检索结果-内蒙古大学图书馆

Automatic point detection on cephalograms using convolutional neural networks: A two-step method

DENTAL MATERIALS JOURNAL 2024年第5期43卷 701-710页

作者： Hori, Miki Jincho, Makoto Hori, Tadasuke Sekine, Hironao Kato, Akiko Miyazawa, Ken Kawai, Tatsushi Aichi Gakuin Univ Sch Dent Dept Dent Mat Sci 1-100 Kusumoto ChoChikusa Ku Nagoya Aichi 4648650 Japan Aichi Gakuin Univ Ctr Adv Oral Sci Grad Sch Dent 1-100 Kusumoto ChoChikusa Ku Nagoya Aichi 4648650 Japan Aichi Gakuin Univ Sch Dent Dept Oral Anat 1-100 Kusumoto ChoChikusa Ku Nagoya Aichi 4648650 Japan Aichi Gakuin Univ Sch Dent Dept Orthodont 2-11 Suemori-DoriChikusa Ku Nagoya Aichi 4648651 Japan

This project aimed to develop an artificial intelligence program tailored for cephalometric images. The program employs a convolutional neural network with 6 convolutional layers and 2 affine layers. It identifies 18 key points on the skull to compute various angles essential for diagnosis. Utilizing a custom-built desktop computer with a moderately priced graphics processing unit, cephalogram images were resized to 800x800 pixels. Training data comprised 833 images, augmented 100 times;an additional 179 images were used for testing. Due to the complexity of training with full-size images, training was divided into two steps. The first step reduced images to 128x128 pixels, recognizing all 18 points. In the second step, 100x100 pixels blocks were extracted from original images for individual point training. The program then measured six angles, achieving an average error of 3.1 pixels for the 18 points, with SNA and SNB angles showing an average difference of less than 1 degrees.

关键词： Artificial intelligence Convolutional neural networks Cephalogram image point detection Simultaneous detection

来源：评论

学校读者我要写书评

暂无评论

point detection through multi-instance deep heatmap regression for sutures in endoscopy

引用

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2021年第12期16卷 2107-2117页

作者： Sharan, Lalith Romano, Gabriele Brand, Julian Kelm, Halvar Karck, Matthias De Simone, Raffaele Engelhardt, Sandy Heidelberg Univ Hosp Dept Internal Med 3 Grp Artificial Intelligence Cardiovasc Med D-69120 Heidelberg Germany Heidelberg Univ Hosp Dept Cardiac Surg D-69120 Heidelberg Germany

Purpose: Mitral valve repair is a complex minimally invasive surgery of the heart valve. In this context, suture detection from endoscopic images is a highly relevant task that provides quantitative information to analyse suturing patterns, assess prosthetic configurations and produce augmented reality visualisations. Facial or anatomical landmark detection tasks typically contain a fixed number of landmarks, and use regression or fixed heatmap-based approaches to localize the landmarks. However in endoscopy, there are a varying number of sutures in every image, and the sutures may occur at any location in the annulus, as they are not semantically unique. Method: In this work, we formulate the suture detection task as a multi-instance deep heatmap regression problem, to identify entry and exit points of sutures. We extend our previous work, and introduce the novel use of a 2D Gaussian layer followed by a differentiable 2D spatial Soft-Argmax layer to function as a local non-maximum suppression. Results: We present extensive experiments with multiple heatmap distribution functions and two variants of the proposed model. In the intra-operative domain, Variant 1 showed a mean F-1 of +0.0422 over the baseline. Similarly, in the simulator domain, Variant 1 showed a mean F-1 of +0.0865 over the baseline. Conclusion: The proposed model shows an improvement over the baseline in the intra-operative and the simulator domains. The data is made publicly available within the scope of the MICCAI AdaptOR2021 Challenge https://***/, and the code at https://***/Cardio-AI/suture-detection-pytorch/.

