重新审视基础模型在小像素病理图像细胞级分析中的作用——在小补丁约束下训练数据规模和模糊扰动对CNN和视觉变换器的影响
Revisiting the Role of Foundation Models in Cell-Level Histopathological Image Analysis under Small-Patch Constraints -- Effects of Training Data Scale and Blur Perturbations on CNNs and Vision Transformers
AI总结：
本研究探讨了在小补丁约束下，基础模型与任务特定架构在细胞级病理图像分析中的性能差异，发现任务特定架构在数据充足时表现更优。
摘要：
背景和目的：细胞级病理图像分析需要处理极小的图像补丁（40x40像素），远低于标准ImageNet的分辨率。目前尚不清楚现代深度学习架构和基础模型是否能在这种约束下学习到鲁棒且可扩展的表示。我们系统评估了小补丁细胞分类任务的架构适配性和数据规模效应。方法：我们分析了303例结直肠癌病例的CD103/CD8免疫染色，生成了185,432张标注的细胞图像。八种任务特定的架构在多个数据规模下从头训练（FlagLimit：256-16,384样本每类），三种基础模型通过线性探测和输入调整到224x224像素后进行微调进行评估。鲁棒性对模糊的评估使用预处理和后处理的高斯扰动。结果：任务特定模型随着数据规模的增加而持续改进，而基础模型在中等样本规模时饱和。一种针对小补丁优化的视觉变换器（CustomViT）实现了最高准确率，其准确率优于所有基础模型，且推理成本显著较低。模糊鲁棒性在各架构间表现相当，未观察到基础模型在定性上的优势。结论：在极端空间约束下进行细胞级分类时，一旦有足够的训练数据，任务特定架构比基础模型更有效和高效。更高的干净准确率并不意味着鲁棒性更优，大预训练模型在小补丁情况下提供有限的益处。
英文摘要：
Background and objective: Cell-level pathological image analysis requires working with extremely small image patches (40x40 pixels), far below standard ImageNet resolutions. It remains unclear whether modern deep learning architectures and foundation models can learn robust and scalable representations under this constraint. We systematically evaluated architectural suitability and data-scale effects for small-patch cell classification. Methods: We analyzed 303 colorectal cancer specimens with CD103/CD8 immunostaining, generating 185,432 annotated cell images. Eight task-specific architectures were trained from scratch at multiple data scales (FlagLimit: 256--16,384 samples per class), and three foundation models were evaluated via linear probing and fine-tuning after resizing inputs to 224x224 pixels. Robustness to blur was assessed using pre- and post-resize Gaussian perturbations. Results: Task-specific models improved consistently with increasing data scale, whereas foundation models saturated at moderate sample sizes. A Vision Transformer optimized for small patches (CustomViT) achieved the highest accuracy, outperforming all foundation models with substantially lower inference cost. Blur robustness was comparable across architectures, with no qualitative advantage observed for foundation models. Conclusion: For cell-level classification under extreme spatial constraints, task-specific architectures are more effective and efficient than foundation models once sufficient training data are available. Higher clean accuracy does not imply superior robustness, and large pre-trained models offer limited benefit in the small-patch regime.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
