Recent years have witnessed a growing interest in the use of U-Net and its improvement. It is one of the classic semantic segmentation networks with an encoder-decoder architecture and is widely used in medical image segmentation. In the series versions of U-Net, U-Net++ has been developed as an improved U-Net by designing an architecture with nested and dense skip connections, and U-Net 3+ has been developed as an improved U-Net++ by taking advantage of full-scale skip connections and deep supervision on full-scale aggregated feature maps. Each network architecture has its own advantages in the use of the encoder and decoder. In this paper, we propose an efficient and lightweight U-Net (ELU-Net) with deep skip connections. The deep skip connections include same-and large-scale skip connections from the encoder to fully extract the features of the encoder. In addition, the proposed ELU-Net with different loss functions is discussed to improve the effect of brain tumor learning including WT (whole tumor), TC (tumor core) and ET (enhance tumor) and a new loss function DFK is designed. The effectiveness of the proposed method is demonstrated for a brain tumor dataset used in the BraTS 2018 Challenge and liver dataset used in the ISBI LiTS 2017 Challenge.
The chaos phenomenon often exists in the dynamics system of the mechanism with clearance and friction, which has obvious effect on the stability of the mechanism, then it is worthy of attention for identifying the relationship between the friction coefficient and the stability of the mechanism. Two rotational degrees of freedom decoupled parallel mechanism RU-RPR is taken as the research object. Considering the clearance existing in the revolute pair, Lankarani–Nikravesh contact force model is used to calculate the normal contact force, and the Coulomb friction force model is used to calculate the tangential contact force. The dynamics model is established using Newton–Euler equations, and the Baumgarte stabilization method is used to keep the stability of the numerical analysis. Then, the equations are solved using the fourth adaptive Runge–Kutta method, and the effect of the revolute pair’s clearance on the dynamic behavior is analyzed. Poincare mapping is plotted, and the bifurcation diagrams are analyzed with varying the friction coefficient corresponding to different values of clearance size. The research contents possess a certain theoretical guidance significance and practical application value on the analysis of the chaotic motion and its stability in the dynamics of the parallel mechanism.
Background: In the series of improved versions of U-Net, while the segmentation accuracy continues to improve, the number of parameters does not change, which makes the hardware required for training expensive, thus affecting the speed of training convergence. Objective: The objective of this study is to propose a lightweight U-Net to balance the relationship between the parameters and the segmentation accuracy. Methods: A lightweight U-Net with full skip connections and deep supervision (LFU-Net) was proposed. The full skip connections include skip connections from shallow encoders, deep decoders, and sub-networks, while the deep supervision learns hierarchical representations from full-resolution feature representations in outputs of sub-networks. The key lightweight design is that the number of output channels is based on 8 rather than 64 or 32. Its pruning scheme was designed to further reduce parameters. The code is available at: https://github.com/dengdy22/U-Nets. Results: For the ISBI LiTS 2017 Challenge validation dataset, the LFU-Net with no pruning received a Dice value of 0.9699, which achieved equal or better performance with a mere about 1% of the parameters of existing networks. For the BraTS 2018 validation dataset, its Dice values were 0.8726, 0.9363, 0.8699 and 0.8116 on average, WT, TC and ET, respectively, and its Hausdorff95 distances values were 3.9514, 4.3960, 3.0607 and 4.3975, respectively, which was not inferior to the existing networks and showed that it can achieve balanced recognition of each region. Conclusion: LFU-Net can be used as a lightweight and effective method in the segmentation tasks of two and multiple classification medical imaging datasets.
Background Percutaneous vertebroplasty (PVP) has become the mainstream method for the treatment of osteoporotic vertebral compression fractures(OVCF). Generally, surgeons manually plan the puncture path by themselves. This is time-consuming and laborious, which increases the working pressure of surgeons. Image processing algorithm is used to automatically segment contour of vertebral body, and plan the puncture path before operation. In order to obtain the contours of vertebral body and skin, binarization and contour extraction algorithm were performed. The connecting algorithm we proposed was used to connect the discontinuous contour of vertebral foramen. We determined the centerline of vertebral body by inscribed circle center of the contours of vertebral body and vertebral foramen, located the narrowest part of vertebral pedicle based on rotating segment algorithm and calculated medical parameters. The experimental results show that the segmentation accuracy of algorithm is 95.92%, the average relative error of extracted parameters was no more than 4.18%. This method realizes automatic and accurate planning of puncture path before PVP, and it is of great significance to reduce the workload of surgeons, the number of intraoperative fluoroscopy and the harm of radiation to surgeons.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.