检索结果-内蒙古大学图书馆

A survey on deep learning for polyp segmentation: techniques, challenges and future trends

Visual Intelligence 2025年第1期3卷 1-20页

作者： Mei, Jiaxin Zhou, Tao Huang, Kaiwen Zhang, Yizhe Zhou, Yi Wu, Ye Fu, Huazhu PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Southeast University Nanjing China Institute of High Performance Computing A*STAR Singapore Singapore

Early detection and assessment of polyps play a crucial role in the prevention and treatment of colorectal cancer (CRC). Polyp segmentation provides an effective solution to assist clinicians in accurately locating and segmenting polyp regions. In the past, people often relied on manually extracted lower-level features such as color, texture, and shape, which often had problems capturing global context and lacked robustness to complex scenarios. With the advent of deep learning, more and more medical image segmentation algorithms based on deep learning networks have emerged, making significant progress in the field. This paper provides a comprehensive review of polyp segmentation algorithms. We first review some traditional algorithms based on manually extracted features and deep segmentation algorithms, and then describe benchmark datasets related to the topic. Specifically, we carry out a comprehensive evaluation of recent deep learning models and results based on polyp size, taking into account the focus of research topics and differences in network structures. Finally, we discuss the challenges of polyp segmentation and future trends in the field. © The Author(s) 2025.

关键词： Comprehensive evaluation Deep learning Medical imaging Polyp segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-View Test-Time Adaptation for Semantic Segmentation in Clinical Cataract Surgery

引用

IEEE Transactions on Medical Imaging 2025年第5期44卷 2307-2318页

作者： Li, Heng Ou, Mingyang Li, Haojin Qiu, Zhongxi Niu, Ke Fu, Huazhu Liu, Jiang Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems Shenzhen518055 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China Beijing Information Science and Technology University Computer School Beijing100192 China Institute of High Performance Computing Agency for Science Technology and Research Fusionopolis Way 138632 Singapore Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Shenzhen518055 China

Cataract surgery, a widely performed operation worldwide, is incorporating semantic segmentation to advance computer-assisted intervention. However, the tissue appearance and illumination in cataract surgery often differ among clinical centers, intensifying the issue of domain shifts. While domain adaptation offers remedies to the shifts, the necessity for data centralization raises additional privacy concerns. To overcome these challenges, we propose a Multi-view Test-time Adaptation algorithm (MUTA) to segment cataract surgical scenes, which leverages multi-view learning to enhance model training within the source domain and model adaptation within the target domain. In the training phase, the segmentation model is equipped with multi-view decoders to boost its robustness against variations in cataract surgery. During the inference phase, test-time adaptation is implemented using multi-view knowledge distillation, enabling model updates in clinics without data centralization or privacy concerns. We conducted experiments in a simulated cross-center scenario using several cataract surgery datasets to evaluate the effectiveness of MUTA. Through comparisons and investigations, we have validated that MUTA effectively learns a robust source model and adapts the model to target data during the practical inference phase. © 1982-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Medical Imaging: high-performance Hardware for Image Processing, Machine Learning 24

Optimizing Medical Imaging: High-Performance Hardware for Im...

引用

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Kalyan Chakravarthy, N.S. Balapanur, Mouli Chandra Pandian, Arun Nambi Pulikanti, Jyothi Prasad, D. Syed Masood, Jafar Ali Ibrahim High-Performance Computing Research Laboratory QIS College of Engineering and Technology Andhra Pradesh Ongole India Department of Internet of Things School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798400709586

The demand for high-performance hardware solutions for machine learning tasks is growing as medical imaging evolves. In this paper, we will focus on the latest hardware advanced technologies: GPUs, TPUs and FPGAs that can be used for image processing optimization in medical imaging such as brain tumor segmentation or chest X-ray classification. We test these devices on the BraTS and ChestX-ray14 datasets to show how running models quicker increases diagnostic performance. The study offers a comprehensive performance and energy efficiency evaluation of all the considered hardware solutions when training deep learning models for medical imaging, providing clinical guidelines to choose appropriate new-generation accelerators before engaging in expensive leasing contracts. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： GPUS

