Open-Source Periorbital Segmentation Dataset for Ophthalmic Applications

Abstract

Objective: We aimed to create and validate a dataset for oculoplastic segmentation and periorbital distance prediction.

Design: This was an experimental study.

Subjects: Images of faces from 2 open-source datasets were included in this study.

Methods: The images were sourced from 2 open-source datasets and cropped to include only the eyes. All images had the iris, sclera, lid, caruncle, and brow segmented by 5 trained annotators. Intergrader reliability analysis was done by having 5 annotators annotate the same 100 images randomly selected after at least a 2-week forgetting period. Intragrader analysis was done by having 5 annotators annotate the same 20 images after a 2-week forgetting period. Three DeepLabV3 segmentation models were trained for segmentation using the datasets following standard procedures.

Main outcome measures: The quality of the annotations was evaluated by Dice score through intragrader and intergrader experiments. Segmentation models were trained to demonstrate the dataset's utility for deep learning. The Dice score was used to evaluate deep learning models.

Results: We annotated 2842 images. Agreement between annotators (intergrader) on a randomly selected subset of 100 images was very high, with an average Dice score of 0.82 ± 0.01. Intragrader analysis also demonstrates that the same grader accurately reproduces annotations with an average Dice score, across all classes, of 0.81 ± 0.08. The average Dice score across all classes of a segmentation network trained on the Chicago Facial dataset, the CelebAMask-HQ dataset, and both combined was 0.90 ± 0.11, 0.81 ± 0.20, and 0.84 ± 0.18, respectively.

Conclusions: We have developed a first-of-its-kind dataset for use in oculoplastic and craniofacial segmentation tasks. All the annotations are publicly available for free download. Having access to segmentation datasets designed specifically for oculoplastic surgery will permit more rapid development of clinically useful segmentation networks that can be leveraged for periorbital distance prediction and other downstream tasks. In addition to the annotations, we also provide an open-source toolkit for periorbital distance prediction from segmentation masks, which are available via an application programming interface. The weights of all models have also been open-sourced and are publicly available for use by the community.

Financial disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Keywords: Artificial intelligence; Computer Vision; Datasets; Oculoplastic surgery; Open source.

Figure 1

Representative images and annotations from the CFD and Celeb dataset used to construct the dataset described here. Celeb = CelebAMask-HQ; CFD = Chicago Facial dataset.

Figure 2

Schematic of preprocessing and training pipeline. Full details are described in the methods, but briefly, the dataset was split using an 80/20 train test split. The input image was split at the midline, and both halves of the image (and label) were resized to 256 × 256. A DeepLabV3 model with a ResNet101 backbone pretrained on ImageNet1K was trained for 500 steps. The same preprocessing procedure was used at the test time. Following segmentation, the left and right halves of the image were resized and stitched back together such that the full segmentation mask was the same size as the input.

Figure 3

Pairwise matrices representing intergrader agreement as the average Dice score between graders or DeepLabV3 (DLV3) over 100 randomly sampled images. A, The average pairwise Dice score between all graders, and (B–F) represent the Dice score of the iris, sclera, brow, lid, and caruncle classes respectively.

Figure 4

Periorbital distances on 2 images from the CFD. These distances can be calculated using the toolkit, which we have made available via API. The periorbital distances from the CFD have been released as a benchmark dataset. Blue line denotes horizontal palpebral fissure, green line denotes outer canthal distance, yellow line denotes inner canthal distance, purple lines denote brow heights, light blue lines denotes MRD 1, orange lines denote MRD 2, and red dashed line denotes inner pupillary distance. API = application programming interface; CFD = Chicago Facial dataset.