Article
Automation & Control Systems
Wenqiang Li, Yuk Ming Tang, Ziyang Wang, Kai Ming Yu, Suet To
Summary: Automatic vertebrae segmentation using CT plays a crucial role in automated spine analysis, and recent advancements in deep learning have led to precise performance through deep convolutional neural networks. While DCNN-based semantic segmentation algorithms have advantages, they face limitations that are addressed by the proposed novel algorithm, which includes encoder-decoder framework, Layer Normalization, Atrous Residual Path, and a 3D Attention Module to improve segmentation accuracy. Experimental results show competitive performance compared to existing methods for automatic vertebrae semantic segmentation.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Aksh Garg, Sana Salehi, Marianna La Rocca, Rachael Garner, Dominique Duncan
Summary: This paper utilizes 20 convolutional neural networks to classify patients as COVID-19 positive, healthy, or suffering from other pulmonary infections based on chest CT scans. The study finds that the EfficientNet-B5 model performs the best, offering a rapid and accurate diagnostic for COVID-19.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Medicine, Research & Experimental
Ke Si, Ying Xue, Xiazhen Yu, Xinpei Zhu, Qinghai Li, Wei Gong, Tingbo Liang, Shumin Duan
Summary: Artificial intelligence can facilitate clinical decision making by considering massive amounts of medical imaging data. Various algorithms have been implemented for different clinical applications. Accurate diagnosis and treatment require reliable and interpretable data. This study established a fully end-to-end deep-learning model for diagnosing pancreatic tumors and proposing treatment, achieving high accuracy and efficiency.
Article
Biology
Jose Denes Lima Araujo, Luana Batista da Cruz, Joao Otavio Bandeira Diniz, Jonnison Lima Ferreira, Aristofanes Correa Silva, Anselmo Cardoso de Paiva, Marcelo Gattass
Summary: This study shows that liver segmentation, even in the presence of lesions in CT images, can be efficiently carried out using a cascade approach and incorporating a reconstruction step based on deep convolutional neural networks.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Information Systems
Mamoona Humayun, Muhammad Ibrahim Khalil, Saleh Naif Almuayqil, N. Z. Jhanjhi
Summary: Breast cancer is a leading cause of mortality, and recent advancements in gene expression research and deep learning techniques have improved the accuracy of risk prediction, enabling tailored screening and prevention decisions.
Article
Oncology
Qingwen Zeng, Zongfeng Feng, Yanyan Zhu, Yang Zhang, Xufeng Shu, Ahao Wu, Lianghua Luo, Yi Cao, Jianbo Xiong, Hong Li, Fuqing Zhou, Zhigang Jie, Yi Tu, Zhengrong Li
Summary: This research aims to construct an AI model for discriminating early gastric cancer (EGC). The results showed that the deep learning model based on ResNet101 neural network can effectively discriminate EGC and differentiate between different tumor locations. This suggests that deep learning classifiers have the potential to be used as a screening tool for EGC, which is crucial in the individualized treatment of EGC patients.
FRONTIERS IN ONCOLOGY
(2022)
Article
Neurosciences
Meera Srikrishna, Joana B. Pereira, Rolf A. Heckemann, Giovanni Volpe, Danielle van Westen, Anna Zettergren, Silke Kern, Lars-Olof Wahlund, Eric Westman, Ingmar Skoog, Michael Scholl
Summary: In this study, an automatic method for segmenting grey matter, white matter, cerebrospinal fluid, and intracranial volume from head CT images using a U-Net deep learning model trained on MRI-derived segmentation labels was proposed and validated. Results showed accurate prediction of brain tissue classes from unseen CT images, demonstrating the potential for CT-derived segmentations to be used in clinical practice and research.
