arXiv 2302.021502023-02-07cs.CVcs.LGeess.IV

这条肠道并不存在：用于生成逼真无线胶囊内窥镜图像的多尺度残差变分自编码器

This Intestine Does Not Exist: Multiscale Residual Variational Autoencoder for Realistic Wireless Capsule Endoscopy Image Generation

University of Thessaly（塞萨利大学）；Svendborg Hospital（斯文堡医院）；University of Southern Denmark（南丹麦大学）

Dimitrios E. Diamantis, Panagiota Gatoula, Anastasios Koulaouzidis, Dimitris K. Iakovidis

备注：: 10 pages
发表信息：: IEEE Access, 12, 25668-25683 (2024)
DOI：: 10.1109/ACCESS.2024.3366801

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对无线胶囊内窥镜带标注数据稀缺导致GAN训练不稳的问题，提出多尺度残差变分自编码器TIDE，可生成逼真且多样的图像并完全替代真实数据用于分类。

摘要：

医学图像合成已成为一种很有前景的解决方案，可用于解决在基于图像的临床决策支持（CDS）系统中训练机器学习算法所需的带标注医学数据有限的问题。为此，生成对抗网络（GAN）主要被用于通过生成合成图像进行数据增强，从而支持算法训练过程。然而，在无线胶囊内窥镜（WCE）领域，现有公开带标注数据集有限的内容多样性和规模，对GAN的训练稳定性和合成性能均造成不利影响。为了给WCE图像合成提供一种可行方案，本文提出了一种新颖的变分自编码器架构，即“This Intestine Does not Exist”（TIDE）。所提出的架构包含多尺度特征提取卷积块和残差连接，即使在训练图像数量有限的情况下，也能够生成高质量且多样化的数据集。与当前面向增强可用数据集的方法不同，本研究表明，使用TIDE可以用人工生成的数据集完全替代真实WCE数据集，而不会降低分类性能。此外，由经验丰富的WCE专家开展的定性评估和用户评估研究，从医学角度验证了TIDE合成的正常和异常WCE图像均具有足够的逼真度。

英文摘要：

Medical image synthesis has emerged as a promising solution to address the limited availability of annotated medical data needed for training machine learning algorithms in the context of image-based Clinical Decision Support (CDS) systems. To this end, Generative Adversarial Networks (GANs) have been mainly applied to support the algorithm training process by generating synthetic images for data augmentation. However, in the field of Wireless Capsule Endoscopy (WCE), the limited content diversity and size of existing publicly available annotated datasets, adversely affect both the training stability and synthesis performance of GANs. Aiming to a viable solution for WCE image synthesis, a novel Variational Autoencoder architecture is proposed, namely "This Intestine Does not Exist" (TIDE). The proposed architecture comprises multiscale feature extraction convolutional blocks and residual connections, which enable the generation of high-quality and diverse datasets even with a limited number of training images. Contrary to the current approaches, which are oriented towards the augmentation of the available datasets, this study demonstrates that using TIDE, real WCE datasets can be fully substituted by artificially generated ones, without compromising classification performance. Furthermore, qualitative and user evaluation studies by experienced WCE specialists, validate from a medical viewpoint that both the normal and abnormal WCE images synthesized by TIDE are sufficiently realistic.

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。

AI总结：

摘要：

英文摘要：

相关论文