scholarly journals Accurate Instance Segmentation in Pediatric Elbow Radiographs

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7966
Author(s):  
Dixiao Wei ◽  
Qiongshui Wu ◽  
Xianpei Wang ◽  
Meng Tian ◽  
Bowen Li
Keyword(s):  
Elbow Joint ◽  
Segmentation Method ◽  
Qualitative And Quantitative ◽  
Robust Segmentation ◽  
Local Contexts ◽  
Good Potential ◽  
Quantitative Results ◽  
Bounding Boxes ◽  
Global And Local ◽  
Instance Segmentation

Radiography is an essential basis for the diagnosis of fractures. For the pediatric elbow joint diagnosis, the doctor needs to diagnose abnormalities based on the location and shape of each bone, which is a great challenge for AI algorithms when interpreting radiographs. Bone instance segmentation is an effective upstream task for automatic radiograph interpretation. Pediatric elbow bone instance segmentation is a process by which each bone is extracted separately from radiography. However, the arbitrary directions and the overlapping of bones pose issues for bone instance segmentation. In this paper, we design a detection-segmentation pipeline to tackle these problems by using rotational bounding boxes to detect bones and proposing a robust segmentation method. The proposed pipeline mainly contains three parts: (i) We use Faster R-CNN-style architecture to detect and locate bones. (ii) We adopt the Oriented Bounding Box (OBB) to improve the localizing accuracy. (iii) We design the Global-Local Fusion Segmentation Network to combine the global and local contexts of the overlapped bones. To verify the effectiveness of our proposal, we conduct experiments on our self-constructed dataset that contains 1274 well-annotated pediatric elbow radiographs. The qualitative and quantitative results indicate that the network significantly improves the performance of bone extraction. Our methodology has good potential for applying deep learning in the radiography’s bone instance segmentation.

scholarly journals Kvasir-Instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy

2020 ◽  
Author(s):  
Debesh Jha ◽  
Sharib Ali ◽  
Krister Emanuelsen ◽  
Steven Hicks ◽  
Vajira Thambawita ◽  
...  
Keyword(s):  
Gastrointestinal Endoscopy ◽  
Ground Truth ◽  
Jaccard Index ◽  
Dice Coefficient ◽  
Therapeutic Tool ◽  
Current Standard ◽  
Qualitative And Quantitative ◽  
Quantitative Results ◽  
Bounding Boxes

Gastrointestinal (GI) pathologies are periodically screened, biopsied, and resected using surgical tools. Usually, the procedures and the treated or resected areas are not specifically tracked or analysed during or after colonoscopies. Information regarding disease borders, development and amount and size of the resected area get lost.This can lead to poor follow-up and bothersome reassessment difficulties post-treatment. To improve the current standard and also to foster more research on the topic we have released the "Kvasir-Instrument" dataset which consists of 590 annotated frames containing GI procedure tools such as snares, balloons and biopsy forceps, etc. Beside of the images, the dataset includes ground truth masks and bounding boxes and has been verified by two expert GI endoscopists. Additionally, we provide a baseline for the segmentation of the GI tools to promote research and algorithm development. We obtained a dice coefficient score of 0.9158 and a Jaccard index of 0.8578 using a classical U-Net architecture. A similar dice coefficient score was observed for DoubleUNet. The qualitative results showed that the model did not work for the images with specularity and the frames with multiple instruments, while the best result for both methods was observed on all other types of images. Both, qualitative and quantitative results show that the model performs reasonably good, but there is a large potential for further improvements. Benchmarking using the dataset provides an opportunity for researchers to contribute to the field of automatic endoscopic diagnostic and therapeutic tool segmentation for GI endoscopy.

scholarly journals Real-Time Instance Segmentation of Traffic Videos for Embedded Devices

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 275
Author(s):  
Ruben Panero Martinez ◽  
Ionut Schiopu ◽  
Bruno Cornelis ◽  
Adrian Munteanu
Keyword(s):  
Real Time ◽  
Network Architecture ◽  
Training Procedure ◽  
Segmentation Method ◽  
Embedded Devices ◽  
Network Training ◽  
Assignment Algorithm ◽  
Ablation Study ◽  
Reduced Rate ◽  
Instance Segmentation

