ScholarDeck

AI / informaticsTranslational vision science & technology · 2026

Deep Learning-Based Automated Segmentation and Multi-Parametric Quantitative Assessment of the Lacrimal Drainage System on CT-DCG.

Peifang Xu, Yishu Zhang, Pengjie Chen … Han Wu

OphthalmologyAI / informatics

AI-based CT scans matched expert assessment of tear duct sac size closely.

Deep Learning-Based Automated Segmentation and Multi-Parametric Quantitative Assessment of the Lacrimal Drainage System on CT-DCG.

Peifang Xu … Han Wu

Translational vision science & technology · 2026

Background

Primary acquired nasolacrimal duct obstruction (primary acquired nasolacrimal duct obstruction) is a common cause of epiphora.

Purpose

Primary acquired nasolacrimal duct obstruction (primary acquired nasolacrimal duct obstruction) is a common cause of epiphora.

Methods

The system performed automated quantification of the long axis, short axis, and cross-sectional area for each slice from the superior to the inferior opening of the bony nasolacrimal duct, as well as for the lacrimal sac.

n = 151 patients

Results

AI matched the eye specialist's sac-size ratings most of the time

84.7%

Agreement rate

0.76%

Cohen's kappa

More results

The deep learning model achieved robust performance in segmenting the lacrimal drainage system, with an average Dice coefficient of 0.79 for the bony nasolacrimal duct.

It accurately identified and localized the narrowest cross-sectional plane and the obstruction site within the bony nasolacrimal duct.

“

Conclusion · 1 of 2

The proposed deep learning framework demonstrates the technical feasibility of automated segmentation and morphological quantification of the lacrimal sac and bony nasolacrimal duct on CT dacryocystography.

Conclusion · 2 of 2

Although further prospective validation is required, the objective anatomic metrics provided by this system hold promising potential to assist in preoperative assessment and surgical planning for primary acquired nasolacrimal duct obstruction treatment.

Post

Deep Learning-Based Automated Segmentation and Multi-Parametric Quantitative Assessment of the Lacrimal Drainage System on CT-DCG.

AI-based CT scans matched expert assessment of tear duct sac size closely.

Related papers