检索结果-内蒙古大学图书馆

POS-BERT: Point Cloud One-Stage BERT Pre-Training

学校读者我要写书评

暂无评论

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

Ventricular Wave Feature Extraction of ECG Signal based on Synthesized Algorithm

学校读者我要写书评

暂无评论

Ventricular Wave Feature Extraction of ECG Signal based on S...

2015 Global Conference on Biological Engineering and Biomedical(CBEB 2015)

作者： Wang Cong Wu Xiaomei Department of Electric Engineering School of InformationFudan University Digital Medical Research Center of Fudan University Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention

Electrocardiogram(ECG) is a record of the electrical activity of the heart. Using computer to extract feature points of ventricular wave of ECG automatically is of great significance, for it can indicate plenty of heart diseases. In this paper,a synthesized algorithm is proposed to analyse ventricular wave of ECG. After multiresolution wavelet decomposition,QRS complex and T wave are reconstructed with different coefficients based on the spectrum characteristics of different portion of ECG. Self-adaptive threshold is applied in peak detection. Maximum and minimum modulus is used to obtain QRS onset and offset. Area integration is adopted to acquire T offset. This synthesized algorithm achieves a preferable detection result in QT database of Physionet with higher accuracy and precision, which will lay a better foundation for analysis and prediction of ventricular heart diseases.

关键词： ventricular wave of ECG signal analysis,feature extraction,synthesized algorithm

Histological grade and type classification of glioma using Magnetic Resonance imaging

学校读者我要写书评

暂无评论

Histological grade and type classification of glioma using M...

International Congress on Image and Signal Processing, Biomedical Engineering and Informatics (CISP-BMEI)

作者： Yuan Gao Zhifeng Shi Yuanyuan Wang Jinhua Yu Liang Chen Yi Guo Qi Zhang Ying Mao Department of Electronic Engineering Fudan University Shanghai China Department of Neurosurgery Fudan University Shanghai China Key laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China School of Communication and Information Engineering Shanghai University Shanghai China

ISBN: (纸本)9781509037117

Glioma is one of the most common brain tumors with high mortality and its histological grading and typing is important both in therapeutic decision and prognosis evaluation. This paper aims at using the high-throughput image feature analysis method to estimate the histological grade and type of a patient by using Magnetic Resonance imaging (MRI) instead of histological examination. The proposed method consists of the initial label definition, the region-of-interest delineation, the self-adaptive feature extraction, the feature subset selection, and the multi-class voting classification. Hereinto, a novel feature extraction strategy is designed, which could avoid the MRI scan diversity so as to get the robust feature extraction result and make the proposed framework more stable and effective. This method was validated on a database of 124 patients with the grade II to IV of 78, 25, and 21, and with astrocytoma, oligodendroglioma, oligoastrocytoma of 86, 16, and 22, respectively. We show that by using the leave-one-out cross-validation, the multi-class classification accuracy and macro average could reach 88.71%, 0.8362 respectively for the grade classification, and 70.97%, 0.5692 respectively for the type classification. It can be concluded that the histological grade and subtype information could be estimated from the MRI image analysis.

关键词： Feature extraction Magnetic resonance imaging Tumors Support vector machines Optimization Hospitals Image segmentation

Multi-label inductive matrix completion for joint MGMT and IDH1 status prediction for glioma patients 1

学校读者我要写书评

暂无评论

20th International Conference on medical Image computing and computer-assisted intervention, MICCAI 2017

作者： Chen, Lei Zhang, Han Thung, Kim-Han Liu, Luyan Lu, Junfeng Wu, Jinsong Wang, Qian Shen, Dinggang Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China Department of Radiology and BRIC University of North Carolina Chapel Hill United States School of Biomedical Engineering Med-X Research Institute Shanghai Jiao Tong University Shanghai China Department of Neurosurgery Huashan Hospital Fudan University Shanghai China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Shanghai China

