Giap Binh Duong, Srinivasan Karthik, Mahmoud Ossama, Ballouz Dena, Lustre Jefferson, Likosky Keely, Mian Shahzad I, Tannen Bradford L, Nallasamy Nambi
Kellogg Eye Center, Department of Ophthalmology & Visual Sciences, University of Michigan, 1000 Wall Street, Ann Arbor, Michigan, 48105.
Department of Vitreo Retinal, Aravind Eye Hospital, Chennai, Tamil Nadu, 600077, India.
Ophthalmol Sci. 2024 Aug 22;5(1):100597. doi: 10.1016/j.xops.2024.100597. eCollection 2025 Jan-Feb.
Pupillary instability is a known risk factor for complications in cataract surgery. This study aims to develop and validate an innovative and reliable computational framework for the automated assessment of pupil morphologic changes during the various phases of cataract surgery.
Retrospective surgical video analysis.
Two hundred forty complete surgical video recordings, among which 190 surgeries were conducted without the use of pupil expansion devices (PEDs) and 50 were performed with the use of a PED.
The proposed framework consists of 3 stages: feature extraction, deep learning (DL)-based anatomy recognition, and obstruction (OB) detection/compensation. In the first stage, surgical video frames undergo noise reduction using a tensor-based wavelet feature extraction method. In the second stage, DL-based segmentation models are trained and employed to segment the pupil, limbus, and palpebral fissure. In the third stage, obstructed visualization of the pupil is detected and compensated for using a DL-based algorithm. A dataset of 5700 intraoperative video frames across 190 cataract surgeries in the BigCat database was collected for validating algorithm performance.
The pupil analysis framework was assessed on the basis of segmentation performance for both obstructed and unobstructed pupils. Classification performance of models utilizing the segmented pupil time series to predict surgeon use of a PED was also assessed.
An architecture based on the Feature Pyramid Network model with Visual Geometry Group 16 backbone integrated with the adaptive wavelet tensor feature extraction feature extraction method demonstrated the highest performance in anatomy segmentation, with Dice coefficient of 96.52%. Incorporation of an OB compensation algorithm improved performance further (Dice 96.82%). Downstream analysis of framework output enabled the development of a Support Vector Machine-based classifier that could predict surgeon usage of a PED prior to its placement with 96.67% accuracy and area under the curve of 99.44%.
The experimental results demonstrate that the proposed framework (1) provides high accuracy in pupil analysis compared with human-annotated ground truth, (2) substantially outperforms isolated use of a DL segmentation model, and (3) can enable downstream analytics with clinically valuable predictive capacity.
Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
瞳孔不稳定是白内障手术并发症的已知风险因素。本研究旨在开发并验证一种创新且可靠的计算框架，用于自动评估白内障手术各阶段瞳孔形态变化。
回顾性手术视频分析。
240份完整的手术视频记录，其中190例手术未使用瞳孔扩张装置（PED），50例手术使用了PED。
所提出的框架包括3个阶段：特征提取、基于深度学习（DL）的解剖结构识别以及遮挡（OB）检测/补偿。在第一阶段，使用基于张量的小波特征提取方法对手术视频帧进行降噪处理。在第二阶段，训练并采用基于DL的分割模型来分割瞳孔、角膜缘和睑裂。在第三阶段，使用基于DL的算法检测并补偿瞳孔的遮挡可视化。收集了BigCat数据库中190例白内障手术的5700个术中视频帧数据集，以验证算法性能。
基于遮挡和未遮挡瞳孔的分割性能对瞳孔分析框架进行评估。还评估了利用分割后的瞳孔时间序列预测外科医生是否使用PED的模型的分类性能。
基于带有视觉几何组16主干的特征金字塔网络模型并集成自适应小波张量特征提取方法的架构在解剖结构分割中表现出最高性能，骰子系数为96.52%。纳入OB补偿算法进一步提高了性能（骰子系数96.82%）。对框架输出的下游分析促成了基于支持向量机的分类器的开发，该分类器能够在放置PED之前预测外科医生的使用情况，准确率为96.67%，曲线下面积为99.44%。
实验结果表明，所提出的框架（1）与人工标注的真值相比，在瞳孔分析中具有高精度；（2）明显优于单独使用DL分割模型；（3）能够实现具有临床价值预测能力的下游分析。
在本文末尾的脚注和披露中可能会发现专有或商业披露信息。
