Automatic detection of complete and measurable cardiac cycles in antenatal pulsed-wave Doppler signals

• Published in: Computer methods and programs in biomedicine Vol. 190; p. 105336
• Main Authors: Sulas, Eleonora, Urru, Monica, Tumbarello, Roberto, Raffo, Luigi, Pani, Danilo
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.07.2020
• Subjects: Algorithms; Doppler; Echocardiography, Doppler, Pulsed - methods; Female; Fetal echocardiography; Fetus; Humans; Pattern recognition; Pattern Recognition, Automated; Pregnancy; Pulse Wave Analysis; Ultrasonography, Prenatal; Ultrasound; Fetal echocardiography; Pattern recognition; Ultrasound; Doppler
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2020.105336

•It is possible to automatically detect complete and clinically valuable fetal heartbeats in the PWD spectrum velocity envelope.•By using the samples of the PWD envelope and pixel intensity features, a classifier can be trained for this aim.•Performance over fetuses’ signals between 21 and 27 weeks of gestation reveals accuracies up to 98%.•The approach is robust with respect to the classifier choice and superior to template matching.•It can be adopted to help in the objective and automated analysis of fetal echocardiographic signals. Pulsed-wave Doppler (PWD) echocardiography is the primary tool for antenatal cardiological diagnosis. Based on it, different measurements and validated reference parameters can be extracted. The automatic detection of complete and measurable cardiac cycles would represent a useful tool for the quality assessment of the PWD trace and the automated analysis of long traces. This work proposes and compares three different algorithms for this purpose, based on the preliminary extraction of the PWD velocity spectrum envelopes: template matching, supervised classification over a reduced set of relevant waveshape features, and supervised classification over the whole waveshape potentially representing a cardiac cycle. A custom dataset comprising 43 fetal cardiac PWD traces (174,319 signal segments) acquired on an apical five-chamber window was developed and used for the assessment of the different algorithms. The adoption of a supervised classifier trained with the samples representing the upper and lower envelopes of the PWD, with additional features extracted from the image, achieved significantly better results (p < 0.0001) than the other algorithms, with an average accuracy of 98% ± 1% when using an SVM classifier and a leave-one-subject-out cross-validation. Further, the robustness of the results with respect to the classifier model was proved. The results reveal excellent detection performance, suggesting that the proposed approach can be adopted for the automatic analysis of long PWD traces or embedded in ultrasound machines as a first step for the extraction of measurements and reference clinical parameters.