Peijun Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Peijun Hu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Jingsong Li
College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China
2 shared publications Tianshu Zhou
Research Center for Scientific Data Hub, Zhejiang Lab, Hangzhou, China
2 shared publications- Xueli Bai
Department of Hepatobiliary and Pancreatic Surgery The First Affiliated Hospital, Zhejiang University School of Medicine Hangzhou China
2 shared publications Yan Zhu
Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, China
2 shared publicationsBennett A. Landman
Vanderbilt University
1 shared publication- Chengkai Wu
School of Intelligent Science and Technology, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China
1 shared publication
Latest Publications
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (6) , 5311-5324
Dynamically Enhanced Multi-organ Segmentation Base on Boundary-Aware Partial Label
Accurate multi-organ segmentation of abdominal CT is essential for many clinical applications, yet it often relies on large, fully annotated datasets. However, most available datasets are partially labeled, collected from different medical centers. To address this, we propose BAPLDE-MOSNet, a boundary-aware multi-organ segmentation network that leverages task-guided attention and dynamic feature enhancement modules to handle partially labeled data. BAPLDE-MOSNet integrates an edge prediction auxiliary regression network into the basic segmentation architecture in a multi-task learning manner. In addition, It introduces a boundary correction module by embedding boundary-related edge features into the segmentation task-related feature representation to effectively utilize boundary information to guide more accurate localization and segmentation of abdominal multi-organs. Moreover, a dynamic feature enhancement module is introduced to improve the network's attention to the target area. Our proposed method is rigorously validated on five public datasets (LiTS, KiTS, MSD Pancreas, MSD Spleen and the external BTCV benchmark), achieving state-of-the-art performance with an average DSC of 93.42% and HD95 of 3.635mm. Notably, it exhibits superior generalization on the external BTCV dataset (average DSC of 77.87% and average HD95 of 26.626 mm), outperforming both specialized single-organ networks and existing multi-organ approaches in comprehensive evaluations.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (6) , 5311-5324
Dynamically Enhanced Multi-organ Segmentation Base on Boundary-Aware Partial Label
Accurate multi-organ segmentation of abdominal CT is essential for many clinical applications, yet it often relies on large, fully annotated datasets. However, most available datasets are partially labeled, collected from different medical centers. To address this, we propose BAPLDE-MOSNet, a boundary-aware multi-organ segmentation network that leverages task-guided attention and dynamic feature enhancement modules to handle partially labeled data. BAPLDE-MOSNet integrates an edge prediction auxiliary regression network into the basic segmentation architecture in a multi-task learning manner. In addition, It introduces a boundary correction module by embedding boundary-related edge features into the segmentation task-related feature representation to effectively utilize boundary information to guide more accurate localization and segmentation of abdominal multi-organs. Moreover, a dynamic feature enhancement module is introduced to improve the network's attention to the target area. Our proposed method is rigorously validated on five public datasets (LiTS, KiTS, MSD Pancreas, MSD Spleen and the external BTCV benchmark), achieving state-of-the-art performance with an average DSC of 93.42% and HD95 of 3.635mm. Notably, it exhibits superior generalization on the external BTCV dataset (average DSC of 77.87% and average HD95 of 26.626 mm), outperforming both specialized single-organ networks and existing multi-organ approaches in comprehensive evaluations.
- 15 July 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 111
A Knowledge-Driven Evidence Fusion Network for pancreatic tumor segmentation in CT images
- 15 July 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 111
A Knowledge-Driven Evidence Fusion Network for pancreatic tumor segmentation in CT images
- 2 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (3) , 1588-1599
Prediction of New-Onset Diabetes After Pancreatectomy With Subspace Clustering Based Multi-View Feature Selection
The pancreas plays an important role in glucose metabolism, and developing diabetes or long-term glucose metabolism disturbance may be a prevalent sequela after pancreatectomy. Nevertheless, relative factors of new-onset diabetes after pancreatectomy stay unclear. Radiomics analysis is potential to identify image markers for disease prediction or prognosis. Meanwhile, combination of imaging and electronic medical record (EMR) showed superior performance than imaging or EMR alone in previous studies. One critical step is to identity predictors from high-dimensional features, and it is even more challenging to select and fuse imaging and EMR features. In this work, we develop a radiomics pipeline to assess postoperative new-onset diabetes risk of patients undergoing distal pancreatectomy. Specifically, we extract multiscale image features with 3D wavelet transformation, and include patients' characteristics, body composition and pancreas volume information as clinical features. Then, we propose a multi-view subspace clustering guided feature selection method (MSCUFS) for the selection and fusion of image and clinical features. Finally, a prediction model is constructed with classical machine learning classifier. Experimental results on an established distal pancreatectomy cohort showed that the SVM model with combined imaging and EMR features demonstrated good discrimination, with an AUC value of 0.824, which improved the model with image features alone by 0.037 AUC. Compared with state-of-the-art feature selection methods, the proposed MSCUFS has superior performance in fusing image and clinical features.
