Abstract
As a new 3-D ultrasound imaging method, an automated breast ultrasound (ABUS) has been widely used in breast abnormality examinations. Because of its excellent 3D visualization, ABUS is also well suited to the detection of an abdominal wall hernia mesh. Due to the inherent low signal-to-noise ratio of ultrasound imaging and the large amount of data generated during ABUS scanning, mesh detection based on subjective observation is extremely time-consuming and prone to missed detection. Therefore, we proposed a novel abdominal hernia wall mesh detection method based on the you only look once version 3 (YOLOv3) method named the YOLOv3 for mesh (YOLOM) method to detect abdominal wall hernia mesh to speed up the ABUS reading process. To make a YOLOM method with a good detection efficiency, we utilized a lightweight cross stage partial attention network (CSPA-Net) as the backbone and applied a feature enhancement network (FEP-Net) to boost the mesh detection accuracy. An improved loss function with completed intersection-over-union (CIoU) and the Swish activation function were also employed to optimize the proposed YOLOM method. We designed ablation study to verify the validity of the proposed method. The average mesh detection precision reached 98.36%, which was 12.51% and 2.35% higher than that of the YOLOv3 and you only look once version 4 (YOLOv4) methods, respectively. The experimental results and comparisons demonstrated that the proposed YOLOM detector is efficient for abdominal wall hernia mesh detection.
Highlights
Reduce the incidence of related complications or the removal of a previous mesh. 2 An abdominal wall hernia is one of the most common complications of abdominal surgery
FEP-Net, completed intersection-over-union (CIoU), and the Swish activation function on the YOLOv3 for mesh (YOLOM) method are mentioned. According to this table, when the you only look once version 3 (YOLOv3) backbone is replaced with CSPA-Net, Space = o( Kl2 · Cl−1 · Cl + M 2 · Cl) l=1 l−1 the mean average precision of the YOLOM method 408 increases from 85.85% to 89.59%, which fully shows that the introduction of the cross-stage partial network and SE modwhere M is the width or height of the output feature map 410 ule into the backbone can make the network better learn the of the kernel, K is the width or height of each kernel, respec411 characteristics of a mesh
A mesh detection method based on the YOLOv3 method is proposed that utilizes CSPA-Net, FEP-Net, the Swish activation function and CIoU
Summary
Reduce the incidence of related complications or the removal of a previous mesh. 2 An abdominal wall hernia is one of the most common complications of abdominal surgery. Compared to narrowing the HHUS detection range, the difficulty of an abdominal wall hernia mesh surgery and 32 the ABUS scanning range has been greatly improved, but in VOLUME 4, 2016. Capability of the backbone, improves the detection effect This causes the following two problems in the detection for small targets, and reduces the amount of calculation and of a LW mesh: 1) It is time-consuming and labor-intensive model storage size. In the ratio and accelerate the network convergence, we introduce second stage, these box proposals are used as features from Complete-IoU (CIoU) to optimize the YOLOv3 loss functhe intermediate feature maps. Because the LW mesh is very thin (the tector for abdominal wall hernia mesh based on the YOLOv3 thickness of the LW mesh is only 0.5 mm), doctors usually algorithm named the YOLOM method to improve the detec- choose the coronal plane to detect and evaluate the mesh tion efficiency. Corner of the grid cell where the feature map is located. σ is the sigmoid activation function, which can normalize the coordinate offset between 0 and 1
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
