. From these bowel loops, we extracted “radiomic” features related to shape, brightness, and texture. I then worked with Dr. Li to develop machine learning models to classify images as either being from a patient with Crohn’s or from a patient without Crohn’s. Our model had an accuracy of 89.5%, which was slightly better than the literature-documented accuracy of radiologists4. It is noteworthy that radiologists look at multiple types of MRI images before and after IV contrast administration to assess disease, while our model uses only one image type. 

We then developed a model for predicting Crohn’s using routinely collected data, like weight, age, and laboratory testing. We combined this model with our imaging model to achieve an excellent diagnostic accuracy of 93.5% for diagnosing Crohn’s. 

We believe that this model has the potential to improve our ability to diagnose Crohn’s in children and decrease the variability in diagnosis between radiologists. However, while our results are promising, future multi-center studies are needed.  We hope to use similar methods to investigate other key clinical questions in Crohn’s management, including determining if images from diagnosis predict response to certain medical therapies, the development of future complications, and the need for future surgery. 

Figure: an overview of the machine learning method 

  • 1. Molodecky NA, Soon IS, Rabi DM, et al. Increasing Incidence and Prevalence of the Inflammatory Bowel Diseases With Time, Based on Systematic Review. Gastroenterology. 2012;142(1):46-54.e42. doi:10.1053/j.gastro.2011.10.001 
  • 2. Vasseur F, Gower-Rousseau C, Vernier-Massouille G, et al. Nutritional Status and Growth in Pediatric Crohn’s Disease: A Population-Based Study. Off J Am Coll Gastroenterol ACG. 2010;105(8):1893-1900. doi:10.1038/ajg.2010.20 
  • 3. Kim SJ, Ratchford TL, Buchanan PM, et al. Diagnostic accuracy of non-contrast magnetic resonance enterography in detecting active bowel inflammation in pediatric patients with diagnosed or suspected inflammatory bowel disease to determine necessity of gadolinium-based contrast agents. Pediatr Radiol. 2019;49(6):759-769. doi:10.1007/s00247-019-04369-6 
  • 4. Yoon HM, Suh CH, Kim JR, et al. Diagnostic Performance of Magnetic Resonance Enterography for Detection of Active Inflammation in Children and Adolescents With Inflammatory Bowel Disease: A Systematic Review and Diagnostic Meta-analysis. JAMA Pediatr. 2017;171(12):1208-1216. doi:10.1001/jamapediatrics.2017.3400 

Richard Lui, author; Glenn Miñano, BFA, editor; Meredith Towbin, copy editor 

Subscribe today for more stories, tips, and updates.

Related Articles

<strong>January 2023</strong> Radiology Patient Experience Update 
January 2023 Radiology Patient Experience Update 
<strong>Radiology Shows Its Support for the Cincinnati Bengals</strong>
Radiology Shows Its Support for the Cincinnati Bengals
Happy New Year 2023!
Happy New Year 2023!
New Employees Joins Our IRC Group
New Employees Joins Our IRC Group
TAGS:
  • Crohn’s Disease
  • radiology
  • Summer Research Students
Avatar photo

About the author: Glenn Miñano

Glenn Miñano is a media specialist in the Department of Radiology, providing graphic design, photography, printing, video services, and administration of the department’s online properties. His works have been published in several medical articles, such as the American Journal of Radiology and the American Institute of Ultrasound. He has been providing these services to the Radiology Department since 1996.

Write A Comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

No Comments Yet

Topics

  • Cancer and Blood Diseases
  • Child Development and Behavior
  • Childhood Obesity
  • Chronic Care Networks
  • Cincinnati Walks for Kids
  • Featured Faces
  • Fetal Conditions
  • Fitness and Nutrition
  • Food Allergies
  • Ghana 2012
  • Health Care Public Policy
  • Health Care Quality
  • Health Care Reform
  • Healthy Living
  • Heart Conditions
  • Hospital Operations
  • How We Do It
  • Learning and Growing
  • Meet The Team
  • Nurses Week 2012
  • Patient Family Experience
  • Patient Flow
  • Patient Safety
  • Patient Stories
  • Pin of the Week
  • Radiology
  • Rare and Complex Conditions
  • Research
  • Research and Discoveries
  • Safety and Prevention
  • Share Your Story
  • Technology
  • Uncategorized
  • Vaccines
  • Volunteerism
  • What Makes Us Different
  • What's New
See All Topics
See Less Topics

Subscribe

Never miss a post! Sign up to get new blog updates delivered to your email.

Popular Posts

  • Caring for the Caregivers of Children with Congenital Heart Disease  2.4k views
  • 6 Questions to Ask When Your Child Complains of Chest Pain 2.1k views
  • My Child Has High Blood Pressure, Now What? 842 views
  • Stuttering In Young Kids: When To Be Concerned 729 views
  • Button Batteries: What Parents Should Know 718 views
  • Laryngomalacia: Is My Child’s Noisy Breathing Serious? 655 views
About

The Cincinnati Children’s blog features thoughts and perspectives from our experts on all things pediatric health. This blog does not provide medical advice, diagnosis, or treatment. Learn More »

Contact Us
  • 3333 Burnet Avenue, Cincinnati, Ohio 45229-3026
  • 1-513-636-4200 | 1-800-344-2462
  • TTY: 1-513-636-4900
  • socialmedia@cchmc.org
Connect With Us
  • Subscribe
  • CincinnatiChildrens.org
  • Contact Us

© 2009-2022 Cincinnati Children’s Hospital Medical Center