- 2 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (3) , 1588-1599
Prediction of New-Onset Diabetes After Pancreatectomy With Subspace Clustering Based Multi-View Feature Selection
The pancreas plays an important role in glucose metabolism, and developing diabetes or long-term glucose metabolism disturbance may be a prevalent sequela after pancreatectomy. Nevertheless, relative factors of new-onset diabetes after pancreatectomy stay unclear. Radiomics analysis is potential to identify image markers for disease prediction or prognosis. Meanwhile, combination of imaging and electronic medical record (EMR) showed superior performance than imaging or EMR alone in previous studies. One critical step is to identity predictors from high-dimensional features, and it is even more challenging to select and fuse imaging and EMR features. In this work, we develop a radiomics pipeline to assess postoperative new-onset diabetes risk of patients undergoing distal pancreatectomy. Specifically, we extract multiscale image features with 3D wavelet transformation, and include patients' characteristics, body composition and pancreas volume information as clinical features. Then, we propose a multi-view subspace clustering guided feature selection method (MSCUFS) for the selection and fusion of image and clinical features. Finally, a prediction model is constructed with classical machine learning classifier. Experimental results on an established distal pancreatectomy cohort showed that the SVM model with combined imaging and EMR features demonstrated good discrimination, with an AUC value of 0.824, which improved the model with image features alone by 0.037 AUC. Compared with state-of-the-art feature selection methods, the proposed MSCUFS has superior performance in fusing image and clinical features.
- 10 January 2018
- Published by Springer Nature
- Vol. 10734, 25-35
Automated Characterization of Body Composition and Frailty with Clinically Acquired CT
Quantification of fat and muscle on clinically acquired computed tomography (CT) scans is critical for determination of body composition, a key component of health. Manual tracing has been regarded as the gold standard method of body segmentation; however, manual tracing is time-consuming. Many semi-automated/automated algorithms have been proposed to avoid the manual efforts. Previous efforts largely focused on segmenting two-dimensional cross-sectional images (e.g., at L3/T4 vertebra locations) rather than on the whole-body volume. In this paper, we propose a fully automated three-dimensional (3D) body composition estimation framework for segmenting the muscle and fat from abdominal CT scans. The 3D whole body segmentations are reconstructed from a slice-wise multi-atlas label fusion (MALF) based framework. First, we use a low-dimensional atlas representation to estimate each class for each axial slice. Second, the abdominal wall and psoas muscle are segmented by combining MALF with active shape models and deformable models. Third, skeletal muscle, visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) are measured to assess the areas of muscle and fat tissue. The proposed method was compared to manual segmentation and demonstrated high accuracy. Then, we evaluated the approach on 40 CT scans comparing the new method to a prior atlas-based segmentation method and achieved 0.854, 0.740, 0.887 and 0.933 on Dice similarity index for the skeletal muscle, psoas muscle, VAT and SAT, respectively. Compared with the baseline, our method showed significantly (\(p\,{<}\,0.001\)) higher accuracy on skeletal muscle, VAT and SAT estimation.- 10 January 2018
- Published by Springer Nature
- Vol. 10734, 25-35
Automated Characterization of Body Composition and Frailty with Clinically Acquired CT
Quantification of fat and muscle on clinically acquired computed tomography (CT) scans is critical for determination of body composition, a key component of health. Manual tracing has been regarded as the gold standard method of body segmentation; however, manual tracing is time-consuming. Many semi-automated/automated algorithms have been proposed to avoid the manual efforts. Previous efforts largely focused on segmenting two-dimensional cross-sectional images (e.g., at L3/T4 vertebra locations) rather than on the whole-body volume. In this paper, we propose a fully automated three-dimensional (3D) body composition estimation framework for segmenting the muscle and fat from abdominal CT scans. The 3D whole body segmentations are reconstructed from a slice-wise multi-atlas label fusion (MALF) based framework. First, we use a low-dimensional atlas representation to estimate each class for each axial slice. Second, the abdominal wall and psoas muscle are segmented by combining MALF with active shape models and deformable models. Third, skeletal muscle, visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) are measured to assess the areas of muscle and fat tissue. The proposed method was compared to manual segmentation and demonstrated high accuracy. Then, we evaluated the approach on 40 CT scans comparing the new method to a prior atlas-based segmentation method and achieved 0.854, 0.740, 0.887 and 0.933 on Dice similarity index for the skeletal muscle, psoas muscle, VAT and SAT, respectively. Compared with the baseline, our method showed significantly (\(p\,{<}\,0.001\)) higher accuracy on skeletal muscle, VAT and SAT estimation.