Query：
学者姓名：杨明静
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
Background/Objectives: The morphological characteristics of breast tumors play a crucial role in the preliminary diagnosis of breast cancer. However, malignant tumors often exhibit rough, irregular edges and unclear, boundaries in ultrasound images. Additionally, variations in tumor size, location, and shape further complicate the accurate segmentation of breast tumors from ultrasound images. Methods: For these difficulties, this paper introduces a breast ultrasound tumor segmentation network comprising a multi-scale feature acquisition (MFA) module and a multi-input edge supplement (MES) module. The MFA module effectively incorporates dilated convolutions of various sizes in a serial-parallel fashion to capture tumor features at diverse scales. Then, the MES module is employed to enhance the output of each decoder layer by supplementing edge information. This process aims to improve the overall integrity of tumor boundaries, contributing to more refined segmentation results. Results: The mean Dice (mDice), Pixel Accuracy (PA), Intersection over Union (IoU), Recall, and Hausdorff Distance (HD) of this method for the publicly available breast ultrasound image (BUSI) dataset were 79.43%, 96.84%, 83.00%, 87.17%, and 19.71 mm, respectively, and for the dataset of Fujian Cancer Hospital, 90.45%, 97.55%, 90.08%, 93.72%, and 11.02 mm, respectively. In the BUSI dataset, compared to the original UNet, the Dice for malignant tumors increased by 14.59%, and the HD decreased by 17.13 mm. Conclusions: Our method is capable of accurately segmenting breast tumor ultrasound images, which provides very valuable edge information for subsequent diagnosis of breast cancer. The experimental results show that our method has made substantial progress in improving accuracy.
Keyword ：
breast cancer breast cancer deep learning deep learning multi-scale feature fusion multi-scale feature fusion segmentation segmentation ultrasound image ultrasound image
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Pan, Lin , Tang, Mengshi , Chen, Xin et al. M2UNet: Multi-Scale Feature Acquisition and Multi-Input Edge Supplement Based on UNet for Efficient Segmentation of Breast Tumor in Ultrasound Images [J]. | DIAGNOSTICS , 2025 , 15 (8) . |
| MLA | Pan, Lin et al. "M2UNet: Multi-Scale Feature Acquisition and Multi-Input Edge Supplement Based on UNet for Efficient Segmentation of Breast Tumor in Ultrasound Images" . | DIAGNOSTICS 15 . 8 (2025) . |
| APA | Pan, Lin , Tang, Mengshi , Chen, Xin , Du, Zhongshi , Huang, Danfeng , Yang, Mingjing et al. M2UNet: Multi-Scale Feature Acquisition and Multi-Input Edge Supplement Based on UNet for Efficient Segmentation of Breast Tumor in Ultrasound Images . | DIAGNOSTICS , 2025 , 15 (8) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Myocardial pathology segmentation (MyoPS) is essential for the diagnosis, treatment, and prognosis of myocardial infarction (MI). Recent deep learning MyoPS models have shown promising performance on independent identically distributed data. However, due to the domain shift caused by multi-center data, many methods often fail to generalize to unseen data. In this work, we propose a novel domain generalization framework (SMCANet) for MyoPS, which leverages data statistics (mean and standard deviation) modeling (DSM) and feature covariance alignment (FCA) during training to learn domain-invariant information. Specifically, DSM first models the statistical information of the data images and then performs perturbation-based random sampling to enhance the diversity of data representations. FCA reduces feature discrepancies across different distributions while preserving domain content information through the use of covariance matching loss (CML) and cross-covariance loss (CCL). Experiments on cross-domain MyoPS datasets from CARE2024 MyoPS++ challenge demonstrate that our framework can achieve promising generalization performance without altering the network architecture or employing complex data augmentation networks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
Keyword ：
COVID-19 COVID-19
