3d Ct
3D computed tomography (CT) image analysis is a rapidly evolving field focused on developing automated methods for interpreting complex 3D volumetric data, primarily to assist radiologists and improve diagnostic accuracy. Current research heavily utilizes deep learning, employing architectures like 3D U-Nets, transformers, and generative adversarial networks (GANs) for tasks such as segmentation, classification (e.g., COVID-19 detection), and even the synthesis of high-quality CT images from lower-resolution sources like X-rays. These advancements hold significant promise for improving diagnostic efficiency, reducing healthcare costs, and enabling more precise treatment planning in various medical applications, including radiation therapy and oncology.
Papers
VISTA3D: Versatile Imaging SegmenTation and Annotation model for 3D Computed Tomography
Yufan He, Pengfei Guo, Yucheng Tang, Andriy Myronenko, Vishwesh Nath, Ziyue Xu, Dong Yang, Can Zhao, Benjamin Simon, Mason Belue, Stephanie Harmon, Baris Turkbey, Daguang Xu, Wenqi Li
MTS-Net: Dual-Enhanced Positional Multi-Head Self-Attention for 3D CT Diagnosis of May-Thurner Syndrome
Yixin Huang, Yiqi Jin, Ke Tao, Kaijian Xia, Jianfeng Gu, Lei Yu, Lan Du, Cunjian Chen