Article
Computer Science, Artificial Intelligence
Chen Zhao, Joyce H. Keyak, Jinshan Tang, Tadashi S. Kaneko, Sundeep Khosla, Shreyasee Amin, Elizabeth J. Atkinson, Lan-Juan Zhao, Michael J. Serou, Chaoyang Zhang, Hui Shen, Hong-Wen Deng, Weihua Zhou
Summary: In this study, we aimed to develop a deep-learning-based method for automatic proximal femur segmentation in quantitative computed tomography (QCT) images. We proposed a spatial transformation V-Net (ST-V-Net) that incorporates a shape prior into the segmentation network to improve model performance. Experimental results showed excellent performance of the proposed ST-V-Net for automatic proximal femur segmentation in QCT images.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Engineering, Biomedical
Jordi Minnema, Maureen van Eijnatten, Henri der Sarkissian, Shannon Doyle, Juha Koivisto, Jan Wolff, Tymour Forouzanfar, Felix Lucka, Kees Joost Batenburg
Summary: This study introduces a novel deep learning approach to reduce high cone-angle artifacts in CBCT scans through training convolutional neural networks. The results demonstrate that this method significantly reduces artifacts and outperforms conventional methods.
PHYSICS IN MEDICINE AND BIOLOGY
(2021)
Article
Chemistry, Multidisciplinary
Abdul Rahaman Wahab Sait
Summary: Lung cancer is the primary cause of cancer-related deaths worldwide. Deep learning-based medical image analysis plays a crucial role in detecting and diagnosing lung cancer. The author proposes a deep learning model using PET/CT images for lung cancer detection. By applying image preprocessing and augmentation techniques, as well as convolutional neural networks and deep autoencoders, along with optimization algorithms, the model achieves high accuracy and reduces the need for computational resources. The experimental results show that the proposed model has high accuracy and stability with fewer parameters.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Janjhyam Venkata Naga Ramesh, T. Abirami, T. Gopalakrishnan, Kanagaraj Narayanasamy, Mohamad Khairi Ishak, Faten Khalid Karim, Samih M. Mostafa, Alaa Allakany
Summary: Medical image analysis plays a vital role in the classification and recognition of pancreatic cancer. Deep learning approaches, such as Convolutional Neural Networks, have been shown to effectively support the diagnosis and detection of pancreatic cancer. In this study, a new technique called Sparrow Search Algorithm with Stacked Deep Learning-based Medical Image Analysis for Pancreatic Cancer Detection and Classification (SSASDL-PCDC) was proposed. The technique achieved high accuracy and sensitivity in detecting and classifying pancreatic cancer.
Article
Biology
Shota Watanabe, Kenta Sakaguchi, Daisuke Murata, Kazunari Ishii
Summary: This study compared the accuracy of measuring HU values in the internal carotid artery using a DL-based method and the conventional ROI setting method. The results showed that the DL-based method can improve the accuracy of HU value measurements for ICA in BT images, especially in cases of patient involuntary movement.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Review
Biochemical Research Methods
Yurui Chen, Louxin Zhang
Summary: This article introduces the application of deep learning in drug response prediction and summarizes the latest deep learning methods. Although deep learning methods have shown some limitations in certain cases, combining them with established bioinformatics analyses can help overcome some of these challenges.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Information Systems
Pravda Jith Ray Prasad, Shanmugapriya Survarachakan, Zohaib Amjad Khan, Frank Lindseth, Ole Jakob Elle, Fritz Albregtsen, Rahul Prasanna Kumar
Summary: This study investigates CNN-based multi-dataset image segmentation, optimizing segmentation results through different parameter selection strategies. Experimental results show proposed strategies for achieving optimal segmentation outcomes based on various parameter combinations.
Article
Radiology, Nuclear Medicine & Medical Imaging
Yuhan Yang, Xiuhe Zou, Yixi Wang, Xuelei Ma
Summary: A deep-learning convolution neural network (DL-CNN) system was developed to differentiate muscle-invasive bladder cancer (MIBC) and non-muscle-invasive bladder cancer (NMIBC) on contrast-enhanced CT images, achieving favorable AUROCs. The VGG16 model showed the highest AUROC among the eight deep learning algorithms tested, with promising sensitivity and specificity. The DL-CNN system has the potential to assist in improving diagnostic accuracy in patients with bladder cancer by classifying NMIBC and MIBC based on contrast-enhanced CT images.
