Article
Multidisciplinary Sciences
Philipp Nolte, Marcel Brettmacher, Chris Johann Groger, Tim Gellhaus, Angelika Svetlove, Arndt F. Schilling, Frauke Alves, Christoph Russmann, Christian Dullin
Summary: This study presents a novel workflow for the analysis of hard-tissue histology using conventional microCT scans and 3D printed fiducial markers. The workflow allows for the analysis of 3D structural features and directs the sectioning process to regions of interest. The registration of 2D histological images into the 3D anatomical context enables the co-registration of morphological analysis and local 3D information obtained from microCT data.
SCIENTIFIC REPORTS
(2023)
Article
Materials Science, Characterization & Testing
Sudhir Kumar Chaudhary, Pankaj Wahi, Prabhat Munshi
Summary: This study proposes a new discretization scheme to reduce the computational and storage burden of algebraic methods. The symmetries of the scheme are utilized to speed up the calculations. The proposed approach is validated through experiments with various models and projection data.
NDT & E INTERNATIONAL
(2023)
Article
Computer Science, Interdisciplinary Applications
B. Aubert, T. Cresson, J. A. de Guise, C. Vazquez
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
Radiology, Nuclear Medicine & Medical Imaging
Fabio D'Isidoro, Christophe Chenes, Stephen J. Ferguson, Jerome Schmid
Summary: Evaluation of accuracy in 2D-3D registration is crucial for research and clinical studies. A new gold standard dataset was introduced for CT-to-X-ray registration of the hip joint, resulting in improved accuracy by considering possible noise anisotropy and including corrupted 3D fiducials in the optimization.
Article
Engineering, Biomedical
Jeroen Van Houtte, Emmanuel Audenaert, Guoyan Zheng, Jan Sijbers
Summary: This paper proposes a deep-learning-based 2D/3D registration method that uses an end-to-end trainable network to regress a dense deformation field, which warps an atlas image to match the input 2D radiographs. Experimental results show that the network achieves high accuracy on simulated patient CT images. This method is not restricted to orthogonal projections, increasing its applicability in medical practices.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2022)
Review
Computer Science, Interdisciplinary Applications
Payal Maken, Abhishek Gupta
Summary: In clinical research, the 3D anatomical structure of the human body is crucial for various applications. Medical imaging techniques have drawbacks, thus 3D reconstruction from 2D X-ray images offers a low radiation exposure alternative. This study provides a comprehensive overview of 3D image reconstruction methods and their applicability in different anatomical sections. It includes a critical analysis of computational methods and compares state-of-the-art approaches, motivating further research in this area.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Biology
Jonas Cordes, Thomas Enzlein, Christian Marsching, Marven Hinze, Sandy Engelhardt, Carsten Hopf, Ivo Wolf
Summary: M(2)aia is an extensible open-source application that provides interactive and memory-efficient data access and signal processing for multiple large MSI datasets. It extends MITK and offers features such as fast visual interaction, image segmentation, 3D image reconstruction, and multi-modal registration, making it suitable for a wide range of MSI analysis tasks.
Article
Surgery
Hooman Esfandiari, Simon Weidert, Istvan Koeveshazi, Carolyn Anglin, John Street, Antony J. Hodgson
Summary: Using deep-learning-based inpainting to remove implant projections from X-rays significantly improves the registration performance by up to 85% in terms of capturing range recovery.
INTERNATIONAL JOURNAL OF MEDICAL ROBOTICS AND COMPUTER ASSISTED SURGERY
(2021)
Article
Engineering, Biomedical
Limei Ma, Yang Nie, Qian Feng, Jianshu Cao, Shaoya Guan
Summary: This paper explores the application of deep learning methods in vascular image registration, compares the performance of different CNN models, and discusses the optimization of network structures. The experiments demonstrate that these networks are suitable for vascular image registration, with Alex-reg achieving the best performance.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2024)
Article
Computer Science, Artificial Intelligence
Paul Striewski, Benedikt Wirth
Summary: This paper proposes a method for nonrigidly aligning a 3D volumetric image with a 2D planar image for biological studies. By co-registering the 2D intravital microscopy videos with the more detailed 3D volume microscopy data after tissue excision, both temporal and spatial information can be combined.
JOURNAL OF MATHEMATICAL IMAGING AND VISION
(2022)
Article
Oncology
Max C. Lindemann, Lukas Glaenzer, Anjali A. Roeth, Thomas Schmitz-Rode, Ioana Slabu
Summary: Three-dimensional models of tumor vascular networks are important for in vitro and in silico investigations, and can potentially be used for the development of in vitro systems. This work presents an algorithm-based method using histologic slices to reconstruct a 3D vascular network model with high resolution and accuracy.
Article
Construction & Building Technology
Pawel Polaczyk, Yuetan Ma, Zaher Jarrar, Xi Jiang, Rui Xiao, Baoshan Huang
Summary: The internal structure of asphalt mixture is crucial for its performance, and can be characterized and quantified through image-based analysis. This study used 3D and 2D image analyzing processes to quantify the interlocking properties of asphalt mixture, and the results showed promising nondestructive methods.
