检索结果-内蒙古大学图书馆

2nd International conference on Big data, Machine Learning, and Applications, BigDML 2021

作者： Singh, Yumnam Kirani C-DAC Silchar Ground Floor NIT Silchar Campus Assam Silchar788010 India

ISBN: (纸本)9789819934805

Proposed here is a simple and effective method for segmenting lung regions from CT-scan image. In this method, the CT-scan image in DICOM format is converted into RGB image, which is then further converted into gray image. The resulted grayscale image is then binarized using K-means, which automatically groups the pixels into two clusters of pixels;one belonging to the background pixels, while the other cluster to the pixels belonging to the lung regions. from the cluster of pixels belonging to the lung regions, the left and right lungs can be properly separated. The K-Means clustering used in the method is based on recursive averaging to avoid overflow errors while computing and updating cluster centers. As compared to other traditional methods of lung region segmentation, it is much simpler and gives better results. Also, it is much simpler and faster than the deep learning methods for lung region segmentation as it does not require any rigorous training with a large number of images. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Quantum Convolutional Neural Network for Medical image Classification: A Hybrid Model 2

Quantum Convolutional Neural Network for Medical Image Class...

引用

2nd IEEE International conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Khatoniar, Ria Vyas, Vishu Acharya, Videet Saxena, Anshul Saxena, Amit Neiwal, Rahul Korgaonkar, Kunal Bits Pilani Csis Department K K Birla Goa Campus Goa India C-DAC Pune Pune India Christ University Bengaluru India Delhi India

ISBN: (纸本)9798350384277

This study explores the application of Quantum Convolutional Neural Networks (QCNNs) in the realm of image classification, particularly focusing on datasets with a highly reduced number of features. We investigate the potential quantum computing holds in processing and classifying image data efficiently, even with limited feature availability. This research investigates QCNNs' application within a highly constrained feature environment, using chest X-ray images to distinguish between normal and pneumonia cases. Our findings demonstrate QCNNs' utility in classifying images from the dataset with drastically reduced feature dimensions, highlighting QCNNs' robustness and their promising future in machine learning and computer vision. Additionally, this study sheds light on the scalability of QCNNs and their adaptability across various training-test splits, emphasizing their potential to enhance computational efficiency in machine learning tasks. This suggests a possibility of paradigm shift in how we approach data-intensive challenges in the era of quantum computing. We are looking into quantum paradigms like Quantum Support Vector Machine (QSVM) going forward so that we can explore trade offs effectiveness of different classical and quantum computing techniques. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Improving Nighttime Flare Removal with Subspace Basic Projection 2

Improving Nighttime Flare Removal with Subspace Basic Projec...

引用

2nd IEEE International conference on Signal, Information and data Processing, ICSIDP 2024

作者： Lian, Jiazheng Liu, Zherong Jing, Minge Zhou, Jun Fan, Yibo State Key Laboratory of Integrated Chips and Systems Fudan University Academy for Engineering and Technology Shanghai China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu China Fudan University State Key Laboratory of Integrated Chips and Systems Shanghai China

ISBN: (纸本)9798331515669

Flare is an imaging issue caused by optical refraction in the lens. The imaging hazards caused by flares are more pronounced at night due to the large difference in intensity between the light source and the background. Since it is difficult to infer a flare-free scene from a flare-corrupted image, recovering textures under nighttime flare remains a challenging problem. In this paper, we propose a novel nighttime flare removal framework based on subspace projection and a jet map mask-based crossattention mechanism to remove nighttime flare and recover the scene under the flare, termed FBNet. On one hand, we propose subspace projection as a function of the flare basis network to better separate the flare from the scene. On the other hand, we found that the binarized threshold segmentation result obtained by using the jet map as a threshold segmentation condition is remarkably effective in extracting the flare as an input feature to the cross-attention mechanism. Therefore, we came out with a jet map-based transformer cross-attention block that uses a binary mask as a priori to achieve optimal recovery in the flare region Extensive evaluations on synthetic benchmarks and the real-world datasets Flare7K and Flare7pp highlight the superiority of our approach compared to the previous state-of-the-art methods for flare removal. All proposed methods improve the nighttime flare removal performance. © 2024 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Correlation between Bovine Arch and Thoracic Aortic Disease: A Literature Review

引用

Journal of Long-Term Effects of Medical Implants 2023年第4期33卷 71-76页

作者： Bountou, O. Protogerou, V. Ananikas, K. Tsikouris, G. Angelis, S. Troupis, T. Department of Anatomy School of Medicine National and Kapodistrian University of Athens Greece National and Kapodistrian University of Athens 2nd Department of Ophthalmology Attikon Hospital Greece

The bovine artery is considered the most frequent aortic arch branching variation. Despite being considered a normal variation of the aortic arch branching, still it has been linked with various issues regarding the thoracic aorta. The aim of this study is to highlight the prevalence of bovine artery among specific vascular pathologies throughout the literature and to provide information to clinicians about the importance of identifying this variation. For this specific review, we acquired potentially relevant studies for inclusion from the electronic database of PubMed. We limited our investigation to papers published within the last decade (from 2011 to 2021). Single case reports, papers with language restrictions, letters to the editor, conference abstracts, studies that were non-human centered and studies with unextractable and incomplete data were not included. Searching the PubMed database, it was evident that there is a close relationship between bovine arch and thoracic aortic arch pathology. In the defined period 2011–2021 that our research was focused, we selected eight studies tackling this issue. The majority of the studies in this review (except one) provided concerning data about the prevalence of this aortic arch variant among patients with aortic aneurysmal dilatation and aortic dissection. Following our results, we strongly believe that bovine arch should no longer being considered as a normal variation with no clinical significance, but rather as a potential risk factor for thoracic aortic arch morbidities. © 2023 by Begell House, Inc. ***.

