New tools for comparing classical and neural ODE models for tumor growth

TL;DR

This paper introduces TumorGrowth.jl, a computational tool for comparing classical and neural ODE models of tumor growth, applied to lung and bladder cancer data, highlighting the performance of different models based on data availability.

Contribution

The paper presents a novel tool for comparing traditional and neural ODE tumor growth models, including the first application of neural ODEs in this context.

Findings

General Bertalanffy model outperforms others on average

More complex models may be better with more measurements

Neural ODE models show potential in capturing relapse behavior

Abstract

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.