Improving Axial Resolution of Optical Resolution Photoacoustic Microscopy with Advanced Frequency Domain Eigenspace Based Minimum Variance Beamforming Method

Optical resolution photoacoustic microscopy (OR-PAM) leverages optical focusing and acoustic detection for microscopic optical absorption imaging. Intrinsically it owns high optical lateral resolution and poor acoustic axial resolution. Such anisometric resolution hinders good 3-D visualization; thus 2-D maximum amplitude projection images are commonly presented in the literature. Since its axial resolution is limited by the bandwidth of acoustic detectors, ultrahigh frequency, and wideband detectors with Wiener deconvolution have been proposed to address this issue. Nonetheless, they also introduce other issues such as severe high-frequency attenuation and limited imaging depth. In this work, we view axial resolution improvement as an axial signal reconstruction problem, and the axial resolution degradation is caused by axial sidelobe interference. We propose an advanced frequency-domain eigenspace-based minimum variance (F-EIBMV) beamforming technique to suppress axial sidelobe interference and noises. This method can simultaneously enhance the axial resolution and contrast of OR-PAM. For a 25-MHz OR-PAM system, the full-width at half-maximum of an axial point spread function decreased significantly from 69.3 $\mu$m to 16.89 $\mu$m, indicating a significant improvement in axial resolution.

Improved Ultrasound Attenuation Coefficient Estimation Using Spectral Normalization on Local Interference-Free Single-Scatterer Power Spectrum

Ultrasound attenuation coefficient estimation (ACE) can be utilized to quantify liver fat content, offering significant diagnostic potential in addressing the growing global public health issue of non-alcoholic fatty liver and other chronic liver diseases. Among ACE methods, the reference frequency method (RFM) proposed recently possesses the advantages of being system-independent and not requiring reference phantom. However, the presence of large oscillations in frequency power ratio decay curves leads to unstable ACE results with RFM, originating from noise as well as constructive and destructive interference in the backscattered signal's power spectrum. To address this issue, we propose an improved RFM version where a single-scatterer power spectrum estimator is incorporated to restore interference free single-scatterer power spectrum, thereby reducing oscillations in the frequency power ratio decay curves and greatly improving the accuracy of ACE.

Improved Row-Column-Addressed Array Imaging by Leveraging Ghost Echoes

Among various choices of 2-D ultrasound transducer arrays, the row-column-addressed (RCA) 2-D array has shown its promise for 3-D imaging. However, RCA suffers from notable edge effects and thus receives ghost echoes, which result in ghost artifacts showing in the volumetric image. In this research, rather than discarding these ghost echoes, we consider them as supportive signals and incorporate them into a postfiltering-based method to enhance the RCA imaging quality. Field II simulation and results of a single scatterer are presented in this work. The strongest ghost artifact is suppressed by 23 dB and the -6 dB lateral resolution is improved from 1.06 to 0.81 mm. The proposed method shows promising results in suppressing ghost artifacts and enhancing lateral resolution.

Phase Aberration Correction with Adaptive Coherence-Weighted Point Spread Function Restoration Filtering Technique

Phase aberration is an inherent side effect of ultrasound imaging due to the speed of sound inhomogeneity nature of human tissues, resulting in focusing error and reduced image contrast. This work introduces a phase aberration correction technique by leveraging a point spread function (PSF) restoration filter. A convolutional neural network (CNN) is used to estimate phase-aberrated PSFs and design the restoration filter. In addition, we incorporate coherence index weighting, derived from the restoration filtering, to further suppress sidelobe energy. Evaluation using Field II-simulated phantoms showed clearer cyst borders and reduced sidelobe energy leakage after PSF restoration and filter-derived coherence weighting, leading to improvement in image contrast and quality.

Copy-Paste Image Augmentation with Poisson Image Editing for Ultrasound Instance Segmentation Learning

Deep learning has shown great success in high-level image analysis problems; yet its efficacy relies on the quality and diversity of the training data. In this work, we introduce a copypaste image augmentation for ultrasound images. The Poisson image editing technique is used to generate realistic and seamless boundary transitions around the pasted image. Results showed that the proposed image augmentation technique improves training performance in terms of higher objective metrics and more stable training results.

Representative Image Feature Extraction via Contrastive Learning Pretraining for Chest X-ray Report Generation

Medical report generation is a challenging task since it is time-consuming and requires expertise from experienced radiologists. The goal of medical report generation is to accurately capture and describe the image findings. Previous works pretrain their visual encoding neural networks with large datasets in different domains, which cannot learn general visual representation in the specific medical domain. In this work, we propose a medical report generation framework that uses a contrastive learning approach to pretrain the visual encoder and requires no additional meta information. In addition, we adopt lung segmentation as an augmentation method in the contrastive learning framework. This segmentation guides the network to focus on encoding the visual feature within the lung region. Experimental results show that the proposed framework improves the performance and the quality of the generated medical reports both quantitatively and qualitatively.