发现病理图像数据集存在严重偏差，简单模型即可高精度分类
NCT-CRC-HE: Not All Histopathological Datasets Are Equally Useful
- 用颜色直方图等低级特征即可达到82%准确率，无需细胞形态信息
- 仅3个颜色通道特征的极简模型在9类任务上超50%准确率
- 预训练EfficientNet-B0模型达97.7%准确率，优于复杂专用模型
近年来大量深度学习方法被用于组织病理图像分析，尽管其精度普遍很高，但其性能是否受显微成像处理和预处理带来的低级图像属性影响仍存疑问。本文分析了广泛使用的NCT-CRC-HE-100K结直肠癌数据集，揭示其存在显著数据偏差：不恰当的颜色归一化、不同类别间严重的JPEG伪影差异，以及因动态范围处理错误导致的完全损坏组织样本。实验表明，仅使用每张图像3个特征（红、绿、蓝颜色强度）的最简模型在9类任务上准确率超过50%，而基于颜色直方图的模型（未捕捉细胞形态特征）准确率超过82%。此外，一个基础的ImageNet预训练EfficientNet-B0模型在该数据集上准确率超过97.7%，超越所有此前针对此任务设计的专用模型，包括大型细胞形态感知神经网络与专用基础模型。相关代码与预训练模型已公开于https://github.com/gmalivenko/NCT-CRC-HE-experiments。
原文摘要 · Abstract (English)
Numerous deep learning-based solutions have been proposed for histopathological image analysis over the past years. While they usually demonstrate exceptionally high accuracy, one key question is whether their precision might be affected by low-level image properties not related to histopathology but caused by microscopy image handling and pre-processing. In this paper, we analyze a popular NCT-CRC-HE-100K colorectal cancer dataset used in numerous prior works and show that both this dataset and the obtained results may be affected by data-specific biases. The most prominent revealed dataset issues are inappropriate color normalization, severe JPEG artifacts inconsistent between different classes, and completely corrupted tissue samples resulting from incorrect image dynamic range handling. We show that even the simplest model using only 3 features per image (red, green and blue color intensities) can demonstrate over 50% accuracy on this 9-class dataset, while using color histogram not explicitly capturing cell morphology features yields over 82% accuracy. Moreover, we show that a basic EfficientNet-B0 ImageNet pretrained model can achieve over 97.7% accuracy on this dataset, outperforming all previously proposed solutions developed for this task, including dedicated foundation histopathological models and large cell morphology-aware neural networks. The NCT-CRC-HE dataset is publicly available and can be freely used to replicate the presented results. The codes and pre-trained models used in this paper are available at https://github.com/gmalivenko/NCT-CRC-HE-experiments
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。