关键词： point detection Mitral valve repair Endoscopy

来源：评论

学校读者我要写书评

暂无评论

A CRISPR/Cas9 eraser strategy for contamination-free PCR end-point detection

引用

BIOTECHNOLOGY AND BIOENGINEERING 2021年第5期118卷 2053-2066页

作者： Lin, Wei Tian, Tian Jiang, Yongzhong Xiong, Erhu Zhu, Debin Zhou, Xiaoming South China Normal Univ MOE Key Lab Laser Life Sci Coll Biophoton Guangzhou Peoples R China South China Normal Univ Inst Laser Life Sci Coll Biophoton Guangzhou Peoples R China South China Normal Univ Coll Biophoton Guangdong Prov Key Lab Laser Life Sci Guangzhou Peoples R China South China Normal Univ Sch Life Sci Guangzhou 510631 Peoples R China Wuhan Univ Coll Chem & Mol Sci Wuhan Peoples R China Hubei Prov Ctr Dis Control & Prevent Wuhan Peoples R China South China Normal Univ Sch Chem Guangzhou Key Lab Analyt Chem Biomed Guangzhou 510006 Peoples R China

Polymerase chain reaction (PCR), a central technology for molecular diagnostics, is highly sensitive but susceptible to the risk of false positives caused by aerosol contamination, especially when an end-point detection mode is applied. Here, we proposed a solution by designing a clustered regularly interspaced short palindromic repeat (CRISPR)/Cas9 eraser strategy for eliminating potential contamination amplification. The CRISPR/Cas9 engineered eraser is firstly adopted into artpcr reverse-transcription PCR (RT-PCR) system to achieve contamination-free RNA detection. Subsequently, we extended this CRISPR/Cas9 eraser to the PCR system. We engineered conventional PCR primers to enable the amplified products to contain an implanted NGG (protospacer adjacent motif, PAM) site, which is used as a code for specific CRISPR/Cas9 recognition. Pre-incubation of Cas9/sgRNA with PCR mix leads to a selective cleavage of contamination amplicons, thus only the template DNA is amplified. The developed CRISPR/Cas9 eraser, adopted by both RT-PCR and PCR systems, showed high-fidelity detection of SARS-CoV-2 and African swine fever virus with a convenient strip test.

关键词： contamination‐ free CRISPR Cas9 end‐ point detection PCR RT‐ PCR

来源：评论

学校读者我要写书评

暂无评论

A Low-Complexity Compressive Sensing Algorithm for point Target detection Using Ultrafast Plane Wave Imaging

引用

IEEE ACCESS 2024年 12卷 2977-2988页

作者： Paridar, Roya Asl, Babak Mohammadzadeh Tarbiat Modares Univ Dept Biomed Engn Tehran 14115111 Iran

Ultrasound plane wave imaging is an ultrafast technique to obtain the reconstructed images in real-time. However, identifying the point targets (such as microcalcifications) is challenging in this imaging technique due to the presence of strong acoustic clutter. In this paper, a compressive sensing (CS)-based algorithm, named modified-CS (M-CS), is proposed which can be used to accurately identify the point targets. In the proposed algorithm, the processing matrix is divided into some non-overlapping sub-matrices, and each part is processed separately. Then, the output passes through the thresholding and localization processes to obtain the locations of the point targets. Compared to the conventional CS algorithm, identifying the point targets in deeper regions of the imaging medium is provided using the M-CS algorithm. Also, due to the usage of smaller sub-matrices, the proposed M-CS algorithm speeds up, and also, needs less memory compared to the conventional CS algorithm. The simulation results confirm the good performance of the proposed algorithm.

关键词： Ultrasound ultrafast imaging sparsity point detection

来源：评论

学校读者我要写书评

暂无评论

Sub-Pixel point detection Algorithm for point Tracking with Low-Power Wearable Camera Systems A Simplified Linear Interpolation 28

Sub-Pixel Point Detection Algorithm for Point Tracking with ...

引用

28th Irish Signals and Systems Conference (ISSC)

作者： Wilk, Mariusz P. Urru, Andrea Tedesco, Salvatore O'Flynn, Brendan Univ Coll Cork Tyndall Natl Inst Cork Ireland

ISBN: (纸本)9781538610466

With the continuous developments in vision sensor technology, highly miniaturized low-power and wearable vision sensing is becoming a reality. Several wearable vision applications exist which involve point tracking. The ability to efficiently detect points at a sub-pixel level can be beneficial, as the accuracy of point detection is no longer limited to the resolution of the vision sensor. In this work, we propose a novel Simplified Linear Interpolation (SLI) algorithm that achieves high computational efficiency, which outperforms existing algorithms in terms of the accuracy under certain conditions. We present the principles underlying our algorithm and evaluate it in a series of test scenarios. Its performance is finally compared to similar algorithms currently available in the literature.

