Learning Higher-Order Dynamics in Video-Based Cardiac Measurement

TL;DR

This paper demonstrates that explicitly optimizing neural models for higher-order derivatives improves the accuracy of waveform morphology in camera-based cardiac measurements, especially for clinically relevant metrics like LVET.

Contribution

It introduces a method to incorporate second derivatives into the training process, enhancing the estimation of higher-order cardiac dynamics from videos.

Findings

Improved estimation of second-order dynamics with derivative-aware training.

Enhanced accuracy in LVET interval measurement.

Neural models benefit from second-derivative inputs for waveform morphology.

Abstract

Computer vision methods typically optimize for first-order dynamics (e.g., optical flow). However, in many cases the properties of interest are subtle variations in higher-order changes, such as acceleration. This is true in the cardiac pulse, where the second derivative can be used as an indicator of blood pressure and arterial disease. Recent developments in camera-based vital sign measurement have shown that cardiac measurements can be recovered with impressive accuracy from videos; however, most of the research has focused on extracting summary statistics such as heart rate. Less emphasis has been put on the accuracy of waveform morphology that is necessary for many clinically meaningful assessments. In this work, we provide evidence that higher-order dynamics are better estimated by neural models when explicitly optimized for in the loss function. Furthermore, adding second-derivative inputs also improves performance when estimating second-order dynamics. We illustrate this, by showing that incorporating the second derivative of both the input frames and the target vital sign signals into the training procedure, models are better able to estimate left ventricle ejection time (LVET) intervals.