检索结果-内蒙古大学图书馆

Promptable Representation Distribution Learning and Data Augmentation for Gigapixel Histopathology WSI Analysis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Kunming Jiang, Zhiguo Shi, Jun Wang, Wei Wu, Haibo Zheng, Yushan Beijing Advanced Innovation Center on Biomedical Engineering School of Engineering Medicine Beihang University China Image Processing Center School of Astronautics Beihang University China Tianmushan Laboratory China School of Software Hefei University of Technology China Department of Pathology The First Affiliated Hospital of USTC China Intelligent Pathology Institute Division of Life Sciences and Medicine University of Science and Technology of China China

Gigapixel image analysis, particularly for whole slide images (WSIs), often relies on multiple instance learning (MIL). Under the paradigm of MIL, patch image representations are extracted and then fixed during the training of the MIL classifiers for efficiency consideration. However, the invariance of representations makes it difficult to perform data augmentation for WSI-level model training, which significantly limits the performance of the downstream WSI analysis. The current data augmentation methods for gigapixel images either introduce additional computational costs or result in a loss of semantic information, which is hard to meet the requirements for efficiency and stability needed for WSI model training. In this paper, we propose a Promptable Representation Distribution Learning framework (PRDL) for both patch-level representation learning and WSI-level data augmentation. Meanwhile, we explore the use of prompts to guide data augmentation in feature space, which achieves promptable data augmentation for training robust WSI-level models. The experimental results have demonstrated that the proposed method stably outperforms state-of-the-art methods. © 2024, CC BY.

关键词： WSI circuits

A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Yandi Gao, Haobo Gao, Yunxuan Guo, Jianxiong Wu, Weili Department of Computer Science BNU-HKBU United International College China Advanced Institute of Natural Sciences Beijing Normal University China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College China Department of Computer Science The University of Texas Dallas United States

Influence Maximization (IM) is a classical combinatorial optimization problem, which can be widely used in mobile networks, social computing, and recommendation systems. It aims at selecting a small number of users such that maximizing the influence spread across the online social network. Because of its potential commercial and academic value, there are a lot of researchers focusing on studying the IM problem from different perspectives. The main challenge comes from the NP-hardness of the IM problem and #P-hardness of estimating the influence spread, thus traditional algorithms for overcoming them can be categorized into two classes: heuristic algorithms and approximation algorithms. However, there is no theoretical guarantee for heuristic algorithms, and the theoretical design is close to the limit. Therefore, it is almost impossible to further optimize and improve their performance. With the rapid development of artificial intelligence, the technology based on Machine Learning (ML) has achieved remarkable achievements in many fields. In view of this, in recent years, a number of new methods have emerged to solve combinatorial optimization problems by using ML-based techniques. These methods have the advantages of fast solving speed and strong generalization ability to unknown graphs, which provide a brand-new direction for solving combinatorial optimization problems. Therefore, we abandon the traditional algorithms based on iterative search and review the recent development of ML-based methods, especially Deep Reinforcement Learning, to solve the IM problem and other variants in social networks. We focus on summarizing the relevant background knowledge, basic principles, common methods, and applied research. Finally, the challenges that need to be solved urgently in future IM research are pointed out. Copyright © 2022, The Authors. All rights reserved.

关键词： Combinatorial optimization

Optimizing Empirical and Hybrid Modeling for Advanced Canopy Chlorophyll and Nitrogen Retrieval Technique Using EnMAP Data

学校读者我要写书评

暂无评论

Environmental Challenges 2025年 18卷

作者： Alam, Mir Md Tasnim Simic Milas, Anita Verrelst, Jochem Tian, Qing Kripal, Alia Soleil Osei, Henry Poku Rahman, Md Atiqur School of Earth Environment and Society Bowling Green State University 190 Overman Hall Bowling Green OH United States Image Processing Laboratory (IPL) Parc Científic Universitat de València València Paterna 46980 Spain Department of Computer Science University of Alabama at Birmingham 1402 10th Avenue South Birmingham AL United States

