检索结果-内蒙古大学图书馆

Lung Lesion Classification Scheme Using Optimization Techniques and Hybrid (KNN-SVM) Classifier

IETE JOURNAL OF RESEARCH 2022年第2期68卷 1485-1499页

作者： Rani, K. Vijila Jawhar, S. Joseph Anna Univ Informat & Commun Engn Chennai Tamil Nadu India Arunachala Coll Engn Women Nagercoil Tamil Nadu India

This paper proposes an intellectual classification system to classify normal and abnormal CT scan lung images. Prediction of cancer cells from lung image is such a difficult task for physicians and researchers. A novel technique for lung tumour detection with Grey Wolf Optimized & Whale Optimization Algorithm - Support Vector Machine (GWO & WOA-SVM) is proposed. CT scan images are used as input images. Investigations focused on the segmentation and classification part to find the lung lesion region. For finding the lung abnormality and lesion region in the lung, four different stages are used. The first stage is the image acquisition process. The second stage is the image pre-processing and enhancement stage, here Advanced Clustering (AC) technique is used. The next stage is the segmentation process, here the advanced surface normal overlap (ASNO) lung segmentation algorithm is used. Finally, the lung lesion is classified using the hybrid classifier followed by a different optimization technique. The research gap for this paper is to find the lung lesion using an optimization-based hybrid classification technique. Nowadays, classification decision and treatment of lung tumours are based on symptoms and radiological appearance. Here Hybrid Classifier (KNN-SVM) is used to classify 700 images;it is observed from the results that the Hybrid classifier KNN-SVM demonstrated the highest classification accuracy rate of 97.6% among other methods.

关键词： Lung tumour Advanced Clustering segmentation process ASNO Hybrid KNN-SVM Classifier Grey Wolf Optimized Whale Optimization Algorithm

来源：评论

学校读者我要写书评

暂无评论

Combine unlabeled with labeled MR images to measure acute ischemic stroke lesion by stepwise learning

引用

IET IMAGE processING 2022年第14期16卷 3965-3976页

作者： Zhao, Bin Liu, Zhiyang Liu, Guohua Wu, Mengran Cao, Chen Jin, Song Wu, Hong Ding, Shuxue Nankai Univ Tianjin Key Lab Optoelect Sensor & Sensing Networ Coll Elect Informat & Opt Engn Tianjin 300350 Peoples R China Guilin Univ Elect Technol Sch Artificial Intelligence Guilin Guangxi Peoples R China Tianjin Huanhu Hosp Key Lab Cerebral Artery & Neural Degenerat Tianji Dept Med Imaging Tianjin Peoples R China

Acute ischemic stroke is a common threat to human health and may obtain timely treatment by fast localizing and quantitatively evaluating the lesions. Most CNN-based methods try to segment and measure the lesions, however, they require a training on a large number of labeled subjects that are labor-intensive and time-consuming to obtain. In this paper, a method is proposed that can combine limited labeled subjects with abundant unlabeled subjects to alleviate the problem. The proposed method consists of two stages: stepwise learning process and segmentation process. Stepwise learning is used to obtain the pretrained encoder. The pretrained encoder and the proposed decoder are connected into a new end-to-end segmentation network, which is retrained on the labeled subjects in the segmentation process. By using 5 labeled subjects and 79 unlabeled subjects, the proposed method achieves a mean dice coefficient of 0.663 +/-$\,{\pm}\,$0.205, a mean average symmetric surface distance (ASSD) of 2.17 mm and a mean 95 percentile Hausdorff distance (HD) of 18.38 mm on a clinical MR dataset with 179 subjects. More importantly, it achieves lesion-wise F-1 score of 0.857 and a subject-wise detection rate of 0.966.

关键词： end-to-end segmentation network medical image processing convolutional neural nets image segmentation labeled MR image unlabeled MR image CNN acute ischemic stroke lesion biomedical MRI stepwise learning process learning (artificial intelligence) encoder-decoder diseases segmentation process

来源：评论

学校读者我要写书评

暂无评论

Direct Estimation of Appearance Models for segmentation

引用

SIAM JOURNAL ON IMAGING SCIENCES 2022年第1期15卷 172-191页

作者： Rocha Neto, Jeova F. S. Felzenszwalb, Pedro Vazquez, Marilyn Brown Univ Sch Engn Providence RI 02912 USA Ohio State Univ Math Biosci Inst Columbus OH 43210 USA

Image segmentation algorithms often depend on appearance models that characterize the distribution of pixel values in different image regions. We describe a new approach for estimating appearance models directly from an image, without explicit consideration of the pixels that make up each region. Our approach is based on novel algebraic expressions that relate local image statistics to the appearance of spatially coherent regions. We describe two algorithms that can use the aforementioned algebraic expressions to estimate appearance models directly from an image. The first algorithm solves a system of linear and quadratic equations using a least squares formulation. The second algorithm is a spectral method based on an eigenvector computation. We present experimental results that demonstrate the proposed methods work well in practice and lead to effective image segmentation algorithms.

