检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Fu, Kexue Gao, Peng Liu, Shaolei Zhang, Renrui Qiao, Yu Wang, Manning Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai AI Lab China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention China

Recently, the pre-training paradigm combining Transformer and masked language modeling has achieved tremendous success in NLP, images, and point clouds, such as BERT. However, directly extending BERT from NLP to point clouds requires training a fixed discrete Variational AutoEncoder (dVAE) before pre-training, which results in a complex two-stage method called Point-BERT. Inspired by BERT and MoCo, we propose POS-BERT, a one-stage BERT pre-training method for point clouds. Specifically, we use the mask patch modeling (MPM) task to perform point cloud pre-training, which aims to recover masked patches information under the supervision of the corresponding tokenizer output. Unlike Point-BERT, its tokenizer is extra-trained and frozen. We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process. Further, in order to learn high-level semantic representation, we combine contrastive learning to maximize the class token consistency between different transformation point clouds. Extensive experiments have demonstrated that POS-BERT can extract high-quality pre-training features and promote downstream tasks to improve performance. Using the pretraining model without any fine-tuning to extract features and train linear SVM on ModelNet40, POS-BERT achieves the state-of-the-art classification accuracy, which exceeds Point-BERT by 3.5%. In addition, our approach has significantly improved many downstream tasks, such as fine-tuned classification, few-shot classification, part segmentation. The code and trained-models will be available at: https://***/fukexue/POS-BERT. Copyright © 2022, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

COVID-19 classification in X-ray chest images using a new convolutional neural network: CNN-COVID

引用

Research on Biomedical Engineering 2022年第1期38卷 87-97页

作者： de Sousa, Pedro Moisés Carneiro, Pedro Cunha Oliveira, Mariane Modesto Pereira, Gabrielle Macedo da Costa Junior, Carlos Alberto de Moura, Luis Vinicius Mattjie, Christian da Silva, Ana Maria Marques Patrocinio, Ana Claudia Biomedical Lab Faculty of Electrical Engineering Federal University of Uberlândia Campus Sta Mônica Av. João Naves de Ávila 2121 Bloco 1E CEP MG Uberlândia38400-000 Brazil Medical Image Computing Laboratory Pontifical Catholic University of Rio Grande do Sul Av. Ipiranga 6681 Partenon CEP RS Porto Alegre90619-900 Brazil

Purpose: COVID-19 causes lung inflammation and lesions, and chest X-ray and computed tomography images are remarkably suitable for differentiating the new disease from patients with other lung diseases. In this paper, we propose a computer model to classify X-ray images of patients diagnosed with COVID-19. Chest X-ray exams were chosen over computed tomography scans because they are low cost, results are quickly obtained, and X-ray equipment is readily available. Methods: A new CNN network, called CNN-COVID, has been developed to classify X-ray patient’s images. images from two different datasets were used. The images of Dataset I is originated from the COVID-19 image data collection and the ChestXray14 repository, and the images of Dataset II belong to the BIMCV COVID-19+ repository. To assess the accuracy of the network, 10 training and testing sessions were performed in both datasets. A confusion matrix was generated to evaluate the model’s performance and calculate the following metrics: accuracy (ACC), sensitivity (SE), and specificity (SP). In addition, Receiver Operating Characteristic (ROC) curves and Areas Under the Curve (AUCs) were also considered. Results: After running 10 tests, the average accuracy for Dataset I and Dataset II was 0.9787 and 0.9839, respectively. Since the weights of the best test results were applied in the validation, it was obtained the accuracy of 0.9722 for Dataset I and 0.9884 for Dataset II. Conclusions: The results showed that the CNN-COVID is a promising tool to help physicians classify chest images with pneumonia, considering pneumonia caused by COVID-19 and pneumonia due to other causes. © 2021, Sociedade Brasileira de Engenharia Biomedica.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Adaptive fast composite splitting algorithm for MR image reconstruction 1

引用

2nd International Conference on Machine Intelligence and Signal Processing, MISP 2019

作者： Mathew, Raji Susan Paul, Joseph Suresh Medical Image Computing and Signal Processing Lab Indian Institute of Information Technology and Management TrivandrumKerala India

