The Segment Anything Model (SAM) marks a significant advancement in
segmentation models, offering powerful zero-shot capabilities and dynamic
prompting. However, existing medical SAMs are not suitable for the multi-scale
nature of whole-slide images (WSIs), restricting their effectiveness. To
resolve this drawback, we present WSI-SAM, enhancing SAM with precise object
segmentation capabilities for histopathology images using multi-resolution
patches, while preserving its original prompt-driven design, efficiency, and
zero-shot adaptability. To fully exploit pretrained knowledge while minimizing
training overhead, we keep SAM frozen, only introducing minimal additional
parameters and computation. In particular, we introduce High-Resolution (HR)
token, Low-Resolution (LR) token and dual mask decoder. This decoder integrates
the original SAM mask decoder with a lightweight fusion module that integrates
features at multiple scales. Instead of predicting a mask independently, we
integrate HR and LR token at intermediate layer to jointly learn features of
the same object across multiple resolutions. Experiments show that our WSI-SAM
outperforms state-of-the-art SAM and its variants. In particular, our model
outperforms SAM by 4.1 and 2.5 percent points on a ductal carcinoma in situ
(DCIS) segmentation tasks and breast cancer metastasis segmentation task
(CAMELYON16 dataset). The code will be available at
this https URL

通过使用多分辨率补丁，在保留原始提示驱动设计、高效性和零时适应性的同时，使用精确的对象分割功能增强了 SAM，解决了现有的医学 SAM 在全尺度图像的多尺度本质上并不适用的限制。

WSI-SAM: 多分辨率分割模型 (SAM) 用于组织病理学全切片图像

WSI-SAM: Multi-resolution Segment Anything Model (SAM) for  histopathology whole-slide images

Image anomaly detection consists in detecting images or image portions that
are visually different from the majority of the samples in a dataset. The task
is of practical importance for various real-life applications like biomedical
image analysis, visual inspection in industrial production, banking, traffic
management, etc. Most of the current deep learning approaches rely on image
reconstruction: the input image is projected in some latent space and then
reconstructed, assuming that the network (mostly trained on normal data) will
not be able to reconstruct the anomalous portions. However, this assumption
does not always hold. We thus propose a new model based on the Vision
Transformer architecture with patch masking: the input image is split in
several patches, and each patch is reconstructed only from the surrounding
data, thus ignoring the potentially anomalous information contained in the
patch itself. We then show that multi-resolution patches and their collective
embeddings provide a large improvement in the model's performance compared to
the exclusive use of the traditional square patches. The proposed model has
been tested on popular anomaly detection datasets such as MVTec and head CT and
achieved good results when compared to other state-of-the-art approaches.

基于 Vision Transformer 架构和 Patch 掩蔽技术的图像异常检测方法，将输入图像分成多个分辨率的 Patch，在忽略异常信息的同时对周围数据进行重建，相较传统方法性能更好，MVTec 和 head CT 等数据集上实现了良好的结果。