关键词： image segmentation mixture models Markov random fields segmentation process

来源：评论

学校读者我要写书评

暂无评论

Classification of retinal images based on convolutional neural network

引用

MICROSCOPY RESEARCH AND TECHNIQUE 2021年第3期84卷 394-414页

作者： El-Hag, Noha A. Sedik, Ahmed El-Shafai, Walid El-Hoseny, Heba M. Khalaf, Ashraf A. M. El-Fishawy, Adel S. Al-Nuaimy, Waleed Abd El-Samie, Fathi E. El-Banby, Ghada M. Minia Univ Fac Engn Dept Elect & Elect Comm Al Minya Egypt Kafrelshiekh Univ Fac Artificial Intelligent Dept Robot & Intelligent Machines Kafr Al Sheikh Egypt Menoufia Univ Fac Elect Engn Dept Elect & Elect Commun Engn Menoufia Egypt Al Obour High Inst Engn & Technol Dept Elect & Elect Commun Engn Al Qalyubia Governorate Egypt Univ Liverpool Dept Elect & Elect Engn Liverpool Merseyside England Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Technol Riyadh 21974 Saudi Arabia Menoufia Univ Fac Elect Engn Dept Ind Elect & Control Engn Menoufia Egypt

Automatic detection of maculopathy disease is a very important step to achieve high-accuracy results for the early discovery of the disease to help ophthalmologists to treat patients. Manual detection of diabetic maculopathy needs much effort and time from ophthalmologists. Detection of exudates from retinal images is applied for the maculopathy disease diagnosis. The first proposed framework in this paper for retinal image classification begins with fuzzy preprocessing in order to improve the original image to enhance the contrast between the objects and the background. After that, image segmentation is performed through binarization of the image to extract both blood vessels and the optic disc and then remove them from the original image. A gradient process is performed on the retinal image after this removal process for discrimination between normal and abnormal cases. Histogram of gradients is estimated, and consequently the cumulative histogram of gradients is obtained and compared with a threshold cumulative histogram at certain bins. To determine the threshold cumulative histogram, cumulative histograms of images with exudates and images without exudates are obtained and averaged for each type, and the threshold cumulative histogram is set as the average of both cumulative histograms. Certain histogram bins are selected and thresholded according to the estimated threshold cumulative histogram, and the results are used for retinal image classification. In the second framework in this paper, a Convolutional Neural Network (CNN) is utilized to classify normal and abnormal cases.

关键词： CNN contrast enhancement diabetic maculopathy exudate detection fuzzy enhancement Gaussian gradient retinal images segmentation process

来源：评论

学校读者我要写书评

暂无评论

segmentation of Urea Melt Marbles and Application of One-Shot segmentation in Batch Production of Large Urea Granules

引用

ACS SUSTAINABLE CHEMISTRY & ENGINEERING 2021年第43期9卷 14430-14442页

作者： Huang, Chunni Wu, Pan Liu, Shuyuan He, Yunyi He, Jian Liu, Changjun Jiang, Wei Sichuan Univ Sch Chem Engn Low Carbon Technol & Chem React Engn Lab Chengdu 610065 Peoples R China

Steel strip granulation is a promising technology for preparing large urea granules;however, easy blocking of the feeding nozzle by urea melt limits its industrial applications. In this study, a dust-free and anticlogging urea granulation process for the mass production of large urea granules is proposed by introducing a urea melt marble (UMM) formed by covering urea melt with super-urea-phobic poly(tetrafluoroethylene) (PTFE) particles to improve steel strip granulation. Large urea granules are obtained by directly cutting a large-sized cake-shaped mother-UMM into segments. These segments shrink into spherical baby-UMMs and solidify after condensation to form rigid particles. The results confirm that the PTFE powder distribution density for constructing a stable mother-UMM by the segmentation process is crucial. The PTFE powder distribution density for obtaining usable baby-UMMs and subsequent qualified large urea granules should be within 0.0009-0.0011 g/cm(2). Super-urea-phobic honeycomb-shaped cutters are used for the batch preparation of qualified urea products with adequate quality distribution. This study provides a promising strategy for improving the production of urea granules.