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Dong, Jinwei , Wan, Kaiwen , Lin, Bogen et al. Domain Generalized Myocardial Pathology Segmentation via Data Statistics Modeling and Feature Covariance Alignment [C] . 2025 : 46-54 . |
| MLA | Dong, Jinwei et al. "Domain Generalized Myocardial Pathology Segmentation via Data Statistics Modeling and Feature Covariance Alignment" . (2025) : 46-54 . |
| APA | Dong, Jinwei , Wan, Kaiwen , Lin, Bogen , Yang, Mingjing . Domain Generalized Myocardial Pathology Segmentation via Data Statistics Modeling and Feature Covariance Alignment . (2025) : 46-54 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Cardiovascular diseases are a leading cause of mortality worldwide, necessitating accurate segmentation of cardiac structures from 3D CT and MR images for effective diagnosis and treatment planning. Manual segmentation is time-consuming, labor-intensive, and challenging due to the complexity of cardiac anatomy structures. General CNNs, while effective, often struggle to generalize across different imaging domains. To address these issues, we developed a PPM-UNet, which integrates a probabilistic perturbation module (PPM) into the traditional U-Net architecture. Here, the PPM is introduced to control randomness during training, enhancing the model’s robustness and improving its performance across different imaging domains. Furthermore, the PPM is lightweight and easy to implement, making it a practical addition to existing network architectures for domain generalization tasks in medical imaging. Evaluated on the WHS++ dataset, our method demonstrates superior performance in segmenting cardiac structures, particularly in unseen domains, as evidenced by improved Dice Similarity Coefficient, Precision, Sensitivity, and Hausdorff Distance metrics. In addition to its performance benefits, the proposed module requires minimal computational overhead, making it practical for real-world clinical applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
Keyword ：
Cardiology Cardiology Computerized tomography Computerized tomography Diffusion tensor imaging Diffusion tensor imaging Image segmentation Image segmentation Intelligent systems Intelligent systems Magnetic resonance imaging Magnetic resonance imaging
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Bogen , Dong, Jinwei , Zheng, Yaqiong et al. Enhancing Domain Generalization for Cardiac Image Segmentation with Probabilistic Perturbation [C] . 2025 : 1-12 . |
| MLA | Lin, Bogen et al. "Enhancing Domain Generalization for Cardiac Image Segmentation with Probabilistic Perturbation" . (2025) : 1-12 . |
| APA | Lin, Bogen , Dong, Jinwei , Zheng, Yaqiong , Xiang, Yihan , Yang, Mingjing . Enhancing Domain Generalization for Cardiac Image Segmentation with Probabilistic Perturbation . (2025) : 1-12 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Accurate segmentation of myocardial pathology, including scar and edema, from magnetic resonance images (MRI) is of significant clinical importance for diagnosing, planning treatment, and assessing prognosis in cardiovascular diseases. Multi-sequence cardiac magnetic resonance images provide additional information for pathological segmentation, while ventricular blood pool regions offer positional anatomical priors for identifying scar and edema. Therefore, we propose a multi-task framework based on SimAM-UNet, where SimAM generates feature weights to better focus on modality-specific features for the segmentation of myocardial pathology using multi-sequence cardiac magnetic resonance images. The first task involves segmenting and extracting features of the myocardium and blood pool, which are relatively easy to obtain. The second task focuses on segmenting scars and edema by integrating positional feature constraints derived from the myocardium and blood pool. To address the multi-center data problem encountered in real-world data, we incorporate a data augmentation pipeline that simulates the generation of data samples from different centers, enhancing the domain generalization of our method. Our proposed method was evaluated on the MyoPS++ track of the CARE2024 Challenge, and the experimental results demonstrated the effectiveness of our multi-task framework for myocardial pathological segmentation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
