中国科学院分子影像重点实验室知识库

Simple Summary Accurate tumor localization is essential for effective clinical diagnosis and treatment. However, traditional magnetic particle imaging (MPI) algorithms struggle to precisely locate tumors, resulting in challenges when quantifying them. This study aims to address the issue of precise tumor localization in MPI through the application of a deep learning approach. By integrating Convolutional Neural Network (CNN) and Transformer modules, the goal is to improve image quality and enhance the accuracy of tumor quantification in MPI images. The research utilizes a combination of CNN and Transformer modules to capture both global and local features within MPI images. Through the application of deep learning techniques, the study seeks to remove blurry artifacts from reconstructed images, ultimately may help improve the precision of tumor localization and quantification in MPI. This approach holds significant potential for advancing MPI technology and introducing novel methodologies for future medical imaging research. Additionally, the validation of transfer learning on authentic MPI images may enhance the overall accuracy and reliability of MPI image reconstruction.Abstract Background: Magnetic Particle Imaging (MPI) is an emerging molecular imaging technique. However, since X-space reconstruction ignores system properties, it can lead to blurring of the reconstructed image, posing challenges for accurate quantification. To address this issue, we propose the use of deep learning to remove the blurry artifacts; (2) Methods: Our network architecture consists of a combination of Convolutional Neural Network (CNN) and Transformer. The CNN utilizes convolutional layers to automatically extract pixel-level local features and reduces the size of feature maps through pooling layers, effectively capturing local information within the images. The Transformer module is responsible for extracting contextual features from the images and efficiently capturing long-range dependencies, enabling a more effective modeling of global features in the images. By combining the features extracted by both CNN and Transformer, we capture both global and local features simultaneously, thereby improving the quality of reconstructed images; (3) Results: Experimental results demonstrate that the network effectively removes blurry artifacts from the images, and it exhibits high accuracy in precise tumor quantification. The proposed method shows superior performance over the state-of-the-art methods; (4) Conclusions: This bears significant implications for the image quality improvement and clinical application of MPI technology.