检索结果-内蒙古大学图书馆

Deep Learning in Palmprint Recognition-A Comprehensive Survey

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gao, Chengrui Yang, Ziyuan Jia, Wei Leng, Lu Zhang, Bob Teoh, Andrew Beng Jin College of Computer Science Sichuan University Chengdu610065 China Singapore School of Computer and Information Hefei University of Technology Hefei China Jiangxi Provincial Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China Pattern Analysis and Machine Intelligence Group Department of Computer and Information Science University of Macau Taipa China School of Electrical and Electronic Engineering College of Engineering Yonsei University Seoul Korea Republic of

Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on researchers' prior knowledge. Deep learning (DL) has been introduced to address this limitation, leveraging its remarkable successes across various domains. While existing surveys focus narrowly on specific tasks within palmprint recognition-often grounded in traditional methodologies-there remains a significant gap in comprehensive research exploring DL-based approaches across all facets of palmprint recognition. This paper bridges that gap by thoroughly reviewing recent advancements in DL-powered palmprint recognition. The paper systematically examines progress across key tasks, including region-of-interest segmentation, feature extraction, and security/privacy-oriented challenges. Beyond highlighting these advancements, the paper identifies current challenges and uncovers promising opportunities for future research. By consolidating state-of-the-art progress, this review serves as a valuable resource for researchers, enabling them to stay abreast of cutting-edge technologies and drive innovation in palmprint recognition. Copyright © 2025, The Authors. All rights reserved.

关键词： Biometrics

Dermoscopic image Classification Using Attention Mechanism and Ensemble Learning Approaches

学校读者我要写书评

暂无评论

Dermoscopic Image Classification Using Attention Mechanism a...

IEEE International Conference on Big Data

作者： Shanchuan Huang Hongwei Lei Liuhan Jin Jinzhu Yang Tao Jiang Yudong Yao Marcin Grzegorzek Chen Li Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang Liaoning China School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu China Department of Electrical and Computer Engineering Stevens Institute of Technology USA Institute of Medical Informatics University of Luebeck Luebeck Germany

Background and purpose: Skin tumours have become one of the most common diseases worldwide. While benign ones are not usually a threat to human health, malignant ones can develop into skin cancer and become life-threatening if left untreated. Early detection of the disease is important for the treatment of patients with skin tumours and dermoscopy is the most effective means of diagnosing skin tumours. However, the complexity of skin tumour cells makes the diagnosis somewhat erroneous for doctors. Therefore, a dermoscopic classification network based on deep learning and computer-aided diagnostic techniques is needed to obtain a high diagnostic accuracy rate for skin tumours. Methods: In this paper, Deep-skin, a model for dermoscopic image classification is proposed, which is based on both attention mechanism and ensemble learning. Considering the characteristics of dermoscopic images, embedding different attention mechanisms on top of Inception-V3 has been suggested to obtain more potential features. We then improve the classification performance by late fusion of the different models. To demonstrate the effectiveness of Deep-skin, experiments and evaluations are performed on the publicly available dataset Skin Cancer: Malignant vs. Benign and compare the performance of Deep-skin with other classification models. Results: The experimental results indicate that Deep-skin performs well on the dataset in comparison to other models, achieving a maximum accuracy of 87.8%.Conclusion: In this paper, the Deep-skin model is proposed for the classification of dermoscopic images and has shown better performance. In the future, we intend to investigate better classification models for automatic diagnosis of skin tumours. Such models can potentially assist physicians and patients in clinical settings.

关键词：

Two-Stream Regression Network for Dental Implant Position Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Xinquan Li, Xuguang Li, Xuechen Chen, Wenting Shen, Linlin Li, Xin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China Department of Electrical Engineering City University of Hong Kong Hong Kong

In implant prosthesis treatment, the design of surgical guide requires lots of manual labors and is prone to subjective variations. When deep learning based methods has started to be applied to address this problem, the space between teeth are various and some of them might present similar texture characteristic with the actual implant region. Both problems make a big challenge for the implant position prediction. In this paper, we develop a two-stream implant position regression framework (TSIPR), which consists of an implant region detector (IRD) and a multi-scale patch embedding regression network (MSPENet), to address this issue. For the training of IRD, we extend the original annotation to provide additional supervisory information, which contains much more rich characteristic and do not introduce extra labeling costs. A multi-scale patch embedding module is designed for the MSPENet to adaptively extract features from the images with various tooth spacing. The global-local feature interaction block is designed to build the encoder of MSPENet, which combines the transformer and convolution for enriched feature representation. During inference, the RoI mask extracted from the IRD is used to refine the prediction results of the MSPENet. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TSIPR achieves superior performance than existing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

HyperScore: A unified measure to model hypertension progression using multi-modality measurements and semi-supervised learning

