Automatic leukocoria detection
This page is about our research on automatic detection of leukocoria (white-eye reflection) using software. Our research is producing algorithms which can learn from examples to automatically detect when a photo contains a white-eye reflection that may be an indication of a solid-tumor pediatric cancer called Retinoblastoma. Here is an example of an eye that appears leukocoric:
Our research involves analyzing images of eyes detected within larger natural images. As such, we are especially interested in separating true leukocoria (caused by diseases such as Retinoblastoma) from normal (black and red) pupils, as well as pseudoleukocoria (caused by some camera flashes, but not indicating a negative condition).
Android / iOS apps
You can download our white-eye detector app for Android and iOS! It's free. Please give it a try, and let others know about it.
We previously had a web-based version of this software available, but the app version has much better software support. Please use that version.
Submit your photos
If you have photos of leukocoria you'd like to contribute to our research, you can do so at https://leuko.ecs.baylor.edu/.
Research: papers / presentations / abstracts
If you wish to cite our software work, please refer to the current page as leuko.net.
If you wish to cite our research, please refer to the publications and technical reports below.
- Autonomous early detection of eye disease in childhood photographs. Micheal C. Munson, Devon L. Plewman, Katelyn M. Baumer, Ryan Henning, Collin T. Zahler, Alexander T. Kietzman, Alexandra A. Beard, Shizuo Mukai, Lisa Diller, Greg Hamerly, Bryan F. Shaw.
- Detection of Leukocoria using a Soft Fusion of Expert Classifiers under Non-clinical Settings. Pablo Rivas-Perea, Erich Baker, Greg Hamerly, and Bryan Shaw. In BMC Opthamology, 2014.
- Finding the Smallest Circle Containing the Iris in the Denoised Wavelet Domain. Pablo Rivas-Perea, Ryan Henning, Bryan Shaw, and Greg Hamerly. In proceedings of SSIAI 2014. Here is the IEEE link.
- A Convolutional Neural Network Approach for Classifying Leukocoria. Ryan Henning, Pablo Rivas-Perea, Bryan Shaw, and Greg Hamerly. In proceedings of SSIAI 2014. See attributions for Flickr data used in our study. Here is the IEEE link.
- Colorimetric and Longitudinal Analysis of Leukocoria in Recreational Photographs of Children with Retinoblastoma. Alireza Abdolvahabi, Brandon W. Taylor, Rebecca L. Holden, Elizabeth V. Shaw, Alex Kentsis, Carlos Rodriguez-Galindo, Shizuo Mukai, and Bryan F. Shaw. PLOS One, October 30 2013.
- Colorimetric Image Analysis in Detection of Leukocoria from Retinoblastoma in Snapshots Taken by Standard Digital Photography. Katherine Talcott; Elizabeth Shaw; Rebecca Holden; Brandon Taylor; Erich Baker; Greg Hamerly; Alex Kentsis; Shizuo Mukai; Carlos Rodriguez-Galindo; Bryan Shaw.
- Facetag, The Image Managing Service for the Leukocoria Detection Project. Vaclav Cibur. Baylor MS CSI Project, 2016.
- Age classification from facial images for detecting retinoblastoma. Tak-Chien Chiam. Baylor MS CSI Thesis, 2012.
Federal testimony
Press
- App scans photos to detect eye disease (CBS This Morning, February 12, 2020)
- Community rallies around 10-month-old battling cancer in both eyes (KHOU, February 11, 2020)
- Baylor Connections — Bryan Shaw and Greg Hamerly; interview by Derek Smith (December 13, 2019)
- When a Picture is Worth a Life (Data Crunch Podcast, Vault Analytics, April 29, 2017).
- How your phone's camera could help detect a rare cancer in kids (Upworthy, June 24, 2016).
- UMMS student testing smartphone app to detect childhood cancer in Guatemala (UMass Med, June 16, 2016); see video here: Clear As Day: the Free Tech That's Saving the Sight & Lives of Guatemala's Children
- Glow reveals eye tumor (12 News / KPNX TV, January 27 2016)
- Devoted Dad Creates App That Can Detect Eye Cancer in Children After His Son Was Diagnosed at 3 Months Old (People, January 14 2016)
- App als Früwarnung vor Augenkrebs ("App as early warning of eye cancer"; ZDF, September 7, 2015) — tells that the app identified two children who were then diagnosed with Retinoblastoma.
- The Impact Of Medical Apps On Healthcare (Huffington Post Live, July 16 2015)
- Detecting Eye Cancer Using Flash Photography (KFYR, June 24 2015)
- Deutschland RTL Now — fast-forward to 20:50 (RTL.de, November 26 2014)
- Neue App kann Kinderleben retten! (Bild, November 24 2014)
- Eye disease catching app for iphone could save vision and lives (TMR, November 15 2014)
- White Eye app can give red flag to eye abnormalities (BBC, November 12 2014)
- App Helps Detect Cancer Hiding in Plain Sight (CBS Austin, November 6 2014)
- App made to detect possible eye disease (Baylor Lariat, November 6 2014)
- Eye cancer in children? Baylor profs develop an app for that (Waco Tribune-Herald, November 2 2014)
- Look Here: Phone App Checks Photos For Eye Disease (NPR, October 31 2014)
- White-Eye Photos May Indicate Rare Cancer In Children (CBS Dallas/Fort Worth, May 19 2014)
- Faith Drives A Father To Create A Test For Childhood Cancer (NPR, May 7 2014)
- Chemist Turns Software Developer After Son's Cancer Diagnosis (NPR, May 6 2014)
- How Pictures Of Infant Boy's Eyes Helped Diagnose Cancer (NPR, November 6 2013)
Video
Dr. Bryan Shaw on TEDxUtica (November 7, 2014)
Other resources
- Childhood Eye Cancer Trust (CHECT) in the UK
- Retinoblastoma at American Association for Pediatric Ophthamology and Strabismus (AAPOS)
- Verizon Wireless: 11 Apps to Help Monitor Your Health
Contributors
- Dr. Greg Hamerly, associate professor in computer science, Baylor University
- Ryan Henning, MS computer science, Baylor University — Ryan wrote the initial neural network detector as well as the iOS and Android apps.
- Dr. Bryan Shaw, assistant professor in chemistry, Baylor University
- Dr. Pablo Rivas Perea, postdoctoral researcher in computer science, Baylor University
- Dr. Erich Baker, associate professor in bioinformatics, Baylor University
- Jan Sladek, MS student in computer science, Baylor University — Improvements to the CRADLE app.
- James Boer, MS student in computer science, Baylor University — New frameworks for training and deploying neural networks for leukocoria detection.
- Vaclav Cibur, MS computer science, Baylor University — Facetag, The Image Managing Service for the Leukocoria Detection Project
- Ryan Yan, MS computer science, Baylor University — Implementing age-based filtering of images
- Li Guo, MS computer science, Baylor University — Learning to classify pupil/non-pupil image patches.
- Tak-Chien Chiam, MS computer science, Baylor University — Age classification from facial images for detecting retinoblastoma