ISBN: (数字)9789811513664

ISBN: (纸本)9789811513657

Reconstruction of an image from undersampled k-space data using conventional sparsity priors use any of the pre-specified transforms like wavelet, which utilizes the global sparsity of images. Alternatively, methods such as block-matching and 3D filtering (BM3D) utilize the non-local sparsity of images, resulting in better preservation of finer details. However, use of either of the methods cannot utilize global and non-local sparsity at the same time. In this paper, we propose an efficient combination of the global and non-local sparsity realized using wavelet and BM3D, implemented using the fast composite splitting denoising (FCSD) algorithm. Furthermore, we use an adaptive regularization parameter for the wavelet to yield the best achievable performance using adaptive thresholded Landweber (ATL). The proposed adaptive fast composite splitting denoising algorithm (AFCSD) combines the advantages of both BM3D with adaptive TL through the use of FCSD and thus exploits the self-repetitive structure in images by enforcing non-local sparsity as well as entire consistency of the image. Experimental results reveal that the proposed method is superior to any of the individual methods in terms of reconstruction accuracy and computation complexity. Additionally, when used as an auxiliary constraint in dictionary learning (DL), this can result in further improvements in reconstruction with significant reduction in the computation time as compared to a conventional DL reconstruction. © Springer Nature Singapore Pte Ltd. 2020.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Skin3D: Detection and Longitudinal Tracking of Pigmented Skin Lesions in 3D Total-Body Textured Meshes

arXiv

引用

arXiv 2021年

作者： Zhao, Mengliu Kawahara, Jeremy Abhishek, Kumar Shamanian, Sajjad Hamarneh, Ghassan Medical Image Analysis Lab. School of Computing Science Simon Fraser University Canada

We present an automated approach to detect and longitudinally track skin lesions on 3D total-body skin surface scans. The acquired 3D mesh of the subject is unwrapped to a 2D texture image, where a trained objected detection model, Faster R-CNN, localizes the lesions within the 2D domain. These detected skin lesions are mapped back to the 3D surface of the subject and, for subjects imaged multiple times, we construct a graph-based matching procedure to longitudinally track lesions that considers the anatomical correspondences among pairs of meshes and the geodesic proximity of corresponding lesions and the inter-lesion geodesic distances. We evaluated the proposed approach using 3DBodyTex, a publicly available dataset composed of 3D scans imaging the coloured skin (textured meshes) of 200 human subjects. We manually annotated locations that appeared to the human eye to contain a pigmented skin lesion as well as tracked a subset of lesions occurring on the same subject imaged in different poses. Our results, when compared to three human annotators, suggest that the trained Faster R-CNN detects lesions at a similar performance level as the human annotators. Our lesion tracking algorithm achieves an average matching accuracy of 88% on a set of detected corresponding pairs of prominent lesions of subjects imaged in different poses, and an average longitudinal accuracy of 71% when encompassing additional errors due to lesion detection. As there currently is no other large-scale publicly available dataset of 3D total-body skin lesions, we publicly release over 25,000 3DBodyTex manual annotations, which we hope will further research on total-body skin lesion analysis. © 2021, CC BY-NC-ND.

关键词： Geodesy

来源：评论

学校读者我要写书评

暂无评论

Rethinking Multiple Instance Learning for Whole Slide image Classification: A Good Instance Classifier is All You Need

arXiv

引用

arXiv 2023年

作者： Qu, Linhao Ma, Yingfan Luo, Xiaoyuan Guo, Qinhao Wang, Manning Song, Zhijian Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China Department of Gynecologic Oncology Fudan University Shanghai Cancer Center 270 Dong-An Road Shanghai200032 China

Weakly supervised whole slide image classification is usually formulated as a multiple instance learning (MIL) problem, where each slide is treated as a bag, and the patches cut out of it are treated as instances. Existing methods either train an instance classifier through pseudo-labeling or aggregate instance features into a bag feature through attention mechanisms and then train a bag classifier, where the attention scores can be used for instance-level classification. However, the pseudo instance labels constructed by the former usually contain a lot of noise, and the attention scores constructed by the latter are not accurate enough, both of which affect their performance. In this paper, we propose an instance-level MIL framework based on contrastive learning and prototype learning to effectively accomplish both instance classification and bag classification tasks. To this end, we propose an instance-level weakly supervised contrastive learning algorithm for the first time under the MIL setting to effectively learn instance feature representation. We also propose an accurate pseudo label generation method through prototype learning. We then develop a joint training strategy for weakly supervised contrastive learning, prototype learning, and instance classifier training. Extensive experiments and visualizations on four datasets demonstrate the powerful performance of our method. Codes are available at https://***/miccaiif/INS. Copyright © 2023, The Authors. All rights reserved.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Few-shot Semantic Segmentation with Self-supervision from Pseudo-classes 32

