检索结果-内蒙古大学图书馆

Reler: Relearning Controversial Regions to Accurately Segment Nasopharyngeal Carcinoma

学校读者我要写书评

暂无评论

Reler: Relearning Controversial Regions to Accurately Segmen...

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Tao, Guihua Li, Haojiang Lu, Dandan Ling, Ziqin Liu, Lizhi Cai, Hongmin South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University Cancer Center Sun Yat-sen University State Key Laboratory of Oncology in South China Collaborative Innovation Center for Cancer Medicine Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy Guangzhou China Pazhou Lab Brain and Affective Cognitive Research Center Guangzhou China

ISBN: (纸本)9781665468190

Accurate nasopharyngeal carcinoma (NPC) segmentation is significant in preventing local recurrence and improving patients' survival rates. However, existing deep learning-based methods often yield unsatisfactory segmentation results, especially in fine-grained detail. Because NPC is a tiny and infiltrative tumor with a huge background, traditional deep neural networks tend to be dominated by salient information, thus missing the fine-grained details of NPC. To achieve accurate NPC segmentation, a relearning controversial regions method (Reler) is proposed. It consists of three modules, including the controversial features generator (CFG), controversial features finding module (CFF), and controversial regions arbitration module (CRA). First, CFG constructs global and local feature extractors to generate two types of different features. Then, CFF finds the controversial features and corresponding regions by comparing the global and local features' estimates of the segmentation results of the same input regions. Next, the CRA focuses on controversial features, relearns new features, and produces new segmentation results through a proposed Transformer-based self-attention network. Finally, the uncontroversial segmentation results from CFF and CRA are combined as the final segmentation results. Extensive experiments are conducted on a large NPC dataset containing 6342 images from 596 patients. The experimental results show that the proposed method Reler is effective and superior to the nine state-of-the-art methods. © 2022 IEEE.

关键词： Deep neural networks

SONIA: an immersive customizable virtual reality system for the education and exploration of brain networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hellum, Owen Steele, Christopher Xiao, Yiming Department of Computer Science and Software Engineering Concordia University MontrealQC Canada Department of Psychology Concordia University MontrealQC Canada PERFORM Centre Concordia University MontrealQC Canada Department of Neurology Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany

While mastery of neuroanatomy is important for the investigation of the brain, there is an increasing interest in exploring the neural pathways to better understand the roles of neural circuitry in brain functions. To tackle the limitations of traditional 2D-display-based neuronavigation software in intuitively visualizing complex 3D anatomies, several virtual reality (VR) and augmented reality (AR) solutions have been proposed to facilitate neuroanatomical education. However, with the increasing knowledge on brain connectivity and the functioning of the sub-systems, there is still a lack of similar software solutions for the education and exploration of these topics, which demand more elaborate visualization and interaction strategies. To address this gap, we designed the immerSive custOmizable Neuro learnIng plAform (SONIA), a novel user-friendly VR software system with a multi-scale interaction paradigm that allowed flexible customization of learning materials. With both quantitative and qualitative evaluations through user studies, the proposed system was shown to have high usability, attractive visual design, and good educational value. As the first immersive system that integrated customizable design and detailed narratives of the brain sub-systems for the education of neuroanatomy and brain connectivity, SONIA showcased new potential directions and provided valuable insights regarding medical learning and exploration in VR. © 2023, CC BY-NC-SA.

关键词： Virtual reality

Adversarially trained neural representations may already be as robust as corresponding biological neural representations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Guo, Chong Lee, Michael J. Leclerc, Guillaume Dapello, Joel Rao, Yug Madry, Aleksander DiCarlo, James J. McGovern Institute for Brain Research MIT United States Department of Brain and Cognitive Sciences MIT United States Center for Brains Minds and Machines MIT United States Computer Science and Artificial Intelligence Laboratory MIT United States School of Engineering and Applied Sciences Harvard University United States Purdue University United States Department of Electrical Engineering and Computer Science MIT United States

Visual systems of primates are the gold standard of robust perception. There is thus a general belief that mimicking the neural representations that underlie those systems will yield artificial visual systems that are adversarially robust. In this work, we develop a method for performing adversarial visual attacks directly on primate brain activity. We then leverage this method to demonstrate that the above-mentioned belief might not be well founded. Specifically, we report that the biological neurons that make up visual systems of primates exhibit susceptibility to adversarial perturbations that is comparable in magnitude to existing (robustly trained) artificial neural networks. Copyright © 2022, The Authors. All rights reserved.