JOURNAL OF MATERIALS IN CIVIL ENGINEERING
(2023)
Article
Medicine, General & Internal
Ahmed Jibril Abdi, Bo R. Mussmann, Alistair Mackenzie, Oke Gerke, Benedikte Klaerke, Poul Erik Andersen
Summary: The study aimed to compare the quantitative image quality metrics of the low-dose 2D/3D EOS slot scanner X-ray imaging system with conventional digital radiography X-ray imaging systems. Results showed that the LDSS system achieved significantly higher eNEQ and eDQE compared to DR systems in both chest and knee protocols, suggesting its potential for clinical diagnostic purposes.
Article
Computer Science, Interdisciplinary Applications
Wei Wei, Xu Haishan, Julian Alpers, Marko Rak, Christian Hansen
Summary: This study proposes a novel approach to address the registration problem between ultrasound and computed tomography/magnetic resonance imaging in liver tumor ablation procedures. By estimating the ultrasound probe angle roughly and improving the registration through segmentation, the proposed method outperforms traditional approaches in terms of accuracy and robustness.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Chemistry, Analytical
Frank Foerste, Leona Bauer, Korbinian Heimler, Bastian Hansel, Carla Vogt, Birgit Kanngiesser, Ioanna Mantouvalou
Summary: Confocal micro-X-ray fluorescence spectroscopy is a technique that can be used for elemental imaging with 3D resolution using laboratory spectrometers. Quantification techniques are important for interpreting data and reconstructing sample composition and geometry. This article presents an analytical routine for the quantitative investigation of 3D data sets obtained with laboratory spectrometers.
JOURNAL OF ANALYTICAL ATOMIC SPECTROMETRY
(2022)
Article
Computer Science, Artificial Intelligence
Zhiyuan Zhu, Taicheng Huang, Zonglei Zhen, Boyu Wang, Xia Wu, Shuo Li
Summary: Achieving predictions of brain functional activation patterns/task-fMRI maps from its underlying anatomy is an important yet challenging problem. In this work, a Unified Geometric Deep Learning framework (BrainUGDL) is proposed to perform the cross-modal brain anatomo-functional mapping task by effectively learning the context-aware information of brain anatomy and overcoming the interference of noise-containing task-fMRI labels.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Information Systems
Chenchu Xu, Yifei Wang, Dong Zhang, Longfei Han, Yanping Zhang, Jie Chen, Shuo Li
Summary: This paper proposes a semi-supervised myocardial infarction segmentation method that consists of a boundary mining model and an adversarial learning model. The boundary mining model solves the boundary ambiguity problem by enlarging the gap between foreground and background features. The adversarial learning model enables the boundary mining model to learn from additional unlabeled data, increasing the model's robustness.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Information Systems
Xingxin Xu, Qikui Zhu, Hanning Ying, Jiongcheng Li, Xiujun Cai, Shuo Li, Xiaoqing Liu, Yizhou Yu
Summary: In this study, a Knowledge-guided framework named MCCNet is proposed to adaptively integrate multi-phase liver lesion information and construct a lesion classification network. The effectiveness of the proposed modules in exploiting and fusing multi-phase information is demonstrated through extensive experimental results and evaluations on a dataset containing 3,683 lesions from 2,333 patients in 9 hospitals.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Oncology
Lei Cheng, Fan Zhang, Xingang Zhao, Leiming Wang, Wanru Duan, Jian Guan, Kai Wang, Zhenlei Liu, Xingwen Wang, Zuowei Wang, Hao Wu, Zan Chen, Lianghong Teng, Yifei Li, Fei Xiao, Tao Fan, Fengzeng Jian
Summary: This study analyzed the genomic sequencing of primary spinal cord astrocytoma (SCA) to characterize its mutational landscape. The study identified 12 driver genes and three rare mutated driver genes. It also observed genetic mutations associated with the risk of brain glioma and recurrent amplification of the CDK4 gene in the 12q14.1 region. Additionally, mutations in the cell cycle pathway were found in 39.2% of patients. Overall, SCAs share a significant degree of somatic mutation landscape with brainstem glioma.
JOURNAL OF PATHOLOGY
(2023)
Article
Neurosciences
Yunzhe Li, Banghua Yang, Zuowei Wang, Ruyan Huang, Xi Lu, Xiaoying Bi, Shu Zhou
Summary: In 2019, the International Classification of Diseases 11th Revision (ICD-11) introduced the concept of chronic primary pain (CPP), which is a type of chronic pain characterized by severe functional disability and emotional distress. This study aimed to explore the neural characteristics of CPP by analyzing EEG data from 67 subjects under the auditory oddball paradigm. The results revealed significant differences in brain network connectivity between CPP patients and depressive patients, suggesting hyperexcitability in attentional control in CPP patients. The study also proposed a novel method for objectively assessing chronic primary pain using deep learning-based EEG classification models.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Qiongyi Zhou, Changde Du, Dan Li, Haibao Wang, Jian K. K. Liu, Huiguang He
Summary: In this article, a novel neural encoding and decoding method called FLIG model is proposed, which addresses the issues of information losses and the separate modeling of neural encoding and decoding. The method utilizes a two-stage flow-based invertible generative model to establish a bidirectional mapping between image features and neural signals. Experimental results demonstrate that the FLIG model achieves the best comprehensive performance among the comparison models.