Keyword ：
Bioinformatics Bioinformatics Cardiology Cardiology Diagnosis Diagnosis Image segmentation Image segmentation Nuclear magnetic resonance Nuclear magnetic resonance Pathology Pathology
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Yilin , Yang, Xiao , Liu, Yongli et al. Multi-task Framework for Myocardial Pathological Segmentation on Multi-sequence Cardiac Magnetic Resonance [C] . 2025 : 116-125 . |
| MLA | Wu, Yilin et al. "Multi-task Framework for Myocardial Pathological Segmentation on Multi-sequence Cardiac Magnetic Resonance" . (2025) : 116-125 . |
| APA | Wu, Yilin , Yang, Xiao , Liu, Yongli , Zheng, Jiahao , Yang, Mingjing . Multi-task Framework for Myocardial Pathological Segmentation on Multi-sequence Cardiac Magnetic Resonance . (2025) : 116-125 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Myocardial infarction (MI) is a leading cause of death and disability, underscoring the critical importance of accurate and effective assessment of myocardial viability. However, existing CNNs are insufficient for extracting long-range contexts information, while the computational cost of Transformer architectures is prohibitively high, making segmentation of scars and edema in multi-center cardiac MRI (CMR) sequences particularly challenging. To address this issue, we propose Mamaba Enhanced UNet (ME-UNet), a deep learning architecture that integrates the advantages of the U-Net model with residual mechanisms and state space models (SSMs) for the segmentation of myocardial scars and edema. The advantage of ME-UNet lies in its Vision Mamba block, which significantly enhances the model’s ability to extract global information. Additionally, Enhanced 3D residual block (E3DR) further enhances and consolidates the extraction of local and spatial information. Experimental results demonstrate that ME-UNet exhibits exceptional performance on the MyoPS challenge dataset, effectively segmenting myocardial scars and edema, thereby validating the efficacy of our framework. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
Keyword ：
Cardiography Cardiography Deep learning Deep learning Image enhancement Image enhancement Image segmentation Image segmentation Magnetic resonance imaging Magnetic resonance imaging Medical imaging Medical imaging State space methods State space methods
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhu, Zhanpeng , Lin, Yuqi , Yang, Mingjing . ME-UNet: Enhancing Mamba for Myocardial Pathology Segmentation in Multi-center Multi-sequence CMR Images [C] . 2025 : 66-76 . |
| MLA | Zhu, Zhanpeng et al. "ME-UNet: Enhancing Mamba for Myocardial Pathology Segmentation in Multi-center Multi-sequence CMR Images" . (2025) : 66-76 . |
| APA | Zhu, Zhanpeng , Lin, Yuqi , Yang, Mingjing . ME-UNet: Enhancing Mamba for Myocardial Pathology Segmentation in Multi-center Multi-sequence CMR Images . (2025) : 66-76 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Myocardium scar segmentation is essential for clinical diagnosis and prognosis for cardiac vascular diseases. Late gadolinium enhancement (LGE) imaging technology has been widely utilized to visualize left atrial and ventricular scars. However, automatic scar segmentation remains challenging due to the imbalance between scar and background and the variation in scar sizes. To address these challenges, we introduce an innovative network, i.e., LGENet, for scar segmentation. LGENet disentangles anatomy and pathology features from LGE images. Note that inherent spatial relationships exist between the myocardium and scarring regions. We proposed a boundary attention module to allow the scar segmentation conditioned on anatomical boundary features, which could mitigate the imbalance problem. Meanwhile, LGENet can predict scar regions across multiple scales with a multi-depth decision module, addressing the scar size variation issue. In our experiments, we thoroughly evaluated the performance of LGENet using LAScarQS 2022 and EMIDEC datasets. The results demonstrate that LGENet achieved promising performance for cardiac scar segmentation.
