TGM-Nets: A deep learning framework for enhanced forecasting of tumor growth by integrating imaging and modeling

作者：Chen, Qijing; Ye, Qi; Zhang, Weiqi; Li, He; Zheng, Xiaoning^*

来源：ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 126: 106867.

DOI：10.1016/j.engappai.2023.106867

• Physics-informed neural networks
• Tumor growth models
• Inverse problem
• Phase-field approach
• Uncertainty quantification

Prediction and uncertainty quantification of tumor progression are vital in clinical practice, i.e., disease prognosis and decision-making on treatment strategies. In this work, we propose TGM-Nets, a deep learning framework that combines bioimaging and tumor growth modeling (TGM) for enhanced prediction of tumor growth. This proposed framework, developed based on physics-informed neural networks (PINNs), is capable of integrating the TGM and sequential observations of tumor morphology for patient-specific prediction of tumor growth. The novelties of the design of TGM-Nets include the employment of Fourier layers to extract the features of the input images as well as the utilization of sequential learning and fine-tuning with physics for extrapolation to improve the prediction accuracy. The validity of TGM-Nets for tumor growth forecasting is verified by testing the model performance on synthetic and in-vitro datasets, respectively. Our results show that the TGM-Nets not only can track the growth rates of the mild and aggressive tumors but also capture their detailed morphological features within and outside the training domain. In particular, TGM-Nets can be used to predict the long time dynamics of tumor growth in mild and aggressive cases. Our results show that the parameters inferred from the TGM-Nets can be used for long-time prediction for up to 4 months with a maximum error of & SIM; 4%. We also systematically study the effects of the number of training points and noisy data on the performance of TGM-Nets as well as quantify the uncertainty of the model predictions. We show that TGM-Nets can integrate the biomedical images to predict the growth of the in-vitro cultured pancreatic cancer cells and identify the associated growth rates, demonstrating the possibilities of using TGM-Nets in clinical practice. In summary, we propose a new deep learning model that combines imaging and TGM to improve the current approaches for predicting tumor growth and thus provide an advanced computational tool for patient-specific tumor prognosis.

• 单位
  南方医科大学