.png){kind=icon}
返回
Self-supervised driven consistency training for annotation efficient histopathology image analysis
.png){kind=icon}
OA
AI
DOI：10.1016/j.media.2021.102256.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Training a neural network with a large labeled dataset is still a dominant paradigm in computational histopathology. However, obtaining such exhaustive manual annotations is often expensive, laborious, and prone to inter and intra-observer variability. While recent self-supervised and semi-supervised methods can alleviate this need by learning unsupervised feature representations, they still struggle to generalize well to downstream tasks when the number of labeled instances is small. In this work, we overcome this challenge by leveraging both task-agnostic and task-specific unlabeled data based on two novel strategies: (i) a self-supervised pretext task that harnesses the underlying multi-resolution contextual cues in histol-ogy whole-slide images to learn a powerful supervisory signal for unsupervised representation learning; (ii) a new teacher-student semi-supervised consistency paradigm that learns to effectively transf er the pretrained representations to downstream tasks based on prediction consistency with the task-specific unlabeled data. We carry out extensive validation experiments on three histopathology benchmark datasets across two classification and one regression based tasks, i.e., tumor metastasis detection, tissue type classifica-tion, and tumor cellularity quantification. Under limited-label data, the proposed method yields tangible improvements, which is close to or even outperforming other state-of-the-art self-supervised and su-pervised baselines. Furthermore, we empirically show that the idea of bootstrapping the self-supervised pretrained features is an effective way to improve the task-specific semi-supervised learning on stan-dard benchmarks. Code and pretrained models are made available at: https://github.com/srinidhiPY/ SSL _ CR _ Histo . (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Self-supervised learning
Semi-supervised learning
Limited annotations
Histopathology image analysis
Digital pathology
期刊
IF:
11.8
论文数:
3.8K
被引数:
2.4W
机构
引用论文
Clinical-grade computational pathology using weakly supervised deep learning on whole slide images在整个幻灯片图像上使用弱监督深度学习的临床级计算病理学.png)
NATURE MEDICINE
OAAI
NATURE MEDICINEIF50
OAAI分享收藏The Role of CD80, CD86, and CTLA4 in Alloimmune Responses and the Induction of Long-Term Allograft SurvivalCD80，CD86和CTLA4在同种免疫反应中的作用以及诱导同种异体移植长期存活OAAI
OAAI分享收藏Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology数字病理学中的人工智能-诊断和精确肿瘤学的新工具OAAI
OAAI分享收藏Self-supervised learning for medical image analysis using image context restorationMEDICAL IMAGE ANALYSISOAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏Natural History and Prognosis of Epilepsy: Report of a Multi‐institutional Study in JapanEpilepsia
EpilepsiaIF0
PREAI
分享收藏
查看更多内容