scholarly journals Robust segmentation method for noisy images based on an unsupervised denosing filter

2021 ◽  
Vol 26 (5) ◽  
pp. 736-748
Author(s):  
Ling Zhang ◽  
Jianchao Liu ◽  
Fangxing Shang ◽  
Gang Li ◽  
Juming Zhao ◽  
...  
Keyword(s):  
Segmentation Method ◽  
Noisy Images ◽  
Robust Segmentation

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.

An Automated Robust Segmentation Method for Intravascular Ultrasound Images

2014 ◽  
pp. 407-426
Author(s):  
Prakash Manandhar ◽  
Chi Hau Chen ◽  
Ahmet Umit Coskun ◽  
Uvais A. Qidwai
Keyword(s):  
Intravascular Ultrasound ◽  
Ultrasound Images ◽  
Segmentation Method ◽  
Robust Segmentation

Robust segmentation of noisy images using a neural network model

1992 ◽  
Vol 10 (4) ◽  
pp. 233-240 ◽  
Author(s):  
Wang Tao ◽  
Zhuang Xinhua ◽  
Xing Xiaoliang
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Noisy Images ◽  
Robust Segmentation

A robust segmentation method for counting bovine milk somatic cells in microscope slide images

2015 ◽  
Vol 115 ◽  
pp. 142-149 ◽  
Author(s):  
G.J.A. de Melo ◽  
V. Gomes ◽  
C.C. Baccili ◽  
L.A.L. de Almeida ◽  
A.C. de C. Lima
Keyword(s):  
Somatic Cells ◽  
Bovine Milk ◽  
Segmentation Method ◽  
Microscope Slide ◽  
Robust Segmentation ◽  
Milk Somatic Cells

scholarly journals An Recognition–Verification Mechanism for Real-Time Chinese Sign Language Recognition Based on Multi-Information Fusion

Sensors ◽  
2019 ◽  
Vol 19 (11) ◽  
pp. 2495 ◽  
Author(s):  
Fei Wang ◽  
Shusen Zhao ◽  
Xingqun Zhou ◽  
Chen Li ◽  
Mingyao Li ◽  
...  
Keyword(s):  
Sign Language ◽  
Classification Model ◽  
Measurement Unit ◽  
Language Recognition ◽  
Segmentation Method ◽  
Sign Language Recognition ◽  
Online Data ◽  
Recognition Mechanism ◽  
Sliding Windows ◽  
Robust Segmentation

For online sign language recognition (SLR) based on inertial measurement unit (IMU) and a surface electromyography (sEMG) sensor, achieving high-accuracy is a major challenge. The traditional method for that is the segmentation–recognition mechanism, which has two key challenges: (1) it is difficult to design a highly robust segmentation method for online data with inconspicuous segmentation information; and (2) the diversity of input data will increase the burden of the classification. The recognition–verification mechanism was proposed to improve the performance of online SLR. In the recognition stage, we used sliding windows to pull the data, and applied a convolutional neural network (CNN) to classify the sign language signal. In the verification stage, the confidence was evaluated by the Siamese network to judge the correctness of the classification results. The accuracy and rapidity of the classification model were discussed for 86 categories of Chinese sign language. In the experiments for online SLR, the superiority of the recognition–verification mechanism compared to the segmentation–recognition mechanism was verified.

3D Segmentation of the Left Ventricle Combining Long- and Short-axis MR Images

2009 ◽  
Vol 48 (04) ◽  
pp. 340-343 ◽  
Author(s):  
J. Relan ◽  
M. Groth ◽  
K. Müllerleile ◽  
H. Handels ◽  
D. Säring
Keyword(s):  
Left Ventricle ◽  
Automatic Segmentation ◽  
Surface Model ◽  
Short Axis ◽  
Segmentation Method ◽  
Cine Mr ◽  
Robust Segmentation ◽  
Lv Remodeling ◽  
Volume Properties ◽  
The Mean

Summary Objectives: Segmentation of the left ventricle (LV) is required to quantify LV remodeling after myocardial infarction. Therefore spatiotemporal cine MR sequences including long-axis and short-axis images are acquired. In this paper a new segmentation method for fast and robust segmentation of the left ventricle is presented. Methods: The new approach considers the position of the mitral valve and the apex as well as the long-axis contours to generate a 3D LV surface model. The segmentation result can be checked and adjusted in the short-axis images. Finally quantitative parameters were extracted. Results: For evaluation the LV was segmented in eight datasets of the same subject by two medical experts using a contour drawing tool and the new segmentation tool. The results of both methods were compared concerning interaction time and intra- and inter-observer variance. The presented segmentation method proved to be fast. The mean difference and standard deviation of all parameters are decreased. In case of intra-observer comparison e.g. the mean ESV difference is reduced from 8.8% to 0.5%. Conclusion: A semi-automatic LV segmentation method has been developed that combines long- and short-axis views. Using the presented approach the intra- and inter-observer difference as well as the time for the segmentation process are decreased. So the semi-automatic segmentation using long-and short-axis information proved to be fast and robust for the quantification of LV mass and volume properties.

Sign in / Sign up

Export Citation Format

Share Document