A Novel High-Capacity Information Hiding Scheme Based on Improved U-Net

Computational Intelligence and Neuroscience

et al. 2022

Applying the method of semantic segmentation to the segmentation of grape leaves is an important method to solve how to segment grape leaves from complex backgrounds. This article uses U-net++ convolutional neural network to segment grape leaves from complex backgrounds using MIOU, PA, and mPA as evaluation metrics. After the leaves are segmented, the OTSU threshold segmentation + EXG algorithm is used to extract the diseased spots of grape leaves and healthy grape leaves by increasing the proportion of green vectors. Grape leaf disease was automatically graded by the ratio of the healthy green part of the grape to the total leaf area.

“…After U-net++ segmentation [13][14][15][16][17][18][19][20][21], the effect is shown in the figure, and the background is set to black and the pixel value is 0.…”

Section: Analysis Of U-net++ Experimentalmentioning

confidence: 99%

Grape Leaf Disease Classification Combined with U-Net++ Network and Threshold Segmentation

Computational Intelligence and Neuroscience

et al. 2022

“…However, semantic segmentation could solve the difficulty associated with an accurate localisation. Currently, the state-of-the-art semantic segmentation model being employed is UNet [18][19][20][21][22][23], which is depicted in Figure 4 [14].…”

Section: Automatic Catheter Segmentation In 2-d Echocardiography Thro...mentioning

confidence: 99%

A Hybrid Catheter Localisation Framework in Echocardiography Based on Electromagnetic Tracking and Deep Learning Segmentation

Jia

Computational Intelligence and Neuroscience

Pham

2022

Interventional cardiology procedure is an important type of minimally invasive surgery that deals with the catheter-based treatment of cardiovascular diseases, such as coronary artery diseases, strokes, peripheral arterial diseases, and aortic diseases. Ultrasound imaging, also called echocardiography, is a typical imaging tool that monitors catheter puncturing. Localising a medical device accurately during cardiac interventions can help improve the procedure’s safety and reliability under ultrasound imaging. However, external device tracking and image-based tracking methods can only provide a partial solution. Thus, we proposed a hybrid framework, with the combination of both methods to localise the catheter tip target in an automatic way. The external device used was an electromagnetic tracking system from North Digital Inc (NDI), and the ultrasound image analysis was based on UNet, a deep learning network for semantic segmentation. From the external method, the tip’s location was determined precisely, and the deep learning platform segmented the exact catheter tip automatically. This novel hybrid localisation framework combines the advantages of external electromagnetic (EM) tracking and the deep learning-based image method, which offers a new solution to identify the moving medical device in low-resolution ultrasound images.

“…Currently, the state-of-the-art semantic segmentation model being employed is UNet [18][19][20][21][22][23],…”

Section: Automatic Catheter Segmentation In 2-d Echocardiography Thro...mentioning

confidence: 99%

A Hybrid Catheter Localisation Framework in Echocardiography Based on Electromagnetic Tracking and Deep Learning Segmentation

Jia

2020

Preprint

Interventional cardiology procedure is an important type of minimally invasive surgery that deals with the catheter-based treatment of cardiovascular diseases, such as coronary artery diseases, strokes, peripheral arterial diseases and aortic diseases. Ultrasound imaging, also called echocardiography, is a typical imaging tool that monitors catheter puncturing. Localising a medical device accurately during cardiac interventions can help improve the procedure’s safety and reliability under ultrasound imaging. However, external device tracking and image-based tracking methods can only provide a partial solution. Thus, we proposed a hybrid framework, with the combination of both methods to localise the catheter tip target in an automatic way. The external device used was an electromagnetic tracking system from North Digital Inc (NDI) and the ultrasound image analysis was based on UNet, a deep learning network for semantic segmentation. From the external method, the tip’s location was determined precisely, and the deep learning platform segmented the exact catheter tip automatically. This novel hybrid localisation framework combines the advantages of external electromagnetic (EM) tracking and deep-learning-based image method, which offers a new solution to identify the moving medical device in low-resolution ultrasound images.Featured ApplicationThis framework can be applied to other medical-device localisation fields to help doctors identify a moving target in low-resolution ultrasound images.