用于显微镜图像的掩码自编码器是细胞生物学的可扩展学习器
Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology
AI总结：
本研究探讨弱监督分类器与自监督掩码自编码器在显微镜图像上的扩展性，提出通道无关的CA-MAE架构，证明其在多任务和跨实验条件数据集上表现优异，为构建细胞生物学基础模型提供支持。
摘要：
将显微镜图像特征化以用于生物学研究仍然是一项重大挑战，特别是对于跨越数百万张图像的大规模实验。本研究探讨了弱监督分类器和自监督掩码自编码器（MAEs）在采用更大模型骨干和显微镜数据集进行训练时的扩展特性。结果表明，基于ViT的MAEs在多种任务上优于弱监督分类器，在召回从公共数据库中整理的已知生物学关系时，实现了高达11.5%的相对提升。此外，我们开发了一种新的通道无关MAE架构（CA-MAE），允许在推理时输入不同数量和顺序通道的图像。我们证明了CA-MAE能有效泛化，方法是在与预训练数据（RPI-93M）通道结构不同、且在不同实验条件下生成的显微镜图像数据集（JUMP-CP）上进行推断和评估。这些发现推动了在显微镜数据上持续研究扩展自监督学习，以构建强大的细胞生物学基础模型，从而有望加速药物发现及相关领域的进展。
英文摘要：
Featurizing microscopy images for use in biological research remains a significant challenge, especially for large-scale experiments spanning millions of images. This work explores the scaling properties of weakly supervised classifiers and self-supervised masked autoencoders (MAEs) when training with increasingly larger model backbones and microscopy datasets. Our results show that ViT-based MAEs outperform weakly supervised classifiers on a variety of tasks, achieving as much as a 11.5% relative improvement when recalling known biological relationships curated from public databases. Additionally, we develop a new channel-agnostic MAE architecture (CA-MAE) that allows for inputting images of different numbers and orders of channels at inference time. We demonstrate that CA-MAEs effectively generalize by inferring and evaluating on a microscopy image dataset (JUMP-CP) generated under different experimental conditions with a different channel structure than our pretraining data (RPI-93M). Our findings motivate continued research into scaling self-supervised learning on microscopy data in order to create powerful foundation models of cellular biology that have the potential to catalyze advancements in drug discovery and beyond.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
