Journal Article

Multihead Attention U‐Net for Magnetic Particle Imaging–Computed Tomography Image Segmentation

Piyawattanametha, Wibool, Juhong, Aniwat, Li, Bo, Bumpers, Harvey, Agnew, Dalen W., Luker, Gary D., Qiu, Zhen, Yang, Chia‐Wei, Liu, Yifan, Yao, Cheng‐You, Huang, Xuefei, Lei, Yu Leo

2024

Overview

Magnetic particle imaging (MPI) is an emerging noninvasive molecular imaging modality with high sensitivity and specificity, exceptional linear quantitative ability, and potential for successful applications in clinical settings. Computed tomography (CT) is typically combined with the MPI image to obtain more anatomical information. Herein, a deep learning‐based approach for MPI‐CT image segmentation is presented. The dataset utilized in training the proposed deep learning model is obtained from a transgenic mouse model of breast cancer following administration of indocyanine green (ICG)‐conjugated superparamagnetic iron oxide nanoworms (NWs‐ICG) as the tracer. The NWs‐ICG particles progressively accumulate in tumors due to the enhanced permeability and retention (EPR) effect. The proposed deep learning model exploits the advantages of the multihead attention mechanism and the U‐Net model to perform segmentation on the MPI‐CT images, showing superb results. In addition, the model is characterized with a different number of attention heads to explore the optimal number for our custom MPI‐CT dataset. The use of the multihead attention mechanism is proposed to enhance the U‐Net model's capability to perform segmentation on magnetic particle imaging (MPI)–computed tomography (CT) images of a transgenic mouse with breast tumors, showing encouraging results. The mouse is injected with promising tumor‐targeting nanoparticles, namely indocyanine green‐conjugated superparamagnetic iron oxide nanoworms (NWs‐ICG) as an MPI tracer.

• Publisher: John Wiley & Sons, Inc,Wiley Blackwell (John Wiley & Sons),Wiley
• Subject: Artificial intelligence / Computed tomography / Data analysis / Datasets / Deep learning / Image enhancement / Image segmentation / Iron oxides / Magnetic fields / magnetic iron oxide nanoworms / magnetic particle imaging / magnetic particle imaging–computed tomography / Magnetic resonance imaging / Medical imaging / Nanoparticles / Nanostructured materials / Neural networks / Tomography / Tumors