ISBN: (数字)9783319661858

ISBN: (纸本)9783319661841

MGMT promoter methylation and IDH1 mutation in high-grade gliomas (HGG) have proven to be the two important molecular indicators associated with better prognosis. Traditionally, the statuses of MGMT and IDH1 are obtained via surgical biopsy, which is laborious, invasive and time-consuming. Accurate presurgical prediction of their statuses based on preoperative imaging data is of great clinical value towards better treatment plan. In this paper, we propose a novel Multi-label Inductive Matrix Completion (MIMC) model, highlighted by the online inductive learning strategy, to jointly predict both MGMT and IDH1 statuses. Our MIMC model not only uses the training subjects with possibly missing MGMT/IDH1 labels, but also leverages the unlabeled testing subjects as a supplement to the limited training dataset. More importantly, we learn inductive labels, instead of directly using transductive labels, as the prediction results for the testing subjects, to alleviate the overfitting issue in small-sample-size studies. Furthermore, we design an optimization algorithm with guaranteed convergence based on the block coordinate descent method to solve the multivariate non-smooth MIMC model. Finally, by using a precious single-center multi-modality presurgical brain imaging and genetic dataset of primary HGG, we demonstrate that our method can produce accurate prediction results, outperforming the previous widely-used single- or multi-task machine learning methods. This study shows the promise of utilizing imaging-derived brain connectome phenotypes for prognosis of HGG in a non-invasive manner. © Springer International Publishing AG 2017.

关键词： Forecasting

MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Zhiwei Meng, Yucong Fu, Kexue Wang, Shuo Song, Zhijian Academy for Engineering and Technology Fudan University Shanghai200433 China Digital Medical Research Center School of Basic Medical Sciences Fudan University Shanghai200032 China Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention Shanghai200032 China China

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically uses Class Activation Maps (CAM) to achieve dense predictions. Recently, Vision Transformer (ViT) has provided an alternative to generate localization maps from class-patch attention. However, due to insufficient constraints on modeling such attention, we observe that the Localization Attention Maps (LAM) often struggle with the artifact issue, i.e., patch regions with minimal semantic relevance are falsely activated by class tokens. In this work, we propose MoRe to address this issue and further explore the potential of LAM. Our findings suggest that imposing additional regularization on class-patch attention is necessary. To this end, we first view the attention as a novel directed graph and propose the Graph Category Representation module to implicitly regularize the interaction among class-patch entities. It ensures that class tokens dynamically condense the related patch information and suppress unrelated artifacts at a graph level. Second, motivated by the observation that CAM from classification weights maintains smooth localization of objects, we devise the Localization-informed Regularization module to explicitly regularize the class-patch attention. It directly mines the token relations from CAM and further supervises the consistency between class and patch tokens in a learnable manner. Extensive experiments are conducted on PASCAL VOC and MS COCO, validating that MoRe effectively addresses the artifact issue and achieves state-of-the-art performance, surpassing recent single-stage and even multi-stage methods. Code is available at https://***/zwyang6/MoRe. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Rethinking Multi-Exposure Image Fusion with Extreme and Diverse Exposure Levels: A Robust Framework Based on Fourier Transform and Contrastive Learning

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Qu, Linhao Liu, Shaolei Wang, Manning Song, Zhijian Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China

Multi-exposure image fusion (MEF) is an important technique for generating high dynamic range images. However, most existing MEF studies focus on fusing a moderately over-exposed image and a moderately under-exposed image, and they are not robust in fusing images with extreme and diverse exposure levels. In this paper, we propose a robust MEF framework based on Fourier transform and contrastive learning. Specifically, we develop a Fourier transform-based pixel intensity transfer strategy to synthesize images with diverse exposure levels from normally exposed natural images and train an encoder-decoder network to reconstruct the original natural image. In this way, the encoder and decoder can learn to extract features from images with diverse exposure levels and generate fused images with normal exposure. We propose a contrastive regularization loss to further enhance the capability of the network in recovering normal exposure levels. In addition, we construct an extreme MEF benchmark dataset and a random MEF benchmark dataset for a more comprehensive evaluation of MEF algorithms. We extensively compare our method with nine competitive traditional and deep learning-based MEF algorithms on three benchmark datasets, and our method outperforms the other methods in both subjective visual effects and objective evaluation metrics. Our code, datasets and all fused images will be released. © 2022, The Authors. All rights reserved.

