arXiv 2307.121382023-07-22eess.IVcs.CV

SCPAT-GAN：用于人类冠状动脉OCT图像虚拟组织学染色的结构约束与病理感知卷积Transformer-GAN

SCPAT-GAN: Structural Constrained and Pathology Aware Convolutional Transformer-GAN for Virtual Histology Staining of Human Coronary OCT images

Stevens Institute of Technology（史蒂文斯理工学院）；The University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；The Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）

Xueshen Li, Hongshan Liu, Xiaoyu Song, Brigitta C. Brott, Silvio H. Litovsky, Yu Gan

备注：: 9 pages, 4 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有冠状动脉OCT图像虚拟组织学生成方法需大量配对数据、病理区域映射能力不足的问题，提出结构约束与病理感知的SCPAT-GAN，用Transformer网络在结构层施加病理引导，从OCT生成虚拟H&E染色组织学图像。

摘要：

目前亟需从冠状动脉光学相干断层扫描（OCT）图像生成虚拟组织学信息，以更好地指导冠状动脉疾病的治疗。然而，现有方法要么需要大量像素级配对的训练数据集，要么在病理区域映射方面能力有限。为解决这些问题，我们提出了一种结构约束、病理感知的Transformer生成对抗网络，即SCPAT-GAN，用于从OCT图像生成虚拟H&E染色组织学图像。所提出的SCPAT-GAN通过一种新颖设计改进了现有方法，该设计使用基于Transformer的网络在结构层上施加病理引导。

英文摘要：

There is a significant need for the generation of virtual histological information from coronary optical coherence tomography (OCT) images to better guide the treatment of coronary artery disease. However, existing methods either require a large pixel-wisely paired training dataset or have limited capability to map pathological regions. To address these issues, we proposed a structural constrained, pathology aware, transformer generative adversarial network, namely SCPAT-GAN, to generate virtual stained H&E histology from OCT images. The proposed SCPAT-GAN advances existing methods via a novel design to impose pathological guidance on structural layers using transformer-based network.

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。