Few-shot Semantic Segmentation with Self-supervision from Ps...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Li, Yiwen Data, Gratianus Wesley Putra Fu, Yunguan Hu, Yipeng Prisacariu, Victor Adrian Active Vision Lab University of Oxford Oxford United Kingdom Centre for Medical Image Computing and Wellcome EPSRC Centre for Interventional and Surgical Sciences University College London London United Kingdom InstaDeep London United Kingdom

Despite the success of deep learning methods for semantic segmentation, few-shot semantic segmentation remains a challenging task due to the limited training data and the generalisation requirement for unseen classes. While recent progress has been particularly encouraging, we discover that existing methods tend to have poor performance in terms of meanIoU when query images contain other semantic classes besides the target class. To address this issue, we propose a novel self-supervised task that generates random pseudo-classes in the background of the query images, providing extra training data that would otherwise be unavailable when predicting individual target classes. To that end, we adopted superpixel segmentation for generating the pseudo-classes. With this extra supervision, we improved the meanIoU performance of the state-of-the-art method by 2.5% and 5.1% on the one-shot tasks, as well as 6.7% and 4.4% on the five-shot tasks, on the PASCAL-5i and COCO benchmarks, respectively. © 2021. The copyright of this document resides with its authors.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The Imaging Database for Epilepsy And Surgery (IDEAS)

arXiv

引用

arXiv 2024年

作者： Taylor, Peter N. Wang, Yujiang Simpson, Callum Janiukstyte, Vytene Horsley, Jonathan Leiberg, Karoline Little, Beth Clifford, Harry Adler, Sophie Vos, Sjoerd B. Winston, Gavin P. McEvoy, Andrew W. Miserocchi, Anna de Tisi, Jane Duncan, John S. CNNP Lab Interdisciplinary Computing and Complex BioSystems Group School of Computing Newcastle University Newcastle upon Tyne United Kingdom Faculty of Medical Sciences Newcastle University Newcastle upon Tyne United Kingdom UCL Queen Square Institute of Neurology Queen Square London United Kingdom UCL Great Ormond Street Institute of Child Health London United Kingdom Centre for Medical Image Computing Department of Computer Science UCL London United Kingdom Centre for Microscopy Characterisation and Analysis The University of Western Australia Nedlands Australia

Magnetic resonance imaging (MRI) is a crucial tool to identify brain abnormalities in a wide range of neurological disorders. In focal epilepsy MRI is used to identify structural cerebral abnormalities. For covert lesions, machine learning and artificial intelligence algorithms may improve lesion detection if abnormalities are not evident on visual inspection. The success of this approach depends on the volume and quality of training data. Herein, we release an open-source dataset of preprocessed MRI scans from 442 individuals with drug-refractory focal epilepsy who had neurosurgical resections, and detailed demographic information. The MRI scan data includes the preoperative 3D T1 and where available 3D FLAIR, as well as a manually inspected complete surface reconstruction and volumetric parcellations. Demographic information includes age, sex, age of onset of epilepsy, location of surgery, histopathology of resected specimen, occurrence and frequency of focal seizures with and without impairment of awareness, focal to bilateral tonic-clonic seizures, number of anti-seizure medications (ASMs) at time of surgery, and a total of 1764 patient years of post-surgical follow up. Crucially, we also include resection masks delineated from post-surgical imaging. To demonstrate the veracity of our data, we successfully replicated previous studies showing long-term outcomes of seizure freedom in the range of around 50%. Our imaging data replicates findings of group level atrophy in patients compared to controls. Resection locations in the cohort were predominantly in the temporal and frontal lobes. We envisage our dataset, shared openly with the community, will catalyse the development and application of computational methods in clinical neurology. Copyright © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

