发表机构
University of Thessaly（色萨利大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对内窥镜图像跨数据集性能下降问题，提出基于参考的统计颜色协调方法，在息肉检测中提升跨数据集性能最高达30.7%，无需重新训练。
AI 中文摘要
内窥镜图像分析中的一个重要问题是，用于此目的的机器学习（ML）模型在应用于来自与训练集图像采集所用内窥镜不同的内窥镜所获取的图像时，通常表现不佳。来自不同内窥镜的图像的主要差异在于其颜色分布，这既取决于图像传感器，也取决于所使用的光源。尽管先前的研究已强调这一挑战，但据我们所知，此前尚未明确解决该问题。本研究聚焦于此问题，并提出了一种非常简单但有效的方法。该方法实现了一种基于参考的图像协调，减少了内窥镜数据集之间的全局外观差异。具体而言，它从选定的参考数据集中提取CIE-Lab颜色空间中的全局颜色统计信息，并应用统计性的逐通道变换，将每个目标图像映射到参考数据集图像的外观。该方法在灵活结肠镜检查和胶囊内窥镜数据集中的息肉检测背景下，采用数据集级别的交叉验证协议进行评估。结果表明，所提出的协调方法持续提高了跨数据集性能，最高提升达30.7%，优于相关基线和最先进的方法。结果还表明，泛化差距的很大一部分是由低层次外观变化驱动的，这种变化可以在不重新训练的情况下得到缓解。
英文摘要
A significant problem in endoscopic image analysis is that the machine learning (ML) models used for this purpose usually underperform when applied on images acquired from endoscopes that are different from those used to acquire the images of their training set. The main difference of the images originating from different endoscopes is their color distributions, which depend both on the image sensors and the light sources used. Although previous studies have highlighted this challenge, to the best of our knowledge it has not been previously explicitly tackled. This study focuses on this problem and proposes very simple but impactful method. It implements a reference-based image harmonization that reduces global appearance differences between endoscopic datasets. Specifically, it extracts global color statistics from a chosen reference dataset in the CIE-Lab color space and applies a statistical channel-wise transformation to map each target image toward the appearance of the images of the reference dataset. The method is evaluated in the context of polyp detection in both flexible colonoscopy and capsule endoscopy datasets using a dataset-level cross validation protocol. The results indicate that the proposed harmonization consistently improves cross-dataset performance up to 30.7%, outperforming relevant baseline and state-of-the-art methods. The results indicate that a substantial part of the generalization gap is driven by low-level appearance variation that can be mitigated without retraining.