This study evaluates empirical and hybrid physical models for estimating canopy chlorophyll content (CCC) and canopy nitrogen content (CNC) using hyperspectral imagery from the Environmental Mapping and Analysis Program (EnMAP) over Michigan's Kellogg Biological Station in summer 2023. In the empirical approach, six machine learning regression algorithms (MLRAs) have been evaluated. In the hybrid modeling approach, each MLRA was combined with the PROSAIL radiative transfer model. Results show the empirical model outperforms the hybrid model for CNC retrieval, while both perform similarly for CCC. In the empirical approach, KRR demonstrated the best performance among MLRAs for both CCC (RMSE = 0.10 g/m², NRMSE = 9.76 %, R² = 0.93) and CNC (RMSE = 0.10 g/m², NRMSE = 8.13 %, R² = 0.94). In the hybrid modeling, GPR performed best for CCC (RMSE = 0.10 g/m², NRMSE = 9.43 %, R² = 0.93), while KRR remained the top performer for CNC (RMSE = 0.17 g/m², NRMSE = 13.67 %, R² = 0.83). Furthermore, the findings indicate that the hybrid model exhibits greater sensitivity in heterogeneous areas where field data are limited, while both approaches effectively distinguish between organic and non-organic treatments. The nitrogen conversion factor refined from 4.43 to 3.03 for corn in this study significantly improves the accuracy of the estimated CNC. This enhancement provides further evidence of the efficacy of EnMAP imagery in estimating biochemical parameters and its potential application in Precision Agriculture. © 2025 The Author(s)

关键词： Canopy chlorophyll Canopy nitrogen ENMAP Hybrid radiative transfer model Hyperspectral imagery Machine learning

Learn2Synth: Learning Optimal Data Synthesis using Hypergradients for Brain image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Xiaoling Zeng, Xiangrui Puonti, Oula Iglesias, Juan Eugenio Fischl, Bruce Balbastre, Yaël Massachusetts General Hospital Harvard Medical School United States Danish Research Centre for Magnetic Resonance Copenhagen University Hospital Denmark Centre for Medical Image Computing University College London United Kingdom Computer Science and AI Laboratory Massachusetts Institute of Technology United States Department of Experimental Psychology University College London United Kingdom

Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts during training, thereby minimizing overfitting to appearance and maximizing generalization to unseen data. Although powerful, this approach relies on the accurate tuning of a large set of hyperparameters that govern the probabilistic distribution of the synthesized images. Instead of manually tuning these parameters, we introduce Learn2Synth, a novel procedure in which synthesis parameters are learned using a small set of real labeled data. Unlike methods that impose constraints to align synthetic data with real data (e.g., contrastive or adversarial techniques), which risk misaligning the image and its label map, we tune an augmentation engine such that a segmentation network trained on synthetic data has optimal accuracy when applied to real data. This approach allows the training procedure to benefit from real labeled examples, without ever using these real examples to train the segmentation network, which avoids biasing the network towards the properties of the training set. Specifically, we develop parametric and nonparametric strategies to enhance synthetic images in a way that improves the performance of the segmentation network. We demonstrate the effectiveness of this learning strategy on synthetic and real-world brain scans. Code is available at: https://***/HuXiaoling/ Learn2Synth. © 2024, CC BY-NC-ND.

关键词： image segmentation

Towards Disease-Aware Self-Supervised Dynamic Brain Network Learning For Mental Diagnosis

学校读者我要写书评

暂无评论

Towards Disease-Aware Self-Supervised Dynamic Brain Network ...

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

作者： Zhiyong Jin Guangqi Wen Peng Cao Lingwen Liu Jinzhu Yang Xinrong Zhu Osmar R. Zaiane Fei Wang Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University Shenyang China Department of Psychiatry Affiliated Nanjing Brain Hospital Early Intervention Unit Nanjing Medical University Nanjing China Alberta Machine Intelligence Institute University of Alberta Edmonton Alberta Canada

