Article
Biology
Xiaoguang Li, Ziyao Zhu, Hongxia Yin, Zhenchang Wang, Li Zhuo, Yichao Zhou
Summary: In this paper, a robust segmentation method for the labyrinth in temporal bone CT images is proposed via multi-model inconsistency. The method introduces an informative sample assessment strategy and an observer network in the active learning paradigm to improve segmentation performance and sample screening efficiency.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biochemical Research Methods
Xin Xu, Qing Geng, Feng Gao, Du Xiong, Hongbo Qiao, Xinming Ma
Summary: This study developed an advanced deep learning technique for the segmentation counting model of wheat grains. The model achieved unprecedented predictive counting accuracy, providing algorithmic support for efficient and intelligent wheat yield estimation.
Article
Radiology, Nuclear Medicine & Medical Imaging
Jiabing Gu, Baosheng Li, Huazhong Shu, Jian Zhu, Qingtao Qiu, Tong Bai
Summary: The study developed a radiomics-based framework for image segmentation, demonstrating good feasibility and accuracy in tumor volume segmentation through feature extraction.
Article
Biology
Elisa Mussi, Michaela Servi, Flavio Facchini, Rocco Furferi, Lapo Governi, Yary Volpe
Summary: The growing interest in auricular anatomy stems from two main areas of research: autologous ear reconstruction in medicine and human detection and recognition in surveillance and law enforcement. Systems for ear analysis vary based on the type of input data, acquisition tools, and algorithms used. While segmentation and recognition of the ear from the face is well-discussed, detection and recognition of individual anatomical elements remains an area that has not been extensively studied.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Materials Science, Multidisciplinary
Anand Patel, Tao Hou, Juan D. Beltran Rodriguez, Tamal K. Dey, Dunbar P. Birnie
Summary: This study introduces a filtering algorithm called PERSPLAT based on topological persistence, and compares its segmentation quality with other methods on synthetic images and a real 3D image, finding significant improvements in microstructure characteristics calculation.
COMPUTATIONAL MATERIALS SCIENCE
(2022)
Article
Acoustics
Gaofei Jin, Hui Zhu, Daohuai Jiang, Jinwei Li, Lili Su, Jianfeng Li, Fei Gao, Xiran Cai
Summary: Image segmentation is important for improving the diagnostic capability of ultrasound computed tomography (USCT) and photoacoustic computed tomography (PACT). A new signal domain object segmentation method is introduced for USCT and PACT, which is automatic, robust, computationally efficient, accurate, and straightforward. The method establishes the relationship between the time-of-flight (TOF) of the received first arrival waves and the object's boundary described by ellipse equations.
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL
(2023)
Article
Computer Science, Interdisciplinary Applications
Yulei Qin, Hao Zheng, Yun Gu, Xiaolin Huang, Jie Yang, Lihui Wang, Feng Yao, Yue-Min Zhu, Guang-Zhong Yang
Summary: The proposed CNNs-based method effectively segments pulmonary airway, artery, and vein, showing superior sensitivity and performance by utilizing feature recalibration and attention distillation modules for representation learning of tubular objects. Integration of anatomy prior and distance transform map enhances artery-vein differentiation capacity, leading to considerable performance gains compared to state-of-the-art methods while extracting more branches for competitive overall segmentation performance.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Computer Science, Artificial Intelligence
Taiping Qu, Xiuli Li, Xiheng Wang, Wenyi Deng, Li Mao, Ming He, Xiao Li, Yun Wang, Zaiyi Liu, Longjiang Zhang, Zhengyu Jin, Huadan Xue, Yizhou Yu
Summary: This study proposes a Transformer guided progressive fusion network (TGPFN) for segmenting and detecting various types of pancreatic masses, while accurately segmenting the pancreas. TGPFN alleviates the limitations of convolution operations in capturing global representations by utilizing global representations captured by the Transformer. Experimental results show that TGPFN improves mass segmentation and detection accuracy on both private and public CT scans.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Construction & Building Technology
Hyeung-Tae Kim, D. F. Tiana R. Razakamandimby, Veronika Szilagyi, Zoltan Kis, Laszlo Szentmiklosi, Michal A. Glinicki, Kyoungsoo Park
Summary: The concrete microstructure was successfully reconstructed by combining X-ray and neutron CT information, capturing information about void, aggregate, and cement paste phases. Image-based finite element analysis demonstrated the effects of microstructure on stress and strain.
CEMENT AND CONCRETE RESEARCH
(2021)
Article
Agriculture, Multidisciplinary
Dong-Yan Zhang, Han-Sen Luo, Dao-Yong Wang, Xin-Gen Zhou, Wei-Feng Li, Chun-Yan Gu, Gan Zhang, Fang-Ming He
Summary: This study developed a new method based on object detection network to effectively detect and assess the damage caused by Fusarium head blight in wheat under field conditions. The method combines object detection, feature extraction, and classification to achieve high detection accuracy and efficient evaluation.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Engineering, Biomedical
Alena-Kathrin Golla, Dominik F. Bauer, Ralf Schmidt, Tom Russ, Dominik Norenberg, Khanlian Chung, Christian Toennes, Lothar R. Schad, Frank G. Zoellner
Summary: The study presents an automatic method for extracting and differentiating abdominal blood vessel trees using convolutional neural networks (CNNs), achieving high accuracy and generalizability. Ensemble networks outperform individual CNNs and surpass state-of-the-art methods in segmentation of vascular structures.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2021)
Article
Anthropology
Ville-Pauli Karjalainen, Mikko A. J. Finnila, Phil L. Salmon, Sanna Lipkin
Summary: In this study, high-resolution micro-computed tomography (mu CT) and nanoscale CT imaging were used to examine and identify the internal structures and fiber materials of archaeological textiles. The results showed that mu CT imaging provided a 3D visualization of the woven textiles, revealing the intertwining of warp and weft, while nanoscale CT imaging allowed for the identification of individual fibers in the fabric.
JOURNAL OF ARCHAEOLOGICAL SCIENCE
(2023)
Article
Computer Science, Interdisciplinary Applications
Shuai Wang, Mingxia Liu, Jun Lian, Dinggang Shen
Summary: This study introduces a novel boundary coding network (BCnet) to learn discriminative representations of organ boundaries for segmentation in male pelvic CT images. Experimental results show that this method outperforms several state-of-the-art methods in terms of segmentation accuracy.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Engineering, Biomedical
Xiaoxu Li, Yu Peng, Min Xu
Summary: This paper proposes a novel semi-supervised learning method for training a bone segmentation model in CT images. It leverages the unique bone structures in CT for data augmentation and utilizes unlabeled CT slices for training. The experiment results demonstrate the superior performance of the proposed method over other methods on different bone CT datasets.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Interdisciplinary Applications
Tianling Lyu, Guanyu Yang, Xingran Zhao, Huazhong Shu, Limin Luo, Duanduan Chen, Jiang Xiong, Jian Yang, Shuo Li, Jean-Louis Coatrieux, Yang Chen
Summary: This study proposed a deep-learning-based algorithm for segmenting dissected aorta, achieving high accuracy and robustness by combining 3-D and 2-D models. The edge extraction branch also improved segmentation accuracy near aorta boundaries.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)