The paper proposes a novel instance segmentation method for traffic videos devised for deployment on real-time embedded devices. A novel neural network architecture is proposed using a multi-resolution feature extraction backbone and improved network designs for the object detection and instance segmentation branches. A novel post-processing method is introduced to ensure a reduced rate of false detection by evaluating the quality of the output masks. An improved network training procedure is proposed based on a novel label assignment algorithm. An ablation study on speed-vs.-performance trade-off further modifies the two branches and replaces the conventional ResNet-based performance-oriented backbone with a lightweight speed-oriented design. The proposed architectural variations achieve real-time performance when deployed on embedded devices. The experimental results demonstrate that the proposed instance segmentation method for traffic videos outperforms the you only look at coefficients algorithm, the state-of-the-art real-time instance segmentation method. The proposed architecture achieves qualitative results with 31.57 average precision on the COCO dataset, while its speed-oriented variations achieve speeds of up to 66.25 frames per second on the Jetson AGX Xavier module.

scholarly journals Affective communication: a mixed method investigation into COVID-19 outbreak communication using the Taiwanese government Facebook page

2021 ◽  
pp. 175797592110035
Author(s):  
Chia Yu Lien ◽  
Yun-Hsuan Wu
Keyword(s):  
Social Media ◽  
Mixed Method ◽  
Health Authority ◽  
Disease Outbreak ◽  
Government Agencies ◽  
Affective Communication ◽  
Frontline Workers ◽  
The Public ◽  
Qualitative And Quantitative ◽  
Quantitative Results

The COVID-19 outbreak has created an unprecedented challenge for governments to convey information to the public, and social media has become a critical method of COVID-19 communication in Taiwan. Objectives: This study examines a total of 1128 Facebook posts published by Taiwan’s principal health authority from December 1, 2019 to May 31, 2020. Methods: Using both qualitative and quantitative approaches, this study investigates strategies used by the Taiwan government to communicate the COVID-19 outbreak and public responses toward these strategies. Result: Novel uses of Facebook posts on outbreak communication were identified, including solidarity, reviews of actions, press conferences, and the use of animal and cartoon images. Quantitative results showed that the public responded significantly more frequently to messages generating positive affects, such as posts that reviewed government actions and public efforts; posts that expressed thanks, approval, or comradeship; and posts that paired text with photographs of frontline workers or cute animals. Conclusion: These results suggest that, amid a disease outbreak, the public not only look for updated situations and guidelines but also for affective affirmation from government agencies.

scholarly journals An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms

2021 ◽  
Vol 11 (3) ◽  
pp. 968
Author(s):  
Yingchun Sun ◽  
Wang Gao ◽  
Shuguo Pan ◽  
Tao Zhao ◽  
Yahui Peng
Keyword(s):  
Feature Extraction ◽  
Spatial Structure ◽  
Semantic Feature ◽  
Semantic Features ◽  
Segmentation Method ◽  
Spatial Dimensions ◽  
Feature Pyramid ◽  
Multi Level ◽  
High Level ◽  
Instance Segmentation

Recently, multi-level feature networks have been extensively used in instance segmentation. However, because not all features are beneficial to instance segmentation tasks, the performance of networks cannot be adequately improved by synthesizing multi-level convolutional features indiscriminately. In order to solve the problem, an attention-based feature pyramid module (AFPM) is proposed, which integrates the attention mechanism on the basis of a multi-level feature pyramid network to efficiently and pertinently extract the high-level semantic features and low-level spatial structure features; for instance, segmentation. Firstly, we adopt a convolutional block attention module (CBAM) into feature extraction, and sequentially generate attention maps which focus on instance-related features along the channel and spatial dimensions. Secondly, we build inter-dimensional dependencies through a convolutional triplet attention module (CTAM) in lateral attention connections, which is used to propagate a helpful semantic feature map and filter redundant informative features irrelevant to instance objects. Finally, we construct branches for feature enhancement to strengthen detailed information to boost the entire feature hierarchy of the network. The experimental results on the Cityscapes dataset manifest that the proposed module outperforms other excellent methods under different evaluation metrics and effectively upgrades the performance of the instance segmentation method.

Multidirection Validation of a Finite Element 50th Percentile Male Hybrid III Anthropomorphic Test Device for Spaceflight Applications

2019 ◽  
Vol 141 (3) ◽  
Author(s):  
Derek A. Jones ◽  
James P. Gaewsky ◽  
Mona Saffarzadeh ◽  
Jacob B. Putnam ◽  
Ashley A. Weaver ◽  
...  
Keyword(s):  
Finite Element ◽  
Injury Risk ◽  
Fe Model ◽  
Fe Modeling ◽  
Test Device ◽  
Qualitative And Quantitative ◽  
Hybrid Iii ◽  
Physical Tests ◽  
Quantitative Results ◽  
Male Hybrid