关键词： Mammals

Human Decision-making is Susceptible to AI-driven Manipulation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sabour, Sahand Liu, June M. Liu, Siyang Yao, Chris Z. Cui, Shiyao Zhang, Xuanming Zhang, Wen Cao, Yaru Bhat, Advait Guan, Jian Wu, Wei Mihalcea, Rada Althoff, Tim Lee, Tatia M.C. Huang, Minlie The CoAI Group DCST Institute for Artificial Intelligence Tsinghua University Beijing China State Key Laboratory of Brain and Cognitive Sciences The University of Hong Kong Hong Kong Laboratory of Neuropsychology and Human Neuroscience The University of Hong Kong Hong Kong The LIT Group Department of Computer Science and Engineering University of Michigan Ann Arbor United States Department of Psychology University of International Relations Beijing China Department of Chinese Language and Literature Northwest Minzu University Lanzhou China Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States ANT Group China

Artificial Intelligence (AI) systems are increasingly intertwined with daily life, assisting users in executing various tasks and providing guidance on decision-making. This integration introduces risks of AI-driven manipulation, where such systems may exploit users’ cognitive biases and emotional vulnerabilities to steer them toward harmful outcomes. Through a randomized controlled trial with 233 participants, we examined human susceptibility to such manipulation in financial (e.g., purchases) and emotional (e.g., conflict resolution) decision-making contexts. Participants interacted with one of three AI agents: a neutral agent (NA) optimizing for user benefit without explicit influence, a manipulative agent (MA) designed to covertly influence beliefs and behaviors, or a strategy-enhanced manipulative agent (SEMA) employing established psychological tactics to reach its hidden objectives. To ensure participant well-being, this study involved hypothetical scenarios, pre-screening for at-risk individuals, and comprehensive post-study debriefing. By analyzing participants’ decision patterns and shifts in their preference ratings post-interaction, we found significant susceptibility to AI-driven manipulation. Particularly, across both decision-making domains, participants interacting with the manipulative agents shifted toward harmful options at substantially higher rates (financial, MA: 62.3%, SEMA: 59.6%;emotional, MA: 42.3%, SEMA: 41.5%) compared to the NA group (financial, 35.8%;emotional, 12.8%). Notably, our results reveal that even simple manipulative objectives (MA) can be as effective as employing established psychological strategies (SEMA) in swaying human decision-making. These findings suggest that AI-driven manipulation could become widely spread, as it does not require sophisticated tactics and expertise to influence users. By revealing the potential for covert AI influence, this study highlights a critical vulnerability in human-AI interactions, emphasiz

关键词： Finance

How does the primate brain combine generative and discriminative computations in vision?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Peters, Benjamin DiCarlo, James J. Gureckis, Todd Haefner, Ralf Isik, Leyla Tenenbaum, Joshua Konkle, Talia Naselaris, Thomas Stachenfeld, Kimberly Tavares, Zenna Tsao, Doris Yildirim, Ilker Kriegeskorte, Nikolaus Zuckerman Mind Brain Behavior Institute Columbia University United States School of Psychology & Neuroscience University of Glasgow United Kingdom Department of Brain and Cognitive Sciences MIT United States McGovern Institute for Brain Research MIT United States NSF Center for Brains Minds and Machines MIT United States Quest for Intelligence Schwarzman College of Computing MIT United States Department of Psychology New York University United States Brain and Cognitive Sciences University of Rochester United States Center for Visual Science University of Rochester United States Department of Cognitive Science Johns Hopkins University United States Computer Science and Artificial Intelligence Laboratory MIT United States Department of Psychology Harvard University United States Center for Brain Science Harvard University United States Kempner Institute for Natural and Artificial Intelligence Harvard University United States Department of Neuroscience University of Minnesota United States DeepMind United Kingdom Data Science Institute Columbia University United States Dept of Molecular & Cell Biology University of California Berkeley United States Howard Hughes Medical Institute United States Department of Psychology Yale University United States Department of Statistics and Data Science Yale University United States Department of Psychology Columbia University United States Department of Neuroscience Columbia University United States Department of Electrical Engineering Columbia University United States