Keyword ：
Adaptive decision Adaptive decision Boundary attention Boundary attention Multi-depth network Multi-depth network Scar segmentation Scar segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yang, Mingjing , Yang, Kangwen , Wu, Mengjun et al. LGENet: disentangle anatomy and pathology features for late gadolinium enhancement image segmentation [J]. | MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING , 2025 , 63 (8) : 2311-2323 . |
| MLA | Yang, Mingjing et al. "LGENet: disentangle anatomy and pathology features for late gadolinium enhancement image segmentation" . | MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 63 . 8 (2025) : 2311-2323 . |
| APA | Yang, Mingjing , Yang, Kangwen , Wu, Mengjun , Huang, Liqin , Ding, Wangbin , Pan, Lin et al. LGENet: disentangle anatomy and pathology features for late gadolinium enhancement image segmentation . | MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING , 2025 , 63 (8) , 2311-2323 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Pedestrian Attribute Recognition (PAR) involves identifying the attributes of individuals in person images. Existing PAR methods typically rely on CNNs as the backbone network to extract pedestrian features. However, CNNs process only one adjacent region at a time, leading to the loss of long-range inter-relations between different attribute-specific regions. To address this limitation, we leverage the Vision Transformer (ViT) instead of CNNs as the backbone for PAR, aiming to model long-range relations and extract more robust features. However, PAR suffers from an inherent attribute imbalance issue, causing ViT to naturally focus more on attributes that appear frequently in the training set and ignore some pedestrian attributes that appear less. The native features extracted by ViT are not able to tolerate the imbalance attribute distribution issue. To tackle this issue, we propose two novel components: the Selective Feature Activation Method (SFAM) and the Orthogonal Feature Activation Loss. SFAM smartly suppresses the more informative attribute-specific features, compelling the PAR model to capture discriminative features from regions that are easily overlooked. The proposed loss enforces an orthogonal constraint on the original feature extracted by ViT and the suppressed features from SFAM, promoting the complementarity of features in space. We conduct experiments on several benchmark PAR datasets, including PETA, PA100K, RAPv1, and RAPv2, demonstrating the effectiveness of our method. Specifically, our method outperforms existing state-of-the-art approaches by GRL, IAA-Caps, ALM, and SSC in terms of mA on the four datasets, respectively. Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Keyword ：
Artificial intelligence Artificial intelligence Chemical activation Chemical activation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Junyi , Huang, Yan , Gao, Min et al. Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition [C] . 2024 : 6039-6047 . |
| MLA | Wu, Junyi et al. "Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition" . (2024) : 6039-6047 . |
| APA | Wu, Junyi , Huang, Yan , Gao, Min , Niu, Yuzhen , Yang, Mingjing , Gao, Zhipeng et al. Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition . (2024) : 6039-6047 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Accurate and efficient segmentation of multiple abdominal organs from medical images is crucial for clinical applications such as disease diagnosis and treatment planning. In this paper, we propose a novel approach for abdominal organ segmentation using the U-Net architecture. Our method addresses the challenges posed by anatomical variations and the proximity of organs in the abdominal region. To improve the segmentation accuracy, we introduce an attention mechanism into the U-Net architecture. This mechanism allows the network to focus on salient regions and suppress irrelevant background regions, enhancing the overall segmentation performance. Additionally, we incorporate 3D information by connecting three consecutive slices as 3-dimensional inputs. This enables us to exploit the spatial context across the slices while minimizing the increase in GPU memory usage. We evaluate our proposed method on the MICCAI FLARE 2023 validation dataset, the mean DSC is 0.3683 and the mean NSD is 0.3668.
