New tools for comparing classical and neural ODE models for tumor growth
This provides a tool for researchers to compare tumor growth models, but it is incremental as it applies existing methods to new data without major breakthroughs.
The authors introduced TumorGrowth.jl, a computational tool for comparing classical and neural ODE models in tumor growth modeling, applied to a meta-study of lung and bladder cancer, finding that the General Bertalanffy model performed best on average with 6.3 measurements, but more complex models may be better with more data.
A new computational tool TumorGrowth$.$jl for modeling tumor growth is introduced. The tool allows the comparison of standard textbook models, such as General Bertalanffy and Gompertz, with some newer models, including, for the first time, neural ODE models. As an application, we revisit a human meta-study of non-small cell lung cancer and bladder cancer lesions, in patients undergoing two different treatment options, to determine if previously reported performance differences are statistically significant, and if newer, more complex models perform any better. In a population of examples with at least four time-volume measurements available for calibration, and an average of about 6.3, our main conclusion is that the General Bertalanffy model has superior performance, on average. However, where more measurements are available, we argue that more complex models, capable of capturing rebound and relapse behavior, may be better choices.