BriefGPT.xyz
Nov, 2023
弱监督学习的良好特征提取器
A Good Feature Extractor Is All You Need for Weakly Supervised Learning in Histopathology
HTML
PDF
Georg Wölflein, Dyke Ferber, Asier Rabasco Meneghetti, Omar S. M. El Nahhas, Daniel Truhn...
TL;DR
深度学习在病理学中的应用包括疾病预测和个体化治疗,研究表明,在计算机病理学中,传统的染色归一化处理在深度学习时代仍然存在争议,采用以自我监督学习训练的特征提取器可以在省内存和计算资源的同时不影响下游性能,同时对染色和图像扩增具有鲁棒性。
Abstract
deep learning
is revolutionising
pathology
, offering novel opportunities in disease prognosis and personalised treatment. Historically,
stain nor
→