关键词： urea melt marbles segmentation process mechanical strength large urea granule super-urea-phobic surface

来源：评论

学校读者我要写书评

暂无评论

An MRI-based deep learning approach for efficient classification of brain tumors

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2021年第6期14卷 6697-6718页

作者： Ul Haq, Ejaz Huang Jianjun Kang Li Ul Haq, Hafeez Tijiang Zhang Shenzhen Univ Sch Elect & Informat Engn Guangdong Key Lab Intelligent Informat Proc Shenzhen Peoples R China Fujian Normal Univ Fuzhou Peoples R China Zunyi Med Univ Imaging Dept Zunyi Guizhou Peoples R China

Efficient and reliable identification and classification of brain tumors from imaging data is essential in the diagnosis and treatment of brain cancer cells. Magnetic resonance imaging (MRI) is the most commonly used imaging modality in the analysis of infected brain tissue. However, manual segmentation requires significant time to process data produced by magnetic resonance imaging. In this study, we present two fast and proficient brain tumor identification techniques based on deep convolutional neural networks (CNNs) using magnetic resonance imaging data for the effective detection and classification of different types of brain tumors. We use two publicly available datasets from Figshare and BraTS 2018, and apply conditional random fields to eliminate forged outputs, considering spatial information on fine segmentation tasks. The first proposed architecture, based on the Figshare dataset, classifies brain tumors as gliomas, meningiomas, or pituitary tumors. The second architecture differentiates between high- and low-grade gliomas (HGG and LGG, respectively). An intensity normalization method is also investigated as a pre-processing step, which proves highly effective at detection and classification of brain tumors in combination with data augmentation techniques. The Figshare and BraTS 2018 datasets included 3062 and 251 images, respectively. The experimental results demonstrate an accuracy of 97.3% and a dice similarity coefficient (DSC) 95.8% on the task of classifying brain tumor as gliomas, meningiomas, or pituitary tumors achieved by the first proposed CNN architecture, while second proposed CNN architecture achieved an accuracy of 96.5% with a DSC of 94.3% on the task of classifying glioma grades as HGG or LGG. Experimental results reveal that our proposed model attained improved performance and increased classification accuracy compared to state-of-the-art methods.

关键词： segmentation process Brain tumor Deep convolutional neural network Data augmentation Magnetic resonance images

来源：评论

学校读者我要写书评

暂无评论

Optimised hybrid classifiers for automatic HEp-2 cell classification

引用

IET IMAGE processING 2020年第16期14卷 4316-4328页

作者： Chariyamparambil Chandran, Manju Victor Jose, Marianthiran Noorul Islam Ctr Higher Educ Dept Comp Sci & Engn Kumaracoil 629180 TN India Noorul Islam Ctr Higher Educ Dept MCA Kumaracoil 629180 TN India

This paper introduces a new HEp-2 cell classification model under two phases. In the initial phase, the input image is segmented using the morphological operations (opening and closing), and the segmented image is given for Convolutional Neural Network (CNN) classifier that gives the classified output. In the second phase, the given input is processed under (i) segmentation process (ii) Feature Extraction, and (iii) Classification. From the segmented images;the features like Gray level co-occurrence Matrix TGLCM) and Gray level Run Length Matrix (GLRM) are extracted. After extracting the features, they are subjected to a classification process, where Neural Network (NN) is used. Finally, the mean of both classified output (first phase and second phase) is considered to be the final classified output. As the main contribution, to enhance the classification accuracy, the hidden neurons of both classifiers (CNN and NN) are optimally chosen during the classification process. To make this possible, this paper aims to propose a new Randomized Update based Grey Wolf Optimization (RP-GWO) algorithm. Finally, the performance of the implemented approach is compared over other conventional approaches and its superiority is proven with respect to certain measures.

关键词： medical image processing image segmentation image classification cellular biophysics feature extraction neural nets image texture diseases image representation improved diagnosis ability huge intra-class deviations HEp-2 cell classification model input image segmented image convolutional neural network classifier segmentation process co-occurrence matrix grey-level run-length matrix classification process final classified output classification accuracy randomised update-based grey wolf optimisation algorithm optimised hybrid classifiers automatic HEp-2 cell classification human epithelial type 2 cell image classifications computer-aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Review of advanced computational approaches on multiple sclerosis segmentation and classification

引用

IET SIGNAL processING 2020年第6期14卷 333-341页

作者： Shanmuganathan, Manimurugan Almutairi, Saad Aborokbah, Majed Mohammed Ganesan, Subramaniam Ramachandran, Varatharajan Univ Tabuk Fac Comp & Informat Technol Tabuk City Saudi Arabia Univ Tabuk Fac Comp & Informat Technol Ind Innovat & Robot Ctr Tabuk City Saudi Arabia Oakland Univ Dept Elect & Comp Engn Rochester MI 48063 USA Bharath Inst Higher Educ & Res Dept Elect & Commun Engn Chennai Tamil Nadu India