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
(2023)
Article
Computer Science, Information Systems
Gongning Luo, Xinghua Ma, Jinwen Guo, Mingye Zou, Wei Wang, Yang Cao, Kuanquan Wang, Shuo Li
Summary: This paper introduces a method for removing guidewire artifacts in IVOCT videos and proposes a Trajectory-aware Adaptive imaging Clue analysis Network (TAC-Net). TAC-Net, with its innovative designs of adaptive clue aggregation and trajectory-aware transformer, reliably restores the texture and structure of artifact areas.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Information Systems
Kaini Wang, Shuaishuai Zhuang, Juzheng Miao, Yang Chen, Jie Hua, Guang-Quan Zhou, Xiaopu He, Shuo Li
Summary: This article proposes a framework for comprehensive learning in the frequency domain to identify colonic disease subtypes. The experimental results demonstrate that the proposed method achieves state-of-the-art accuracy rate.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Information Systems
Yinli Tian, Wenjian Qin, Fei Xue, Ricardo Lambo, Meiyan Yue, Songhui Diao, Lequan Yu, Yaoqin Xie, Hailin Cao, Shuo Li
Summary: In this paper, a novel fine-grained segmentation framework called ARR-GCN is proposed, which incorporates prior anatomical relations into the learning process. The framework outperforms other methods in liver segment and lung lobe segmentation tasks.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Automation & Control Systems
Liansheng Wang, Jiacheng Wang, Lei Zhu, Huazhu Fu, Ping Li, Gary Cheng, Zhipeng Feng, Shuo Li, Pheng-Ann Heng
Summary: Automated detection of lung infections from CT data is crucial for combatting COVID-19. However, there are challenges in AI system development, such as the reliance on 2D CT images, limitations of existing 3D segmentation methods, and the lack of annotated CT volumes. To address these issues, a multiple dimensional-attention CNN is proposed to aggregate multiscale information, and a dual multiscale mean teacher network is utilized for semi-supervised segmentation. Experimental results demonstrate the superiority of this approach over state-of-the-art methods.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Yukun Zhang, Shuang Qiu, Wei Wei, Xuelin Ma, Huiguang He
Summary: The study proposes a dynamic weighted filter bank domain adaptation framework to enhance motor imagery decoding accuracy by using data from existing subjects to reduce the requirement of data from new subjects.
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Shimeng Yang, Teng Li, Yinping Lv, Yi Xia, Shuo Li
Summary: This letter proposes a boundary-guided pseudo-labeling method that utilizes prior anatomical knowledge to generate and select reliable pseudo-labels for unlabeled data to improve measurement performance. The proposed method incorporates a fine self-attention module and a boundary attention module to enhance the quality of pseudo-labels. Experiments conducted on challenging carotid ultrasound datasets demonstrate that the proposed method outperforms existing state-of-the-art algorithms.
IEEE SIGNAL PROCESSING LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Zhongyi Han, Xian-Jin Gui, Haoliang Sun, Yilong Yin, Shuo Li
Summary: In this paper, a noise-robust domain adaptation method is proposed to address the issue of corrupted source domain examples in multiple noisy environments. By utilizing offline curriculum learning, gradually decreasing noisy distribution distance, estimating open-set noise degree, robust parameter learning, and domain-invariant feature learning, these components are seamlessly transformed into an adversarial network for efficient joint optimization, leading to significant improvements in transfer tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Guanyu Yang, Yuting He, Yang Lv, Yang Chen, Jean-Louis Coatrieux, Xiaoxuan Sun, Qiang Wang, Yongyue Wei, Shuo Li, Yinsu Zhu
Summary: PAH treatment requires accurate prognosis prediction on 3D non-contrast CT images, which is challenging due to the large volume and low contrast regions. In this paper, we propose a multi-task learning-based framework, P-2-Net, which optimizes the model and represents task-dependent features effectively. Our approach utilizes Memory Drift (MD) to densely sample biomarkers and Prior Prompt Learning (PPL) to embed clinical prior knowledge, achieving high prognostic correlation and great generalization.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Chenchu Xu, Yuhong Song, Dong Zhang, Leonardo Kayat Bittencourt, Sree Harsha Tirumani, Shuo Li
Summary: Liver tumor detection without contrast agents has great potential in advancing liver cancer screening. This paper proposes a novel teacher-student reinforcement learning method that allows the student network to directly detect tumors from non-enhanced images guided by explicit liver tumor knowledge obtained from contrast-enhanced images. Experimental results show that this method achieves state-of-the-art performance in liver tumor detection without contrast agents.
MEDICAL IMAGE ANALYSIS
(2023)