关键词： sub-pixel point detection low power wearable vision approximation

来源：评论

学校读者我要写书评

暂无评论

A generalised framework for saliency-based point feature detection

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2017年 157卷 117-137页

作者： Brown, Mark Windridge, David Guillemaut, Jean-Yves Univ Surrey Ctr Vis Speech & Signal Proc Guildford GU2 7XH Surrey England Middlesex Univ Sch Sci & Technol London NW4 4BT England

Here we present a novel, histogram-based salient point feature detector that may naturally be applied to both images and 3D data. Existing point feature detectors are often modality specific, with 2D and 3D feature detectors typically constructed in separate ways. As such, their applicability in a 2D-3D context is very limited, particularly where the 3D data is obtained by a LiDAR scanner. By contrast, our histogram based approach is highly generalisable and as such, may be meaningfully applied between 2D and 3D data. Using the generalised approach, we propose salient point detectors for images, and both untextured and textured 3D data. The approach naturally allows for the detection of salient 3D points based jointly on both the geometry and texture of the scene, allowing for broader applicability. The repeatability of the feature detectors is evaluated using a range of datasets including image and LiDAR input from indoor and outdoor scenes. Experimental results demonstrate a significant improvement in terms of 2D-2D and 2D-3D repeatability compared to existing multi-modal feature detectors. (C) 2016 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license.

关键词： point detection Feature detection Feature matching 2D-3D registration Saliency

来源：评论

学校读者我要写书评

暂无评论

point-Based Learnable Query Generator for Human–Object Interaction detection

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 6469-6484页

作者： Lin, Wang-Kai Zhang, Hong-Bo Fan, Zongwen Liu, Jing-Hua Yang, Li-Jie Lei, Qing Du, Jixiang Huaqiao Univ Dept Comp Sci & Technol Xiamen 361000 Peoples R China Huaqiao Univ Fujian Prov Univ Key Lab Comp Vis & Machine Learning Xiamen 361000 Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361000 Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen 361000 Peoples R China

Transformer-based and interaction point-based methods have demonstrated promising performance and potential in human-object interaction detection. However, due to differences in structure and properties, direct integration of these two types of models is not feasible. Recent Transformer-based methods divide the decoder into two branches: an instance decoder for human-object pair detection and a classification decoder for interaction recognition. While the attention mechanism within the Transformer enhances the connection between localization and classification, this paper focuses on further improving HOI detection performance by increasing the intrinsic correlation between instance and action features. To address these challenges, this paper proposes a novel Transformer-based HOI detection framework. In the proposed method, the decoder contains three parts: learnable query generator, instance decoder, and interaction classifier. The learnable query generator aims to build an effective query to guide the instance decoder and interaction classifier to learn more accurate instance and interaction features. These features are then applied to update the query generator for the next layer. Especially, inspired by the interaction point-based HOI and object detection methods, this paper introduces the prior bounding boxes, keypoints detection and spatial relation feature to build the novel learnable query generator. Finally, the proposed method is verified on HICO-DET and V-COCO datasets. The experimental results show that the proposed method has the better performance compared with the state-of-the-art methods.

关键词： Human-object interaction detection learnable query generator prior bounding boxes point detection spatial relation feature

来源：评论

学校读者我要写书评

暂无评论

mvHOTA: A multi-view higher order tracking accuracy metric to measure temporal and spatial associations in multi-point tracking

引用

COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION 2023年第4期11卷 1281-1289页

作者： Sharan, Lalith Kelm, Halvar Romano, Gabriele Karck, Matthias De Simone, Raffaele Engelhardt, Sandy DZHK German Ctr Cardiovasc Res Partner Site Heidelberg Mannheim Mannheim Germany Heidelberg Univ Hosp Dept Cardiac Surg Heidelberg Germany

