1 四川通信科研规划设计有限责任公司, 四川成都 610041
2 电子科技大学 a.信息与软件工程学院
3 电子科技大学 b.计算机科学与工程学院, 四川成都 611731
传统 U-Net语义分割模型在医学影像领域具有广泛的应用, 但该模型的准确率受限于单一尺度的预测模式以及上下采样引起的信息丢失。针对上述问题, 本文基于 U-Net编码—解码架构以及空洞可分离卷积提出了一种高低层级信息丰富的多尺度医学影像语义分割算法, 该算法由特征提取网络以及多尺度语义分割预测网络两部分构成。特征提取网络使用空洞可分离卷积和类残差块分别替换原 U-Net中上、下采样以及卷积块, 在增加感受野的同时使信息得到最大化的保留；提出一个通道注意力机制, 强化目标核心特征的表达以及无关背景区域的抑制；在多尺度上挖掘带有图像级全局上下文的卷积特征, 进一步提高分割性能。本文在采集的胚胎以及 DRIVE数据集上进行仿真实验, 其结果表明, 与 U-Net及其衍生模型相比该方法具有更高的准确率和鲁棒性。
医学影像 语义分割 空洞可分离卷积 通道注意力 多尺度预测 biomedical image semantic segmentation atrous separable convolution channel attention multi-scale prediction 太赫兹科学与电子信息学报
2022, 20(10): 1073
Author Affiliations
Abstract
1 Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, 518055, P. R. China
2 School of Electrical Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, 610054, P. R. China
3 Department of Medical Engineering, University of South Florida, Tampa, FL 33620, USA
4 Guangdong Provincial Key Laboratory of Advanced Biomaterials, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, 518055, P. R. China
Microwave-induced thermoacoustic imaging (MTAI) has emerged as a potential biomedical imaging modality with over 20-year growth. MTAI typically employs pulsed microwave as the pumping source, and detects the microwave-induced ultrasound wave via acoustic transducers. Therefore, it features high acoustic resolution, rich electromagnetic contrast, and large imaging depth. Benefiting from these unique advantages, MTAI has been extensively applied to various fields including pathology, biology, material and medicine. Till now, MTAI has been deployed for a wide range of biomedical applications, including cancer diagnosis, joint evaluation, brain investigation and endoscopy. This paper provides a comprehensive review on (1) essential physics (endogenous/exogenous contrast mechanisms, penetration depth and resolution), (2) hardware configurations and software implementations (excitation source, antenna, ultrasound detector and image recovery algorithm), (3) animal studies and clinical applications, and (4) future directions.
Thermoacoustic imaging biomedical imaging electromagnetic radiation acoustic waves biomedical image processing Journal of Innovative Optical Health Sciences
2022, 15(4): 2230007
Author Affiliations
Abstract
1 Jiangsu Key Laboratory of Medical Optics, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, Jiangsu 215163, P. R. China
2 Department of Biomedical Engineering, University of Science and Technology of China, Hefei, Anhui 230041, P. R. China
3 Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai 200031, P. R. China
Cone photoreceptor cell identification is important for the early diagnosis of retinopathy. In this study, an object detection algorithm is used for cone cell identification in confocal adaptive optics scanning laser ophthalmoscope (AOSLO) images. An effectiveness evaluation of identification using the proposed method reveals precision, recall, and F1-score of 95.8%, 96.5%, and 96.1%, respectively, considering manual identification as the ground truth. Various object detection and identification results from images with different cone photoreceptor cell distributions further demonstrate the performance of the proposed method. Overall, the proposed method can accurately identify cone photoreceptor cells on confocal adaptive optics scanning laser ophthalmoscope images, being comparable to manual identification.
Biomedical image processing retinal imaging adaptive optics scanning laser ophthalmoscope object detection. Journal of Innovative Optical Health Sciences
2022, 15(1): 2250001
华南师范大学激光生命科学研究所激光生命科学教育部重点实验室, 广州 510631
简要介绍了光声成像技术的基本原理，采集系统和成像算法。重点阐述了光声成像技术在肿瘤的早期检测和疗效监测，脑成像和脑功能监测以及临床血管监测等生物医学领域的应用。对光声成像技术应用前景进行了展望。
医学影像 光声成像 肿瘤检测 脑功能监测 光声分子与功能成像
北京理工大学信息科学技术学院光电工程系，北京 100081
应用菲涅耳波带片光学扫描全息术原理，研究强散射介质中吸收体的三维成像．针对由成像物体强散射背景产生的背景噪音，提出复合扫描全息术成像方法．实验中应用这一方法，对嵌埋在浓度为1%，深度为1．7cm的脂肪乳剂中的吸收体成像，得到了信噪比和对比度较好的再现像．在此基础上，对复合扫描全息成像系统的信噪比，对比度及分辨率等性能进行了深入的理论分析和实验测试．研究表明，与单一模式相比，复合扫描全息术在信噪比和对比度方面有较大改善，但分辨率还需进一步提高．
生物医学成像 光学扫描全息术 菲涅耳波带板 编码孔径 Biomedical image Optical scanning holography Fresnel zone plate Coding aperture
