基于深度神经网络的前列腺癌多参数超声成像
研究训练深度神经网络(DNN)将ARFI、SWEI、QUS-MF和B模式四种超声模态整合为多参数超声(mpUS)容积,用于前列腺癌检测。在15例活检确诊前列腺癌患者中,DNN生成的mpUS容积清晰显示组织病理证实的癌灶,对比噪声比(CNR)较线性SVM显著提高(2.79±0.88 vs 1.98±0.73,配对t检验p<0.001)。
要点
- DNN生成的mpUS容积较线性SVM显著提高前列腺癌灶CNR(2.79±0.88 vs 1.98±0.73,p<0.001)。
- 选择性省略输入模态时CNR随输入减少而下降,硬度和回声源性模态均为重要贡献者。
- 在前列腺体模中,DNN较线性SVM提高病灶CNR。
核心结论
- DNN可优化生成高CNR的mpUS前列腺容积(基于ARFI、SWEI、MF和B模式),且该方法的性能优于线性SVM方法。
研究设计与样本
- 研究论文:使用15例活检确诊前列腺癌患者根治性前列腺切除术前采集的配准ARFI、SWEI、MF和B模式数据(共980,620个体素)训练DNN;数据来自经改装可用户控制声束序列并获取原始图像数据的商用扫描仪;以全 mount 组织病理学数据为参考,手动分割每个受试者的索引病灶和非癌区域。
关键影像表现/征象
- 在体测试数据集(n=15)中,基于DNN的mpUS容积清晰显示组织病理证实的 前列腺癌。
- 在前列腺体模中,DNN较先前使用的线性SVM提高病灶CNR。
诊断标准与关键数值
- 在体测试数据集(n=15)中,DNN组CNR为2.79±0.88,线性SVM组为1.98±0.73,DNN较线性SVM显著提高(配对样本t检验p<0.001)。
- 亚组分析中选择性省略DNN输入模态时,CNR随输入模态减少而下降;硬度和回声源性模态均为多参数模型的重要贡献者。
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: A deep neural network (DNN) was trained to generate a multiparametric ultrasound (mpUS) volume from four input ultrasound-based modalities (acoustic radiation force impulse [ARFI] imaging, shear wave elasticity imaging [SWEI], quantitative ultrasound-midband fit [QUS-MF], and B-mode) for the detection of prostate cancer.
METHODS: A DNN was trained using co-registered ARFI, SWEI, MF, and B-mode data obtained in men with biopsy-confirmed prostate cancer prior to radical prostatectomy (15 subjects, comprising 980,620 voxels). Data were obtained using a commercial scanner that was modified to allow user control of the acoustic beam sequences and provide access to the raw image data. For each subject, the index lesion and a non-cancerous region were manually segmented using visual confirmation based on whole-mount histopathology data.
RESULTS: In a prostate phantom, the DNN increased lesion contrast-to-noise ratio (CNR) compared to a previous approach that used a linear support vector machine (SVM). In the in vivo test datasets (n = 15), the DNN-based mpUS volumes clearly portrayed histopathology-confirmed prostate cancer and significantly improved CNR compared to the linear SVM (2.79 ± 0.88 vs. 1.98 ± 0.73, paired-sample t-test p < 0.001). In a sub-analysis in which the input modalities to the DNN were selectively omitted, the CNR decreased with fewer inputs; both stiffness- and echogenicity-based modalities were important contributors to the multiparametric model.
CONCLUSION: The findings from this study indicate that a DNN can be optimized to generate mpUS prostate volumes with high CNR from ARFI, SWEI, MF, and B-mode and that this approach outperforms a linear SVM approach.
引用
- Chan DY, Morris DC, Moavenzadeh SR, et al. Multiparametric Ultrasound Imaging of Prostate Cancer Using Deep Neural Networks. Ultrasound Med Biol. 2024. PMID: 39174376. doi:10.1016/j.ultrasmedbio.2024.07.012
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。