Unsupervised respiratory signal extraction from ungated cardiac magnetic resonance imaging at rest and during exercise

Abstract

We propose and evaluate a method to estimate a respiratory signal from ungated cardiac magnetic resonance (CMR) images. Ungated CMR images were acquired in 5 subjects who performed exercise at different intensity levels under different physiological conditions while breathing freely. The respiratory motion was estimated by applying principal components analysis (PCA). A sign correction procedure was developed to correctly define inspiration and expiration, based on either tracking of the diaphragmatic motion or estimation of the lung volume or a combination of both. Evaluation was done using a plethysmograph signal as reference. There was a good correspondence between the plethysmograph and the estimated respiratory signals. Respiratory motion was effectively captured by one of the PCA components in 88% of the cases. Moreover, the proposed method successfully estimated the respiratory phase in 91% of the evaluated slices. The pipeline is robust, admitting a slight decline in performance with increased exercise intensity. Respiratory motion was accurately estimated by means of PCA and the application of a sign correction procedure. Our method showed promising results even for acquisitions during exercise where excessive body motion occurs. The proposed method provides a way to extract the respiratory signal from ungated CMR images, at rest as well as during exercise, in a fully unsupervised fashion, which may reduce the clinician's workload drastically.

Ensuring respiratory phase consistency to improve cardiac function quantification in real‐time CMR

“…Linear PCA was used both in this work and URE, 13 but there are differences between the two approaches: (i) In our method, the images are pre‐filtered to suppress the cardiac motion and (ii) the temporal mean is subtracted before applying linear PCA. Our directionality determination procedure, which is the major contribution of this work, is distinct from URE.…”

Endurance exercise and the risk of cardiovascular pathology in men: a comparison between lifelong and late-onset endurance training and a non-athletic lifestyle - rationale and design of the Master@Heart study, a prospective cohort trial

“…Our research group has previously demonstrated the feasibility, reliability and clinical utility of CMR to quantify cardiac volumes and function during exercise. [74][75][76] The assessment of myocardial function during exercise will allow us to investigate whether the duration and intensity of long-term endurance exercise affect LV and RV functional reserve.…”

Automatic Extraction and Sign Determination of Respiratory Signal in Real-time Cardiac Magnetic Resonance imaging

“…The motion information is already present in the RT cine images; therefore, the respiratory signal can be extracted directly using data-driven methods. Various strategies to extract the respiratory signal from RT cine data have been developed [2,3,4]. Among them, PCA-based methods [3,4] are particularly appealing because they are fast and independent of the slice orientation.…”

“…Various strategies to extract the respiratory signal from RT cine data have been developed [2,3,4]. Among them, PCA-based methods [3,4] are particularly appealing because they are fast and independent of the slice orientation. However, due to the nature of PCA, the extracted signal has an arbitrary sign, which means that the maximal signal could refer either to the inspiration or expiration phase.…”

“…Bertolli et al assumed the directionality of craniocaudal motion of the internal organs to resolve the sign ambiguity in PET images [5]. In MRI, Felipe et al developed a sign correction method by tracking the diaphragmatic motion or estimating the lung volume, but this method requires selecting the lung-diaphragm interface [4].…”