Objective: Development of a contact microphone-driven screening framework for the diagnosis of coexisting valvular heart diseases (VHDs). Methods: A sensitive accelerometer contact microphone (ACM) is employed to capture heart-induced acoustic components on the chest wall. Inspired by the human auditory system, ACM recordings are initially transformed into Mel-frequency cepstral coefficients (MFCCs) and their first and second derivatives, resulting in 3-channel images. An image-to-sequence translation network based on the convolutionmeets-transformer (CMT) architecture is then applied to each image to find local and global dependencies in images, and predict a 5-digit binary sequence, where each digit corresponds to the presence of a specific type of VHD. The performance of the proposed framework is evaluated on 58 VHD patients and 52 healthy individuals using a 10-fold leave-subject-out cross-validation (10- LSOCV) approach. Results: Statistical analyses suggest an average sensitivity, specificity, accuracy, positive predictive value, and F1 score of 93.28%, 98.07%, 96.87%, 92.97%, and 92.4% respectively, for the detection of coexisting VHDs. Furthermore, areas under the curve (AUC) of 0.99 and 0.98 are respectively reported for the validation and test sets. Conclusion: The high performances achieved prove that local and global features of ACM recordings effectively characterize heart murmurs associated with valvular abnormalities. Significance: Limited access of primary care physicians to echocardiography machines has resulted in a low sensitivity of 44% when using a stethoscope for the identification of heart murmurs. The proposed framework provides accurate decision-making on the presence of VHDs, thus reducing the number of undetected VHD patients in primary care settings. 

Objective: The development of a method for non-invasive monitoring of fetal electrocardiogram (FECG) signals from single-channel abdominal recordings. Methods: The dual-path source separation (DPSS) architecture is introduced for the simultaneous separation of fetal and maternal ECG signals from abdominal ECG recordings. DPSS initially denoises abdominal ECG (AECG) recordings using a generative dual-path long short-term memory (DP-LSTM) network. An inception module along with a series of DP-LSTM blocks is then employed to extract the masking maps associated with fetal and maternal components. Finally, these masking maps are weighted by the AECG recording to separate maternal and fetal ECG signals. The performance of this network is evaluated on 10 pregnancies from the fetal ECG synthetic database (FECGSYNDB), 22 cases of labor and pregnancy from the abdominal and direct fetal ECG database (ADFECGDB), and 69 pregnancies from set A of non-invasive FECG challenge (NIFECGC) datasets. Results: F1-scores of 99.03%, 97.7%, and 95.3% are reported for the detection of fetal QRS complexes in FECGSYNDB, ADFECGDB, and NIFECGC respectively. DPSS technique is also evaluated in terms of separability of fetal and maternal clusters. According to the clustering-based analyses, the average purity index of 0.9750, Jaccard index of 0.9705, and Davies-Bouldin index of 0.7429 demonstrate the high source separation capability of DPSS. Conclusion: The achieved performance suggests that DPSS enables accurate single-channel FECG extraction, and can replace state-of-the-art source separation techniques for this purpose. Significance: This study signifies a fundamental step towards non-invasive fetal ECG monitoring systems, which favors at-home prenatal care.

Objective: The development of an accurate, non-invasive method for the diagnosis of peripheral artery disease (PAD) from accelerometer contact microphone (ACM) recordings of the cardiac system. Methods: Mel frequency cepstral coefficients (MFCCs) are initially extracted from ACM recordings. The extracted MFCCs are then used to fine-tune a pre-trained ResNet50 network whose middle layers provide streams of high-level-of-abstraction coefficients (HLACs) which could provide information on blood pressure backflow caused by arterial obstructions in PAD patients. A vision transformer is finally integrated with the feature extraction layer to detect PAD, and stratify the severity level. This architecture is coined multi-stream-powered vision transformer (MSPViT). The performance of MSPViT is evaluated on 74 PAD and 21 healthy subjects. Results: Sensitivity, specificity, F1 score, and area under the curve (AUC) of 99.45%, 98.21%, 99.37%, and 0.99, respectively, are reported for the binary classification which ensures accurate detection of PAD. Furthermore, MSPViT suggests average sensitivity, specificity, F1 score, and AUC of 96.66%, 97.34%, 96.29%, and 0.96, respectively, for the classification of subjects into healthy, mild-PAD, and severe-PAD classes. The silhouette score is calculated to assess the separability of clusters formed for classes in the penultimate layer of MSPViT. An average silhouette score of 0.66 and 0.81 demonstrate excellent cluster separability in PAD detection and severity classification, respectively. Conclusion: The achieved performance suggests that the proximal ACMdriven framework can replace state-of-the-art techniques for PAD detection. Significance: This study presents a fundamental step towards prompt and accurate diagnosis of PAD and stratification of its severity level. 

This study develops a camera-guided frequency-modulated continuous-wave (FMCW) radar to monitor vital signs. A red-green-blue-depth (RGB-D) camera estimates the human torso landmarks and a processing unit constantly adapts the radar beams to the direction of the subjects. To constantly optimize the regions of interest for monitoring respiratory rate (RR) and heart rate (HR), a novel method, coined “singular value-based point detection (SVPD),” is designed. Vital sign extraction is then followed as the last step. Experiments are conducted for the cases of single-subject (10 subjects, 31 scenarios, and 1550 repetitions) and dual-subject monitoring (6 subjects, 6 scenarios, and 90 repetitions). Average (RR, HR) accuracies of (97.68%, 85.88%), (90.02%, 86.05%), (96.71%, 89.50%), and (97.52%, 86.71%) are achieved for the range of distances (0.5-2.5 m), azimuth angles (0°–30°), elevation angles (−30°–+30°), and incident angles (−30°–+30°), respectively. The higher chest and upper abdomen are determined as the optimal regions for RR and HR estimation respectively, with average accuracies of 98.31% and 86.93%. Finally, the capability of dual-subject monitoring at various inter-subject distances (range of 20–70 cm) is confirmed with average accuracies of 92.26% and 73.23% for RR and HR respectively.