A Heart Image Segmentation Method Based on Position Attention Mechanism and Inverted Pyramid
Author:
Luo Jinbin1, Wang Qinghui1, Zou Ruirui1, Wang Ying1, Liu Fenglin1, Zheng Haojie2, Du Shaoyi3, Yuan Chengzhi4
Affiliation:
1. School of Physics and Mechanical and Electrical Engineering, Longyan University, Longyan 364012, China 2. School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, China 3. Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, China 4. Department of Mechanical, Industrial and Systems Engineering, University of Rhode Island, Kingston, RI 02881, USA
Abstract
In the realm of modern medicine, medical imaging stands as an irreplaceable pillar for accurate diagnostics. The significance of precise segmentation in medical images cannot be overstated, especially considering the variability introduced by different practitioners. With the escalating volume of medical imaging data, the demand for automated and efficient segmentation methods has become imperative. This study introduces an innovative approach to heart image segmentation, embedding a multi-scale feature and attention mechanism within an inverted pyramid framework. Recognizing the intricacies of extracting contextual information from low-resolution medical images, our method adopts an inverted pyramid architecture. Through training with multi-scale images and integrating prediction outcomes, we enhance the network’s contextual understanding. Acknowledging the consistent patterns in the relative positions of organs, we introduce an attention module enriched with positional encoding information. This module empowers the network to capture essential positional cues, thereby elevating segmentation accuracy. Our research resides at the intersection of medical imaging and sensor technology, emphasizing the foundational role of sensors in medical image analysis. The integration of sensor-generated data showcases the symbiotic relationship between sensor technology and advanced machine learning techniques. Evaluation on two heart datasets substantiates the superior performance of our approach. Metrics such as the Dice coefficient, Jaccard coefficient, recall, and F-measure demonstrate the method’s efficacy compared to state-of-the-art techniques. In conclusion, our proposed heart image segmentation method addresses the challenges posed by diverse medical images, offering a promising solution for efficiently processing 2D/3D sensor data in contemporary medical imaging.
Funder
Natural Science Foundation of Fujian Province External Collaboration Project of Science and Technology Department of Fujian Province Fujian Province Chinese Academy of Sciences STS Program Supporting Project Qimai Science and Technology Innovation Project of Wuping Country Longyan Economic Development Zone (High-tech Zone) Qimai Technology Innovation Fund Project
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference51 articles.
1. Azam, M.A., Khan, K.B., Salahuddin, S., Rehman, E., Khan, S.A., Khan, M.A., and Gandomi, A.H. (2022). A review on multimodal medical image fusion: Compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics. Comput. Biol. Med., 144. 2. Sakshi, and Kukreja, V (2023). Image Segmentation Techniques: Statistical, Comprehensive, Semi-Automated Analysis and an Application Perspective Analysis of Mathematical Expressions. Arch. Comput. Methods Eng., 30, 457–495. 3. Review the state-of-the-art technologies of semantic segmentation based on deep learning;Mo;Neurocomputing,2022 4. Gradient-based learning applied to document recognition;LeCun;Proc. IEEE,1998 5. ImageNet classification with deep convolutional neural networks;Krizhevsky;Commun. Acm,2017
|
|