检索结果-内蒙古大学图书馆

External validation of a commercially available deep learning algorithm for fracture detection in children

DIAGNOSTIC AND INTERVENTIONAL IMAGING 2022年第3期103卷 151-159页

作者： Dupuis, Michel Delbos, Leo Veil, Raphael Adamsbaum, Catherine Bicetre Hosp AP HP Pediat Imaging Dept F-94270 Le Kremlin Bicetre France Bicetre Hosp AP HP Epidemiol & Publ Hlth Dept F-94270 Le Kremlin Bicetre France Paris Saclay Univ Fac Med F-94270 Le Kremlin Bicetre France

Purpose: The purpose of this study was to conduct an external validation of a fracture assessment deep learning algorithm (Rayvolve (R)) using digital radiographs from a real-life cohort of children presenting routinely to the emergency room. Materials and methods: This retrospective study was conducted on 2634 radiography sets (5865 images) from 2549 children (1459 boys, 1090 girls;mean age, 8.5 +/- 4.5 [SD] years;age range: 0-17 years) referred by the pediatric emergency room for trauma. For each set was recorded whether one or more fractures were found, the number of fractures, and their location found by the senior radiologists and the algorithm. Using the senior radiologist diagnosis as the standard of reference, the diagnostic performance of deep learning algorithm (Rayvolve (R)) was calculated via three different approaches: a detection approach (presence/absence of a fracture as a binary variable), an enumeration approach (exact number of fractures detected) and a localization approach (focusing on whether the detected fractures were correctly localized). Subgroup analyses were performed according to the presence of a cast or not, age category (0-4 vs. 5-18 years) and anatomical region. Results: Regarding detection approach, the deep learning algorithm yielded 95.7% sensitivity (95% CI: 94.0-96.9), 91.2% specificity (95% CI: 89.8-92.5) and 92.6% accuracy (95% CI: 91.5-93.6). Regarding enumeration and localization approaches, the deep learning algorithm yielded 94.1% sensitivity (95% CI: 92.1-95.6), 88.8% specificity (95% CI: 87.3-90.2) and 90.4% accuracy (95% CI: 89.2-91.5) for both approaches. Regarding age-related subgroup analyses, the deep learning algorithm yielded greater sensitivity and negative predictive value in the 5-18-years age group than in the 0-4-years age group for the detection approach (P < 0.001 and P = 0.002) and for the enumeration and localization approaches (P = 0.012 and P = 0.028). The high negative predictive value was robust, pers

关键词： Radiographs deep learning algorithm Artificial intelligence Fractures Pediatric

来源：评论

学校读者我要写书评

暂无评论

引用

INTERNATIONAL JOURNAL OF BIOMETRICS 2021年第2-3期13卷 272-288页

作者： Ge, Dong-yuan Yao, Xi-fan Xiang, Wen-jiang Liu, En-chen Xu, Zhi-bin Guangxi Univ Sci & Technol Sch Mech & Transportat Engn Liuzhou 545006 Peoples R China South China Univ Technol Sch Mech & Automot Engn Guangzhou 510640 Peoples R China Shaoyang Univ Sch Mech & Energy Engn Shaoyang 422004 Peoples R China

In order to overcome the problem of low accuracy of traditional facial image feature similarity measurement methods, the paper proposes a new cross-age facial image feature similarity measurement method based on a deep learning algorithm. Face segmentation is performed based on eye coordinates to determine the effective area for face detection. This study introduces deep learning algorithms to build the basic architecture of deep learning networks, define network input as face image data containing age and identity tags in a cross-age database, and define output as face image features under constant age, and pass the foundation separately training and cross-age training complete the network training, and calculate the facial features under the same age. The cosine distance method is used to measure the similarity of face image features across ages. The experimental results show that the method has obtained more accurate measurement results in different age data sets, and the highest measurement accuracy is 97.9%.

关键词： deep learning algorithm face image similarity measurement cosine distance method

来源：评论

学校读者我要写书评

暂无评论

Enhancing the function of the aids to navigation by practical usage of the deep learning algorithm

引用

JOURNAL OF NAVIGATION 2024年第3期77卷 347-358页

作者： Sim, Yoontae Chae, Chong-Ju Mopko Maritime Univ Div Nav Safety Syst Mokpo South Korea World Maritime Univ Maritime Safety & Environm Adm MSEA Malmo Sweden

Information is provided to navigators through advanced onboard navigation equipment, such as the electronic chart display and information system (ECDIS), radar and the automatic identification system (AIS). However, maritime accidents still occur, especially in coastal and inland water where many navigational dangers exist. The recent artificial intelligence (AI) technology is actively applied in navigation fields, such as collision avoidance and ship detection. However, utilising the aids to navigation (AtoN) system requires more engagement and further exploration. The AtoN system provides critical navigation information by marking the navigation hazards, such as shallow water areas and wrecks, and visually marking narrow passageways. The prime function of the AtoN can be enhanced by applying AI technology, particularly deep learning technology. With the help of this technology, an algorithm could be constructed to detect AtoN in coastal and inland waters and utilise the detected AtoN to create a safety function to supplement watchkeepers using recent navigation equipment.