Vision is widely understood as an inference problem. However, two contrasting conceptions of the inference process have each been influential in research on biological vision as well as the engineering of machine vision. The first emphasizes bottom-up signal flow, describing vision as a largely feedforward, discriminative inference process that filters and transforms the visual information to remove irrelevant variation and represent behaviorally relevant information in a format suitable for downstream functions of cognition and behavioral control. In this conception, vision is driven by the sensory data, and perception is direct because the processing proceeds from the data to the latent variables of interest. The notion of "inference" in this conception is that of the engineering literature on neural networks, where feedforward convolutional neural networks processing images are said to perform inference. The alternative conception is that of vision as an inference process in Helmholtz's sense, where the sensory evidence is evaluated in the context of a generative model of the causal processes that give rise to it. In this conception, vision inverts a generative model through an interrogation of the sensory evidence in a process often thought to involve top-down predictions of sensory data to evaluate the likelihood of alternative hypotheses. The authors include scientists rooted in roughly equal numbers in each of the conceptions and motivated to overcome what might be a false dichotomy between them and engage the other perspective in the realm of theory and experiment. The primate brain employs an unknown algorithm that may combine the advantages of both conceptions. We explain and clarify the terminology, review the key empirical evidence, and propose an empirical research program that transcends the dichotomy and sets the stage for revealing the mysterious hybrid algorithm of primate vision. © 2024, CC BY.

关键词： Feedforward neural networks

A Comprehensive Survey of Foundation Models in Medicine

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Khan, Wasif Leem, Seowung See, Kyle B. Wong, Joshua K. Zhang, Shaoting Fang, Ruogu J. Crayton Pruitt Family Department of Biomedical Engineering Herbert Wertheim College of Engineering University of Florida GainesvilleFL United States Norman Fixel Institute for Neurological Diseases University of Florida GainesvilleFL United States Department of Neurology University of Florida GainesvilleFL United States Department of Computer Science The University of North Carolina at Charlotte CharlotteNC United States Center for Cognitive Aging and Memory McKnight Brain Institute University of Florida GainesvilleFL United States Department of Electrical and Computer Engineering Herbert Wertheim College of Engineering University of Florida GainesvilleFL United States Department of Computer Information Science Engineering Herbert Wertheim College of Engineering University of Florida GainesvilleFL United States

Foundation models (FMs) are large-scale deep learning models trained on massive datasets, often using self-supervised learning techniques. These models serve as a versatile base for a wide range of downstream tasks, including those in medicine and healthcare. FMs have demonstrated remarkable success across multiple healthcare domains. However, existing surveys in this field do not comprehensively cover all areas where FMs have made significant strides. In this survey, we present a comprehensive review of FMs in medicine, focusing on their evolution, learning strategies, flagship models, applications, and associated challenges. We examine how prominent FMs, such as the BERT and GPT families, are transforming various aspects of healthcare, including clinical large language models, medical image analysis, and omics research. Additionally, we provide a detailed taxonomy of FM-enabled healthcare applications, spanning clinical natural language processing, medical computer vision, graph learning, and other biology- and omics- related tasks. Despite the transformative potentials of FMs, they also pose unique challenges. This survey delves into these challenges and highlights open research questions and lessons learned to guide researchers and practitioners. Our goal is to provide valuable insights into the capabilities of FMs in health, facilitating responsible deployment and mitigating associated risks. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

Self-attending RNN for Speech Enhancement to Improve Cross-corpus Generalization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Pandey, Ashutosh Wang, DeLiang The Department of Computer Science and Engineering The Ohio State University ColumbusOH43210 United States The Department of Computer Science and Engineering The Center for Cognitive and Brain Sciences The Ohio State University ColumbusOH43210 United States

