Article
Multidisciplinary Sciences
Mei Zhang, Dan Meng, Lingling Liu, Jinghua Wen
Summary: This paper proposes an improved algorithm based on the no-weight initialization level set model to address the shortcomings of the traditional level set model. The improved method introduces bilateral filters and uses implicit surface level sets to accurately extract and segment the original target image object. Experimental results demonstrate that the improved method achieves better edge contour extraction and noise reduction compared to the traditional non-reinitialized level set model.
Article
Mathematics, Interdisciplinary Applications
Xiangguo Liu, Guojun Liu, Yazhen Wang, Gengsheng Li, Rui Zhang, Weicai Peng
Summary: To address the limitations of conventional level set segmentation algorithms, a segmentation model based on the fusion of texture and structural information is developed. The model utilizes a rotation invariant mask and factorization theory to capture global image information and integrate pixel and neighboring pixel information into an energy generalization function. Experimental results demonstrate that the proposed model outperforms current active contour models in terms of robustness, segmentation accuracy, and algorithm running time.
FRACTAL AND FRACTIONAL
(2022)
Article
Geochemistry & Geophysics
Wenjing He, Hongjun Song, Yuanyuan Yao, Xinlin Jia, Yajun Long
Summary: This research introduces a novel level set method to address the segmentation issue in synthetic aperture radar (SAR) images, integrating local intensity and global feature information for improved results. Experiments confirm the effectiveness of the proposed method in both synthetic and real SAR images.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Biology
Sumaira Hussain, Xiamong Xi, Inam Ullah, Syed Azeem Inam, Farah Naz, Kashif Shaheed, Syed Asif Ali, Cuihuan Tian
Summary: This paper proposes a novel deep-feature embedded level set group for breast tumor segmentation in B-mode ultrasound imaging. The method combines deep networks to extract semantic features and level set methods to improve accuracy. Experimental results show that the proposed method outperforms other methods in segmenting breast tumors in complex images.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Instruments & Instrumentation
Yajie Li, Haoting Liu, Zhen Tian, Wenjia Geng
Summary: In order to address the segmentation difficulties and inaccurate computation issues in near-infrared vascular images, a series of image processing methods are proposed. The images are preprocessed by removing the background, stretching the contrast, and suppressing noise. Then, a two-stage image enhancement method is used to enhance the images by combining the benefits of convolutional neural network and traditional image enhancement method. Finally, an Adaptive Prior Shape Level Set Evolution (APSLSE) method is applied to segment the images and improve the common problems of initial contour sensitivity and unidirectional variation of area terms. A dataset of 360 images is collected for algorithm research and validation, and experimental results show that the proposed algorithms can effectively process poor quality near-infrared blood vessel images and segment their vascular shape. The False Negative Rate (FNR) is 0.1930 and False Positive Rate (FPR) is 0.04633 when compared to manually labelled results by experts.
INFRARED PHYSICS & TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
J. Jayanthi, M. Kavitha, T. Jayasankar, A. Sagai Francis Britto, N. B. Prakash, Mohamed Yacin Sikkandar, C. Bharathiraja
Summary: This study focuses on improving early diagnosis of glioma using a P-BTLBO algorithm, which automatically segments a brain tumor in a given MRI image. By preprocessing, segmenting, and extracting information from the MRI images, the results show that this method outperforms other existing algorithms.
CMC-COMPUTERS MATERIALS & CONTINUA
(2021)
Article
Computer Science, Artificial Intelligence
Guirong Weng, Bin Dong, Yu Lei
Summary: The proposed additive bias correction (ABC) model based on intensity inhomogeneity offers faster and more accurate segmentation of images with intensity inhomogeneity compared to traditional models, addressing issues such as slow segmentation speed and limited application fields.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
R. Pitchai, Ch Madhu Babu, P. Supraja, Mahesh Kumar Challa
Summary: Automatic segmentation of the tumor region from MRI images is a challenging task in medical image analysis. The proposed SS-2D ConvNet technique achieves better performance with dice scores of 91%, accuracy of 89%, specificity of 98%, and sensitivity of 87%, compared to existing methods. Convoluted Neural Networks have shown improved effectiveness in recognition tasks.
NEURAL PROCESSING LETTERS
(2021)
Article
Computer Science, Interdisciplinary Applications
Shuxin Zhang, Jun Song
Summary: Surface segmentation design is a conceptual problem in the structural design of large radio telescope antennas. A weighting level set topology optimization method is proposed for antenna backup supporting structure, followed by a surface segmentation optimization scheme. The method's effectiveness is easily illustrated through applications in two large radio telescope antenna designs.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Optics
Rajni Maurya, Sulochana Wadhwani
Summary: This paper proposes a brain tumor segmentation method based on watershed algorithm, which effectively achieves tumor segmentation through MRI image preprocessing and feature extraction. The system has high PSNR value and shorter computation time.
Article
Computer Science, Interdisciplinary Applications
Asieh Khosravanian, Mohammad Rahmanimanesh, Parviz Keshavarzi, Saeed Mozaffari
Summary: A novel level set method is proposed in this paper for reliable and automatic brain tumor segmentation. Experimental results show that the method is robust to noise, initialization, and intensity non-uniformity, and it is faster and more accurate compared to other state-of-the-art segmentation methods.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Herng-Hua Chang, Shin-Joe Yeh, Ming-Chang Chiang, Sung-Tsang Hsieh
Summary: The study investigates practical rat brain extraction and hemisphere segmentation algorithms in DWI and T2WI images, showing improved performance compared to existing methods. Experiment results with 55 subjects demonstrated high accuracy in rat brain extraction with average Dice scores of 97.13% in DWI and 97.42% in T2WI images, and hemisphere segmentation with average Hausdorff distances of 0.17mm in DWI and 0.15mm in T2WI subjects.
Article
Engineering, Biomedical
Poonam Rani Verma, Ashish Kumar Bhandari
Summary: This article proposes a fully unsupervised approach to brain extraction using a cascaded loss function and leaky ReLU activation function. The brain image is enhanced before extraction, resulting in better skull stripping.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2024)
Article
Engineering, Biomedical
Bruno Machado Pacheco, Guilherme de Souza e Cassia, Danilo Silva
Summary: State-of-the-art brain tumor segmentation is achieved using deep learning models on multi-modal MRIs. However, manual correction of images is time-consuming and may result in skull-stripping faults that negatively affect tumor segmentation quality. Training models on non-skull-stripped images may be the best option for achieving high performance in clinical practice.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Information Systems
Asieh Khosravanian, Mohammad Rahmanimanesh, Parviz Keshavarzi, Saeed Mozaffari, Kamran Kazemi
Summary: This paper proposes a new level set method called Fuzzy Kernel Level Set (FKLS) for brain tumor segmentation in MRI images. The method uses fuzzy c-means clustering and kernel mapping to transfer the image and extract the volume of interest. Experimental results show that the method outperforms existing segmentation methods in terms of accuracy.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