学校读者我要写书评

暂无评论

HyperScore: A unified measure to model hypertension progress...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mohanad Alkhodari Winok Lapidaire Zhaohan Xiong Turkay Kart Yasser Iturria-Medina Leontios Hadjileontiadis Ahsan Khandoker Adam J. Lewandowski Abhirup Banerjee Paul Leeson Radcliffe Department of Medicine Cardiovascular Clinical Research Facility University of Oxford Oxford UK Department of Biomedical Engineering Healthcare Engineering Innovation Center Khalifa University Abu Dhabi UAE Department of Computing Biomedical Image Analysis Group Imperial College London London UK Neuroinformatics for Personalized Medicine Lab McGill University Montreal Canada Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK

Hypertension is a serious medical condition that affects over a billion people worldwide. The proper management of disease progression requires an extended knowledge of the overall functional and structural changes in the whole body in response to the hypertension. Here, we propose HyperScore, an integrative and unified measure of hypertension progression relative to multi-organ and multi-modality clinical measurements and based on a semi-supervised machine learning (ML) approach. We developed the measure based on a large participating cohort from the UK Biobank database (n=27,099) with over 500 imaging and clinical variables from multiple modalities. The semi-supervised approach was developed based on the contrastive trajectory inference mechanism to provide a score that reflects the proximity of a participant to the disease state (range: 0–1). Modelling revealed that majority of hypertensive participants had scores above 0.25, whereas normotensives had scores below this threshold. The sensitivity and specificity were above 89%, with an area under the receiver operating characteristics of 96.4%. The modelling showed a stable performance when evaluating hidden testing sets on a 10-fold cross-validation scheme with nearly 0.1 error. There was a strong association (r 2 >0.6) between HyperScore and organs’ phenotypic patterns, especially for variables such as white matter hyperintensity and body mass index. This study is the first to potentiate ML-based modelling of hypertension progression from a multi-organ perspective, which could significantly aid in clinical decision making to save lives.

关键词：

Object Detection at Sea Using Ensemble Methods Across Spectral Ranges

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2021年第16期54卷 1-6页

作者： Frederik E.T. Schöller Martin K. Plenge-Feidenhans’l Jonathan D. Stets Mogens Blanke Automation and Control Group Department of Electrical Engineering Technical University of Denmark DK-2800 Kgs. Lyngby Denmark Section of Image Analysis and Computger Graphics Department of Applied Mathematics and Computer Science DTU

Having the option of a temporally unmanned bridge when conditions allow, while maintaining or even enhancing navigational safety, is a long term aim in the maritime industry. Such a system requires excellent perception of the environment using an array of sensors. This paper investigates performance of object detection at sea using electro-optical sensors in relevant spectral ranges and discusses how missed detection risk is minimised for objects within navigation range. Using a combination of cameras in visible, near- and far infrared ranges, convolutional neural networks are employed for object detection. Ensemble techniques are suggested to minimise the amount of missed detections and it is shown how optimisation of confidence thresholds can be used to increase performance. The results are based on image data from vessels in near-coast operation in Danish waters.

关键词： Multi-modal sensor fusion Deep learning Detection performance Object detection at sea computer vision Autonomous Marine Vehicles

Generation of Synthetic Echocardiograms Using video Diffusion Models

学校读者我要写书评

暂无评论

Generation of Synthetic Echocardiograms Using Video Diffusio...

IEEE Southwest Symposium on image analysis and Interpretation

作者： Alexandre Olive Pellicer Amit Kumar Singh Yadav Kratika Bhagtani Ziyue Xiang Zygmunt Pizlo Irmina Gradus-Pizlo Edward J. Delp Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering Purdue University West Lafayette Indiana USA Department of Cognitive Sciences University of California-Irvine Irvine California USA School of Medicine University of California-Irvine Irvine California USA Escola Tècnica Superior d’Enginyeria de Telecomunicació de Barcelona Universitat Politècnica de Catalunya (UPC) Barcelona Spain

An echocardiogram is a video sequence of a human heart captured using ultrasound imaging, which helps in diagnosis of cardiovascular diseases. Deep learning methods, which require large amounts of training data, have shown success in using echocardiograms to detect cardiovascular disorders. Large datasets of echocardiograms that can be used for machine learning training are scarce. This problem can be addressed by generating synthetic echocardiograms that can be used for machine learning training. In this paper, we propose a video diffusion method for echocardiograms generation. We show that our method generates better echocardiograms with higher resolution as compared to existing methods.

