Affiliations: [a] State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| [b]
University of Chinese Academy of Sciences, Beijing, China
| [c] National Center for Electron Microscopy in Beijing, School of Materials Science and Engineering, The State Key Laboratory of New Ceramics and Fine Processing, Key Laboratory of Advanced Materials (MOE), Tsinghua University, Beijing, China
| [d] Focus e-Beam Technology (Beijing) Co., Ltd., Beijing, China
| [e] College of Computer Science, Nankai University, Tianjin, China
Correspondence:
[*]
Corresponding author. Guoqing Li, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China. E-mail: guoqing.li@ia.ac.cn.
Abstract: Recent advances in high-throughput electron microscopy (EM) have revolutionized the examination of microstructures by enabling fast EM image generation. However, accurately segmenting EM images remains challenging due to inherent characteristics, including low contrast and subtle grayscale variations. Moreover, as manually annotated EM images are limited, it is usually impractical to utilize deep learning techniques for EM image segmentation. To address these challenges, the pyramid multiscale channel attention network (PmcaNet) is specifically designed. PmcaNet employs a convolutional neural network-based architecture and a multiscale feature pyramid to effectively capture global context information, enhancing its ability to comprehend the intricate structures within EM images. To enable the rapid extraction of channel-wise dependencies, a novel attention module is introduced to enhance the representation of intricate nonlinear features within the images. The performance of PmcaNet is evaluated on two general EM image segmentation datasets as well as a homemade dataset of superalloy materials, regarding pixel-wise accuracy and mean intersection over union (mIoU) as evaluation metrics. Extensive experiments demonstrate that PmcaNet outperforms other models on the ISBI 2012 dataset, achieving 87.85% pixel-wise accuracy and 73.11% mean intersection over union (mIoU), while also advancing results on the Kathuri and SEM-material datasets.
