罗亦铭,王建林,田 艳,张 波,随恩光,韩思齐.基于注意力机制的甲状腺超声图像感兴趣区域定位方法[J].电子测量与仪器学报,2023,37(6):39-47 |
基于注意力机制的甲状腺超声图像感兴趣区域定位方法 |
Location of regions of interest in thyroid ultrasound images based on attention mechanism |
|
DOI: |
中文关键词: 甲状腺超声图像 注意力机制 感兴趣区域 区域定位模型 特征网络 |
英文关键词:thyroid ultrasound image attention mechanism region of interest (ROI) region localization model feature networks |
基金项目:中央高效基本科研业务费专项资金(3332020076)项目资助 |
|
|
摘要点击次数: 708 |
全文下载次数: 857 |
中文摘要: |
针对甲状腺超声图像中背景干扰及数据集规模受限的问题,提出了基于注意力机制的甲状腺超声图像感兴趣区域定位
方法。 采用跨尺度注意力交互策略,改进定位模型的特征网络,提高不同尺度下各层级特征的融合效率;通过知识蒸馏实现特
征网络特征提取能力的强化,解决数据规模不足引起的网络过拟合问题;依据解剖学甲状腺形态统计分布设计 t 掩码,联合注
意力掩码计算特征损失,引导网络对甲状腺超声图像关键通道和像素信息的学习,实现对甲状腺超声图像感兴趣区域的定位。
实验结果表明,当 IoU 阈值为 0. 5 时,甲状腺超声图像感兴趣区域定位 AP 达到 92. 7%,对辅助医生进行甲状腺疾病的诊断具有
临床意义和价值。 |
英文摘要: |
To address the problems of background interference and limited dataset size, we propose a method for locating the region of
interest in thyroid ultrasound images. The method utilizes an attention mechanism based on cross-scale attention interaction strategy to
improve the fusion efficiency of hierarchical features in the localization model. The feature network of the localization model is enhanced
through knowledge distillation to solve the problem of overfitting. A t-mask is designed based on the statistical distribution of anatomical
thyroid morphology, and a joint attention mask is calculated to guide the network in learning key channels and pixel information of thyroid
ultrasound images, thereby achieving the localization of the region of interest. Experimental results demonstrate that the average precision
(AP) for thyroid ultrasound image region of interest localization reaches 92. 7% when the IoU threshold is set to 0. 5, which is clinically
significant and valuable for assisting doctors in diagnosing thyroid diseases. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|