EUROPEAN JOURNAL OF RADIOLOGY
(2021)
Article
Engineering, Geological
Pengfei Dou, Chengshun Xu, Xiuli Du, Su Chen
Summary: The study on seismic response and stability of liquefiable sites with and without structures found that non-free field has higher natural frequency and lower damping ratio. Under weak seismic loading condition, similar dynamic response is observed in both sites. However, under strong ground motion condition, the presence of structures in the non-free field leads to lower liquefaction depth, slower accumulation of porewater pressure, and smaller lateral displacements and acceleration compared to the free field.
BULLETIN OF EARTHQUAKE ENGINEERING
(2022)
Article
Immunology
Maogui Hu, Jinfeng Wang, Hui Lin, Corrine W. Ruktanonchai, Chengdong Xu, Bin Meng, Xin Zhang, Alessandra Carioli, Yuqing Feng, Qian Yin, Jessica R. Floyd, Nick W. Ruktanonchai, Zhongjie Li, Weizhong Yang, Andrew J. Tatem, Shengjie Lai
Summary: The transmission attack rate of SARS-CoV-2 on airplane seats ranges from 0.33% to 0.60%. The risk varies based on seat distance from index cases and joint travel time, with no significant difference in transmission risk between different types of aircraft. Overall, the risk of SARS-CoV-2 transmission during domestic air travel is relatively low.
CLINICAL INFECTIOUS DISEASES
(2022)
Article
Optics
Cheng Xu, Hui Pang, Axiu Cao, Qiling Deng
Summary: A multiple-plane phase retrieval method is proposed in this paper, using diffraction of a grating to determine the initial distance and improve the accuracy and robustness of the reconstructed optical field. Numerical simulations and optical experiments confirm the effectiveness of the proposed method in recovering the complete complex amplitude of the optical field.
OPTICS AND LASERS IN ENGINEERING
(2022)
Article
Optics
Xiuhui Sun, Xingyu Mu, Cheng Xu, Hui Pang, Qiling Deng, Ke Zhang, Haibo Jiang, Jinglei Du, Shaoyun Yin, Chunlei Du
Summary: A dual-task convolutional neural network based on the combination of U-Net and a diffraction propagation model is proposed in this paper for the design of phase holograms to suppress speckle noise in reconstructed images. The feasibility and effectiveness of the proposed method are demonstrated through simulations and optical experiments, showing its advantages over traditional methods.
Article
Gastroenterology & Hepatology
Meng Li, Xin Song, Qi Jin, Yishu Chen, Jie Zhang, Jianguo Gao, Li Cen, Yiming Lin, Chengfu Xu, Xinjue He, Youming Li, Chaohui Yu
Summary: The study found that MPST plays a tumor suppressor role in HCC, and is closely related to tumor size and overall survival. Overexpression of MPST inhibits cell proliferation, induces apoptosis, and suppresses tumor growth. MPST expression is negatively correlated with H2S production, inhibition of the AKT/FOXO3a/Rb signaling pathway, and pRb expression, and the combination of these factors is a strong indicator of poor prognosis in HCC.
LIVER INTERNATIONAL
(2022)
Review
Nutrition & Dietetics
Hangkai Huang, Linjie Lu, Yishu Chen, Yan Zeng, Chengfu Xu
Summary: This systematic review and meta-analysis explored the efficacy of vitamin D supplementation in patients with irritable bowel syndrome (IBS). The results indicated that vitamin D supplementation was superior to placebo in improving IBS symptoms and quality of life.
Article
Surgery
Yanli Zhou, Chenghua Xu
Summary: The use of vascular closure devices in ischemic cerebrovascular interventions can effectively shorten the bleeding time, improve patient comfort, and reduce the incidence of complications.
FRONTIERS IN SURGERY
(2022)
Article
Development Studies
Di Guo, Kun Jiang, Chenggang Xu, Xiyi Yang
Summary: This study provides evidence of the relationship between industrial clusters and rural income in China. The findings suggest that industrial clusters developed through joint efforts of entrepreneurs and local governments have reduced institutional constraints and provided relatively equal opportunities for rural residents to engage in nonfarm activities, resulting in increased rural household income and reduced income inequality.
