发表机构
The University of Tokyo; Environmental Science Center, The University of Tokyo; Collaborative Research Institute for Innovative Microbiology, The University of Tokyo（东京大学; 东京大学环境科学中心; 东京大学创新微生物学协同研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究比较了不同模型架构与学习策略在活性污泥显微图像分类中的表现，发现Transformer与替代预训练有效，保持视野的降采样更优，且深度学习准确率优于定量图像分析。
AI 中文摘要
显微图像分析长期以来被认为是监测活性污泥的一种有前景的方法。近年来，基于深度学习的图像分析因其高性能而在该领域得到越来越多的采用。然而，以往关于活性污泥显微图像分析的研究很少探索基于Transformer的模型或自监督基础模型，而是依赖CNN和监督式ImageNet预训练。此外，以往研究常常对图像尺寸进行降采样，但降采样的影响尚未得到充分研究，降采样策略与图像分析性能之间的关系仍不清楚。而且，尚无研究将深度学习性能与定量图像分析（QIA）进行定量比较，QIA在深度学习出现之前被广泛使用。在本研究中，为了考察模型架构和学习策略如何影响活性污泥显微图像分析的性能，并定量确定深度学习是否优于QIA，我们制备了三种类型的活性污泥样本，对其显微图像进行分类，并评估分类准确率。结果表明，基于Transformer的架构和替代预训练方法在分类准确率方面是有效的。我们的降采样分析表明，使用过小的图像会降低准确率，但将图像尺寸增大到一定程度以上并不能进一步提高准确率。此外，分析表明，为实现高分类准确率，保持视野比保持分辨率是更有效的降采样策略。最后，我们深度学习与QIA的比较表明，深度学习在准确率方面优于QIA。
英文摘要
Microscopic image analysis has long been recognized as a promising approach for monitoring activated sludge. In recent years, deep learning-based image analysis has been increasingly adopted in this field because of its high performance. However, previous studies on microscopic image analysis of activated sludge have rarely explored transformer-based models or self-supervised foundation models and have instead relied on CNNs and supervised ImageNet pretraining. In addition, previous studies often downsampled image sizes, but the effects of downsampling have not been sufficiently investigated, and the relationship between downsampling strategies and image analysis performance remains unclear. Furthermore, no study has quantitatively compared deep learning performance with quantitative image analysis (QIA), which was widely used before the emergence of deep learning. In this study, to examine how model architecture and learning strategies affect performance in microscopic image analysis of activated sludge and to quantitatively determine whether deep learning outperforms QIA, we prepared three types of activated sludge samples, classified their microscopic images, and evaluated classification accuracy. Our results showed that transformer-based architectures and alternative pretraining methods were effective in terms of classification accuracy. Our downsampling analysis showed that using overly small images reduced accuracy, but increasing image size beyond a certain point did not improve it further. In addition, the analysis indicated that, to achieve high classification accuracy, maintaining the field of view was a more effective downsampling strategy than maintaining resolution. Finally, our comparison between deep learning and QIA showed that deep learning outperformed QIA in terms of accuracy.
