检索结果-内蒙古大学图书馆

Diffusion Model with Self-supervised Training for Subject-aware Photoplethysmography Recovery

学校读者我要写书评

暂无评论

Diffusion Model with Self-supervised Training for Subject-aw...

IEEE Biomedical Circuits and Systems (BIOCAS)

作者： Daomiao Wang Qihan Hu Xujian Feng Cuiwei Yang Center for Biomedical Engineering School of Information Science and Technology Fudan University Shanghai China Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China

Photoplethysmography (PPG) has emerged as a promising technology for wearable personal healthcare due to its non-invasive and cost-effective nature. However, owing to the vulnerability to various noise, the useful PPG signals are few and the usability of PPG-based systems are limited. In this paper, we address the challenge of recovering extremely corrupted PPG waveforms with severe distortions, which lead to missing data. Specifically, we propose a novel diffusion-based framework that incorporates remaining values and subject-aware embedding, along with a self-supervised generative training strategy. Extensive experiments were performed on two datasets under three missing rates and two missing patterns. Our proposed model achieves significant improvements of nearly 100% over existing imputation models on quantitative metrics, and together with the visualization, demonstrating its effectiveness for data distribution generation and corrupted PPG restoration. Our proposed method also provides a new perspective for PPG denoising.

关键词：

WaveFuse: A unified unsupervised framework for image fusion with discrete wavelet transform

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Shaolei Wang, Manning Song, Zhijian Digital Medical Research Center School of Basic Medical Science Fudan University China Shanghai Key Laboratory of Medical Image Computing and Computer Assited Intervention

We propose an unsupervised image fusion architecture for multiple application scenarios based on the combination of multi-scale discrete wavelet transform through regional energy and deep learning. To our best knowledge, this is the first time that a conventional frequency method has been combined with deep learning for feature maps fusion. The useful information of feature maps can be utilized adequately through multi-scale discrete wavelet transform in our proposed method. Compared with other state-of-the-art fusion methods, the proposed algorithm exhibits better fusion performance in both subjective and objective evaluation. Moreover, it's worth mentioning that comparable fusion performance trained in COCO dataset can be obtained by training with a much smaller dataset with only hundreds of images chosen randomly from COCO. Hence, the training time is shortened substantially, leading to the improvement of the model's performance both in practicality and training efficiency. Copyright © 2020, The Authors. All rights reserved.

关键词： image fusion

PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yuan, Mingzhi Fu, Kexue Li, Zhihao Meng, Yucong Wang, Manning Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention China Shandong Computer Science Center National Supercomputer Center Jinan China

Point cloud registration is a task to estimate the rigid transformation between two unaligned scans, which plays an important role in many computer vision applications. Previous learning-based works commonly focus on supervised registration, which have limitations in practice. Recently, with the advance of inexpensive RGB-D sensors, several learning-based works utilize RGB-D data to achieve unsupervised registration. However, most of existing unsupervised methods follow a cascaded design or fuse RGB-D data in a unidirectional manner, which do not fully exploit the complementary information in the RGB-D data. To leverage the complementary information more effectively, we propose a network implementing multi-scale bidirectional fusion between RGB images and point clouds generated from depth images. By bidirectionally fusing visual and geometric features in multi-scales, more distinctive deep features for correspondence estimation can be obtained, making our registration more accurate. Extensive experiments on ScanNet and 3DMatch demonstrate that our method achieves new state-of-the-art performance. Code will be released at https://***/phdymz/PointMBF. Copyright © 2023, The Authors. All rights reserved.