关键词：

Localization of Seizure Onset Zone based on Spatio-Temporal Independent Component analysis on fMRI

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sadjadi, Seyyed Mostafa Ebrahimzadeh, Elias Fallahi, Alireza Habibabadi, Jafar Mehvari Nazem-Zadeh, Mohammad-Reza Soltanian-Zadeh, Hamid School of Electrical and Computer Engineering University of Tehran Tehran Iran Tehran Iran Biomedical Engineering Department Hamedan University of Technology Hamedan Iran Isfahan Neuroscience Research Center Isfahan University of Medical Sciences Isfahan Iran Tehran University of Medical Sciences Tehran Iran Medical Physics and Biomedical Engineering Department Tehran University of Medical Sciences Tehran Iran Department of Neuroscience Monash University MelbourneVIC Australia Medical Image Analysis Laboratory Departments of Radiology and Research Administration Henry Ford Health System DetroitMI United States

Localization of the seizure onset zone (SOZ) as a step of presurgical planning leads to higher efficiency in surgical and stimulation treatments. However, the clinical localization including structural, ictal, and invasive data acquisition and assessment is a difficult and long procedure with increasing challenges in patients with complex epileptic foci. The interictal methods are proposed to assist in presurgical planning with simpler data acquisition and higher speed. In this study, spatio-temporal component classification is presented for the localization of epileptic foci using resting-state functional magnetic resonance imaging (rs-fMRI) data. This method is based on spatio-temporal independent component analysis (ST-ICA) on rs-fMRI with a component-sorting procedure upon dominant power frequency, biophysical constraints, spatial lateralization, local connectivity, temporal energy, and functional non-Gaussianity. This method aimed to utilize the rs-fMRI potential to reach a high spatial accuracy in localizing epileptic foci from interictal data while retaining the reliability of results for clinical usage. Thirteen patients with temporal lobe epilepsy (TLE) who underwent surgical resection and had seizure-free surgical outcomes after a 12-month follow-up were included in this study. All patients had pre-surgical structural MRI and rs-fMRI while post-surgical MRI images were available for ten. Based on the relationship between the localized foci and resection, the results were classified into three groups "fully concordant", "partially concordant", and "discordant". These groups had the resulting cluster aligned with, in the same lobe with, and outside the lobe of the resection area, respectively. This method showed promising results highlighting valuable features as SOZ functional biomarkers. Contrary to most methods which depend on simultaneous EEG information, the occurrence of epileptic spikes, and the depth of the epileptic foci, the presented method is ent

关键词： Magnetic resonance imaging

TOD-CNN: An Effective Convolutional Neural Network for Tiny Object Detection in Sperm videos

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zou, Shuojia Li, Chen Sun, Hongzan Xu, Peng Zhang, Jiawei Ma, Pingli Yao, Yudong Huang, Xinyu Grzegorzek, Marcin Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Shengjing Hospital China Medical University Shenyang China Jinghua Hospital Shenyang China Department of Electrical and Computer Engineering Stevens Institute of Technology United States Institute of Medical Informatics University of Luebeck Luebeck Germany

The detection of tiny objects in microscopic videos is a problematic point, especially in large-scale experiments. For tiny objects (such as sperms) in microscopic videos, current detection methods face challenges in fuzzy, irregular, and precise positioning of objects. In contrast, we present a convolutional neural network for tiny object detection (TOD-CNN) with an underlying data set of high-quality sperm microscopic videos (111 videos, > 278,000 annotated objects), and a graphical user interface (GUI) is designed to employ and test the proposed model effectively. TOD-CNN is highly accurate, achieving 85.60% AP50 in the task of real-time sperm detection in microscopic videos. To demonstrate the importance of sperm detection technology in sperm quality analysis, we carry out relevant sperm quality evaluation metrics and compare them with the diagnosis results from medical doctors. © 2022, CC0.

关键词： Convolution

A Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI Data

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Nohel, Michal Ulrich, Constantin Suprijadi, Jonathan Wald, Tassilo Maier-Hein, Klaus Division of Medical Image Computing Heidelberg Germany Department of Biomedical Engineering Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic University hospital Ostrava Department of Deputy director for science research and education Czech Republic Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany NCT Heidelberg A partnership between DKFZ University Medical Center Heidelberg Germany Medical Faculty Heidelberg University of Heidelberg Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Germany

This study presents an open-source toolkit to address critical challenges in preprocessing data for self-supervised learning (SSL) for 3D medical imaging, focusing on data privacy and computational efficiency. The toolkit comprises two main components: a segmentation network that delineates foreground regions to optimize data sampling and thus reduce training time, and a segmentation network that identifies anonymized regions, preventing erroneous supervision in reconstructionbased SSL methods. Experimental results demonstrate high robustness, with mean Dice scores exceeding 98.5 across all anonymization methods and surpassing 99.5 for foreground segmentation tasks, highlighting the toolkit's efficacy in supporting SSL applications in 3D medical imaging for both CT and MRI images. The weights and code is available at https://***/MIC-DKFZ/Foreground-and- Anonymization-Area-Segmentation. © 2025, CC BY.

关键词： Self-supervised learning