相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Biotechnology & Applied Microbiology
Guoya Dong et al.
Summary: This paper proposes a non-rigid 2D/3D registration method based on deep learning with orthogonal angle projections, which can achieve alignment quickly in a short time. The method is tested with lungs (with and without tumors) and phantom data, and the results show Dice and normalized cross-correlations greater than 0.97 and 0.92, respectively, with a registration time of less than 1.2 seconds. The proposed model also demonstrates the ability to track lung tumors, highlighting the clinical potential of the method.
BIOENGINEERING-BASEL
(2023)
Article
Engineering, Biomedical
Fei Zhu et al.
Summary: This study proposes a similarity attention-based convolutional neural network (CNN) for accurate and robust three-dimensional medical image registration. The proposed method uses a similarity-based local attention model to build a displacement searching space and focuses on high similarity spatial correspondences. Experimental results demonstrate its superior performance compared to state-of-the-art methods for various medical image registration applications.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Biomedical
Gangcheng Cai et al.
Summary: In this paper, a deformable registration network (DR-Net) and a multi-scale cascading strategy are proposed for the registration of largely deformed 3D medical images. The DR-Net is constructed with a U-shaped convolutional neural network, a pyramidal input module, a light weighted sequential Inception module, and an SCAM convolutional attention module. The multi-scale cascading strategy integrates the deformation field information within and between sub-networks at different scales to synthesize the cascaded deformation fields.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Interdisciplinary Applications
B. Aubert et al.
Summary: This paper investigates the robustness and accuracy of intensity-based 3D/2D registration, highlighting the importance of image correspondences. It is found that converting X-ray images into DRR images can improve registration results, especially with the use of GAN-based cross-modality image-to-images translation. The proposed method is applied to precise registration of deformable vertebral models to biplanar radiographs, demonstrating its effectiveness and enhancement.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Engineering, Biomedical
Kaicong Sun et al.
Summary: This article introduces a lightweight resolution enhancement module (REM) based on CNN, which can be used to improve spatial resolution and registration accuracy in image registration. Experimental results show that REM not only improves registration accuracy, but also reconstructs resolution enhanced images that can be used for subsequent diagnosis.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Review
Engineering, Biomedical
Hanguang Xiao et al.
Summary: This study summarizes the segmentation methods based on Transformer in medical images of abdominal organs, heart, brain, and lungs in the past two years. The findings show that Unet-based Transformer models are preferred by researchers, and placing the Transformer structure in the encoder improves segmentation performance. However, there is a lack of related studies on lungs, indicating a new direction for future research.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Information Systems
Jing Hu et al.
Summary: This study proposes a deep reinforcement learning method for image registration, which explicitly models the step-wise nature of the human registration process. The approach outperforms other methods and achieves state-of-the-art performance in multi-modal medical image registration.
Article
Biology
Wei Wang et al.
Summary: Since 2019, the COVID-19 pandemic has posed a significant threat to the global economy and human health. Deep learning-based computer-aided diagnosis models can effectively alleviate the challenges of diagnosing COVID-19 due to limited healthcare resources. To overcome the time-consuming and unstable nature of traditional hyperparameter tuning methods, we propose a Particle Swarm Optimization-guided Self-Tuning Convolution Neural Network (PSTCNN) that automatically adjusts the model's hyperparameters.
Article
Engineering, Biomedical
Yiwei Yang et al.
Summary: The study introduces a novel structure-contextual representations approach based on 3D high-resolution network for segmentation of OARs and CTV of rectal cancer, showing superior performance. By designing a structure-contextual representation module, the accuracy of segmentation is significantly improved.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Chemistry, Multidisciplinary
Shan Liu et al.
Summary: Image-guided surgery (IGS) reduces tissue damage and improves accuracy and targeting of lesions by increasing visual field. This experiment studies a 2D/3D medical image registration algorithm based on gray level and introduces a new similarity measure and a multiresolution strategy to enhance registration accuracy and efficiency.
APPLIED SCIENCES-BASEL
(2022)
Article
Automation & Control Systems
Wei Wang et al.
Summary: With the global COVID-19 pandemic, the fast diagnosis and monitoring of the disease have become crucial challenges. This research presents a deep learning model called WE-SAJ, which utilizes artificial intelligence techniques to classify CT images and distinguish infected patients from healthy populations. The experiments show the superior performance of the model and the effectiveness of the Self-adaptive Jaya algorithm in medical image classification tasks.
SYSTEMS SCIENCE & CONTROL ENGINEERING
(2022)
Article
Biology
Yuanbo He et al.
Summary: This article presents a novel nonfinite-modality data augmentation method for brain image registration. By collecting available whole-brain segmentation masks and generating diverse nonfinite-modality brain images, as well as introducing intensity-level reconstruction loss and structure-level reconstruction loss to obtain realistic ground truth deformations, the authors created a new Synthetic Nonfinite-Modality Brain Image Dataset. Experiments showed that pre-training on this dataset improved the accuracy of registration.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Junyu Chen et al.
Summary: Convolutional neural networks (ConvNets) have been a major focus in medical image analysis, but their performance is limited by a lack of consideration for long-range spatial relationships in images. Vision Transformer architectures have recently been proposed to address this issue and have shown state-of-the-art performances in medical imaging applications. In this paper, the researchers propose a hybrid Transformer-ConvNet model called TransMorph for volumetric medical image registration. The proposed model improves the performance significantly compared to existing registration methods and Transformer architectures, demonstrating the effectiveness of Transformers for medical image registration.
MEDICAL IMAGE ANALYSIS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhipeng Ding et al.
