Ma Manfu, Zhang Xiaoming, Li Yong, Wang Xia, Zhang Ruigen, Wang Yang, Sun Penghui, Wang Xuegang, Sun Xuan
College of Computer Science & Engineering, Northwest Normal University, Lanzhou, 730070, China.
College of Computer Science & Engineering, Northwest Normal University, Lanzhou, 730070, China.
Comput Biol Med. 2023 Sep;164:107313. doi: 10.1016/j.compbiomed.2023.107313. Epub 2023 Aug 7.
Accurate quantification of tumor growth patterns can indicate the development process of the disease. According to the important features of tumor growth rate and expansion, physicians can intervene and diagnose patients more efficiently to improve the cure rate. However, the existing longitudinal growth model can not well analyze the dependence between tumor growth pixels in the long space-time, and fail to effectively fit the nonlinear growth law of tumors. So, we propose the ConvLSTM coordinated longitudinal Transformer (LCTformer) under spatiotemporal features for tumor growth prediction. We design the Adaptive Edge Enhancement Module (AEEM) to learn static spatial features of different size tumors under time series and make the depth model more focused on tumor edge regions. In addition, we propose the Growth Prediction Module (GPM) to characterize the future growth trend of tumors. It consists of a Longitudinal Transformer and ConvLSTM. Based on the adaptive abstract features of current tumors, Longitudinal Transformer explores the dynamic growth patterns between spatiotemporal CT sequences and learns the future morphological features of tumors under the dual views of residual information and sequence motion relationship in parallel. ConvLSTM can better learn the location information of target tumors, and it complements Longitudinal Transformer to jointly predict future imaging of tumors to reduce the loss of growth information. Finally, Channel Enhancement Fusion Module (CEFM) performs the dense fusion of the generated tumor feature images in the channel and spatial dimensions and realizes accurate quantification of the whole tumor growth process. Our model has been strictly trained and tested on the NLST dataset. The average prediction accuracy can reach 88.52% (Dice score), 89.64% (Recall), and 11.06 (RMSE), which can improve the work efficiency of doctors.
准确量化肿瘤生长模式可以指示疾病的发展进程。根据肿瘤生长速率和扩展的重要特征，医生可以更高效地对患者进行干预和诊断，以提高治愈率。然而，现有的纵向生长模型无法很好地分析长时空内肿瘤生长像素之间的依赖性，也未能有效拟合肿瘤的非线性生长规律。因此，我们提出了基于时空特征的卷积长短期记忆网络协调纵向变换器（LCTformer）用于肿瘤生长预测。我们设计了自适应边缘增强模块（AEEM）来学习不同大小肿瘤在时间序列下的静态空间特征，使深度模型更关注肿瘤边缘区域。此外，我们提出了生长预测模块（GPM）来表征肿瘤的未来生长趋势。它由纵向变换器和卷积长短期记忆网络组成。纵向变换器基于当前肿瘤的自适应抽象特征，探索时空CT序列之间的动态生长模式，并在残差信息和序列运动关系的双重视角下并行学习肿瘤的未来形态特征。卷积长短期记忆网络可以更好地学习目标肿瘤的位置信息，它与纵向变换器互补，共同预测肿瘤的未来成像，以减少生长信息的损失。最后，通道增强融合模块（CEFM）在通道和空间维度上对生成的肿瘤特征图像进行密集融合，实现对整个肿瘤生长过程的准确量化。我们的模型在NLST数据集上经过了严格的训练和测试。平均预测准确率可达88.52%（Dice分数）、89.64%（召回率）和11.06（均方根误差），能够提高医生的工作效率。