关键词： artificial intelligence deep learning algorithm object detection AtoN detection

来源：评论

学校读者我要写书评

暂无评论

Views of deep learning algorithm Applied to Computer Vision Knowledge Discovery

引用

NATIONAL ACADEMY SCIENCE LETTERS-INDIA 2022年第6期45卷 561-566页

作者： Jeyaraj, Pandia Rajan Asokan, Siva Prakash Kathiresan, Aravind Chellachi Mepco Schlenk Engn Coll Autonomous Dept Elect & Elect Engn Sivakasi India

During the last few decades, the development of deep learning algorithms for obtaining better performance, accurate classification, extracting valuable information has gained much attention. In recent years, many deep learning architecture methods have been proposed. The main contribution of this research view is to fill the gap between each research by comparing and summarizing the analysis and research findings of reputed deep learning papers. We analysed 20 representative papers published in various reputed publishers like Springer, Elsevier, Nature, IEEE, Sage, Wiley, etc., for a past period of 5 years (June 2016-2021). Also, in this view, we compared the deep learning algorithm used, their architecture, research problem, evaluation metrics, hardware specification, and conclusions. Based on this view, we pointed out future scope and challenges in data analysis research using deep learning algorithms towards computer vision.

关键词： deep learning algorithm Computer vision Pattern recognition Data analysis Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancement of the Multiplexing Capacity and Measurement Accuracy of FBG Sensor System Using IWDM Technique and deep learning algorithm

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2020年第6期38卷 1589-1603页

作者： Manie, Yibeltal Chanie Peng, Peng-Chun Shiu, Run-Kai Hsu, Yuan-Ta Chen, Ya-Yu Shao, Guan-Ming Chiu, Justin Natl Taipei Univ Technol Dept Electroopt Engn Taipei 10608 Taiwan

In this article, we are the first to propose deep learning algorithms for intensity wavelength division multiplexing (IWDM)-based self-healing fiber Bragg grating (FBG) sensor network. A deep learning algorithm is proposed to improve the accuracy of measuring the sensing signal of the sensor system. Furthermore, to increase the total number of FBG sensors multiplexed in the sensor network for multipoint measurements, a multiplexing technique called IWDM is proposed. The proposed IWDM-based ring structure FBG sensor network can also have a self-healing purpose to improve the sensor system's reliability and survivability. However, IWDM has unmeasurable gap or crosstalk problems when the number of FBG sensors increases, which causes high sensing signal measurement errors. To solve this problem, a gated recurrent unit (GRU) deep learning algorithm is proposed and experimentally demonstrated. To prove the sensing signal measurement performance of our proposed algorithm, we test the well-trained GRU model using two cases. The first case is when the spectra of FBGs are overlapped as well as the minimum intensity difference between FBGs is 10%, and the second case is when the spectra of FBGs are overlapped as well as the minimum intensity difference between FBGs is 3% which is a very small intensity difference. From the experimental results, the well-trained GRU algorithm achieves high strain sensing signal measurement performance in both cases compared to other algorithms. Therefore, the proposed IWDM based FBG sensor system using deep learning algorithm enhances the multiplexing capacity and survivability of the sensor system, reduces the computational time, and improves strain sensing signal measurement accuracy of FBGs even when FBGs has very small intensity difference and overlap problem.

关键词： deep learning algorithm fiber Bragg grating (FBG) intensity wavelength division multiplexing (IWDM) sensor system

来源：评论

学校读者我要写书评

暂无评论

Big data network security defense mode of deep learning algorithm

引用

OPEN COMPUTER SCIENCE 2022年第1期12卷 345-356页

作者： Yu, Yingle NYU Tandon Sch Engn Brooklyn NY 11201 USA

With the rapid development and progress of big data technology, people can already use big data to judge the transmission and distribution of network information and make better decisions in time, but it also faces major network threats such as Trojan horses and viruses. Traditional network security functions generally wait until the network power is turned on to a certain extent before starting, and it is difficult to ensure the security of big data networks. To protect the network security of big data and improve its ability to defend against attacks, this article introduces the deep learning algorithm into the research of big data network security defense mode. The test results show that the introduction of deep learning algorithms into the research of network security model can enhance the security defense capability of the network by 5.12%, proactively detect, and kill cyber attacks that can pose threats. At the same time, the security defense mode will evaluate the network security of big data and analyze potential network security risks in detail, which will prevent risks before they occur and effectively protect the network security in the context of big data.