来源：评论

学校读者我要写书评

暂无评论

Adaptive Occlusion Face Recognition Feature Fusion Network Based on Precise Guidance Mask Extraction

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-12页

作者： Ye, Jihua Zhang, Lei Wang, Chao Tu, Qixuan Zheng, Rehua Huang, Huiyuan Jiang, Aiwen School of Computer and Information Engineering Jiangxi Normal University Nanchang330022 China Jiangxi Provincial Key Laboratory for High Performance Computing Jiangxi Normal University Nanchang330022 China State International Science & Technology Cooperation Base of Networked Supporting Software Jiangxi Normal University Nanchang330022 China

The uncertainty in the position and size of occluding objects greatly affects the extraction of identity features in facial recognition, which is a challenge that existing methods fail to effectively address. To tackle this issue, this paper introduces a novel feature fusion network for occluded facial recognition that adaptively handles arbitrary occlusions and accurately extracts occlusion information masks. The network effectively mitigates the impact of occlusions on facial identity features through a feature fusion module. The proposed method employs an occlusion classification module and an occlusion classification loss to precisely guide the extraction of accurate occlusion masks. Subsequently, an occlusion-aware hybrid attention module is introduced, which focuses on the relationship between facial features and occlusion masks across channel and spatial dimensions. This fusion strategy enables the extraction of facial identity features that are resilient to occlusions. Experimental results indicate that the proposed method holds a significant advantage in handling facial recognition tasks with arbitrary occlusions. On the LFW and MF1 synthetic occlusion datasets, the average accuracy rates reached 93.19% and 72.57%, respectively, showing improvements of 1.7 and 2.39 percent points over mainstream methods. © Shanghai Jiao Tong University 2025.

关键词： A feature fusion occluded facial recognition occlusion mask occlusion perception TP391.41

来源：评论

学校读者我要写书评

暂无评论

MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining

arXiv

引用

arXiv 2025年

作者： Wu, Ruiqi Su, Na Zhang, Chenran Ma, Tengfei Zhou, Tao Cui, Zhiting Tang, Nianfeng Mao, Tianyu Zhou, Yi Fan, Wen Wu, Tianxing Jing, Shenqi Fu, Huazhu School of Computer Science and Engineering Southeast University Nanjing China Department of Ophthalmology The First Affiliated Hospital of Nanjing Medical University Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Institute of High-Performance Computing Agency for Science Technology and Research Singapore

Vision-language pretraining (VLP) has been investigated to generalize across diverse downstream tasks for fundus image analysis. Although recent methods showcase promising achievements, they significantly rely on large-scale private image-text data but pay less attention to the pretraining manner, which limits their further advancements. In this work, we introduce MM-Retinal V2, a high-quality image-text paired dataset comprising CFP, FFA, and OCT image modalities. Then, we propose a novel fundus vision-language pretraining model, namely KeepFIT V2, which is pretrained by integrating knowledge from the elite data spark into categorical public datasets. Specifically, a preliminary textual pretraining is adopted to equip the text encoder with primarily ophthalmic textual knowledge. Moreover, a hybrid image-text knowledge injection module is designed for knowledge transfer, which is essentially based on a combination of global semantic concepts from contrastive learning and local appearance details from generative learning. Extensive experiments across zero-shot, few-shot, and linear probing settings highlight the generalization and transferability of KeepFIT V2, delivering performance competitive to state-of-the-art fundus VLP models trained on large-scale private image-text datasets. Our dataset and model are publicly available via https://***/lxirich/MM-Retinal. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Numerical simulations of attachment-line boundary layer in hypersonic flow. Part 1. Roughness-induced subcritical transitions

引用

Journal of Fluid Mechanics 2025年 1009卷

作者： Xi, Youcheng Yan, Bowen Yang, Guangwen Sha, Xinguo Zhu, Dehua Fu, Song School of Aerospace Engineering Tsinghua University Beijing100084 China Institute of High Performance Computing Department of Computer Science and Technology Tsinghua University Beijing100084 China China Academy of Aerospace Aerodynamics Beijing100074 China