关键词： Arches

来源：评论

学校读者我要写书评

暂无评论

Localizing Action Moments with Dual-Guidance Augmented Discriminability 2

Localizing Action Moments with Dual-Guidance Augmented Discr...

引用

2nd IEEE International conference on image Processing and Computer Applications, ICIPCA 2024

作者： Chen, Qiantai Wang, Meiqing Cheng, Hang Chen, Fei Luo, Danni Dong, Yuxin College of Mathematics and Statistics Fuzhou University Fuzhou China College of Computer Science and Big Data Fuzhou University Fuzhou China

ISBN: (纸本)9798350360240

Temporal action detection (TAD) aims at locating the action boundaries and recognizing their categories among video action clips. However, vague boundary predictions suffer from quick switches of short action moments. At the same time, due to the vulnerable boundaries cheated by similar video backgrounds altering instead of the motion, the model's fine-grained discrimination is highly reliant on the background. To mitigate these issues, we present a novel dual-guidance graph-based architecture, dubbed as dual-guidance self-augmented graph network (DSGN). Specifically, we first exploit an effective expansion approach, inserting a full zero gap sequence between the original feature and the enhanced feature to eliminate the effect and increase the localization accuracy of short action boundaries. Then, a relational dual-aggregation method is designed to integrate two levels of context representations, namely, the local fragment-level feature and the global video-level feature, into the target proposal-level feature, based on their attention correlations according to the self-attention mechanism, to augment the destination proposal clip. We demonstrate that our model outperforms other state-of-the-art methods experimentally on HACS, ActivityNet vI.3 and FineActions. © 2024 IEEE.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

S2Q-Net: Mining the High-Pass Filtered Phase data in Susceptibility Weighted Imaging for Quantitative Susceptibility Mapping

引用

IEEE JOURNAL OF BIOMEDICAL And HEALTH INFORMATICS 2022年第8期26卷 3938-3949页

作者： Lu, Zhiyang Li, Jun Wang, Chaoyue Ge, Rongjun Chen, Lili He, Hongjian Shi, Jun Shanghai Univ Shanghai Inst Adv Commun & Data SciSch Commun & Key Lab Specialty Fiber Opt & Opt Access Networks Joint Int Res Lab Specialty Fiber Opt & Adv Commu Shanghai 200444 Peoples R China Zhejiang Univ Coll Biomed Engn & Instrumental Sci Ctr Brain Imaging Sci & Technol Hangzhou 310027 Zhejiang Peoples R China Zhejiang Lab Res Ctr Healthcare Data Sci Hangzhou 311100 Zhejiang Peoples R China Univ Oxford Nuffield Dept Clin Neurosci Wellcome Ctr Integrat Neuroimaging FMRIB Oxford OX1 2JD England Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 210016 Peoples R China Capital Med Univ Ctr Movement Disorders Dept Neurol Beijing Tiantan Hosp Beijing 100050 Peoples R China

Susceptibility weighted imaging (SWI) is a routine magnetic resonance imaging (MRI) sequence that combines the magnitude and high-pass filtered phase images to qualitatively enhance the image contrasts related to tissue susceptibility. Tremendous amounts of the high-pass filtered phase data with low signal to noise ratio and incomplete background field removal have thus been collected under default clinical settings. Since SWI cannot quantitatively estimate the susceptibility, it is thus non-trivial to derive quantitative susceptibility mapping (QSM) directly from these redundant phase data, which effectively promotes the mining of the SWI data collected previously. To this end, a novel deep learning based SWI-to-QSM-Net (S2Q-Net) is proposed for QSM reconstruction from SWI high-pass filtered phase data. S2Q-Net firstly estimates the edge maps of QSM to integrate edge prior into features, which benefits the network to reconstruct QSM with realistic and clear tissue boundaries. Furthermore, a novel Second-order Cross Dense Block is proposed in S2Q-Net, which can capture rich inter-region interactions to provide more non-local phase information related to local tissue susceptibility. Experimental results on both simulated and in-vivo data indicate its superiority over all the compared deep learning based QSM reconstruction methods.

