School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China.
School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China.
J Biomed Inform. 2024 Oct;158:104728. doi: 10.1016/j.jbi.2024.104728. Epub 2024 Sep 21.
Histological classification is a challenging task due to the diverse appearances, unpredictable variations, and blurry edges of histological tissues. Recently, many approaches based on large networks have achieved satisfactory performance. However, most of these methods rely heavily on substantial computational resources and large high-quality datasets, limiting their practical application. Knowledge Distillation (KD) offers a promising solution by enabling smaller networks to achieve performance comparable to that of larger networks. Nonetheless, KD is hindered by the problem of high-dimensional characteristics, which makes it difficult to capture tiny scattered features and often leads to the loss of edge feature relationships.
A novel cross-domain visual prompting distillation approach is proposed, compelling the teacher network to facilitate the extraction of significant high-dimensional features into low-dimensional feature maps, thereby aiding the student network in achieving superior performance. Additionally, a dynamic learnable temperature module based on novel vector-based spatial proximity is introduced to further encourage the student to imitate the teacher.
Experiments conducted on widely accepted histological datasets, NCT-CRC-HE-100K and LC25000, demonstrate the effectiveness of the proposed method and validate its robustness on the popular dermoscopic dataset ISIC-2019. Compared to state-of-the-art knowledge distillation methods, the proposed method achieves better performance and greater robustness with optimal domain adaptation.
A novel distillation architecture, termed VPSP, tailored for histological classification, is proposed. This architecture achieves superior performance with optimal domain adaptation, enhancing the clinical application of histological classification. The source code will be released at https://github.com/xiaohongji/VPSP.
由于组织学组织的外观多样、变化不可预测且边缘模糊，因此组织学分类是一项具有挑战性的任务。最近，许多基于大型网络的方法已经取得了令人满意的性能。然而，这些方法大多严重依赖大量的计算资源和大型高质量数据集，限制了它们的实际应用。知识蒸馏（KD）通过使较小的网络能够实现与较大的网络相当的性能，提供了一个有前途的解决方案。然而，KD 受到高维特征的问题的阻碍，这使得难以捕捉微小的分散特征，并且常常导致边缘特征关系的丢失。
提出了一种新的跨域视觉提示蒸馏方法，迫使教师网络将重要的高维特征提取到低维特征图中，从而帮助学生网络实现卓越的性能。此外，引入了一种基于新颖基于向量的空间接近度的动态可学习温度模块，以进一步鼓励学生模仿老师。
在广泛接受的组织学数据集 NCT-CRC-HE-100K 和 LC25000 上进行的实验证明了所提出方法的有效性，并验证了其在流行的皮肤病学数据集 ISIC-2019 上的稳健性。与最先进的知识蒸馏方法相比，所提出的方法在最佳域自适应方面实现了更好的性能和更大的稳健性。
提出了一种新的用于组织学分类的蒸馏架构，称为 VPSP。该架构在最佳域自适应方面实现了卓越的性能，增强了组织学分类的临床应用。源代码将在 https://github.com/xiaohongji/VPSP 上发布。
