Endo-SemiS：面向内窥镜视频鲁棒半监督图像分割
Endo-SemiS: Towards Robust Semi-Supervised Image Segmentation for Endoscopic Video
- Vanderbilt University（范德比尔特大学）
- Vanderbilt University Medical Center（范德比尔特大学医学中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
Endo-SemiS通过四种策略提升内窥镜视频分割性能，利用未标注数据和互学机制，在有限标注条件下实现更准确的分割结果。
AI中文摘要：
本文提出Endo-SemiS，一种半监督分割框架，用于在有限标注情况下提供可靠的内窥镜视频帧分割。EndoSemiS采用4种策略提高性能，有效利用所有可用数据，尤其是未标注数据：（1）两个单独网络之间的交叉监督，彼此监督；（2）由未标注数据生成的不确定性引导伪标签，通过选择高置信度区域提高其质量；（3）联合伪标签监督，将两个网络的伪标签中可靠的像素聚合，为未标注数据提供准确监督；（4）互学，其中两个网络在特征和图像层面互相学习，减少方差并引导它们朝一致的解决方案发展。此外，还设计了一个单独的校正网络，利用内窥镜视频的时空信息来提高分割性能。Endo-SemiS在两个临床应用上进行评估：输尿管镜下肾结石激光碎石和结肠镜下息肉筛查。与最先进的分割方法相比，Endo-SemiS在有限标注数据的情况下，在两个数据集上均取得了显著优越的结果。代码已公开在https://github.com/MedICL-VU/Endo-SemiS
英文摘要：
In this paper, we present Endo-SemiS, a semi-supervised segmentation framework for providing reliable segmentation of endoscopic video frames with limited annotation. EndoSemiS uses 4 strategies to improve performance by effectively utilizing all available data, particularly unlabeled data: (1) Cross-supervision between two individual networks that supervise each other; (2) Uncertainty-guided pseudo-labels from unlabeled data, which are generated by selecting high-confidence regions to improve their quality; (3) Joint pseudolabel supervision, which aggregates reliable pixels from the pseudo-labels of both networks to provide accurate supervision for unlabeled data; and (4) Mutual learning, where both networks learn from each other at the feature and image levels, reducing variance and guiding them toward a consistent solution. Additionally, a separate corrective network that utilizes spatiotemporal information from endoscopy video to improve segmentation performance. Endo-SemiS is evaluated on two clinical applications: kidney stone laser lithotomy from ureteroscopy and polyp screening from colonoscopy. Compared to state-of-the-art segmentation methods, Endo-SemiS substantially achieves superior results on both datasets with limited labeled data. The code is publicly available at https://github.com/MedICL-VU/Endo-SemiS
