Automated Assessment of Choroidal Mass Dimensions Using Static and Dynamic Ultrasonographic Imaging
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Purpose
To develop and validate an artificial intelligence (AI)-based model that automatically measures choroidal mass dimensions on B□scan ophthalmic ultrasound still images and cine loops.
Design
Retrospective diagnostic accuracy study with internal and external validation.
Participants
The dataset included 1,822 still images and 283 cine loops of choroidal masses for model development and testing. An additional 182 still images were used for external validation, and 302 control images with other diagnoses were included to assess specificity
Methods
A deep convolutional neural network (CNN) based on the U-Net architecture was developed to automatically measure the apical height and basal diameter of choroidal masses on B-scan ultrasound. All still images were manually annotated by expert graders and reviewed by a senior ocular oncologist. Cine loops were analyzed frame by frame and the frame with the largest detected mass dimensions was selected for evaluation.
Outcome Measures
The primary outcome was the model’s measurement accuracy, defined by the mean absolute error (MAE) in millimeters, compared to expert manual annotations, for both apical height and basal diameter. Secondary metrics included the Dice coefficient, coefficient of determination (R 2 ), and mean pixel distance between predicted and reference measurements.
Results
On the internal test set of still images, the model successfully detected the tumor in 99.7% of cases. The mean absolute error (MAE) was 0.38 ± 0.55 mm for apical height (95.1% of measurements <1 mm of the expert annotation) and was 0.99 ± 1.15 mm for basal diameter (64.4% of measurements <1 mm). Linear agreement between predicted and reference measurements was strong, with R 2 values of 0.74 for apical height and 0.89 for basal diameter. When applied to the control set of 302 control images, the model demonstrated a moderate false positive rate. On the external validation set, the model maintained comparable accuracy. Among the cine loops, the model detected tumors in 89.4% of cases with comparable accuracy.
Conclusion
Deep learning can deliver fast, reproducible, millimeter□level measurements of choroidal mass dimensions with robust performance across different mass types and imaging sources. These findings support the potential clinical utility of AI-assisted measurement tools in ocular oncology workflows.