关键词： Surface measurement

Continuous K-space Recovery Network with image Guidance for Fast MRI Reconstruction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Meng, Yucong Yang, Zhiwei Duan, Minghong Shi, Yonghong Song, Zhijian Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China The Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China Academy of Engineering and Technology Fudan University Shanghai200433 China

Magnetic resonance imaging (MRI) is a crucial tool for clinical diagnosis while facing the challenge of long scanning time. To reduce the acquisition time, fast MRI reconstruction aims to restore high-quality MRI images from the undersampled k-space. Existing methods typically train deep learning models to map the undersampled data to artifact-free MRI images. However, these studies often overlook the unique properties of k-space and directly apply general networks designed for image processing to k-space recovery, leaving the precise learning of k-space largely underexplored. In this work, we propose a continuous k-space recovery network from a new perspective of implicit neural representation with image domain guidance, which boosts the performance of MRI reconstruction. Specifically, (1) an implicit neural representation based encoder-decoder structure is customized to continuously query unsampled k-values. (2) an image guidance module is designed to mine the image-domain information from the low-quality MRI images to further guide the k-space recovery. (3) a multi-stage training strategy is proposed to recover dense k-space progressively. Extensive experiments conducted on CC359, fastMRI, IXI, and SKM-TEA datasets demonstrate the effectiveness of our method and its superiority over other competitors. Implementation code will be available in https://***/XiaoMengLiLiLi/IGKR. Copyright © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

An efficient dual-branch framework via implicit self-texture enhancement for arbitrary-scale histopathology image super-resolution

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Duan, Minghong Qu, Linhao Yang, Zhiwei Wang, Manning Zhang, Chenxi Song, Zhijian Digital Medical Research Center School of Basic Medical Sciences Fudan University Shanghai200032 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China Academy for Engineering and Technology Fudan University Shanghai200433 China

High-quality whole-slide scanning is expensive, complex, and time-consuming, thus limiting the acquisition and utilization of high-resolution histopathology images in daily clinical work. Deep learning-based single-image superresolution (SISR) techniques provide an effective way to solve this problem. However, the existing SISR models applied in histopathology images can only work in fixed integer scaling factors, decreasing their applicability. Though methods based on implicit neural representation (INR) have shown promising results in arbitrary-scale super-resolution (SR) of natural images, applying them directly to histopathology images is inadequate because they have unique fine-grained image textures different from natural images. Thus, we propose an Implicit Self-Texture Enhancement-based dual-branch framework (ISTE) for arbitrary-scale SR of histopathology images to address this challenge. The proposed ISTE contains a feature aggregation branch and a texture learning branch. We employ the feature aggregation branch to enhance the learning of the local details for SR images while utilizing the texture learning branch to enhance the learning of high-frequency texture details. Then, we design a two-stage texture enhancement strategy to fuse the features from the two branches to obtain the SR images. Experiments on publicly available datasets, including TMA, HistoSR, and the TCGA lung cancer datasets, demonstrate that ISTE outperforms existing fixed-scale and arbitrary-scale SR algorithms across various scaling factors. Additionally, extensive experiments have shown that the histopathology images reconstructed by the proposed ISTE are applicable to downstream pathology image analysis tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： image texture

Pos-Bert: Point Cloud One-Stage Bert Pre-Training

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Fu, Kexue Gao, Peng Liu, Shaolei Wang, Manning Digital Medical Research Center School of Basic Medical Science Fudan University China Shandong Computer Science Center China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China Shanghai AILab China

Recently, the pre-training paradigm combining Transformer and masked language modeling in BERT has achieved tremendous success not only in NLP, but also in images and point clouds. However, directly extending BERT from NLP to point clouds requires first training a discrete Variational AutoEncoder (dVAE) as the tokenizer, which results in a complex two-stage process, as in 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 masked patch modeling (MPM) task to perform point cloud pre-training, which aims to recover masked patch information under the supervision of a tokenizer's output. Unlike Point-BERT, whose tokenizer is extra-trained and frozen, we propose a momentum tokenizer which is dynamically updated during training the Transformer. Furthermore, in order to better learn high-level semantic representation, we integrate contrastive learning into the proposed framework to maximize the class token consistency between augmented point cloud pairs. Experiments show that POS-BERT achieves the state-of-the-art performance on linear SVM classification of ModelNet40 with fixed feature extractors, and it exceeds Point-BERT by 3.5%. In addition, POS-BERT has significantly improved many downstream tasks, including fine-tuned classification, few-shot classification and part segmentation. The code and the trained model will be released soon. © 2023, The Authors. All rights reserved.

