Advanced Ultrasound and Photoacoustic Imaging in Cardiology

Wu, Min; Awasthi, Navchetan; Rad, Nastaran Mohammadian; Pluim, Josien P. W.; Lopata, R.G.P.

doi:10.3390/s21237947

Cited by 20 publications

(16 citation statements)

References 160 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the original feature map is weighted by multiplication, and the feature map with attention weight in the width and height directions is obtained, as shown in Equation (6).…”

Section: 𝑓 = 𝛿(𝐹 ( 𝑧 𝑧 ))mentioning

confidence: 99%

“…With the development of deep learning tools, target detection models are very effective across different application domains such as vehicle detection [1,2], traffic sign detection [3], face detection [4,5], medical image analysis [6], and target tracking [7,8]. Deep learningbased target identification algorithms include one-stage target detection techniques based on regression analysis and two-stage target detection algorithms based on candidate boxes, as well as two-stage target object detection methods such as R-CNN [9], SPPnet [10], Fast R-CNN [11], Faster R-CNN [12], Mask R-CNN [13], and FPN [14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on Mask-Wearing Detection Algorithm Based on Improved YOLOv5

Guo

et al. 2022

Sensors

View full text Add to dashboard Cite

COVID-19 is highly contagious, and proper wearing of a mask can hinder the spread of the virus. However, complex factors in natural scenes, including occlusion, dense, and small-scale targets, frequently lead to target misdetection and missed detection. To address these issues, this paper proposes a YOLOv5-based mask-wearing detection algorithm, YOLOv5-CBD. Firstly, the Coordinate Attention mechanism is introduced into the feature fusion process to stress critical features and decrease the impact of redundant features after feature fusion. Then, the original feature pyramid network module in the feature fusion module was replaced with a weighted bidirectional feature pyramid network to achieve efficient bidirectional cross-scale connectivity and weighted feature fusion. Finally, we combined Distance Intersection over Union with Non-Maximum Suppression to improve the missed detection of overlapping targets. Experiments show that the average detection accuracy of the YOLOv5-CBD model is 96.7%—an improvement of 2.1% compared to the baseline model (YOLOv5).

show abstract

“…Finally, the original feature map is weighted by multiplication, and the feature map with attention weight in the width and height directions is obtained, as shown in Equation (6).…”

Section: 𝑓 = 𝛿(𝐹 ( 𝑧 𝑧 ))mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Research on Mask-Wearing Detection Algorithm Based on Improved YOLOv5

Guo

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The principle is that the contrast agent converts light energy into thermal energy, causing thermoelastic tissue expansion. Thermoelastic expansion generates acoustic waves, which are detected and converted into PA images by the instrument [57,58]. Contrast agents are divided into endogenous (melanin, hemoglobin) and exogenous contrast agents (nanoprobes) [59,60].…”

Section: Photoacoustic Imagingmentioning

confidence: 99%

Molecular nanoprobe for diagnosis of cardiovascular diseases

Wei

Wang

et al. 2022

ATM

View full text Add to dashboard Cite

Cardiovascular disease (CVD) remains the most leading cause of disease-related death worldwide. Current diagnostic modalities such as biomarkers and electrocardiography are relatively limited, which urgently develop new and effective techniques. Recently, molecular imaging has gained extensive attention in CVD diagnosis due to its ability to non-invasively visualize and quantify physio-pathological processes. However, the current mainstream imaging agents are limited by low specificity, short retention time, and severe side effects. Fortunately, with the development of nanomedicine, nanomaterials could play an important role in molecular imaging and CVD diagnosis. Here, we first summarize the concepts and characteristics of different molecular imaging, then focus on the application of nanoprobes as imaging agents in molecular imaging of CVD, and finally briefly introduce the challenges and prospects of nanomaterials-based molecular imaging.

show abstract

“…EMI noise has also been an ongoing issue in photoacoustic (PA) tomography (PAT) [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 ] because PAT relies on analogue ultrasound (US) signals typically ranging in the RF band 1–100 MHz. PAT is a novel tomographic imaging modality based on the photoacoustic effect, which has been drawing increased attention as a range of biomedical applications have shown promising results over the past decade.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Algorithm for the Removal of Electromagnetic Interference Noise in Photoacoustic Endoscopic Image Processing

Gulenko

Yang

Kim

et al. 2022

Sensors

View full text Add to dashboard Cite

Despite all the expectations for photoacoustic endoscopy (PAE), there are still several technical issues that must be resolved before the technique can be successfully translated into clinics. Among these, electromagnetic interference (EMI) noise, in addition to the limited signal-to-noise ratio (SNR), have hindered the rapid development of related technologies. Unlike endoscopic ultrasound, in which the SNR can be increased by simply applying a higher pulsing voltage, there is a fundamental limitation in leveraging the SNR of PAE signals because they are mostly determined by the optical pulse energy applied, which must be within the safety limits. Moreover, a typical PAE hardware situation requires a wide separation between the ultrasonic sensor and the amplifier, meaning that it is not easy to build an ideal PAE system that would be unaffected by EMI noise. With the intention of expediting the progress of related research, in this study, we investigated the feasibility of deep-learning-based EMI noise removal involved in PAE image processing. In particular, we selected four fully convolutional neural network architectures, U-Net, Segnet, FCN-16s, and FCN-8s, and observed that a modified U-Net architecture outperformed the other architectures in the EMI noise removal. Classical filter methods were also compared to confirm the superiority of the deep-learning-based approach. Still, it was by the U-Net architecture that we were able to successfully produce a denoised 3D vasculature map that could even depict the mesh-like capillary networks distributed in the wall of a rat colorectum. As the development of a low-cost laser diode or LED-based photoacoustic tomography (PAT) system is now emerging as one of the important topics in PAT, we expect that the presented AI strategy for the removal of EMI noise could be broadly applicable to many areas of PAT, in which the ability to apply a hardware-based prevention method is limited and thus EMI noise appears more prominently due to poor SNR.

show abstract

Advanced Ultrasound and Photoacoustic Imaging in Cardiology

Cited by 20 publications

References 160 publications

Research on Mask-Wearing Detection Algorithm Based on Improved YOLOv5

Research on Mask-Wearing Detection Algorithm Based on Improved YOLOv5

Molecular nanoprobe for diagnosis of cardiovascular diseases

Deep-Learning-Based Algorithm for the Removal of Electromagnetic Interference Noise in Photoacoustic Endoscopic Image Processing

Contact Info

Product

Resources

About