Search

Clinicians generally diagnose cardiovascular diseases (CVDs) using standard 12-Lead electrocardiogram (ECG). However, for smartphone-based public healthcare systems, a reduced 3-lead system may be preferred because of (i) increased portability, and (ii) reduced requirement for power, storage and bandwidth. Subsequently, clinicians require accurate 3-lead to 12-Lead ECG reconstruction, which has so far been studied only in the personalized setting. When each device is dedicated to one individual, artificial intelligence (AI) methods such as temporal long short-term memory (LSTM) and a further improved spatio-temporal LSTM-UNet combine have proven effective. In contrast, in the current smartphone-based public health setting where a common device is shared by many, developing an AI lead-reconstruction model that caters to the extensive ECG signal variability in the general population appears a far greater challenge. In this direction, we take a first step, and observe that the performance improvement achieved by a generative model, specifically, 1D Pix2Pix GAN (generative adversarial network), over LSTM-UNet is encouraging., Comment: Accepted to IEEE Healthcom 2024 for presentation as a Main Conference Paper

Diagnosis of cardiovascular diseases usually relies on the widely used standard 12-Lead (S12) ECG system. However, such a system could be bulky, too resource-intensive, and too specialized for personalized home-based monitoring. In contrast, clinicians are generally not trained on the alternative proposal, i.e., the reduced lead (RL) system. This necessitates mapping RL to S12. In this context, to improve upon traditional linear transformation (LT) techniques, artificial intelligence (AI) approaches like long short-term memory (LSTM) networks capturing non-linear temporal dependencies, have been suggested. However, LSTM does not adequately interpolate spatially (in 3D). To fill this gap, we propose a combined LSTM-UNet model that also handles spatial aspects of the problem, and demonstrate performance improvement. Evaluated on PhysioNet PTBDB database, our LSTM-UNet achieved a mean R^2 value of 94.37%, surpassing LSTM by 0.79% and LT by 2.73%. Similarly, for PhysioNet INCARTDB database, LSTM-UNet achieved a mean R^2 value of 93.91%, outperforming LSTM by 1.78% and LT by 12.17%., Comment: 6 pages, 4 figures, 2 Tables

Purpose: To develop and validate a phantom for diagnostic ultrasound (US) scanners by embedding targets in gel wax to determine the image uniformity, lateral and axial resolution, and diameter of a stainless-steel disc. Materials and Methods: Acoustic property (AP), which includes the velocity of US (cus), acoustic impedance (Z), and attenuation coefficient in gel wax were determined. The cus, and attenuation coefficient were estimated using the pulse-echo technique. Z was obtained from the product of sample density (\r{ho}) and cus. Two rectangular frames using polytetrafluoroethylene (PTFE) sheets with holes separated by 5, 10, and 20 mm distances were constructed. Nylon filaments and SS-disc (diameter = 16.8 mm) were threaded through the frames and suitably placed in melted gel wax to obtain orthogonal targets. The targets were measured using computerized tomography (CT) and a 2-9 MHz US probe. Results: The AP of gel wax were cus=1418 m/s, \r{ho}= 0.87 g/cm3, Z=1.23 MRayls, attenuation coefficient= 0.88 dB/cm/MHz. The results of US imaging of the targets were compared with their physical sizes and served as baselines for the scanner and probe. The maximum error in distance measurement in the phantom US images was 7.1%, and the phantom volume decreased by 1.8% over 62 weeks. Conclusion: Gel wax can be useful in developing affordable, highly stable, and customizable diagnostic US phantoms that can be implemented widely., Comment: 6 figures, 2 tables