KEYWORDS: Model-based design, Super resolution, Photoacoustic microscopy, Point spread functions, Acoustics, Diffraction, Photoacoustic spectroscopy, Transducers, Image quality, In vivo imaging
Acoustic-resolution photoacoustic microscopy (AR-PAM) is a promising tool for microvascular imaging. In AR-PAM, a focused transducer is typically used. Limited by acoustic diffraction, in-focus lateral resolution is dependent on the center frequency and numerical aperture of the transducer. On the other hand, out-of-focus lateral resolution will deteriorate, which can be restored to in-focus lateral resolution by synthetic aperture focusing technique (SAFT). Previously, we demonstrated that with prior knowledge of the point-spread function of the AR-PAM imaging system, combined SAFT and Richard-Lucy deconvolution can be applied to achieve super resolution (SR) beyond acoustic diffraction limit and to enhance signal-to-noise ratio (SNR) in both focal and out-of-focus regions. However, SNR of the original AR-PAM image highly affects the performance. Moreover, discontinuities arise in the line pattern that is originally continuous. In this study, we propose a novel algorithm, which combines a novel SAFT method and a directional model-based (D-M) deconvolution method, to break the acoustic diffraction limit. By using our algorithm, FWHM of 20 ~µm for AR-PAM system over DOF of ~1.8 mm is experimentally achieved. Compared with our previous work using Richard-Lucy deconvolution, the D-M deconvolution demonstrates the advantages in high SNR, and good line continuity. Compared with the directional SAFT method, our algorithm achieves SR and higher SNR.
Detection of premature ventricular contraction (PVC) in children is an important step in the diagnosis of arrhythmia. It not only requires professional knowledge, but also occupies a large amount of repetitive work of clinicians. Deep learning based computer model has recently been applied into the clinical field for disease diagnosis. In this study, we built a Long Short-Term Memory (LSTM) recurrent neural networks (RNN) model to detect PVC with children’s electrocardiogram (ECG). 1019 children with and 1198 without PVC were selected for this study. The lead II of the 12 leads ECG signal for each child was used for diagnosis. In total, 220 studies were selected randomly as validation set, 222 studies as testing set, and the rest as training set. The best LSTM model achieved a testing F1 score 0.94 on PVC classification task. With 10- folds validation, the area under receiver operating characteristic curve (AUC) achieved 0.97±0.01. To conclude, this is a meaningful step towards large scale and efficient PVC diagnosis.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.