Article
Metallurgy & Metallurgical Engineering
Chengfu Xu, Jinping Tian, Yongquan Yang, Qingrong Yao, Tianming Li, Zhengfei Gu, Dongdong Ma, Jiang Wang, Guanghui Rao, Chaohao Hu, Xie Delong
Summary: The stability of the Pr3Pt4 phase in Pr42.9Pt57.1-xFex (x = 0, 1, 2, 3) alloys was investigated using XRD and DTA. It was found that the Pr3Pt4 phase decreased in fraction with increasing Fe content and transformed into PrPt and (Pr, Fe)Pt-2 phases.
CANADIAN METALLURGICAL QUARTERLY
(2023)
Article
Gastroenterology & Hepatology
Mengting Ren, Xinxin Zhou, Mosang Yu, Yang Cao, Chengfu Xu, Chaohui Yu, Feng Ji
Summary: In obese patients with nonalcoholic fatty liver disease (NAFLD), three months of endoscopic duodenal-jejunal bypass sleeve (DJBS) implantation resulted in significant weight loss and improvements in hepatic steatosis, liver enzymes, insulin resistance, and metabolic parameters.
DIGESTIVE ENDOSCOPY
(2023)
Article
Engineering, Geological
Jialin Xu, Chengshun Xu, Linghui Huang, Masayuki Hyodo
Summary: This study conducted a series of triaxial tests on artificial methane hydrate-bearing specimens, and discussed the effects of effective confining pressure and hydrate saturation on the strength parameters and stress-dilatancy characteristics. The results showed that the strength and stiffness of hydrate-bearing sediments increase with increasing effective confining pressure, and shearing under high effective confining pressure leads to significant breakage of host particles.
Article
Crystallography
Cheng Xu, Zheng Zhou, Haixiang Han
Summary: The creation of atomically precise nanoclusters has become an important research direction in nanoscience, as these nanomaterials exhibit unique chemo-physical properties that are significantly different from bulk materials. In this study, a new nanocluster with embryonic features of corresponding bulk material was synthesized and its atomic structure was revealed. The structure of the nanocluster is distorted due to its molecular nature, leading to the formation of two chiral enantiomeric isomers.
Article
Nutrition & Dietetics
Zhening Liu, Hangkai Huang, Jiarong Xie, Chengfu Xu
Summary: This study found that dietary patterns are associated with the long-term outcomes of NAFLD. Patients with a high-quality diet had a lower risk, particularly those with high-quality carbohydrate patterns and prudent dietary patterns rich in vegetables, fruits, and fish.
Article
Automation & Control Systems
Chengjie Xu, Haichuan Xu, Zhi-Hong Guan, Yuan Ge
Summary: This paper investigates the observer-based dynamic event-triggered semiglobal bipartite consensus (SGBC) for linear multi-agent systems (MASs) with input saturation under a competitive network. Distributed dynamic event-triggered control (DETC) protocols are proposed for solving the SGBC problems for MASs under different topologies. The bipartite consensus conditions are obtained using gauge transformation and the Lyapunov theory. Simulation examples are presented to verify the theoretical results efficiently.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Review
Medicine, General & Internal
Jiahui Hu, Dongdong Huang, Chengfu Xu, Yi Chen, Han Ma, Zhe Shen
Summary: We report a case of Epstein-Barr virus-positive inflammatory follicular dendritic cell sarcoma (EBV+ iFDCS) presenting as a colon polyp in a 52-year-old woman with a special family history. The excised polypoid mass showed histopathological features consistent with EBV+ iFDCS, including infiltration of IgG4+ cells and positive expression of CD21, CD23, CD35, and EBER. The patient remained disease-free during the 1-year follow-up. This case highlights the importance of identifying the pathogenesis sites and sharing diagnostic experiences of EBV+ iFDCS, as well as summarizing its clinicopathological features presenting as a colon polyp.
MEDICINA-LITHUANIA
(2023)