The dynamic brain network learning methods ignored the separation of redundant disease-irrelevant information, resulting in the model only achieving suboptimal diagnosis results. Meanwhile, the supervised learning scheme inevitably suffers from poor generalization due to the limited data. To address these problems, we propose a Self-supervised Dynamic Brain network Disentangled representation learning framework named SDBD, which incorporates 1) a dynamic topology-aware encoder for capturing diverse topological information, 2) a cross decoder for reconstructing the graph structure and 3) a spatio-temporal learning model based on the multi-head self-attention mechanism for classification. To disentangle the disease-related information from the dynamic brain networks, we design a temporal contrastive loss and a structure reconstruction loss. We evaluate our model on three real-world mental diseases: Autism Spectrum Disorder (ASD), Major Depressive Disorder (MDD), and Bipolar Disorder (BD). The results indicate significant improvements in our SDBD over the state-of-the-art methods owing to the disentangled disease-related information. Moreover, our method can identify the biomarkers associated with the diseases, which is consistent with the previous studies. To the best of our knowledge, our work is the first attempt to disentangle the disease-related information for the dynamic brain network analysis. The code is available at https://***/IntelliDAL/Graph/tree/main/SDBD.

关键词：

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bir...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zijian Zhu Yichi Zhang Hai Chen Yinpeng Dong Shu Zhao Wenbo Ding Jiachen Zhong Shibao Zheng Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Dept. of Comp. Sci. and Tech. THBI Lab Institute for AI Tsinghua University BNRist Center Zhongguancun Laboratory Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University SAIC Motor AI Lab

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

关键词：

SPP-CNN: An Efficient Framework for Network Robustness Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Chengpei Lou, Yang Wang, Lin Li, Junli Li, Xiang Chen, Guanrong The College of Computer Science Sichuan Normal University Chengdu610066 China The Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China The Department of Computer Science National Yang Ming Chiao Tung University Hsinchu300 Taiwan The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201210 China The Department of Control Science and Engineering Tongji University Shanghai200240 China The Department of Electrical Engineering City University of Hong Kong Hong Kong

This paper addresses the robustness of a network to sustain its connectivity and controllability against malicious attacks. This kind of network robustness is typically measured by the time-consuming attack simulation, which returns a sequence of values that record the remaining connectivity and controllability after a sequence of node- or edge-removal attacks. For improvement, this paper develops an efficient framework for network robustness prediction, the spatial pyramid pooling convolutional neural network (SPP-CNN). The new framework installs a spatial pyramid pooling layer between the convolutional and fully-connected layers, overcoming the common mismatch issue in the CNN-based prediction approaches and extending its generalizability. Extensive experiments are carried out by comparing SPP-CNN with three state-of-the-art robustness predictors, namely a CNN-based and two graph neural networks-based frameworks. Synthetic and real-world networks, both directed and undirected, are investigated. Experimental results demonstrate that the proposed SPP-CNN achieves better prediction performances and better generalizability to unknown datasets, with significantly lower time-consumption, than its counterparts. © 2023, CC BY.

关键词： Complex networks

Detection of White Matter Hyperintensities in Magnetic Resonance Imaging by Hyperspectral Subpixel Detection

学校读者我要写书评

暂无评论

IEEE Access 2024年 12卷 111992-112007页

作者： Yung-Chieh Chang Chein-I Chang Yen-Chieh Ouyang Jyh-Wen Chai Wen-Hsien Chen Kuan-Jung Pan Hsin-Che Wang Clayton Chi-Chang Chen Department of Electrical Engineering National Chung Hsing University Taichung Taiwan Department of Radiology Taichung Veterans General Hospital Taichung Taiwan Department of Medical Imaging and Radiological Sciences Central Taiwan University of Science and Technology Taichung Taiwan Department of Computer Science and Electrical Engineering Remote Sensing Signal and Image Processing Laboratory University of Maryland Baltimore County Baltimore MD USA Department of Electrical Engineering National Cheng Kung University Tainan Taiwan Department of Post-Baccalaureate Medicine College of Medicine National Chung Hsing University Taichung Taiwan College of Medicine China Medical University Taichung Taiwan Department of Industrial Engineering and Enterprise Information Tunghai University Taichung Taiwan Department of Medical Research Center for Quantitative Imaging in Medicine (CQUIM) Taichung Veterans General Hospital Taichung Taiwan Department of Medical Imaging China Medical University Hospital Taichung Taiwan

