Consistency Regularisation in Varying Contexts and Feature Perturbations for Semi-Supervised Semantic Segmentation of Histology Images
Consistency Regularisation in Varying Contexts and Feature Perturbations for Semi-Supervised Semantic Segmentation of Histology Images
复制标题
DOI：
10.48550/arxiv.2301.13141
复制
发表时间：
2023-01
影响因子：
10.9
通讯作者：
R. M. S. Bashir;Talha Qaiser;S. Raza;N. Rajpoot
中科院分区：
文献类型：
--
作者：
R. M. S. Bashir;Talha Qaiser;S. Raza;N. Rajpoot
组织学图像中各种组织和细胞核类型的语义分割是计算病理学（CPath）领域中许多下游任务的基础。近年来，深度学习（DL）方法在分割任务上表现良好，但DL方法通常需要大量的像素级注释数据。逐像素注释有时需要专家的知识和时间，这是费力且昂贵的。在本文中，我们提出了一种基于一致性的半监督学习（SSL）方法，该方法可以通过利用大量未标记的数据进行模型训练来帮助减轻这一挑战，从而减轻对大型注释数据集的需求。然而，由于训练数据有限，SSL模型也可能容易受到变化的上下文和特征扰动的影响，从而表现出较差的泛化能力。我们提出了一种SSL方法，通过对不同的上下文和特征扰动实施一致性，从标记和未标记的图像中学习鲁棒的特征。所提出的方法采用了上下文感知的一致性，通过对比对重叠的图像在一个像素明智的方式从不断变化的上下文，从而产生强大的和上下文不变的功能。我们表明，交叉一致性训练使得编码器特征对不同的扰动保持不变，并提高了预测置信度。最后，采用熵最小化来进一步提高来自未标记数据的最终预测图的置信度。我们在两个公开的大型数据集（BCSS和MoNuSeg）上进行了一组广泛的实验，与最先进的方法相比，表现出上级性能。
Semantic segmentation of various tissue and nuclei types in histology images is fundamental to many downstream tasks in the area of computational pathology (CPath). In recent years, Deep Learning (DL) methods have been shown to perform well on segmentation tasks but DL methods generally require a large amount of pixel-wise annotated data. Pixel-wise annotation sometimes requires expert's knowledge and time which is laborious and costly to obtain. In this paper, we present a consistency based semi-supervised learning (SSL) approach that can help mitigate this challenge by exploiting a large amount of unlabelled data for model training thus alleviating the need for a large annotated dataset. However, SSL models might also be susceptible to changing context and features perturbations exhibiting poor generalisation due to the limited training data. We propose an SSL method that learns robust features from both labelled and unlabelled images by enforcing consistency against varying contexts and feature perturbations. The proposed method incorporates context-aware consistency by contrasting pairs of overlapping images in a pixel-wise manner from changing contexts resulting in robust and context invariant features. We show that cross-consistency training makes the encoder features invariant to different perturbations and improves the prediction confidence. Finally, entropy minimisation is employed to further boost the confidence of the final prediction maps from unlabelled data. We conduct an extensive set of experiments on two publicly available large datasets (BCSS and MoNuSeg) and show superior performance compared to the state-of-the-art methods.