论文标题
从具有弱标签的单元图像中对表型表示的自学学习
Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels
论文作者
论文摘要
我们建议WS-DINO作为一种新型框架，以从细胞的高内感荧光图像学习表型表示中使用弱标记信息。我们的模型基于具有视觉变压器骨干（Dino）的知识蒸馏方法，我们将其用作研究的基准模型。使用WS-DINO，我们用弱标签信息进行了微调，可在高含量显微镜屏幕（处理和化合物）中获得，并在不使用弱性实验室的BBBC021数据集（98％）和非same-compound-and-compatch-and-compatch-and-compatch-and-compatch-and-compatch-and-compatch-and-compatch ysportion（96％）中实现了不同意的动作预测的最先进的性能。我们的方法绕过单细胞种植作为预处理步骤，并使用自发图表表明，该模型学习了结构上有意义的表型特征。
We propose WS-DINO as a novel framework to use weak label information in learning phenotypic representations from high-content fluorescent images of cells. Our model is based on a knowledge distillation approach with a vision transformer backbone (DINO), and we use this as a benchmark model for our study. Using WS-DINO, we fine-tuned with weak label information available in high-content microscopy screens (treatment and compound) and achieve state-of-the-art performance in not-same-compound mechanism of action prediction on the BBBC021 dataset (98%), and not-same-compound-and-batch performance (96%) using the compound as the weak label. Our method bypasses single cell cropping as a pre-processing step, and using self-attention maps we show that the model learns structurally meaningful phenotypic profiles.