关键词： deep learning algorithm big data network security defense mode

来源：评论

学校读者我要写书评

暂无评论

Application of a deep learning algorithm for three-dimensional T1-weighted gradient-echo imaging of gadoxetic acid-enhanced MRI in patients at a high risk of hepatocellular carcinoma

引用

ABDOMINAL RADIOLOGY 2024年第3期49卷 738-747页

作者： Kim, Jae Hyun Yoon, Jeong Hee Kim, Se Woo Park, Junghoan Bae, Seong Hwan Lee, Jeong Min Seoul Natl Univ Hosp Dept Radiol Seoul South Korea Seoul Natl Univ Coll Med Dept Radiol 28 Yongon Dong Seoul 110744 South Korea Soonchunhyang Univ Seoul Hosp Dept Radiol Seoul South Korea Seoul Natl Univ Med Res Ctr Inst Radiat Med Seoul South Korea

Purpose To evaluate the efficacy of a vendor-specific deep learning reconstruction algorithm (DLRA) in enhancing image quality and focal lesion detection using three-dimensional T1-weighted gradient-echo images in gadoxetic acid-enhanced liver magnetic resonance imaging (MRI) in patients at a high risk of hepatocellular *** and methods In this retrospective analysis, 83 high-risk patients with hepatocellular carcinoma underwent gadoxetic acid-enhanced liver MRI using a 3-T scanner. Triple arterial phase, high-resolution portal venous phase, and high-resolution hepatobiliary phase images were reconstructed using conventional reconstruction techniques and DLRA (AIRTM Recon DL;GE Healthcare) for subsequent comparison. Image quality and solid focal lesion detection were assessed by three abdominal radiologists and compared between conventional and DL methods. Focal liver lesion detection was evaluated using figures of merit (FOMs) from a jackknife alternative free-response receiver operating characteristic analysis on a per-lesion *** DLRA-reconstructed images exhibited significantly improved overall image quality, image contrast, lesion conspicuity, vessel conspicuity, and liver edge sharpness and reduced subjective image noise, ringing artifacts, and motion artifacts compared to conventionally reconstructed images (all P < 0.05). Although there was no significant difference in the FOMs of non-cystic focal liver lesions between the conventional and DL methods, DLRA-reconstructed images showed notably higher pooled sensitivity than conventionally reconstructed images (P < 0.05) in all phases and higher detection rates for viable post-treatment HCCs in the arterial and hepatobiliary phases (all P < 0.05).Conclusions Implementing DLRA can enhance the image quality in 3D T1-weighted gradient-echo sequences of gadoxetic acid-enhanced liver MRI examinations, leading to improved detection of viable post-treatment HCCs.

关键词： Hepatocellular carcinoma Gadoxetic acid-enhanced MRI deep learning algorithm LI-RADS

来源：评论

学校读者我要写书评

暂无评论

A stratified analysis of a deep learning algorithm in the diagnosis of diabetic retinopathy in a real-world study

引用

JOURNAL OF DIABETES 2022年第2期14卷 111-120页

作者： Li, Na Ma, Mingming Lai, Mengyu Gu, Liping Kang, Mei Wang, Zilong Jiao, Shengyin Dang, Kang Deng, Junxiao Ding, Xiaowei Zhen, Qin Zhang, Aifang Shen, Tingting Zheng, Zhi Wang, Yufan Peng, Yongde Shanghai Jiao Tong Univ Shanghai Gen Hosp Dept Endocrinol & Metab 100 Haining Rd Shanghai 200080 Peoples R China Shanghai Gen Hosp Shanghai Engn Ctr Precise Diag & Treatment Eye Di Shanghai Key Lab Ocular Fundus DisNatl Clin Res Dept OphthalmolShanghai Engn Ctr Visual Sci & Ph 100 Haining Rd Shanghai 200080 Peoples R China Shanghai Jiao Tong Univ Shanghai Gen Hosp Clin Res Ctr Shanghai Peoples R China VoxelCloud Shanghai Peoples R China

