Label2label: training a neural network to selectively restore cellular structures in fluorescence microscopy.
Label2label: training a neural network to selectively restore cellular structures in fluorescence microscopy.
复制标题
DOI：
10.1242/jcs.258994
复制
发表时间：
2022-02-01
影响因子：
4
通讯作者：
McConnell G
中科院分区：
文献类型：
--
作者：
Kölln LS;Salem O;Valli J;Hansen CG;McConnell G
免疫荧光显微镜通常用于可视化决定其细胞功能的蛋白质的空间分布。然而，非特异性抗体结合通常导致高胞质背景信号，降低靶结构的图像对比度。最近，卷积神经网络（CNN）被成功地用于免疫荧光显微镜的图像恢复，但目前的方法不能纠正这些背景信号。我们报告了一种训练CNN以减少免疫荧光图像中非特异性信号的新方法;我们将这种方法命名为label 2label（L2 L）。在L2 L中，CNN使用针对相同细胞结构的两个不同标签的图像对进行训练。我们表明，经过L2 L训练后，网络预测图像的目标结构的对比度显着增加，这在实现多尺度结构相似性损失函数后得到进一步改善。在这里，我们的研究结果表明，训练数据中的样本差异减少了用其他方法观察到的幻觉效应。我们进一步评估了循环生成对抗网络的性能，并表明可以训练CNN来分离两个目标的叠加免疫荧光图像中的结构。总结：Label 2label是一种新的基于深度学习的图像恢复方法，可减少细胞结构免疫荧光图像中的细胞溶质背景信号。
Immunofluorescence microscopy is routinely used to visualise the spatial distribution of proteins that dictates their cellular function. However, unspecific antibody binding often results in high cytosolic background signals, decreasing the image contrast of a target structure. Recently, convolutional neural networks (CNNs) were successfully employed for image restoration in immunofluorescence microscopy, but current methods cannot correct for those background signals. We report a new method that trains a CNN to reduce unspecific signals in immunofluorescence images; we name this method label2label (L2L). In L2L, a CNN is trained with image pairs of two non-identical labels that target the same cellular structure. We show that after L2L training a network predicts images with significantly increased contrast of a target structure, which is further improved after implementing a multiscale structural similarity loss function. Here, our results suggest that sample differences in the training data decrease hallucination effects that are observed with other methods. We further assess the performance of a cycle generative adversarial network, and show that a CNN can be trained to separate structures in superposed immunofluorescence images of two targets. Summary: Label2label is a new deep learning-based image restoration method that reduces cytosolic background signals in immunofluorescence images of cellular structures.
登录
查看更多内容
影响因子：
56.9
作者：
Bates, Mark;Huang, Bo;Zhuang, Xiaowei
通讯作者：
Zhuang, Xiaowei
影响因子：
3.2
作者：
Saper, Clifford B.
通讯作者：
Saper, Clifford B.
影响因子：
4
作者：
Martino F;Perestrelo AR;Vinarský V;Pagliari S;Forte G
通讯作者：
Forte G
影响因子：
2.4
作者：
Suzuki T;Matsuzaki T;Hagiwara H;Aoki T;Takata K
通讯作者：
Takata K
计算机标签：预测未标记图像中的荧光标签。
影响因子：
64.5
作者：
Christiansen EM;Yang SJ;Ando DM;Javaherian A;Skibinski G;Lipnick S;Mount E;O'Neil A;Shah K;Lee AK;Goyal P;Fedus W;Poplin R;Esteva A;Berndl M;Rubin LL;Nelson P;Finkbeiner S
通讯作者：
Finkbeiner S