Respiratory-induced liver motion prediction using ECG as surrogate signal.

purposeThis study investigates the use of electrocardiogram (ECG) as a surrogate signal to model the liver's respiratory-induced motion.

methodsA learning-based model was trained to predict respiratory-induced liver motion by relying exclusively on ECG data, without requiring additional imaging. A correspondence model based on an encoder-decoder architecture was defined to map internal liver motion from ECG signals. Experimental validation was conducted through a human subject study involving eight participants performing various breathing patterns.

resultsThe mean absolute error during normal breathing was 2.83 mm, while the overall error considering all breathing patterns was 4.02 mm with correlation coefficients above 0.90. More than 90% of predictions fell within reported acceptable error margins for needle insertion procedures. The model's performance reduces when the liver motion increases during deep breathing patterns.

conclusionECG can serve as a reliable noninvasive surrogate for predicting liver motion. This approach offers the advantage of being readily available in clinical settings and can provide accurate guidance for interventional procedures.