基于无监督域适应的通用多场景超声图像肿瘤诊断方法
研究提出一种多样域二维特征选择网络(2-D FSN),利用医学图像间的相似性并通过共享权重重建网络提取特征,以两个对抗学习模块惩罚特征域距离、对齐特征空间并选择共同特征。与最新域适应方法相比,该方法在乳腺、甲状腺和内镜超声图像分类准确率分别达82.4%、96.4%和89.7%,在多源超声图像无监督域适应任务中平均准确率为77.3%。
要点
- 2-D FSN在乳腺超声图像分类准确率为82.4%。
- 2-D FSN在甲状腺超声图像分类准确率为96.4%。
- 多源超声无监督域适应任务平均准确率为77.3%。
核心结论
- 2-D FSN通过学习共同特征并结合多模块智能,提升了模型在多域超声数据集上的分类能力,该算法具有良好的临床指导价值。
研究设计与样本
- 提出一种多样域二维特征选择网络(2-D FSN),利用医学图像间相似性并通过共享权重重建网络提取特征,用两个对抗学习模块惩罚特征域距离以对齐特征空间并选择共同特征;实验涵盖乳腺、甲状腺和内镜超声图像以及多源超声图像的无监督域适应任务。
诊断标准与关键数值
- 与最新域适应方法相比,2-D FSN对乳腺超声图像分类准确率为82.4%。
- 与最新域适应方法相比,2-D FSN对甲状腺超声图像分类准确率为96.4%。
- 与最新域适应方法相比,2-D FSN对内镜超声图像分类准确率为89.7%。
- 使用多源超声图像的无监督域适应任务中,模型在广泛变化的域上平均准确率为77.3%。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: The utilization of computer-aided diagnosis (CAD) in breast ultrasound image classification has been limited by small sample sizes and domain shift. Current ultrasound classification methods perform inadequately when exposed to cross-domain scenarios, as they struggle with data sets from unobserved domains. In the medical field, there are situations in which all images must share the same networks as they capture the same symptom of the same participant, implying that they share identical structural content. Nevertheless, most domain adaptation methods are not suitable for medical images as they overlook the common features among the images.
METHODS: To overcome these challenges, we propose a novel diverse-domain 2-D feature selection network (FSN), which uses the similarities among medical images and extracts features with a reconstruction network with shared weights. Additionally, it penalizes the feature domain distance through two adversarial learning modules that align the feature space and select common features. Our experiments illustrate that the proposed method is robust and can be applied to ultrasound images of various diseases.
RESULTS: Compared with the latest domain adaptive methods, 2-D FSN markedly enhances the accuracy of classification of breast, thyroid and endoscopic ultrasound images, achieving accuracies of 82.4%, 96.4% and 89.7%, respectively. Furthermore, the model was evaluated on an unsupervised domain adaptation task using ultrasound images from multiple sources and achieved an average accuracy of 77.3% across widely varying domains.
CONCLUSION: In general, 2-D FSN improves the classification ability of the model on multidomain ultrasound data sets through the learning of common features and the combination of multimodule intelligence. The algorithm has good clinical guidance value.
引用
- Fan L, Gong X, Guo Y, et al. General Multiscenario Ultrasound Image Tumor Diagnosis Method Based on Unsupervised Domain Adaptation. Ultrasound Med Biol. 2023. PMID: 37532633. doi:10.1016/j.ultrasmedbio.2023.06.015
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。