关键词： Natural language processing systems

PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yuan, Mingzhi Li, Zhihao Jin, Qiuye Chen, Xinrong Wang, Manning Digital Medical Research Center School of Basic Medical Sciences Fudan University Shanghai200032 China Academy for Engineering and Technology Fudan University Shanghai200032 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China

Multi-instance point cloud registration is the problem of estimating multiple poses of source point cloud instances within a target point cloud. Solving this problem is challenging since inlier correspondences of one instance constitute outliers of all the other instances. Existing methods often rely on time-consuming hypothesis sampling or features leveraging spatial consistency, resulting in limited performance. In this paper, we propose PointCLM, a contrastive learning-based framework for mutli-instance point cloud registration. We first utilize contrastive learning to learn well-distributed deep representations for the input putative correspondences. Then based on these representations, we propose a outlier pruning strategy and a clustering strategy to efficiently remove outliers and assign the remaining correspondences to correct instances. Our method outperforms the state-of-the-art methods on both synthetic and real datasets by a large margin. The code will be made publicly available at http://***/phdymz/PointCLM. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset

A Fast Global Maximum Searching Strategy in Electromagnetic Tracking

学校读者我要写书评

暂无评论

A Fast Global Maximum Searching Strategy in Electromagnetic ...

2015 World Conference on Control, Electronics and Electrical Engineering(WCEE 2015)

作者： Yifeng Wang Xiaomei Wu Jianguo Yu Department of Electronic Engineering Fudan University Digital Medical Research Center of Fudan University Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention (MICCAI)

In a rotating coil based magnetic tracking system,so long as the rotating coil has seized the direction of the magnetic sensor,geometric algorithm can compute the position and orientation of the target object without tedious iterative ***,the rotation process of the coil is still time *** the coil will be rotated in a plane,the measured magnetic field density should change as a sine/cosine-like *** on this,we proposes a searching strategy in which field densities are measured along four sparse even spaced directions to lock an initial searching range,and then the searching range is continuously halved around the measured maximum field density until a required tracking precision is *** results show that the geometric tracking algorithm with this global searching strategy can track the target object with higher efficiency and higher precision than the algorithm without this searching ***,in the condition of low field noises,the optimized non-iterative algorithm with global searching strategy has better precision than the traditional iterative algorithms as well.

关键词： adaptive algorithm,binary search,global optimization,local optimization,magnetic tracking,non-iterative algorithm.

Segmentation of arteriovenous malformations nidus and vessel in digital subtraction angiography images based on an iterative thresholding method

学校读者我要写书评

暂无评论

Segmentation of arteriovenous malformations nidus and vessel...

International Conference on Biomedical Engineering and Informatics (BMEI)

作者： Yuxi Lian Yuanyuan Wang Jinhua Yu Yi Guo Liang Chen Department of Electronic Engineering Fudan University Shanghai China Key laboratory of Medical Imaging Computing and-Computer Assisted Intervention of Shanghai China Department of Neurosurgery Fudan University Shanghai China

Digital subtraction angiography (DSA) plays an important role in the diagnosis and therapy of vascular diseases. Segmentation of nidus and vessel in DSA images is an essential step in the diagnosis of arteriovenous malformations (AVM). In this paper, a novel segmentation method based on the global and iterative local thresholding is proposed to segment the nidus and vessel in DSA images. Firstly, the original image is divided into proper subimages. For each subimage, Ostu's method is primarily used and pixels are classified into two groups by the threshold. Then, according to the variance of the subimage intensities, the mean or median values of two groups are calculated to sort the pixels into three classes. These three classes represent the dark AVM and vessel, the bright background and undetermined regions in the original DSA image. The first two classes are determined directly and will not be processed further. The undetermined regions are processed in the next iteration to segment tiny vessels until the thresholds between two iterations are less than a preset one. Finally, all classes are combined to create the segmentation result. We test this method on DSA images of the AVM. Experimental results show that the proposed method performs better than the other state-of-the-art methods in the segmentation of DSA images. The proposed method can identify fine and tiny vessel structures, as well as distinguish large AVM nidus in one framework.

关键词： image segmentation Iterative methods Angiography Diseases Blood vessels Hospitals