检索结果-内蒙古大学图书馆

Fusionmlp: A Mlp-Based Unified image Fusion Framework

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Liu, Shaolei Li, Shiman Qu, Linhao 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 China

Due to the powerful feature representation capacity, deep learning-based image fusion methods have improved the fusion results for better information integration. However, some inherent limitations in convolutional neural networks (CNN) and Transformer networks impede further performance improvement. Specifically, CNN-based methods have difficulties in mining global context information;Transformer-based methods are unable to adapt to different image sizes and the computational complexity grows exponentially with the image size. To overcome these problems, we propose the first MLP-based multi-scene image fusion framework, denoted as FusionMLP. In addition, we propose a novel loss function combining the spatial and frequency domain information for model training. Extensive experiments show that FusionMLP not only outperform SOTA multi-scene image fusion methods, but also outperform SOTA fusion algorithms for specific scenes. © 2024, The Authors. All rights reserved.

关键词： image fusion

Boosting Point-BERT by Multi-choice Tokens

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fu, Kexue Yuan, Mingzhi Wang, Manning Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai China

Masked language modeling (MLM) has become one of the most successful self-supervised pre-training task. Inspired by its success, Point-BERT, as a pioneer work in point cloud, proposed masked point modeling (MPM) to pre-train point transformer on large scale unanotated dataset. Despite its great performance, we find the inherent difference between language and point cloud tends to cause ambiguous tokenization for point cloud. For point cloud, there doesn’t exist a gold standard for point cloud tokenization. Point-BERT use a discrete Variational AutoEncoder (dVAE) as tokenizer, but it might generate different token ids for semantically-similar patches and generate the same token ids for semantically-dissimilar patches. To tackle above problem, we propose our McP-BERT, a pre-training framework with multi-choice tokens. Specifically, we ease the previous single-choice constraint on patch token ids in Point-BERT, and provide multi-choice token ids for each patch as supervision. Moreover, we utilitze the high-level semantics learned by transformer to further refine our supervision signals. Extensive experiments on point cloud classification, few-shot classification and part segmentation tasks demonstrate the superiority of our method, e.g., the pre-trained transformer achieves 94.1% accuracy on ModelNet40, 84.28% accuracy on the hardest setting of ScanObjectNN and new state-of-the-art performance on few-shot learning. We also demonstrate that our method not only improves the performance of Point-BERT on all downstream tasks, but also incurs almost no extra computational overhead. The code will be released in https://***/fukexue/McP-BERT. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset

TransMEF: A transformer-based multi-exposure image fusion framework using self-supervised multi-task learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qu, Linhao Liu, Shaolei 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 China

In this paper, we propose TransMEF, a transformer-based multi-exposure image fusion framework that uses self-supervised multi-task learning. The framework is based on an encoder-decoder network, which can be trained on large natural image datasets and does not require ground truth fusion images. We design three self-supervised reconstruction tasks according to the characteristics of multi-exposure images and conduct these tasks simultaneously using multi-task learning;through this process, the network can learn the characteristics of multi-exposure images and extract more generalized features. In addition, to compensate for the defect in establishing long-range dependencies in CNN-based architectures, we design an encoder that combines a CNN module with a transformer module. This combination enables the network to focus on both local and global information. We evaluated our method and compared it to 11 competitive traditional and deep learning-based methods on the latest released multi-exposure image fusion benchmark dataset, and our method achieved the best performance in both subjective and objective evaluations. Copyright © 2021, The Authors. All rights reserved.

关键词： image fusion

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

Reducing Domain Gap in Frequency and Spatial domain for Cross-modality Domain Adaptation on medical image Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

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

Unsupervised domain adaptation (UDA) aims to learn a model trained on source domain and performs well on unlabeled target domain. In medical image segmentation field, most existing UDA methods depend on adversarial learning to address the domain gap between different image modalities, which is ineffective due to its complicated training process. In this paper, we propose a simple yet effective UDA method based on frequency and spatial domain transfer under multi-teacher distillation framework. In the frequency domain, we first introduce non-subsampled contourlet transform for identifying domain-invariant and domain-variant frequency components (DIFs and DVFs), and then keep the DIFs unchanged while replacing the DVFs of the source domain images with that of the target domain images to narrow the domain gap. In the spatial domain, we propose a batch momentum update-based histogram matching strategy to reduce the domain-variant image style bias. Experiments on two cross-modality medical image segmentation datasets (cardiac, abdominal) show that our proposed method achieves superior performance compared to state-of-the-art methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

