作者：Mohammad Sadegh Nasr Amir Hajighasemi Paul Koomey Parisa Boodaghi Malidarreh Michael Robben Jillur Rahman Saurav Helen H. Shang Manfred Huber Jacob M. Luber
在本文中，我们介绍了一种基于可变自动编码器（VAE）的训练方法，该方法可以以1:512的压缩比对癌症病理切片进行压缩和解压缩，这比文献中先前报道的最新技术（SOTA）要好，同时在临床验证任务中仍保持准确性。该压缩方法在更常见的计算机视觉数据集（如CIFAR10）上进行了测试，我们探索了哪些图像特征能够在癌症成像数据上实现此压缩比，而不是在普通图像上。我们从压缩的潜在空间生成并可视化嵌入，并展示它们如何对数据的临床解释有用，以及未来如何使用这些潜在嵌入来加速临床成像数据的搜索。
In this paper, we introduce a Variational Autoencoder (VAE) based training approach that can compress and decompress cancer pathology slides at a compression ratio of 1:512, which is better than the previously reported state of the art (SOTA) in the literature, while still maintaining accuracy in clinical validation tasks. The compression approach was tested on more common computer vision datasets such as CIFAR10, and we explore which image characteristics enable this compression ratio on cancer imaging data but not generic images. We generate and visualize embeddings from the compressed latent space and demonstrate how they are useful for clinical interpretation of data, and how in the future such latent embeddings can be used to accelerate search of clinical imaging data.
论文链接：http://arxiv.org/pdf/2303.13332v1
更多计算机论文：http://cspaper.cn/