Purpose Radiation therapy (RT) is a common treatment option for head and neck (HaN) cancer. An important step involved in RT planning is the delineation of organs‐at‐risks (OARs) based on HaN computed tomography (CT). However, manually delineating OARs is time‐consuming as each slice of CT images needs to be individually examined and a typical CT consists of hundreds of slices. Automating OARs segmentation has the benefit of both reducing the time and improving the quality of RT planning. Existing anatomy autosegmentation algorithms use primarily atlas‐based methods, which require sophisticated atlas creation and cannot adequately account for anatomy variations among patients. In this work, we propose an end‐to‐end, atlas‐free three‐dimensional (3D) convolutional deep learning framework for fast and fully automated whole‐volume HaN anatomy segmentation. Methods Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end‐to‐end fashion, receiving whole‐volume HaN CT images as input and generating masks of all OARs of interest in one shot. AnatomyNet is built upon the popular 3D U‐net architecture, but extends it in three important ways: (a) a new encoding scheme to allow autosegmentation on whole‐volume CT images instead of local patches or subsets of slices, (b) incorporating 3D squeeze‐and‐excitation residual blocks in encoding layers for better feature representation, and (c) a new loss function combining Dice scores and focal loss to facilitate the training of the neural model. These features are designed to address two main challenges in deep learning‐based HaN segmentation: (a) segmenting small anatomies (i.e., optic chiasm and optic nerves) occupying only a few slices, and (b) training with inconsistent data annotations with missing ground truth for some anatomical structures. Results We collected 261 HaN CT images to train AnatomyNet and used MICCAI Head and Neck Auto Segmentation Challenge 2015 as a benchmark dataset to evaluate the performance of AnatomyNet. The objective is to segment nine anatomies: brain stem, chiasm, mandible, optic nerve left, optic nerve right, parotid gland left, parotid gland right, submandibular gland left, and submandibular gland right. Compared to previous state‐of‐the‐art results from the MICCAI 2015 competition, AnatomyNet increases Dice similarity coefficient by 3.3% on average. AnatomyNet takes about 0.12 s to fully segment a head and neck CT image of dimension 178 × 302 × 225, significantly faster than previous methods. In addition, the model is able to process whole‐volume CT images and delineate all OARs in one pass, requiring little pre‐ or postprocessing. Conclusion Deep learning models offer a feasible solution to the problem of delineating OARs from CT images. We demonstrate that our proposed model can improve segmentation accuracy and simplify the autosegmentation pipeline. With this method, it is possible to delineate OARs of a head and neck CT within a fraction of a second.
Aiming at the randomness and obvious fluctuation of photovoltaic power, this paper proposes a method that combines Variational Modal Decomposition (VMD), Long Short-Term Memory (LSTM) network and Relevance Vector Machine (RVM) to achieve ultra-short-term photovoltaic power prediction. Firstly, the VMD decomposition technology is used to decompose the historical photovoltaic power sequence into different modes to reduce the non-stationarity of the data; then an LSTM prediction model is established for each mode, and the modal prediction values are reconstructed to obtain the power prediction value; in order to further improve the prediction accuracy of the model, the error sequence is modeled and predicted by RVM; finally, the prediction power value and the prediction error value are superimposed to obtain the final prediction result. Simulation results show that this method effectively improves the accuracy of photovoltaic power prediction.
An approach of fault diagnosis of bearing based on empirical mode decomposition (EMD), sample entropy and 1.5 dimension spectrum was presented. Firstly, the original vibration signal was decomposed into a number of intrinsic mode functions (IMFs) using EMD. Second, the sample entropies of IMFs were calculated to select the sensitive IMF. Finally, the IMF containing fault infor- mation was analyzed with 1.5 dimension spectrum, The experimental results show the method can be used to effectively diagnose faults of rolling bearing.
Ultrasound computed tomography (USCT) has important clinical application prospect in breast cancer screening and early diagnosis. In this paper, six kinds of coherence factor-like beamforming methods have been applied to improve the image quality for USCT, including coherence factor (CF), phase coherence factor (PCF), sign coherence factor (SCF), phasor dispersion based coherence factor (PDCF), spatial smoothed coherence factor (SSCF) and spatio-temporally smoothed coherence factor (STSCF). The mentioned methods were verified with the radio-frequency (RF) data of the breast phantom captured by the USCT system developed in the Medical Ultrasound Laboratory. The ring-type transducer has 1024 elements with a center frequency of 2.5 MHz. Experimental results show that the reconstructed images of the breast phantom by the CF gets the highest contrast to noise ratio (CNR), but overall image brightness reduces significantly. PCF gets the lowest variance and provides a more homogenous background. STSCF beamforming method can improve the robustness of the PCF and having the ability to suppress clutter while significant removal of black region artifacts. For practical application, these coherence factor-like beamforming methods can be implemented with low computational complexity.
In the late iteration of the gray wolf algorithm, the convergence results will have low accuracy becased of the elite retention.When implementing MPPT control, the maximum power point of the photovoltaic array cannot be accurately tracked, and it is easy to fall into the local optimum. Therefore, this paper proposes gray wolf algorithm improved with Levy flight applied to MPPT control. The algorithm introduces the Levy flight to search the head wolf position globally, then uses the group optimization of the gray wolf algorithm and the random walk of Levy flight to improve the tracking speed and accuracy of the MPPT controller. In the simulation experiment, the algorithm is modeled and verified by setting different lighting conditions. Finally, it is compared with the conductance increment method, modified hybrid method of grey wolf optimization and golden-section optimization, the original gray wolf algorithm. The results show that the algorithm meets the requirements of fast tracking speed, high accuracy and stability in MPPT control.
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.