Orbital and eyelid diseases: The next breakthrough in artificial intelligence?

Abstract

Orbital and eyelid disorders affect normal visual functions and facial appearance, and precise oculoplastic and reconstructive surgeries are crucial. Artificial intelligence (AI) network models exhibit a remarkable ability to analyze large sets of medical images to locate lesions. Currently, AI-based technology can automatically diagnose and grade orbital and eyelid diseases, such as thyroid-associated ophthalmopathy (TAO), as well as measure eyelid morphological parameters based on external ocular photographs to assist surgical strategies. The various types of imaging data for orbital and eyelid diseases provide a large amount of training data for network models, which might be the next breakthrough in AI-related research. This paper retrospectively summarizes different imaging data aspects addressed in AI-related research on orbital and eyelid diseases, and discusses the advantages and limitations of this research field.

A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy

“…One model uses external photographs as the imaging modality, 4 , 21 but orbital imaging is ideal for training AI compared with other data sets because there is less background noise, leading to greater potential detection accuracy. 6 However, CTs do have a cost and expose the patient to ionizing radiation which may limit its widespread use as a screening tool. However, by detecting TED, and in particular TED with optic neuropathy, early, expedited referrals may allow patients to initiate lifestyle modifications and potential pharmacologic or surgical treatments sooner, potentially decreasing morbidity and irreversible vision loss.…”

“…Artificial intelligence has also been incorporated in diagnosing orbital diseases, such as blowout fractures, orbital cavernous venous malformations, and TED. 6 , 7 , 8 , 9 Computed tomography scans of the face and head are commonly ordered by an array of nonophthalmology providers and performed for a wide variety of indications, and therefore represent an opportunity for TED detection.…”

Advances in artificial intelligence in thyroid-associated ophthalmopathy

“…AI can analyze vast amounts of data to identify and evaluate the features of Thyroid-Associated Ophthalmopathy from clinical images, CT scans, and other medical records ( 40 ). The data analysis and assessment outcomes generated by AI can provide medical professionals with valuable information to aid them in making more precise diagnostic and therapeutic decisions ( 39 ).…”

Nonspecific Orbital Inflammation (NSOI): Unraveling the Molecular Pathogenesis, Diagnostic Modalities, and Therapeutic Interventions

“…By directly targeting these specific clinical and molecular changes, it is possible to leverage the challenges of current diagnostic and therapeutic tools by providing personalized medicine. [135]. Orbital CT and MRI images are the mainstay in diagnosing orbital diseases, given the detailed analysis of anatomical structures and subsequent changes involved in the pathophysiology [136].…”