Deep neural networks (DNNs) represent the mainstream methodology for supervised speech enhancement, primarily due to their capability to model complex functions using hierarchical representations. However, a recent study revealed that DNNs trained on a single corpus fail to generalize to untrained corpora, especially in low signal-to-noise ratio (SNR) conditions. Developing a noise, speaker, and corpus independent speech enhancement algorithm is essential for real-world applications. In this study, we propose a self-attending recurrent neural network, or attentive recurrent network (ARN), for time-domain speech enhancement to improve cross-corpus generalization. ARN comprises of recurrent neural networks (RNNs) augmented with self-attention blocks and feedforward blocks. We evaluate ARN on different corpora with nonstationary noises in low SNR conditions. Experimental results demonstrate that ARN substantially outperforms competitive approaches to time-domain speech enhancement, such as RNNs and dual-path ARNs. Additionally, we report an important finding that the two popular approaches to speech enhancement: complex spectral mapping and time-domain enhancement, obtain similar results for RNN and ARN with large-scale training. We also provide a challenging subset of the test set used in this study for evaluating future algorithms and facilitating direct comparisons. Copyright © 2021, The Authors. All rights reserved.

关键词： Recurrent neural networks

IMPROVING WORLD MODELS USING DEEP SUPERVISION WITH LINEAR PROBES

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zahorodnii, Andrii Department of Electrical Engineering and Computer Science MIT United States Department of Brain and Cognitive Sciences McGovern Institute for Brain Research MIT CambridgeMA United States

Developing effective world models is crucial for creating artificial agents that can reason about and navigate complex environments. In this paper, we investigate a deep supervision technique for encouraging the development of a world model in a network trained end-to-end to predict the next observation. While deep supervision has been widely applied for task-specific learning, our focus is on improving the world models. Using an experimental environment based on the Flappy Bird game, where the agent receives only LIDAR measurements as observations, we explore the effect of adding a linear probe component to the network’s loss function. This additional term encourages the network to encode a subset of the true underlying world features into its hidden state. Our experiments demonstrate that this supervision technique improves both training and test performance, enhances training stability, and results in more easily decodable world features – even for those world features which were not included in the training. Furthermore, we observe a reduced distribution drift in networks trained with the linear probe, particularly during high-variability phases of the game (flying between successive pipe encounters). Including the world features loss component roughly corresponded to doubling the model size, suggesting that the linear probe technique is particularly beneficial in compute-limited settings or when aiming to achieve the best performance with smaller models. These findings contribute to our understanding of how to develop more robust and sophisticated world models in artificial agents, paving the way for further advancements in this field. Copyright © 2025, The Authors. All rights reserved.

关键词：

Inhibition of the inferior parietal lobe triggers state-dependent network adaptations

学校读者我要写书评

暂无评论

Heliyon 2024年第21期10卷 e39735页

作者： Williams, Kathleen A. Numssen, Ole Guerra, Juan David Kopal, Jakub Bzdok, Danilo Hartwigsen, Gesa Lise Meitner Research Group Cognition and Plasticity Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany Methods and Development Group “Brain Networks” Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany The Neuro - Montreal Neurological Institute (MNI) McConnell Brain Imaging Centre Department of Biomedical Engineering Faculty of Medicine School of Computer Science McGill University Montreal Canada Mila - Quebec Artificial Intelligence Institute Montreal QC Canada Wilhelm Wundt Institute for Psychology Leipzig University Germany

The human brain comprises large-scale networks that flexibly interact to support diverse cognitive functions and adapt to variability in daily life. The inferior parietal lobe (IPL) is a hub of multiple brain networks that sustain various cognitive domains. It remains unclear how networks respond to acute regional perturbations to maintain normal function. To provoke network-level adaptive responses to local inhibition, we combined offline transcranial magnetic stimulation (TMS) over left or right IPL with neuroimaging during attention, semantic and social cognition tasks, and rest. Across tasks, TMS specifically affected task-active network activity with inhibition and facilitation. Network interaction responses differed between rest and tasks. After TMS over both IPL regions, large-scale network interactions were exclusively facilitated at rest, but mainly inhibited during tasks. Overall, responses to TMS primarily occurred in and between domain-general default mode and frontoparietal subnetworks. These findings elucidate short-term adaptive plasticity in response to network node inhibition. © 2024 The Authors

关键词： Cognition cTBS fMRI Functional connectivity Resting state TMS