Department of Biomedical Engineering, Medical School, Tianjin University, Tianjin 300072, China; State Key Laboratory of Advanced Medical Materials and Devices, Tianjin University, Tianjin, China.
Department of Biomedical Engineering, Medical School, Tianjin University, Tianjin 300072, China; State Key Laboratory of Advanced Medical Materials and Devices, Tianjin University, Tianjin, China; Department of Radiotherapy, Yantai Yuhuangding Hospital, Shandong 264000, China.
Comput Methods Programs Biomed. 2024 Jun;250:108194. doi: 10.1016/j.cmpb.2024.108194. Epub 2024 Apr 22.
Accurate identification of molecular biomarker statuses is crucial in cancer diagnosis, treatment, and prognosis. Studies have demonstrated that medical images could be utilized for non-invasive prediction of biomarker statues. The biomarker status-associated features extracted from medical images are essential in developing medical image-based non-invasive prediction models. Contrast-enhanced mammography (CEM) is a promising imaging technique for breast cancer diagnosis. This study aims to develop a neural network-based method to extract biomarker-related image features from CEM images and evaluate the potential of CEM in non-invasive biomarker status prediction.
An end-to-end learning convolutional neural network with the whole breast images as inputs was proposed to extract CEM features for biomarker status prediction in breast cancer. The network focused on lesion regions and flexibly extracted image features from lesion and peri‑tumor regions by employing supervised learning with a smooth L1-based consistency constraint. An image-level weakly supervised segmentation network based on Vision Transformer with cross attention to contrast images of breasts with lesions against the contralateral breast images was developed for automatic lesion segmentation. Finally, prediction models were developed following further selection of significant features and the implementation of random forest-based classification. Results were reported using the area under the curve (AUC), accuracy, sensitivity, and specificity.
A dataset from 1203 breast cancer patients was utilized to develop and evaluate the proposed method. Compared to the method without lesion attention and with only lesion regions as inputs, the proposed method performed better at biomarker status prediction. Specifically, it achieved an AUC of 0.71 (95 % confidence interval [CI]: 0.65, 0.77) for Ki-67 and 0.73 (95 % CI: 0.65, 0.80) for human epidermal growth factor receptor 2 (HER2).
A lesion attention-guided neural network was proposed in this work to extract CEM image features for biomarker status prediction in breast cancer. The promising results demonstrated the potential of CEM in non-invasively predicting the biomarker statuses in breast cancer.
准确识别分子生物标志物状态对于癌症的诊断、治疗和预后至关重要。研究表明，医学图像可用于非侵入性预测生物标志物状态。从医学图像中提取的与生物标志物状态相关的特征对于开发基于医学图像的非侵入性预测模型至关重要。对比增强乳腺摄影术（CEM）是一种很有前途的乳腺癌诊断成像技术。本研究旨在开发一种基于神经网络的方法，从 CEM 图像中提取与生物标志物相关的图像特征，并评估 CEM 在非侵入性生物标志物状态预测中的潜力。
提出了一种端到端学习卷积神经网络，以全乳图像作为输入，从 CEM 图像中提取生物标志物状态预测的特征。该网络专注于病灶区域，并通过使用基于光滑 L1 的一致性约束的监督学习，灵活地从病灶和肿瘤周围区域提取图像特征。开发了一种基于 Vision Transformer 的基于图像级弱监督分割网络，该网络使用交叉注意力对带有病灶的乳房对比图像和对侧乳房图像进行自动病灶分割。最后，通过进一步选择显著特征并实现基于随机森林的分类，开发了预测模型。使用曲线下面积（AUC）、准确性、敏感性和特异性来报告结果。
使用来自 1203 例乳腺癌患者的数据集来开发和评估所提出的方法。与没有病灶注意力且仅以病灶区域作为输入的方法相比，所提出的方法在生物标志物状态预测方面表现更好。具体而言，对于 Ki-67，它的 AUC 为 0.71（95%置信区间[CI]：0.65，0.77），对于人表皮生长因子受体 2（HER2），它的 AUC 为 0.73（95%CI：0.65，0.80）。
本研究提出了一种病灶注意力引导的神经网络，用于从 CEM 图像中提取生物标志物状态预测的特征。有前景的结果表明，CEM 在非侵入性预测乳腺癌生物标志物状态方面具有潜力。