关键词： image reconstruction image edge detection Feature extraction data mining Imaging Magnetic separation Magnetic resonance imaging Susceptibility weighted imaging high-pass filtered phase quantitative susceptibility mapping second-order statistics edge prior U-Net

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Assisted model for Medical image Fusion 2

Deep Learning Assisted model for Medical Image Fusion

引用

2nd DMIHER International conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Narad, Supriya Reddy, K.T.V. MH Wardha442001 India MH Wardha442001 India

ISBN: (纸本)9798331528713

Accurate prognosis is serious to early detection and successful conduct of non-small cell lung cancer (NSCLC). A deep Q-learning feature representation model that is efficient in order to predict NSCLC is presented in this study. Proposed novel method add adaptive thresholding with many feature extraction methods. By removing distinctive features from the input data, these techniques enable a more complete and accurate depiction of NSCLC characteristics. Usually, these models are not able to increase their classification accuracy with time. To solve these challenges, we offer a 1D convolutional neural network (CNN) with Q-learning, a reinforcement learning method that agrees for continual accuracy increases. The internal algorithms of our proposed model stand out for their reliability and efficiency. Adaptive thresholding allows for precise segmentation of non-small cells by dynamically varying the threshold based on localised pixel intensity. The feature extraction algorithms capture the different spatial and frequency properties found in NSCLC pictures. As a result, the process of feature representation is rich and educational. Furthermore, the model is able to continuously adapt and enhance its classification accuracy thanks to the 1D CNN with Q-learning. A 99.5% effective precision is shown by the experimental results. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Scatter correction using FBP with data rearrangement for a single full scan CBCT 2

Scatter correction using FBP with data rearrangement for a s...

引用

2022 2nd International conference on Electronics, Circuits and Information Engineering, ECIE 2022

作者： Kang, Guanyu Han, Yu Xi, Xiaoqi Li, Lei Tan, Siyu Zhao, Hongfeng Yan, Bin Cyberspace Security Institute of Zhengzhou University Zheng zhou He nan China School of Information Systems Engineering The University of Information Engineering Zheng zhou He nan China Dongguan Xinda Optoelectronics Technology Co Guang dong Dong guan China

A scattering plate consisting of multiple lead strips is an effective tool for scatter correction and dose reduction in cone-beam CT(CBCT). Existing scattering plate correction methods take advantage of data redundancy by partially blocking cone beam data from a single scan to make up and perform scattering correction. However, for geometric objects with large cone angles during CBCT scans, existing backprojection-filteration(BPF) algorithms cannot accurately reconstruct the object due to data inconsistency and truncation, and may produce additional image artifacts. In order to improve the image quality at large cone angles, this paper proposes a hybrid scatter correction method for filteration-backprojection (FBP) image reconstruction from partially blocked cone beam data using data rearrangement. The proposed method uses a blocker consisting of multiple lead strips that are placed between the light source and the object to provide scatter correction and image reconstruction with beam-blocked data. In combination with a data rearrangement algorithm, the cone-beam projection data is rearranged into a tilted parallel projection data, followed by weighted filtering and inverse projection reconstruction. The experimental results of CBCT show that the proposed method effectively corrects the scattering in each projection and reconstructs the scatter-corrected image from a single scan. © Published under licence by IOP Publishing Ltd.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

2nd International conference on Sustainable Computing and data Communication Systems, ICSCDS 2023 - Proceedings

2nd International Conference on Sustainable Computing and Da...

引用

2nd International conference on Sustainable Computing and data Communication Systems, ICSCDS 2023

ISBN: (纸本)9781665491990

The proceedings contain 286 papers. The topics discussed include: machine learning based deceptive speech detection;transfer learning-based driver distraction detection;a backward business-oriented approach of major sectors in emphasizing sustainable technological pillars;prediction of sufficient accuracy for human activity recognition using novel long short term memory in compared with decision tree;automated driver drowsiness detection system using computer vision and machine learning;combining multi-features for lung cancer detection in computed tomography images: a feature fusion model;detection of fruit from an image using a single-shot detector for accurate calorie estimation;a framework for design and development of message sharing using open-source software;review of application of highly interactive and immersive computing technologies for enhancement of post-stroke survivor’s rehabilitation;effective surveillance using computer vision;traffic matrix estimation techniques- a survey on current practices;an improved machine learning based crop recommendation system;and contagious disease prediction using random forest algorithm interpolated with fuzzy model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of the Bone Grid reconstruction Based on CT data 2nd

Implementation of the Bone Grid Reconstruction Based on CT D...

引用

2nd EAI International conference on Edge Computing and IoT: Systems, Management and Security, ICECI 2021

作者： Chen, Yicong Shenzhen University Shenzhen China

ISBN: (纸本)9783031042300

Medical image processing has become an indispensable auxiliary means in the medical field, which make that the reconstruction of the internal image data of the human body can be visually presented to the doctor, providing the doctor with the simulation system of auxiliary diagnosis, which is helpful to find the lesions and improve the diagnostic accuracy. In this paper, a software system based on medical image data for the reconstruction of smooth three-dimension bone is studied. Firstly, software system read the medical image data to be processed (such as tumor site CT and MRI data), through the image denoising (remove bed information etc.), threshold processing (extract the interested region) and contour extraction (outer contour extraction), and other technical means to process medical image data of human surgical site, and then after processing of image data by three-dimensional reconstruction such as surface rendering mainly. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： image enhancement

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：