Background The aim of our research was to prospectively explore the clinical value of a deep learning algorithm (DLA) to detect referable diabetic retinopathy (DR) in different subgroups stratified by types of diabetes, blood pressure, sex, BMI, age, glycosylated hemoglobin (HbA1c), diabetes duration, urine albumin-to-creatinine ratio (UACR), and estimated glomerular filtration rate (eGFR) at a real-world diabetes center in China. Methods A total of 1147 diabetic patients from Shanghai General Hospital were recruited from October 2018 to August 2019. Retinal fundus images were graded by the DLA, and the detection of referable DR (moderate nonproliferative DR or worse) was compared with a reference standard generated by one certified retinal specialist with more than 12 years of experience. The performance of DLA across different subgroups stratified by types of diabetes, blood pressure, sex, BMI, age, HbA1c, diabetes duration, UACR, and eGFR was evaluated. Results For all 1674 gradable images, the area under the receiver operating curve, sensitivity, and specificity of the DLA for referable DR were 0.942 (95% CI, 0.920-0.964), 85.1% (95% CI, 83.4%-86.8%), and 95.6% (95% CI, 94.6%-96.6%), respectively. The DLA showed consistent performance across most subgroups, while it showed superior performance in the subgroups of patients with type 1 diabetes, UACR >= 30 mg/g, and eGFR < 90 mL/min/1.73m(2). Conclusions This study showed that the DLA was a reliable alternative method for the detection of referable DR and performed superior in patients with type 1 diabetes and diabetic nephropathy who were prone to DR.

关键词： deep learning algorithm diabetic retinopathy referable DR retinal fundus images

来源：评论

学校读者我要写书评

暂无评论

Recognition algorithm of athletes' partially occluded face based on a deep learning algorithm

引用

INTERNATIONAL JOURNAL OF BIOMETRICS 2021年第2-3期13卷 305-321页

作者： Li, Wenjuan Millsap, Kevin Wuxi Taihu Univ Dept Phys Educ Wuxi 214000 Jiangsu Peoples R China Univ Iowa Coll Engn Iowa City IA 52242 USA

Because there are a lot of noise data in the partially occluded face image, the existing recognition methods have the problems of low recall rate and long time consumption. In this paper, a new recognition algorithm based on a deep learning algorithm is proposed. This method uses boosting algorithm to locate face information, based on which the face image is greyed and denoised. The local binary pattern is used to extract face features, and the convolution neural network in deep learning algorithm is used to realise face feature recognition. The experimental results show that compared with the traditional face feature recognition algorithm, the proposed method has significantly improved recognition accuracy and recall rate, and the feature recognition time is shorter, which proves that the proposed algorithm has stronger application performance.

关键词： deep learning algorithm convolution neural network athlete local occlusion face feature recognition algorithm

来源：评论

学校读者我要写书评

暂无评论

3D point cloud registration denoising method for human motion image using deep learning algorithm

引用

MULTIMEDIA SYSTEMS 2020年第1期26卷 75-82页

作者： Du, Qidong Guangzhou Railway Polytech Educ Technol Ctr Guangzhou 510430 Guangdong Peoples R China

Aiming at the problem of 3D point cloud noise affecting the efficiency and precision of human body 3D reconstruction in complex scenes, a 3D point cloud registration denoising method for human motion image using depth learning algorithm is proposed. First, two Kinect sensors are used to collect the three-dimensional data of the human body in the scene, and the spatial alignment under the Bursa linear model is used to pre-process the background point cloud data. The depth image of the point cloud is calculated, and the depth image pair is extracted by the convolutional neural network. Furthermore, the feature difference of the depth image pair is taken as the input of the fully connected network and the point cloud registration parameter is calculated, and the above operation is performed iteratively until the registration error is less than the acceptable threshold. Then, the improved C-means algorithm is used to remove the outlier, the noise is clustered, and the large-scale outlier noise is removed. Finally, the high-frequency information is processed by the depth data bilateral filtering method. The experimental results show that compared with the traditional bilateral filtering algorithm and fuzzy C-means algorithm, the proposed method can effectively remove noise of different scales and maintain good performance on the basis of maintaining human body features. In the point cloud model of A, B, and C, the average error of the proposed method is lower than that of the traditional bilateral filtering algorithm with 15.7%, 15.9%, and 19.8%, respectively, and it is lower than that of the fuzzy C-means algorithm with 25.8%, 26.9%, and 30.2%, respectively.

关键词： Human body three-dimensional point cloud Kinect sensor deep learning algorithm Convolutional neural network Point cloud registration

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：