用自监督方法提升乳腺癌分型分类准确率
Beyond Labels: A Self-Supervised Framework with Masked Autoencoders and Random Cropping for Breast Cancer Subtype Classification
- 基于掩码自编码器与随机裁剪构建自监督学习框架
- 在BRACS数据集上达到优于现有基准的分类性能
- 适合缺乏大量标注数据的病理图像分析场景
本研究针对乳腺癌亚型分类任务，利用掩码自编码器（MAEs）在组织病理图像上进行自监督预训练，学习适用于计算机视觉任务的嵌入表示。该表示能够捕捉病理数据中的信息特征，减少对大规模标注数据的依赖。预训练阶段通过随机裁剪技术从全切片图像（WSIs）中自动生成大规模数据集。我们进一步评估了线性探测器在多类癌症亚型分类任务中的表现。实验在BRACS数据集上进行，结果表明该方法能有效提升下游任务性能，充分发挥视觉变换器（ViTs）与自编码器的互补优势。
原文摘要 · Abstract (English)
This work contributes to breast cancer sub-type classification using histopathological images. We utilize masked autoencoders (MAEs) to learn a self-supervised embedding tailored for computer vision tasks in this domain. This embedding captures informative representations of histopathological data, facilitating feature learning without extensive labeled datasets. During pre-training, we investigate employing a random crop technique to generate a large dataset from WSIs automatically. Additionally, we assess the performance of linear probes for multi-class classification tasks of cancer sub-types using the representations learnt by the MAE. Our approach aims to achieve strong performance on downstream tasks by leveraging the complementary strengths of ViTs and autoencoders. We evaluate our model's performance on the BRACS dataset and compare it with existing benchmarks.
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。