Keyword ：
attention mechanism attention mechanism organ segmentation organ segmentation U-Net U-Net
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lei, Ruixiang , Yang, Mingjing . 2.5D U-Net for Abdominal Multi-organ Segmentation [J]. | FAST, LOW-RESOURCE, AND ACCURATE ORGAN AND PAN-CANCER SEGMENTATION IN ABDOMEN CT, FLARE 2023 , 2024 , 14544 : 76-83 . |
| MLA | Lei, Ruixiang et al. "2.5D U-Net for Abdominal Multi-organ Segmentation" . | FAST, LOW-RESOURCE, AND ACCURATE ORGAN AND PAN-CANCER SEGMENTATION IN ABDOMEN CT, FLARE 2023 14544 (2024) : 76-83 . |
| APA | Lei, Ruixiang , Yang, Mingjing . 2.5D U-Net for Abdominal Multi-organ Segmentation . | FAST, LOW-RESOURCE, AND ACCURATE ORGAN AND PAN-CANCER SEGMENTATION IN ABDOMEN CT, FLARE 2023 , 2024 , 14544 , 76-83 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Pedestrian Attribute Recognition (PAR) involves identifying the attributes of individuals in person images. Existing PAR methods typically rely on CNNs as the backbone network to extract pedestrian features. However, CNNs process only one adjacent region at a time, leading to the loss of long-range inter-relations between different attribute-specific regions. To address this limitation, we leverage the Vision Transformer (ViT) instead of CNNs as the backbone for PAR, aiming to model long-range relations and extract more robust features. However, PAR suffers from an inherent attribute imbalance issue, causing ViT to naturally focus more on attributes that appear frequently in the training set and ignore some pedestrian attributes that appear less. The native features extracted by ViT are not able to tolerate the imbalance attribute distribution issue. To tackle this issue, we propose two novel components: the Selective Feature Activation Method (SFAM) and the Orthogonal Feature Activation Loss. SFAM smartly suppresses the more informative attribute-specific features, compelling the PAR model to capture discriminative features from regions that are easily overlooked. The proposed loss enforces an orthogonal constraint on the original feature extracted by ViT and the suppressed features from SFAM, promoting the complementarity of features in space. We conduct experiments on several benchmark PAR datasets, including PETA, PA100K, RAPv1, and RAPv2, demonstrating the effectiveness of our method. Specifically, our method outperforms existing state-of-the-art approaches by GRL, IAACaps, ALM, and SSC in terms of mA on the four datasets, respectively.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Junyi , Huang, Yan , Gao, Min et al. Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition [J]. | THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 6 , 2024 : 6039-6047 . |
| MLA | Wu, Junyi et al. "Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition" . | THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 6 (2024) : 6039-6047 . |
| APA | Wu, Junyi , Huang, Yan , Gao, Min , Niu, Yuzhen , Yang, Mingjing , Gao, Zhipeng et al. Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition . | THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 6 , 2024 , 6039-6047 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Unsupervised domain adaptation(UDA) aims to mitigate the performance drop of models tested on the target domain, due to the domain shift from the target to sources. Most UDA segmentation methods focus on the scenario of solely single source domain. However, in practical situations data with gold standard could be available from multiple sources (domains), and the multi-source training data could provide more information for knowledge transfer. How to utilize them to achieve better domain adaptation yet remains to be further explored. This work investigates multi-source UDA and proposes a new framework for medical image segmentation. Firstly, we employ a multi-level adversarial learning scheme to adapt features at different levels between each of the source domains and the target, to improve the segmentation performance. Then, we propose a multi-model consistency loss to transfer the learned multi-source knowledge to the target domain simultaneously. Finally, we validated the proposed framework on two applications, i.e., multi-modality cardiac segmentation and cross-modality liver segmentation. The results showed our method delivered promising performance and compared favorably to state-of-the-art approaches.
Keyword ：
Domain adaptation Domain adaptation medical image segmentation medical image segmentation multi-source multi-source unsupervised learning unsupervised learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Pei, Chenhao , Wu, Fuping , Yang, Mingjing et al. Multi-Source Domain Adaptation for Medical Image Segmentation [J]. | IEEE TRANSACTIONS ON MEDICAL IMAGING , 2024 , 43 (4) : 1640-1651 . |
| MLA | Pei, Chenhao et al. "Multi-Source Domain Adaptation for Medical Image Segmentation" . | IEEE TRANSACTIONS ON MEDICAL IMAGING 43 . 4 (2024) : 1640-1651 . |
| APA | Pei, Chenhao , Wu, Fuping , Yang, Mingjing , Pan, Lin , Ding, Wangbin , Dong, Jinwei et al. Multi-Source Domain Adaptation for Medical Image Segmentation . | IEEE TRANSACTIONS ON MEDICAL IMAGING , 2024 , 43 (4) , 1640-1651 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
