NSTL国家科技图书文献中心

1. A Gradient-Based Approach to Fast and Accurate Head Motion Compensation in Cone-Beam CT NSTL国家科技图书文献中心

Mareike Thies | Fabian Wagner ... - 《IEEE Transactions on Medical Imaging》 - 2025,44(2) - 1098～1109 - 共12页

摘要：Cone-beam computed tomography (CBCT) systems | , with their flexibility, present a promising avenue | for direct point-of-care medical imaging | , particularly in critical scenarios such as acute stroke | assessment. However, the integration of CBCT into clinical

关键词： Image reconstruction | Measurement | Computed tomography | Optimization | Motion estimation | Motion compensation | Geometry | Estimation | Stroke (medical condition) | Motion measurement

2. IGU-Aug: Information-Guided Unsupervised Augmentation and Pixel-Wise Contrastive Learning for Medical Image Analysis NSTL国家科技图书文献中心

Quan Quan | Qingsong Yao ... - 《IEEE Transactions on Medical Imaging》 - 2025,44(1) - 154～164 - 共11页

摘要：Contrastive learning (CL) is a form of self | -supervised learning and has been widely used for various | tasks. Different from widely studied instance-level | contrastive learning, pixel-wise contrastive learning mainly | helps with pixel-wise dense prediction tasks. The

关键词： Contrastive learning | Task analysis | Data augmentation | Semantics | Training | Feature extraction | Image segmentation

3. Multi-Organ Foundation Model for Universal Ultrasound Image Segmentation With Task Prompt and Anatomical Prior NSTL国家科技图书文献中心

Haobo Chen | Yehua Cai ... - 《IEEE Transactions on Medical Imaging》 - 2025,44(2) - 1005～1018 - 共14页

摘要：Semantic segmentation of ultrasound (US | ) images with deep learning has played a crucial role in | computer-aided disease screening, diagnosis and prognosis | . However, due to the scarcity of US images and small | field of view, resulting segmentation models are

关键词： Image segmentation | Anatomical structure | Ultrasonic imaging | Imaging | Computed tomography | Correlation | Magnetic resonance imaging | Probes | Hospitals | Deep learning

4. Multi-Modal Federated Learning for Cancer Staging Over Non-IID Datasets With Unbalanced Modalities NSTL国家科技图书文献中心

Kasra Borazjani | Naji Khosravan ... - 《IEEE Transactions on Medical Imaging》 - 2025,44(1) - 556～573 - 共18页

摘要：The use of machine learning (ML) for cancer | staging through medical image analysis has gained | substantial interest across medical disciplines. When | accompanied by the innovative federated learning (FL | ) framework, ML techniques can further overcome privacy

关键词： Data models | Cancer | Training | Distributed databases | Biomedical imaging | Federated learning | Data privacy

5. Learning With Explicit Shape Priors for Medical Image Segmentation NSTL国家科技图书文献中心

Xin You | Junjun He ... - 《IEEE Transactions on Medical Imaging》 - 2025,44(2) - 927～940 - 共14页

摘要：Medical image segmentation is a fundamental | task for medical image analysis and surgical planning | . In recent years, UNet-based networks have prevailed | in the field of medical image segmentation. However | , convolutional neural networks (CNNs) suffer from limited

关键词： Shape | Image segmentation | Training | Prototypes | Medical diagnostic imaging | Gaussian distribution | Feature extraction | Transforms | Transformers | Head

6. Self-Supervised Representation Distribution Learning for Reliable Data Augmentation in Histopathology WSI Classification NSTL国家科技图书文献中心

Kunming Tang | Zhiguo Jiang ... - 《IEEE Transactions on Medical Imaging》 - 2025,44(1) - 462～474 - 共13页

摘要：Multiple instance learning (MIL) based whole | slide image (WSI) classification is often carried out | on the representations of patches extracted from | WSI with a pre-trained patch encoder. The | performance of classification relies on both patch-level

关键词： Data augmentation | Training | Representation learning | Data models | Histopathology | Feature extraction | Supervised learning

7. Generative Adversarial Network With Robust Discriminator Through Multi-Task Learning for Low-Dose CT Denoising NSTL国家科技图书文献中心

Sunggu Kyung | Jongjun Won ... - 《IEEE Transactions on Medical Imaging》 - 2025,44(1) - 499～518 - 共20页

摘要：Reducing the dose of radiation in computed | tomography (CT) is vital to decreasing secondary cancer | risk. However, the use of low-dose CT (LDCT) images | is accompanied by increased noise that can | negatively impact diagnoses. Although numerous deep

关键词： Noise reduction | Computed tomography | Biomedical imaging | Generators | Task analysis | Image restoration | Multitasking

8. CQformer: Learning Dynamics Across Slices in Medical Image Segmentation NSTL国家科技图书文献中心

Shengjie Zhang | Xin Shen ... - 《IEEE Transactions on Medical Imaging》 - 2025,44(2) - 1043～1057 - 共15页