SATO: Straighten Any 3D Tubular Object

引用

IEEE Transactions on medical Imaging 2025年

作者： Zhou, Yanfeng Zhou, Jiaheng Wang, Zichen Yang, Ge Shenzhen University School of Artificial Intelligence Shenzhen 518060 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen 518060 China Medical UltraSound Image Computing Lab Shenzhen 518060 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing China Chinese Academy of Sciences Institute of Automation Beijing China

3D tubular objects have complex spatial shapes. Direct volume visualization cannot intuitively display their morphological characteristics and surface abnormalities. Straightening reformation is an effective visualization method for tubular objects. It uses a swept frame to sample cross sections along the centerline of the tubular object to generate straightening result. So far, however, current methods cannot visualize the full 3D view and fail to interface with downstream morphological analysis. Furthermore, current swept frames impose strict restrictions on the shape of tubular objects and are computationally expensive. In this study, we propose a novel swept frame based on vector rotation and construct an automatic straightening reformation pipeline. Our method is applicable to various tubular objects and can be efficiently executed recursively while ensuring that the straightening results have no rotation bias. Extensive experiments on eight different tubular objects and quantitative evaluation on various downstream applications demonstrate the effectiveness and universality of our straightening pipeline. © 1982-2012 IEEE.

关键词： curved planar reformation Straighten swept frame tubular object visualization

来源：评论

学校读者我要写书评

暂无评论

Multi-Modality Transrectal Ultrasound Video Classification for Identification of Clinically Significant Prostate Cancer

Multi-Modality Transrectal Ultrasound Video Classification f...

引用

IEEE International Symposium on Biomedical Imaging

作者： Hong Wu Juan Fu Hongsheng Ye Yuming Zhong Xuebin Zou Jianhua Zhou Yi Wang National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Shenzhen University Shenzhen China Smart Medical Imaging Learning and Engineering (SMILE) Lab Medical UltraSound Image Computing (MUSIC) Lab Shenzhen China The Department of Ultrasound State Key Laboratory of Oncology in South China Guangdong Provincial Clinical Research Center for Cancer Sun Yat-sen University Cancer Center Guangzhou China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Prostate cancer is the most common noncutaneous cancer in the world. Recently, multi-modality transrectal ultrasound (TRUS) has increasingly become an effective tool for the guidance of prostate biopsies. With the aim of effectively identifying prostate cancer, we propose a framework for the classification of clinically significant prostate cancer (csPCa) from multi-modality TRUS videos. The framework utilizes two 3D ResNet-50 models to extract features from B-mode images and shear wave elastography images, respectively. An adaptive spatial fusion module is introduced to aggregate two modalities’ features. An orthogonal regularized loss is further used to mitigate feature redundancy. The proposed framework is evaluated on an in-house dataset containing 512 TRUS videos, and achieves favorable performance in identifying csPCa with an area under curve (AUC) of 0.84. Furthermore, the visualized class activation mapping (CAM) images generated from the proposed framework may provide valuable guidance for the localization of csPCa, thus facilitating the TRUS-guided targeted biopsy. Our code is publicly available at https://***/2313595986/ProstateTRUS.

关键词： Location awareness Visualization Solid modeling Ultrasonic imaging Three-dimensional displays Biopsy Termination of employment

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Speaker Representation for Target Speaker Extraction

Multi-Level Speaker Representation for Target Speaker Extrac...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ke Zhang Junjie Li Shuai Wang Yangjie Wei Yi Wang Yannan Wang Haizhou Li Key Laboratory of Intelligent Computing in Medical Image Northeastern University China SDS SRIBD The Chinese University of Hong Kong Shenzhen China The Hong Kong Polytechnic University Hong Kong China Tencent Ethereal Audio Lab Tencent Shenzhen China Machine Listening Lab (MLL) University of Bremen Germany Department of Electrical and Computer Engineering National University of Singapore Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue. We generate a spectral-level representation from the enrollment magnitude spectrogram as a raw, low-level feature, which significantly improves the model’s generalization capability. Additionally, we propose a contextual embedding feature based on cross-attention mechanisms that integrate frame-level embeddings from a pre-trained speaker encoder. By incorporating speaker features across multiple levels, we significantly enhance the performance of the TSE model. Our approach achieves a 2.74 dB improvement and a 4.94% increase in extraction accuracy on Libri2mix test set over the baseline.

关键词： Accuracy Feature extraction Acoustics Speech processing Spectrogram Overfitting

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：