Multi-point tracking is a challenging task that involves detecting points in the scene and tracking them across time. Here, metrics from Multi-object tracking (MOT) methods are shown to perform better than frame-based F-measures. The recently proposed HOTA metric, used for benchmarks such as the KITTI dataset, better evaluates the performance over metrics like MOTA, DetA, and IDF1. While HOTA takes into account temporal associations, it does not provide a tailored means to analyse the spatial associations of a dataset in a multi-camera setup. Moreover, there are differences in evaluating the detection task for points vs. objects (point distances vs. bounding box overlap). Therefore, we propose a multi-view higher-order tracking metric mvHOTA , to determine the accuracy of multi-point (multi-instance and multi-class) tracking methods while taking into account temporal and spatial associations. We demonstrate its use in evaluating the tracking performance on an endoscopic point detection dataset from a previously organised surgical data science challenge. Furthermore, we compare with other adjusted MOT metrics for this use-case, discuss the properties of mvHOTA, and show how the proposed multi-view Association and the Occlusion index (OI) facilitate analysis of methods with respect to handling of occlusions. The code is available at .

关键词： Evaluation metrics point detection tracking

来源：评论

学校读者我要写书评

暂无评论

Optimizing Crowd Counting in Dense Environments Through Curriculum Learning Training Strategy

引用

SN Computer Science 2024年第6期5卷 683页

作者： Fotia, Lidia Percannella, Gennaro Saggese, Alessia Vento, Mario Department of Information Engineering Electrical Engineering and Applied Mathematics (DIEM) University of Salerno Fisciano Italy

Counting individuals in highly crowded environments, characterized by thousands of people, has garnered significant attention in recent years, due to the high number of vertical markets wherein such algorithms can prove beneficial, ranging from smart city and transportation to retail sectors, among others. Within this context, in this paper we introduce a novel training methodology tailored for estimating the number of people, ensuring precise counting accuracy in both moderately and highly crowded scenarios. The proposed approach exploits a formulation of the problem based on point detection, where each point represents an individual’s head. Our innovative contributions center around the designing of a novel training strategy employing Curriculum Learning (CL), which aims to replicate the gradual learning process observed in human cognition, training on simpler tasks at the beginning and tackling more complex tasks as the training evolves. In order to evaluate the complexity of each sample image, we propose a novel indicator taking into account both the number of people and their distribution within the image. The experimentation phase encompassed 18 publicly available datasets;the obtained results validate the effectiveness of the proposed approach, surpassing the baseline state-of-the-art point detection by 71% and 70% in terms of Mean Absolute Error (MAE) and Mean Squared Error (MSE), respectively. © The Author(s) 2024.

关键词： Curriculum Learning High density crowd counting point detection

来源：评论

学校读者我要写书评

暂无评论

An improved point feature-based sparse stereo vision

引用

IET IMAGE PROCESSING 2022年第12期16卷 3284-3299页

作者： Chen, Changhao Song, Bifeng Bu, Shuhui He, Lei Northwestern Polytech Univ Sch Aeronaut Xian 710072 Peoples R China Northwestern Polytech Univ Yangtze River Delta Res Inst Taicang Peoples R China Chendu Technol Univ Chengdu Peoples R China

Since the limitation on the onboard equipment, the sparse stereo vision is becoming a suitable choice for the deployment of micro air vehicles (MAV) and small robots. However, for the point feature-based sparse stereo, most of the current stereo algorithms ignore the similarity between feature points, so it is hard to achieve high accuracy. In addition, the problem of clustered feature distribution will still affect the performance of point feature-based algorithms in the application. To make up for these deficiencies, the authors propose an improved features from accelerated segment test (FAST) feature detector to suppress the point detection in complex texture regions. Most importantly, the authors present a novel census transform (CT)-based algorithm that contains two encoders 'texture orientation' and 'texture gradient' to get a more efficient census bit string for the feature point. Instead of randomly selecting pixels to calculate the bit string, we combine the texture characteristics of the census windows where feature points are located. Compared with the original CT, the processing speed of our method is improved, and the average error of our method is reduced by 18.05%. The evaluation results show the presented improved point feature-based sparse stereo algorithm has a great value in engineering applications.

关键词： feature point point detection census transform improved point feature-based sparse stereo algorithm improved point feature-based sparse stereo vision image texture texture gradient texture orientation CT-based algorithm clustered feature distribution point feature-based algorithms stereo image processing feature extraction

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：