Smartphone-Based Deep Learning Exophthalmometry in Thyroid Eye Disease: A Multicenter, Multiethnic Validation Study.

Published in Thyroid : official journal of the American Thyroid Association. Abstract: Proptosis is the principal quantitative measure of disease severity in thyroid eye disease (TED), but Hertel exophthalmometry has substantial interobserver variability and requires in-person specialist visits. Existing deep learning (DL) proptosis-from-photograph models require studio-acquired images. We aimed to validate, in a multicenter multiethnic study, a DL model fine-tuned to estimate proptosis (mm) from nonstudio facial photographs-smartphone selfies or clinician-taken photographs. This validation study included 361 patients with confirmed or suspected TED at three institutions. Data were collected prospectively at two Korean sites-Severance Hospital (SH; 203 patients/3654 facial images; internal validation) and Seoul National University Bundang Hospital (SNUBH; 79/933; same-ethnicity external validation)-and retrospectively, from routine-care images, at one Spanish site, Virgen Macarena University Hospital (HUVM; 79/336; different-ethnicity external validation). Korean patients self-acquired selfies on six smartphone models per site using a capture-guidance application; Spanish images were clinician-acquired during routine care without such guidance. The model-a dual-stream ResNet-18 jointly processing a facial image and a per-pixel depth map (ZoeDepth)-outputs a proptosis estimate (mm) per eye from one photograph and was fine-tuned, from a previously published model trained on studio digital single-lens reflex photographs, for these nonstudio acquisitions. Hertel me...

5 Key Takeaways

1. Mean absolute error versus Hertel measurement was 1.14 mm in Severance Hospital internal validation.
2. Mean absolute error versus Hertel measurement was 1.44 mm in Seoul National University Bundang Hospital same-ethnicity external validation.
3. Mean absolute error versus Hertel measurement was 1.58 mm in Virgen Macarena University Hospital different-ethnicity external validation.
4. Predictions were within 2 mm of Hertel in 83.6% of images at Severance Hospital.
5. Area under the receiver operating characteristic curve for detecting severe proptosis (Hertel ≥21 mm) was 0.94 in Severance Hospital.

OpenRounds transcript synthesis · Verify against the source