Summary: Atlas building and image registration are important tasks in medical image analysis. This study explores the use of a convolutional neural network (CNN) to jointly predict the atlas and a stationary velocity field (SVF) parameterization for diffeomorphic image registration with respect to the atlas, achieving better performance than other state-of-the-art image registration algorithms.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Medical Laboratory Technology
Benjamin Balluff et al.
Summary: Mass spectrometry imaging (MSI) is widely used in clinical research, requiring accurate image registration to align data from different imaging modalities. As technology advances, the accuracy and precision of image registration need to be increased accordingly.
JOURNAL OF MASS SPECTROMETRY AND ADVANCES IN THE CLINICAL LAB
(2022)
Article
Computer Science, Artificial Intelligence
Max Blendowski et al.
Summary: Deep learning methods have recently achieved good performance in medical image registration, with significant improvements possible by disentangling feature learning and deformation estimation. The proposed method shows promising results in multi-modal registration and can even handle small and weakly-labeled training datasets.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Interdisciplinary Applications
T. Collins et al.
Summary: The system presented in the research successfully performed markerless real-time registration and augmented reality of a mobile human organ with monocular laparoscopes in the operating room. The system addresses the challenges posed by the weakly-textured, highly mobile nature of the uterus through novel and robust solutions.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Computer Science, Interdisciplinary Applications
Haikun Qi et al.
Summary: A novel unsupervised deep learning-based strategy, RespME-net, is proposed for fast estimation of inter-bin 3D non-rigid respiratory motion fields in free-breathing 3D coronary magnetic resonance angiography. The network can predict 3D non-rigid motion fields with subpixel accuracy within approximately 10 seconds, being about 20 times faster than a GPU-implemented state-of-the-art non-rigid registration method.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Review
Green & Sustainable Science & Technology
Xiangbin Liu et al.
Summary: Medical image segmentation based on deep learning has made significant contributions to sustainable medical care, but still faces challenges such as low segmentation accuracy and limited dataset size. Further research is needed to address these issues and improve the technology.
Article
Computer Science, Artificial Intelligence
Yue Zhang et al.
Summary: This paper introduces a deep learning framework that combines multi-atlas registration and level-set for pancreas segmentation from CT volume images. The framework consists of three stages - coarse, fine, and refine - to achieve segmentation. Through testing on three different datasets, the framework demonstrates superior segmentation results with an average Dice score over 82%.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Engineering, Biomedical
You Zhang
Summary: Using a 2D-3D deformable registration technique can suppress distortions and artifacts in CBCT images and reflect up-to-date patient anatomy. The conventional iterative 2D-3D deformable registration algorithm is computationally expensive and time-consuming, but the developed 2D3D-RegNet using convolutional neural networks can address the speed bottleneck.
PHYSICS IN MEDICINE AND BIOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Jun Ma et al.
Summary: This paper provides a comprehensive review of segmentation loss functions in deep learning-based methods and conducts a large-scale analysis, finding that compound loss functions are the most robust. The study results suggest that no single loss function consistently outperforms others across different segmentation tasks.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Liang Qiu et al.
Summary: The study proposes an unsupervised probabilistic model called U-RSNet for concurrent medical image registration and segmentation. By integrating deep learning techniques with Bayesian inference, the segmentation performance has been successfully improved.
Article
Engineering, Electrical & Electronic
Fei Zhu et al.
Summary: This paper proposes a novel Laplacian Eigenmaps based deep learning network for 2D medical image registration, which aims to extract intrinsic features of different modal medical images and construct a learning based data-adaptive descriptor for structural representations. The experimental results indicate that this method can achieve visually better registered results and higher registration accuracy than several state-of-the-art registration methods.
Article
Computer Science, Information Systems
Shaoya Guan et al.
Summary: Transfer learning was used to address the challenge of large differences in vascular structure deformation among different patients, optimizing frozen weights in the convolutional layers to find the best common feature extractors. Research indicated that the nonrigid registration model performed better on deformable cardiovascular image registration after transfer learning.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yucheng Shu et al.
Summary: Medical image registration has greatly advanced with the emergence of modern deep neural networks, allowing for task-specific feature learning and efficient registration results. However, large inter-image distortion may affect the stability of existing methods. To address this, an iterative framework based on coarse-to-fine strategies has been introduced, but its relative network independence hinders optimal reinforcement of image features.
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT IV
(2021)
Article
Computer Science, Information Systems
Shengyu Zhao et al.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Tony C. W. Mok et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Interdisciplinary Applications
Guha Balakrishnan et al.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2019)
Article
Computer Science, Information Systems
Shaoya Guan et al.
Article
Computer Science, Information Systems
Cai Meng et al.
Article
Computer Science, Hardware & Architecture
Alex Krizhevsky et al.
COMMUNICATIONS OF THE ACM
(2017)
Article
Engineering, Biomedical
Lun Gong et al.
BIOMEDICAL ENGINEERING ONLINE
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Jerome Schmid et al.
COMPUTER VISION - ACCV 2014, PT II
(2015)
Article
Computer Science, Interdisciplinary Applications
Hassan Rivaz et al.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2014)
Article
Biology
Stefanie Demirci et al.
COMPUTERS IN BIOLOGY AND MEDICINE
(2013)
Article
Oncology
Christelle Gendrin et al.
RADIOTHERAPY AND ONCOLOGY
(2012)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jian Wu et al.
Article
Computer Science, Artificial Intelligence
A Khamene et al.
MEDICAL IMAGE ANALYSIS
(2006)