Rethinking Multiple Instance Learning: Developing an Instance-Level Classifier via Weakly-Supervised Self-Training

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Yingfan Luo, Xiaoyuan Yuan, Mingzhi Chen, Xinrong Wang, Manning The 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

Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective, both of which ignore important information contained in some instances and result in limited performance. For example, existing methods often face difficulty in learning hard positive instances. In this paper, we formulate MIL as a semi-supervised instance classification problem, so that all the labeled and unlabeled instances can be fully utilized to train a better classifier. The difficulty in this formulation is that all the labeled instances are negative in MIL, and traditional self-training techniques used in semi-supervised learning tend to degenerate in generating pseudo labels for the unlabeled instances in this scenario. To resolve this problem, we propose a weakly-supervised self-training method, in which we utilize the positive bag labels to construct a global constraint and a local constraint on the pseudo labels to prevent them from degenerating and force the classifier to learn hard positive instances. It is worth noting that easy positive instances are instances are far from the decision boundary in the classification process, while hard positive instances are those close to the decision boundary. Through iterative optimization, the pseudo labels can gradually approach the true labels. Extensive experiments on two MNIST synthetic datasets, five traditional MIL benchmark datasets and two histopathology whole slide image datasets show that our method achieved new SOTA performance on all of them. The code will be publicly available. Impact Statement-MIL is a primary research field within weakly supervised learning and has numerous applications, such as histopathology analysis, video anomaly detection, and drug design. However, current mainstream methods in MIL predominantly rely on bag labels to train the network, consequently overlooking the potential of instance-level supervision information. In our paper, we highlight the

关键词： Self-supervised learning

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

FANCL: Feature-Guided Attention Network with Curriculum Learning for Brain Metastases Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Zijiang Liu, Xiaoyu Qu, Linhao Shi, Yonghong 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

Accurate segmentation of brain metastases (BMs) in MR image is crucial for the diagnosis and followup of patients. Methods based on deep convolutional neural networks (CNNs) have achieved high segmentation performance. However, due to the loss of critical feature information caused by convolutional and pooling operations, CNNs still face great challenges in small BMs segmentation. Besides, BMs are irregular and easily confused with healthy tissues, which makes it difficult for the model to effectively learn tumor structure during training. To address these issues, this paper proposes a novel model called feature-guided attention network with curriculum learning (FANCL). Based on CNNs, FANCL utilizes the input image and its feature to establish the intrinsic connections between metastases of different sizes, which can effectively compensate for the loss of high-level feature from small tumors with the information of large tumors. Furthermore, FANCL applies the voxel-level curriculum learning strategy to help the model gradually learn the structure and details of BMs. And baseline models of varying depths are employed as curriculum-mining networks for organizing the curriculum progression. The evaluation results on the BraTS-METS 2023 dataset indicate that FANCL significantly improves the segmentation performance, confirming the effectiveness of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Curricula

Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Shiman Wang, Haoran Meng, Yucong Zhang, Chenxi 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

Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role in computer-aided diagnosis, surgical simulation, image-guided interventions, and especially in radiotherapy treatment planning. Thus, it is of great significance to explore automatic segmentation approaches, among which deep learning-based approaches have evolved rapidly and witnessed remarkable progress in multi-organ segmentation. However, obtaining an appropriately sized and fine-grained annotated dataset of multiple organs is extremely hard and expensive. Such scarce annotation limits the development of high-performance multi-organ segmentation models but promotes many annotation-efficient learning paradigms. Among these, studies on transfer learning leveraging external datasets, semi-supervised learning using unannotated datasets and partially-supervised learning integrating partially-labeled datasets have led the dominant way to break such dilemma in multi-organ segmentation. We first review the traditional fully supervised method, then present a comprehensive and systematic elaboration of the 3 abovementioned learning paradigms in the context of multi-organ segmentation from both technical and methodological perspectives, and finally summarize their challenges and future trends. Copyright © 2023, The Authors. All rights reserved.

关键词： computer aided diagnosis