论文标题
μSplit：显微镜数据的有效图像分解
μSplit: efficient image decomposition for microscopy data
论文作者
论文摘要
我们提出了μSplit，这是一种在荧光显微镜图像的背景下用于训练的图像分解的专用方法。我们发现，当在训练过程中使用大图像贴片时，使用常规深度体系结构实现最佳结果，这使记忆消耗成为进一步提高性能的限制因素。因此，我们引入了横向上下文化（LC），这是一种新型的元构造，可以使内存有效地掺入大图像膜，我们观察到的是解决手头图像分解任务的关键成分。我们将LC与U-NET，分层AE和分层VAE集成，为此我们制定了修改的Elbo损失。此外，LC可以使培训比其他可能的更深层的层次模型，有趣的是，有助于减少使用瓷砖Vae预测时固有地避免的瓷砖伪像。我们将μSplit应用于五个分解任务，一个在合成数据集上，另外四个来自实际显微镜数据。我们的方法始终取得最佳结果（平均改进为2.25 dB PSNR的最佳基线），同时需要少于GPU内存。可以在https://github.com/juglab/usplit上找到我们的代码和数据集。
We present μSplit, a dedicated approach for trained image decomposition in the context of fluorescence microscopy images. We find that best results using regular deep architectures are achieved when large image patches are used during training, making memory consumption the limiting factor to further improving performance. We therefore introduce lateral contextualization (LC), a novel meta-architecture that enables the memory efficient incorporation of large image-context, which we observe is a key ingredient to solving the image decomposition task at hand. We integrate LC with U-Nets, Hierarchical AEs, and Hierarchical VAEs, for which we formulate a modified ELBO loss. Additionally, LC enables training deeper hierarchical models than otherwise possible and, interestingly, helps to reduce tiling artefacts that are inherently impossible to avoid when using tiled VAE predictions. We apply μSplit to five decomposition tasks, one on a synthetic dataset, four others derived from real microscopy data. Our method consistently achieves best results (average improvements to the best baseline of 2.25 dB PSNR), while simultaneously requiring considerably less GPU memory. Our code and datasets can be found at https://github.com/juglab/uSplit.