The use of anthropomorphic test devices (ATDs) for calculating injury risk of occupants in spaceflight scenarios is crucial for ensuring the safety of crewmembers. Finite element (FE) modeling of ATDs reduces cost and time in the design process. The objective of this study was to validate a Hybrid III ATD FE model using a multidirection test matrix for future spaceflight configurations. Twenty-five Hybrid III physical tests were simulated using a 50th percentile male Hybrid III FE model. The sled acceleration pulses were approximately half-sine shaped, and can be described as a combination of peak acceleration and time to reach peak (rise time). The range of peak accelerations was 10–20 G, and the rise times were 30–110 ms. Test directions were frontal (−GX), rear (GX), vertical (GZ), and lateral (GY). Simulation responses were compared to physical tests using the correlation and analysis (CORA) method. Correlations were very good to excellent and the order of best average response by direction was −GX (0.916±0.054), GZ (0.841±0.117), GX (0.792±0.145), and finally GY (0.775±0.078). Qualitative and quantitative results demonstrated the model replicated the physical ATD well and can be used for future spaceflight configuration modeling and simulation.

Nonlinear Analysis of a Rigid Rotor on Magnetic Bearings

1995 ◽  
Author(s):  
C. Nataraj
Keyword(s):  
Nonlinear Analysis ◽  
Equations Of Motion ◽  
Forced Response ◽  
Magnetic Bearings ◽  
Rigid Rotor ◽  
Stability Criteria ◽  
Safe Operation ◽  
Qualitative And Quantitative ◽  
Quantitative Results ◽  
Nonlinear Equations Of Motion

A simple model of a rigid rotor supported on magnetic bearings is considered. A proportional control architecture is assumed, the nonlinear equations of motion are derived and some essential nondimensional parameters are identified. The free and forced response of the system is analyzed using techniques of nonlinear analysis. Both qualitative and quantitative results are obtained and stability criteria are derived for safe operation of the system.

scholarly journals UCAN: A Learning-based Model to Enhance Poorly Exposed Images

2020 ◽  
Author(s):  
Lucas R. V. Messias ◽  
Cristiano R. Steffens ◽  
Paulo L. J. Drews-Jr ◽  
Silvia S. C. Botelho
Keyword(s):  
Image Quality ◽  
Image Enhancement ◽  
Dynamic Range ◽  
Low Contrast ◽  
Qualitative And Quantitative ◽  
Fast Learning ◽  
Proposed Model ◽  
Quantitative Results ◽  
Critical Process ◽  
Poor Lighting

Image enhancement is a critical process in imagebased systems. In these systems, image quality is a crucial factor to achieve a good performance. Scenes with a dynamic range above the capability of the camera or poor lighting are challenging conditions, which usually result in low contrast images, and, with that, we can have the underexposure and/or overexposure problem. In this work, our aim is to restore illexposed images. For this purpose, we present UCAN, a small and fast learning-based model capable to restore and enhance poorly exposed images. The obtained results are evaluated using image quality indicators which show that the proposed network is able to improve images damaged by real and simulated exposure. Qualitative and quantitative results show that the proposed model outperforms the existing models for this objective.

scholarly journals Automated Filtering of Eye Movements Using Dynamic AOI in Multiple Granularity Levels

2021 ◽  
Vol 12 (1) ◽  
pp. 49-64
Author(s):  
Gavindya Jayawardena ◽  
Sampath Jayarathna
Keyword(s):  
Eye Movements ◽  
Eye Tracking ◽  
Eye Movement ◽  
Eye Gaze ◽  
Movement Analysis ◽  
Movement Data ◽  
Bounding Boxes ◽  
Multiple Granularity ◽  
Instance Segmentation ◽  
Segmentation Models

Eye-tracking experiments involve areas of interest (AOIs) for the analysis of eye gaze data. While there are tools to delineate AOIs to extract eye movement data, they may require users to manually draw boundaries of AOIs on eye tracking stimuli or use markers to define AOIs. This paper introduces two novel techniques to dynamically filter eye movement data from AOIs for the analysis of eye metrics from multiple levels of granularity. The authors incorporate pre-trained object detectors and object instance segmentation models for offline detection of dynamic AOIs in video streams. This research presents the implementation and evaluation of object detectors and object instance segmentation models to find the best model to be integrated in a real-time eye movement analysis pipeline. The authors filter gaze data that falls within the polygonal boundaries of detected dynamic AOIs and apply object detector to find bounding-boxes in a public dataset. The results indicate that the dynamic AOIs generated by object detectors capture 60% of eye movements & object instance segmentation models capture 30% of eye movements.

Sign in / Sign up

Export Citation Format

Share Document