关键词： Fourier transforms

DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qu, Linhao Luo, Xiaoyuan Liu, Shaolei Wang, Manning Song, Zhijian Digital Medical Research Center School of Basic Medical Science Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Fudan University Shanghai200032 China

Multiple Instance Learning (MIL) is widely used in analyzing histopathological Whole Slide Images (WSIs). However, existing MIL methods do not explicitly model the data distribution, and instead they only learn a bag-level or instance-level decision boundary discriminatively by training a classifier. In this paper, we propose DGMIL: a feature distribution guided deep MIL framework for WSI classification and positive patch localization. Instead of designing complex discriminative network architectures, we reveal that the inherent feature distribution of histopathological image data can serve as a very effective guide for instance classification. We propose a cluster-conditioned feature distribution modeling method and a pseudo label-based iterative feature space refinement strategy so that in the final feature space the positive and negative instances can be easily separated. Experiments on the CAMELYON16 dataset and the TCGA Lung Cancer dataset show that our method achieves new SOTA for both global classification and positive patch localization tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

TransFuse: A Unified Transformer-based Image Fusion Framework using Self-supervised Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qu, Linhao Liu, Shaolei Wang, Manning Li, Shiman Yin, Siqi Qiao, Qin Song, Zhijian Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China

Image fusion is a technique to integrate information from multiple source images with complementary information to improve the richness of a single image. Due to insufficient task-specific training data and corresponding ground truth, most existing end-to-end image fusion methods easily fall into overfitting or tedious parameter optimization processes. Two-stage methods avoid the need of large amount of task-specific training data by training encoder-decoder network on large natural image datasets and utilizing the extracted features for fusion, but the domain gap between natural images and different fusion tasks results in limited performance. In this study, we design a novel encoder-decoder based image fusion framework and propose a destruction-reconstruction based self-supervised training scheme to encourage the network to learn task-specific features. Specifically, we propose three destruction-reconstruction self-supervised auxiliary tasks for multi-modal image fusion, multi-exposure image fusion and multi-focus image fusion based on pixel intensity non-linear transformation, brightness transformation and noise transformation, respectively. In order to encourage different fusion tasks to promote each other and increase the generalizability of the trained network, we integrate the three self-supervised auxiliary tasks by randomly choosing one of them to destroy a natural image in model training. In addition, we design a new encoder that combines CNN and Transformer for feature extraction, so that the trained model can exploit both local and global information. Extensive experiments on multi-modal image fusion, multi-exposure image fusion and multi-focus image fusion tasks demonstrate that our proposed method achieves the state-of-the-art performance in both subjective and objective evaluations. The code will be publicly available soon. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

Quantitative assessment of synchronization during atrial fibrillation based on a novel index

学校读者我要写书评

暂无评论

Quantitative assessment of synchronization during atrial fib...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Lin Zhang Cuiwei Yang Zhenning Nie Department of Electronic Engineering Fudan University Department of Electronic Engineering Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention (MICCAI) of Shanghai Fudan University Department of Cardiology Zhonghan Hospital Fudan University

ISBN: (纸本)9781424479276

Atrial Fibrillation (AF), a chaotic rhythm classically considered with random electrical activity, is now demonstrated to show a certain degree of organization and synchronization. Rather than those traditional indices which always focus on the pairwise properties of adjacent signals, a new synchronization index-S estimator-is introduced in this paper to quantify the synchronization level for all the signals in a selected area. By evaluating a complement of the entropy of the normalized eigenvalues of the corresponding correlation matrix, S estimator is designed to be proportional to the amount of synchronization. 400 episodes of 64-channel epicardial signals acquired from four living mongrels were studied under normal sinus rhythm (SN) and AF. The results showed that there were significant decreases of S estimator for both anterior left atrium and anterior right atrium with the rhythm changing from SN to AF. After dividing the research area into eight subparts, S estimator is also capable to demonstrate the different synchronization level for each subpart and revealed the electrophysiology individual difference among four experimental subjects. In conclusion, S estimator succeeds in estimating the synchronization degree for multi-channel signals in a selected area, with no limits to the number of the signals to be analyzed. It can help us to distinguish the region with a high synchronization level during AF, which would be helpful to the clinical AF treatment and enhance our understanding of underlying mechanisms of AF.

关键词： Synchronization Tin Atrial fibrillation Electrodes Rhythm Entropy Correlation