The attachment-line boundary layer is critical in hypersonic flows because of its significant impact on heat transfer and aerodynamic performance. In this study, high-fidelity numerical simulations are conducted to analyse the subcritical roughness-induced laminar–turbulent transition at the leading-edge attachment-line boundary layer of a blunt swept body under hypersonic conditions. This simulation represents a significant advancement by successfully reproducing the complete leading-edge contamination process induced by a surface roughness element in a realistic configuration, thereby providing previously unattainable insights. Two roughness elements of different heights are examined. For the lower-height roughness element, additional unsteady perturbations are required to trigger a transition in the wake, suggesting that the flow field around the roughness element acts as a perturbation amplifier for upstream perturbations. Conversely, a higher roughness element can independently induce the transition. A low-frequency absolute instability is detected behind the roughness, leading to the formation of streaks. The secondary instabilities of these streaks are identified as the direct cause of the final transition. © The Author(s), 2025.

关键词： Hypersonic flow

来源：评论

学校读者我要写书评

暂无评论

ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification

arXiv

引用

arXiv 2025年

作者： Shi, Jiangbo Li, Chen Gong, Tieliang Zheng, Yefeng Fu, Huazhu School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Jarvis Research Center Tencent YouTu Lab Shenzhen China Institute of High Performance Computing Agency for Science Technology and Research Singapore

Multiple instance learning (MIL)-based framework has become the mainstream for processing the whole slide image (WSI) with giga-pixel size and hierarchical image context in digital pathology. However, these methods heavily depend on a substantial number of bag-level labels and solely learn from the original slides, which are easily affected by variations in data distribution. Recently, vision language model (VLM)-based methods introduced the language prior by pre-training on large-scale pathological image-text pairs. However, the previous text prompt lacks the consideration of pathological prior knowledge, therefore does not substantially boost the model’s performance. Moreover, the collection of such pairs and the pre-training process are very time-consuming and source-intensive. To solve the above problems, we propose a dual-scale vision-language multiple instance learning (ViLa-MIL) framework for whole slide image classification. Specifically, we propose a dual-scale visual descriptive text prompt based on the frozen large language model (LLM) to boost the performance of VLM effectively. To transfer the VLM to process WSI efficiently, for the image branch, we propose a prototype-guided patch decoder to aggregate the patch features progressively by grouping similar patches into the same prototype;for the text branch, we introduce a context-guided text decoder to enhance the text features by incorporating the multi-granular image contexts. Extensive studies on three multi-cancer and multi-center subtyping datasets demonstrate the superiority of ViLa-MIL. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Unknown-Aware Bilateral Dependency Optimization for Defending Against Model Inversion Attacks

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Peng, Xiong Liu, Feng Wang, Nannan Lan, Long Liu, Tongliang Cheung, Yiu-Ming Han, Bo Hong Kong Baptist University Department of Computer Science Hong Kong The University of Melbourne School of Computing and Information Systems Australia Xidian University State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Shaanxi Xi'an710071 China National University of Defense Technology State Key Laboratory of High Performance Computing School of Computer Hunan Changsha410000 China The University of Sydney Sydney AI Centre School of Computer Science Faculty of Engineering Australia

By abusing access to a well-trained classifier, model inversion (MI) attacks pose a significant threat as they can recover the original training data, leading to privacy leakage. Previous studies mitigated MI attacks by imposing regularization to reduce the dependency between input features and outputs during classifier training, a strategy known as unilateral dependency optimization. However, this strategy contradicts the objective of minimizing the supervised classification loss, which inherently seeks to maximize the dependency between input features and outputs. Consequently, there is a trade-off between improving the model's robustness against MI attacks and maintaining its classification performance. To address this issue, we propose the bilateral dependency optimization strategy (BiDO), a dual-objective approach that minimizes the dependency between input features and latent representations, while simultaneously maximizing the dependency between latent representations and labels. BiDO is remarkable for its privacy-preserving capabilities. However, models trained with BiDO exhibit diminished capabilities in out-of-distribution (OOD) detection compared to models trained with standard classification supervision. Given the open-world nature of deep learning systems, this limitation could lead to significant security risks, as encountering OOD inputs—whose label spaces do not overlap with the in-distribution (ID) data used during training-is inevitable. To address this, we leverage readily available auxiliary OOD data to enhance the OOD detection performance of models trained with BiDO. This leads to the introduction of an upgraded framework, unknown-aware BiDO (BiDO+), which mitigates both privacy and security concerns. As a highlight, with comparable model utility, BiDO-HSIC+ reduces the FPR95 by 55.02% and enhances the AUCROC by 9.52% compared to BiDO-HSIC, while also providing superior MI robustness. © 1979-2012 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Pareto Set Learning through Genetic Programming for Multi-Objective Dynamic Scheduling

