Article
Physiology
Ying Zhu, Liwei Chen, Wenjie Lu, Yongjun Gong, Ximing Wang
Summary: This study utilized the nnU-Net-based model to assist in the evaluation of CAS and carotid atherosclerotic plaques using CTA imaging. The nnU-Net model showed good performance and consistency in CAS diagnosis and plaque segmentation, with a shorter evaluation time compared to physicians.
FRONTIERS IN PHYSIOLOGY
(2022)
Article
Computer Science, Hardware & Architecture
Shichao Quan, Hui Chen, Liaoyi Lin, Zeren Shi, Haochao Ying, Changzheng Yuan, Ping Wang, Shiyuan Liu, Li Fan
Summary: In this study, an automatic radiomics method based on whole-lung segmentation was proposed for discriminating pneumonia and assisting in clinical diagnosis. The results showed that the model was effective in distinguishing influenza pneumonia, COVID-19, and health, and could assist in the diagnosis of influenza pneumonia and COVID-19.
Article
Instruments & Instrumentation
Wenjun Tan, Luyu Zhou, Xiaoshuo Li, Xiaoyu Yang, Yufei Chen, Jinzhu Yang
Summary: This paper reviews 12 different pulmonary vascular segmentation algorithms for lung CT and CTA images, and objectively evaluates their performances. Most of the algorithms show admirable performance in pulmonary vascular extraction and segmentation, with the top three algorithms having dice coefficients around 0.80. Integrating methods that consider spatial information, fuse multi-scale feature map, or have excellent post-processing to deep neural network training and optimization process are significant for improving the accuracy of pulmonary vascular segmentation.
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY
(2021)
Article
Engineering, Biomedical
Hengzhi Xue, Qingqing Fang, Yudong Yao, Yueyang Teng
Summary: This paper proposes a postprocessing method based on graph convolutional networks (GCN) to improve tumor segmentation results in whole-body positron emission tomography/computed tomography (PET/CT) scans. The experimental results show that this method can effectively improve the performance of tumor segmentation.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiu-Zhi Zhou, Kuan Lu, Du-Chang Zhai, Man -Man Cui, Yan Liu, Ting-Ting Wang, Dai Shi, Guo-Hua Fan, Sheng-Hong Ju, Wu Cai
Summary: This study aimed to evaluate the image quality and diagnostic accuracy of CTA images derived from CTP data and explore the possibility of replacing conventional CTA. The results showed that CTA-DF-CTP data provided similar diagnostic accuracy and image quality to conventional CTA in head and neck CTA.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2023)
Article
Mathematics
Jia Zheng, Chuan Tang, Yuanxi Sun, Mingchi Feng, Congzhe Wang
Summary: This paper proposes a deep learning-based approach to achieve high-precision segmentation of hollow turbine blades, and achieves better segmentation accuracy than traditional methods.
Article
Oncology
Ebbe Laugaard Lorenzen, Bahar Celik, Nis Sarup, Lars Dysager, Rasmus Luebeck Christiansen, Anders Smedegaard Bertelsen, Uffe Bernchou, Soren Nielsen Agergaard, Maximilian Lukas Konrad, Carsten Brink, Faisal Mahmood, Tine Schytte, Christina Junker Nyborg
Summary: An automatic segmentation method using the nnU-net framework was developed and evaluated for MRI-guided radiotherapy (MRIgRT). The network successfully segmented all 600 structures in the test set, outperforming the current clinical practice based on deformable image registration (DIR) algorithm.
FRONTIERS IN ONCOLOGY
(2023)
Article
Medicine, General & Internal
Xiaofang Zhang, Xiaomin Liu, Bin Zhang, Jie Dong, Bin Zhang, Shujun Zhao, Suxiao Li
Summary: This study proposes an accurate segmentation method based on an improved U-Net convolutional network for different types of lung nodules on computed tomography images. The method includes two phases: segmenting lung parenchyma and correcting the lung contour, and extracting image patches of lung nodules with corresponding ground truth to train the network. Results show that the segmentation performance of Dice loss is superior to mean square error and Binary_crossentropy loss, and the alpha-hull algorithm and batch normalization can effectively improve segmentation performance.
Article
Biology
Mohsen Soltanpour, Russ Greiner, Pierre Boulanger, Brian Buck
Summary: Acute ischemic stroke, caused by blood clot blocking brain artery, is a major global cause of death and disability. Current segmentation methods lack precision, but machine learning techniques show promise for improvement. MultiRes U-Net, a deep learning-based technique, presents better results for ischemic stroke lesion segmentation.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Interdisciplinary Applications
Ramazan Ozgur Dogan, Hulya Dogan, Coskun Bayrak, Temel Kayikcioglu
Summary: This paper presents a novel two-phase approach for high-accuracy automatic pancreas segmentation in CT imaging, achieving better performance than existing techniques. The proposed method involves Pancreas Localization and Pancreas Segmentation stages, resulting in top values for DSC, JI, REC and ACC among established studies for automatic pancreas segmentation.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Biochemical Research Methods
Jason Causey, Jonathan Stubblefield, Jake Qualls, Jennifer Fowler, Lingrui Cai, Karl Walker, Yuanfang Guan, Xiuzhen Huang
Summary: This paper presents the solution and results of the Arkansas AI-Campus team in the 2019 Kidney Tumor Segmentation Challenge. Their deep learning model achieved high Dice scores in kidney and tumor segmentation and secured a good ranking in the competition.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Article
Instruments & Instrumentation
Cheng Yan, Jing Liu, Xue Yang, Songqi Cai, Xiuliang Lu, Chun Yang, Mengsu Zeng, Guofeng Zhou, Min Ji
Summary: This study evaluated the image quality of automatic and manual reconstruction of CCTA images in a CT scanner with a rotation speed of 0.25 seconds, a coverage of 16 cm, single-beat scanning, automated phase selection, and AI-assisted motion correction. The results showed that automatic image reconstruction with scanner-equipped auto-phase selection and motion correction algorithm outperformed manually controlled image reconstruction by radiologists.
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY
(2022)
Article
Instruments & Instrumentation
You-Chang Yang, Xiao-Yu Wei, Xiao-Qiang Tang, Ruo-Han Yin, Ming Zhang, Shao-Feng Duan, Chang-Jie Pan
Summary: This study established a machine learning model based on coronary computed tomography angiography (CTA) images to evaluate myocardial ischemia in patients with coronary atherosclerosis. The neural network model demonstrated the best predictive performance.
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY
(2022)
Article
Chemistry, Multidisciplinary
Alyaa Amer, Tryphon Lambrou, Xujiong Ye
Summary: The researchers proposed a novel multi-scale deep learning segmentation model named MDA-Unet to improve the performance of medical image segmentation. The model addressed the issues of semantic gap and multi-scale context information capture in U-Net by introducing a multi-scale spatial attention module and residual blocks. Evaluation on two different datasets showed that the model achieved significant performance gains compared to the basic U-Net model.
APPLIED SCIENCES-BASEL
(2022)
Article
Oncology
Kan He, Xiaoming Liu, Rahil Shahzad, Robert Reimer, Frank Thiele, Julius Niehoff, Christian Wybranski, Alexander C. C. Bunck, Huimao Zhang, Michael Perkuhn
Summary: This study developed a deep learning method for automatic segmentation of liver tumors and ablation zones, achieving high accuracy in liver and liver tumor segmentation based on the evaluation of 252 CT images.
FRONTIERS IN ONCOLOGY
(2021)