In this study, a survey of multiple sclerosis (MS) classification and segmentation process is presented, which is based on magnetic resonance imaging. Knowledge of MS lesions is gained by determining the number of sample lesions in order that the lesion development level can be followed precisely;therefore, the effects of pharmaceuticals in medical tests can be accurately assessed. Accurate recognition of MS lesions in magnetic resonance images is an additionally complex process because of their changing shapes and sizes which can be very difficult to identify based on anatomical positions in various subjects. This can be determined by precise segmentation;manual segmentation would be very difficult to perform as it requires high level knowledge which takes additional time. Inter- and intra-expert variability need to be determined in order to perform the automated segmentation of lesions. The principal aim of this survey effort is to provide an analysis of the different categorization and segmentation methods and their techniques. This survey work will be valuable for researchers working in MS by considering and carefully evaluating the past work. The benefits and drawbacks of existing techniques are reviewed and the issue of MS lesion segmentation and classification is elucidated.

关键词： medical image processing biomedical MRI neurophysiology image segmentation brain classification methods survey work MS lesion segmentation multiple sclerosis segmentation multiple sclerosis classification segmentation process magnetic resonance imaging MS lesions sample lesions lesion development level magnetic resonance images precise segmentation manual segmentation automated segmentation

来源：评论

学校读者我要写书评

暂无评论

Cooperative object segmentation and recognition via restricted Boltzmann machine

引用

ELECTRONICS LETTERS 2020年第8期56卷 378-379页

作者： Huang, Wei Yu, Huimin Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Zhejiang Univ State Key Lab CAD & CG Hangzhou 310027 Peoples R China

The authors present a model where object segmentation and recognition are connected with a bottom-up inference and a top-down generation pathway so that the two models can communicate and cooperate with each other. They are integrated into an energy function and optimised at the same time. To achieve the cooperation, objects are modelled in two aspects: shape and appearance, so that the recognition result could feedback to the segmentation process. Restricted Boltzmann machine is employed to learn the shapes of the objects with corresponding labels and perform object recognition based on the object shapes. Another pathway involved with the appearance knowledge of the objects is also established so that both the shape and appearance information will guide and constrain the evolution of the segmentation developing towards the region of interest, which will further facilitate the performances of both tasks. Experiments demonstrate the effectiveness of the proposed model.

关键词： Boltzmann machines image segmentation object recognition learning (artificial intelligence) recognition result segmentation process object recognition object shapes appearance knowledge appearance information restricted Boltzmann machine generation pathway energy function cooperative object segmentation bottom-up inference top-down generation pathway

来源：评论

学校读者我要写书评

暂无评论

Fully-automatic raw G-band chromosome image segmentation

引用

IET IMAGE processING 2020年第9期14卷 1920-1928页

作者： Altinsoy, Emrecan Yang, Jie Yilmaz, Can Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai Peoples R China Shanghai Jiao Tong Univ Inst Med Robot Shanghai Peoples R China

Analysis of the chromosome images plays an important role in discovering one's genetic information and possible genetic disorders. segmentation has a very substantial place in the chromosome analysis and without an automatic solution, it is a time-consuming and error-prone procedure. Many researchers tried to automate the segmentation process. However, background noise, objects other than chromosomes in the image, touching and overlapped chromosomes are still current issues. To address these issues, the authors proposed fully-automatic raw G-band chromosome image segmentation, which aims to segment every single chromosome with a minimal error. The proposed algorithm contains the following steps: clearing the background noise, eliminating the objects other than chromosomes, distinguishing single chromosomes and chromosome clusters, separating touching and overlapping chromosomes. The proposed algorithm is tested on 508 raw images and achieved an accuracy of 94.7% for touching chromosome separation, 96.3% for overlapped chromosome separation, and 98.94% for segmentation of all chromosomes. The whole segmentation process takes 2-7 s for one image, depending on the number of touching and overlapping chromosomes. The segmentation results showed that compared to the previously proposed methods, their algorithm achieved better accuracy.

关键词： image segmentation genetics cellular biophysics bioinformatics overlapped chromosomes fully-automatic raw G-band chromosome image segmentation background noise chromosome clusters touching overlapping chromosomes raw images overlapped chromosome separation segmentation process chromosome analysis single chromosome segmentation time 2 0 s to 7 0 s

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：