White matter hyperintensities (WMHs) are lesion in brain magnetic resonance images generally associated with Alzheimer’s disease (AD) and cognitive decline. Finding WMHs of AD poses a great challenge for diagnosis. This paper interprets a brain MR image as a hyperspectral image so that a well stablished hyperspectral subpixel detection algorithm, constrained energy minimization (CEM), is applicable to solving the WMHs detection problem at mixed pixel and subpixel level. To resolve nonlinear mixing in detecting WMHs nearby boundaries, a nonlinear CEM, called kernel CEM (KCEM) is also developed. Since CEM is a hyperspectral technique without taking spatial correlation into account, CEM was also extended to iterative CEM (ICEM) by including spatial filters to capture spatial information for WMHs detection. This paper combines ICEM and KCEM to derive a new WHMs detection algorithm, iterative KCEM (IKCEM) to improve ICEM and KCEM on WMHs detection. To evaluate the WMHs detection performance, two criteria, Dice similarity index (DSI) and 3D ROC analysis are used as evaluation tools. In order to show the superiority of IKCEM, two commonly used software packages, statistical parametric mapping (SPM)-based algorithms, SPM-lesion growth algorithm (SPM-LGA) and SPM-lesion prediction algorithm (SPM-LPA) are implemented for validation and comparison.

关键词： Hyperspectral imaging Magnetic resonance imaging Iterative methods Medical diagnostic imaging White matter Manuals Energy management Neuroimaging Brain modeling Alzheimer's disease Energy measurement

On the robustness of EEG tensor completion methods

学校读者我要写书评

暂无评论

science China(Technological sciences) 2021年第9期64卷 1828-1842页

作者： DUAN Feng JIA Hao ZHANG ZhiWen FENG Fan TAN Ying DAI YangYang CICHOCKI Andrzej YANG ZhengLu CAIAFA Cesar F. SUN Zhe SOLE-CASALS Jordi College of Artificial Intelligence Nankai UniversityTianjin 300350China Skolkowo Institute of Science and Technology Moscow 121205Russia College of Computer Science Hangzhou Dianzi UniversityHangzhou 310018China Department of Informatics Nicolaus Copernicus UniversityTorun 87-100Poland Systems Research Institute Polish Academy of SciencesWarsaw 01-447Poland College of Computer Science Nankai UniversityTianjin 300350China Instituto Argentino de Radioastronom´ıa IAR-CCT La Plata CONICET/CIC-PBA/UNLPVilla Elisa 1894Argentina Computational Engineering Applications Unit Head Office for Information Systems and CybersecurityRIKENWako-Shi 351-0106Japan Department of Psychiatry University of CambridgeCambridge CB28AHUK Data and Signal Processing Research Group University of Vic-Central University of CataloniaCatalonia 08500Spain

During the acquisition of electroencephalographic(EEG) signals, data may be missing or corrupted by noise and artifacts. To reconstruct the incomplete data, EEG signals are firstly converted into a three-order tensor(multi-dimensional data) of shape time × channel × trial. Then, the missing data can be efficiently recovered by applying a tensor completion method(TCM).However, there is not a unique way to organize channels and trials in a tensor, and different numbers of channels are available depending on the EEG setting used, which may affect the quality of the tensor completion results. The main goal of this paper is to evaluate the robustness of EEG completion methods with several designed parameters such as the ordering of channels and trials, the number of channels, and the amount of missing data. In this work, the results of completing missing data by several TCMs were compared. To emulate different scenarios of missing data, three different patterns of missing data were ***, the amount of missing data on completion effects was analyzed, including the time lengths of missing data and the number of channels or trials affected by missing data. Secondly, the numerical stability of the completion methods was analyzed by shuffling the indices along channels or trials in the EEG data tensor. Finally, the way that the number of electrodes of EEG tensors influences completion effects was assessed by changing the number of channels. Among all the applied TCMs, the simultaneous tensor decomposition and completion(STDC) method achieves the best performance in providing stable results when the amount of missing data or the electrode number of EEG tensors is changed. In other words, STDC proves to be an excellent choice of TCM, since permutations of trials or channels have almost no influence on the complete results. The STDC method can efficiently complete the missing EEG signals. The designed simulations can be regarded as a procedure to validate whether or

关键词： electroencephalogram corrupted data missing data tensor completion tensor decomposition