Internal validation of a convolutional neural network pipeline for assessing meibomian gland structure from meibography.

Journal: Optometry and vision science : official publication of the American Academy of Optometry
PMID: 39792877

Abstract

SIGNIFICANCE: Optimal meibography utilization and interpretation are hindered due to poor lid presentation, blurry images, or image artifacts and the challenges of applying clinical grading scales. These results, using the largest image dataset analyzed to date, demonstrate development of algorithms that provide standardized, real-time inference that addresses all of these limitations.

Authors

  • Charles Scales
    Johnson & Johnson MedTech (Vision), Irvine, California.
  • John Bai
    Johnson & Johnson MedTech (Vision), Irvine, California.
  • David Murakami
    Johnson & Johnson MedTech (Vision), Irvine, California.
  • Joshua Young
    Department of Ophthalmology, New York University School of Medicine, New York, New York.
  • Daniel Cheng
    Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, 08854, USA.
  • Preeya Gupta
    Cornea and Refractive Surgery, Duke University Eye Center, Durham, North Carolina.
  • Casey Claypool
    Empire Eye Physicians, Spokane, Washington.
  • Edward Holland
    Cincinnati Eye Institute, Edgewood, Kentucky.
  • David Kading
    Kading Consulting, Kirkland, Washington.
  • Whitney Hauser
    Dompé US, Memphis, Tennessee.
  • Leslie O'Dell
    Medical Optometry America, Newtown Square, Pennsylvania.
  • Eugene Osae
    Johnson & Johnson MedTech (Vision), Irvine, California.
  • Caroline A Blackie

Keywords

External Resources

Popular Topics
Recent Journals