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Xu, Meng Mei, Yi Zhang, Fangfang Ong, Yew Soon Zhang, Mengjie Agency for Science Technology and Research Singapore Institute of Manufacturing Technology Singapore Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Agency for Science Technology and Research College of Computing and Data Science Nanyang Technological University Centre for Frontier AI Research Institute of High Performance Computing Singapore Singapore

The multi-objective dynamic flexible job shop scheduling (MO-DFJSS) problem is crucial in modern manufacturing, impacting productivity and operational costs. Genetic Programming (GP) has emerged as a prominent method for MO-DFJSS due to its ability to evolve real-time responsible and effective scheduling heuristics. However, existing GP approaches often learn multiple heuristics for different regions of the Pareto front, making their management and selection complicated in real-world applications. This paper proposes a novel Pareto set learning GP (PSLGP) framework that addresses this limitation by learning a single, preference-conditioned heuristic that encompasses the entire Pareto front based on user preferences. This simplifies scheduling and allows for real-time adaptation to user-defined priorities. The framework employs a novel preference-conditioned heuristic representation that incorporates user preferences as additional inputs, enabling dynamic heuristic adjustments. To efficiently evaluate fitness without increasing training time, a surrogate model is used to estimate individual performance across different preferences, and three new fitness aggregation strategies are designed to ensure effective heuristic alignment across the Pareto front. Experimental results demonstrate that PSLGP significantly outperforms the state-of-the-art multi-objective GP approach, particularly in less busy MO-DFJSS environments, providing a more adaptable and efficient solution for dynamic scheduling challenges. Further analyses of preference influence, solution distribution, and heuristic structure provide evidence that the proposed PSLGP effectively learns preference-conditioned scheduling heuristics that align user preferences with various regions of the Pareto front. © 1997-2012 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering

arXiv

引用

arXiv 2025年

作者： Liao, Zehui Hu, Shishuai Zou, Ke Fu, Huazhu Zhen, Liangli Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Institute of High Performance Computing Agency for Science Technology and Research Singapore138632 Singapore National University of Singapore Singapore119077 Singapore

Multimodal large language models (MLLMs) have demonstrated significant potential in medical Visual Question Answering (VQA). Yet, they remain prone to hallucinations—incorrect responses that contradict input images, posing substantial risks in clinical decision-making. Detecting these hallucinations is essential for establishing trust in MLLMs among clinicians and patients, thereby enabling their real-world adoption. Current hallucination detection methods, especially semantic entropy (SE), have demonstrated promising hallucination detection capacity for LLMs. However, adapting SE to medical MLLMs by incorporating visual perturbations presents a dilemma. Weak perturbations preserve image content and ensure clinical validity, but may be overlooked by medical MLLMs, which tend to over rely on language priors. In contrast, strong perturbations can distort essential diagnostic features, compromising clinical interpretation. To address this issue, we propose Vision Amplified Semantic Entropy (VASE), which incorporates weak image transformations and amplifies the impact of visual input, to improve hallucination detection in medical VQA. We first estimate the semantic predictive distribution under weak visual transformations to preserve clinical validity, and then amplify visual influence by contrasting this distribution with that derived from a distorted image. The entropy of the resulting distribution is estimated as VASE. Experiments on two medical open-ended VQA datasets demonstrate that VASE consistently outperforms existing hallucination detection methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：