摘要：Prevalent studies on deep learning-based 3D | medical image segmentation capture the continuous | variation across 2D slices mainly via convolution | , Transformer, inter-slice interaction, and time series models | . In this work, via modeling this variation by an

关键词： Image segmentation | Transformers | Biomedical imaging | Three-dimensional displays | Time series analysis | Head | Convolution | Shape | Feature extraction | Decoding

9. ConvexAdam: Self-Configuring Dual-Optimization-Based 3D Multitask Medical Image Registration NSTL国家科技图书文献中心

Hanna Siebert | Christoph Großbröhme...... - 《IEEE Transactions on Medical Imaging》 - 2025,44(2) - 738～748 - 共11页

摘要：Registration of medical image data requires | methods that can align anatomical structures precisely | while applying smooth and plausible transformations | . Ideally, these methods should furthermore operate | quickly and apply to a wide variety of tasks. Deep

关键词： Optimization | Feature extraction | Image registration | Deformation | Biomedical imaging | Correlation | Costs

10. LOQUAT: Low-Rank Quaternion Reconstruction for Photon-Counting CT NSTL国家科技图书文献中心

Zefan Lin | Guotao Quan ... - 《IEEE Transactions on Medical Imaging》 - 2025,44(2) - 668～684 - 共17页

摘要：Photon-counting computed tomography (PCCT) may | dramatically benefit clinical practice due to its versatility | such as dose reduction and material characterization | . However, the limited number of photons detected in each | individual energy bin can induce severe noise contamination

摘要：Cone-beam computed tomography (CBCT) systems | , with their flexibility, present a promising avenue | for direct point-of-care medical imaging | , particularly in critical scenarios such as acute stroke | assessment. However, the integration of CBCT into clinical

关键词： Image reconstruction | Measurement | Computed tomography | Optimization | Motion estimation | Motion compensation | Geometry | Estimation | Stroke (medical condition) | Motion measurement

摘要：Contrastive learning (CL) is a form of self | -supervised learning and has been widely used for various | tasks. Different from widely studied instance-level | contrastive learning, pixel-wise contrastive learning mainly | helps with pixel-wise dense prediction tasks. The

关键词： Contrastive learning | Task analysis | Data augmentation | Semantics | Training | Feature extraction | Image segmentation

摘要：Semantic segmentation of ultrasound (US | ) images with deep learning has played a crucial role in | computer-aided disease screening, diagnosis and prognosis | . However, due to the scarcity of US images and small | field of view, resulting segmentation models are

关键词： Image segmentation | Anatomical structure | Ultrasonic imaging | Imaging | Computed tomography | Correlation | Magnetic resonance imaging | Probes | Hospitals | Deep learning

摘要：The use of machine learning (ML) for cancer | staging through medical image analysis has gained | substantial interest across medical disciplines. When | accompanied by the innovative federated learning (FL | ) framework, ML techniques can further overcome privacy

关键词： Data models | Cancer | Training | Distributed databases | Biomedical imaging | Federated learning | Data privacy

摘要：Medical image segmentation is a fundamental | task for medical image analysis and surgical planning | . In recent years, UNet-based networks have prevailed | in the field of medical image segmentation. However | , convolutional neural networks (CNNs) suffer from limited

关键词： Shape | Image segmentation | Training | Prototypes | Medical diagnostic imaging | Gaussian distribution | Feature extraction | Transforms | Transformers | Head

摘要：Multiple instance learning (MIL) based whole | slide image (WSI) classification is often carried out | on the representations of patches extracted from | WSI with a pre-trained patch encoder. The | performance of classification relies on both patch-level

关键词： Data augmentation | Training | Representation learning | Data models | Histopathology | Feature extraction | Supervised learning

摘要：Reducing the dose of radiation in computed | tomography (CT) is vital to decreasing secondary cancer | risk. However, the use of low-dose CT (LDCT) images | is accompanied by increased noise that can | negatively impact diagnoses. Although numerous deep

关键词： Noise reduction | Computed tomography | Biomedical imaging | Generators | Task analysis | Image restoration | Multitasking

摘要：Prevalent studies on deep learning-based 3D | medical image segmentation capture the continuous | variation across 2D slices mainly via convolution | , Transformer, inter-slice interaction, and time series models | . In this work, via modeling this variation by an

关键词： Image segmentation | Transformers | Biomedical imaging | Three-dimensional displays | Time series analysis | Head | Convolution | Shape | Feature extraction | Decoding

摘要：Registration of medical image data requires | methods that can align anatomical structures precisely | while applying smooth and plausible transformations | . Ideally, these methods should furthermore operate | quickly and apply to a wide variety of tasks. Deep

关键词： Optimization | Feature extraction | Image registration | Deformation | Biomedical imaging | Correlation | Costs

摘要：Photon-counting computed tomography (PCCT) may | dramatically benefit clinical practice due to its versatility | such as dose reduction and material characterization | . However, the limited number of photons detected in each | individual energy bin can induce severe noise contamination

关键词： Quaternions | Three-dimensional displays | Tensors | Image reconstruction | Arrays | Computed tomography | Photonics

4008-161-200 800-990-8900

国家科技图书文献中心