scholarly journals Endocardial 3D Ultrasound Segmentation using Autocontext Random Forests

2014 ◽  
Author(s):  
Kevin Keraudren ◽  
Ozan Oktay ◽  
Wenzhe Shi ◽  
Joseph V. Hajnal ◽  
Daniel Rueckert
Keyword(s):  
Contextual Information ◽  
3D Ultrasound ◽  
Local Means ◽  
Testing Dataset ◽  
Segmentation Accuracy ◽  
Systolic Time ◽  
Non Local ◽  
The Mean ◽  
Segmentation Task ◽  
The Cost

In this paper, we present the use of a generic image segmentation method, namely a succession of Random Forest classifiers in an autocontext framework, for the MICCAI 2014 Challenge on Endocardial 3D Ultrasound Segmentation (CETUS). The proposed method segments each frame independently in 90 sec, without requiring temporal information such as end-diastolic or end-systolic time points nor any registration. For better segmentation accuracy, non-local means denoising can be applied to the images at the cost of an increased run-time. The mean Dice score on the testing dataset was 84.4% without denoising and 86.4% with denoising. The originality of our approach lies in the introduction of two classes, the myocardium and the mitral valve, in addition to the left ventricle and the background classes, in order to gain contextual information for the segmentation task.

scholarly journals Dynamic deformable attention (DDANet) for semantic segmentation

2020 ◽  
Author(s):  
Kumar Rajamani ◽  
Hanna Siebert ◽  
Mattias P Heinrich
Keyword(s):  
Contextual Information ◽  
Ground Glass Opacity ◽  
Semantic Segmentation ◽  
Medical Image Segmentation ◽  
Training Data ◽  
Self Similarity ◽  
Complex Models ◽  
Non Local ◽  
Segmentation Task ◽  
Validation Experiments

Deep learning based medical image segmentation is an important step within diagnosis, which relies strongly on capturing sufficient spatial context without requiring too complex models that are hard to train with limited labelled data. Training data is in particular scarce for segmenting infection regions of CT images of COVID-19 patients. Attention models help gather contextual information within deep networks and benefit semantic segmentation tasks. The recent criss-cross-attention module aims to approximate global self-attention while remaining memory and time efficient by separating horizontal and vertical self-similarity computations. However, capturing attention from all non-local locations can adversely impact the accuracy of semantic segmentation networks. We propose a new Dynamic Deformable Attention Network (DDANet) that enables a more accurate contextual information computation in a similarly efficient way. Our novel technique is based on a deformable criss-cross attention block that learns both attention coefficients and attention offsets in a continuous way. A deep segmentation network (in our case a U-Net \cite{Jo2019}) that employs this attention mechanism is able to capture attention from pertinent non-local locations and also improves the performance on semantic segmentation tasks compared to criss-cross attention within a U-Net on a challenging COVID-19 lesion segmentation task. Our validation experiments show that the performance gain of the recursively applied dynamic deformable attention blocks comes from their ability to capture dynamic and precise (wider) attention context. Our DDANet achieves Dice scores of 73.4\% and 61.3\% for Ground-Glass-Opacity and Consolidation lesions for COVID-19 segmentation and improves the accuracy by 4.9\% points compared to a baseline U-Net.

scholarly journals Dynamic deformable attention (DDANet) for semantic segmentation

2020 ◽  
Author(s):  
Kumar T Rajamani ◽  
Hanna Siebert ◽  
Mattias Heinrich
Keyword(s):  
Contextual Information ◽  
Ground Glass Opacity ◽  
Semantic Segmentation ◽  
Medical Image Segmentation ◽  
Training Data ◽  
Self Similarity ◽  
Complex Models ◽  
Non Local ◽  
Segmentation Task ◽  
Validation Experiments

Deep learning based medical image segmentation is an important step within diagnosis, which relies strongly on capturing sufficient spatial context without requiring too complex models that are hard to train with limited labelled data. Training data is in particular scarce for segmenting infection regions of CT images of COVID-19 patients. Attention models help gather contextual information within deep networks and benefit semantic segmentation tasks. The recent criss-cross-attention module aims to approximate global self-attention while remaining memory and time efficient by separating horizontal and vertical self-similarity computations. However, capturing attention from all non-local locations can adversely impact the accuracy of semantic segmentation networks. We propose a new Dynamic Deformable Attention Network (DDANet) that enables a more accurate contextual information computation in a similarly efficient way. Our novel technique is based on a deformable criss-cross attention block that learns both attention coefficients and attention offsets in a continuous way. A deep segmentation network (in our case a U-Net ) that employs this attention mechanism is able to capture attention from pertinent non-local locations and also improves the performance on semantic segmentation tasks compared to criss-cross attention within a U-Net on a challenging COVID-19 lesion segmentation task. Our validation experiments show that the performance gain of the recursively applied dynamic deformable attention blocks comes from their ability to capture dynamic and precise (wider) attention context. Our DDANet achieves Dice scores of 73.4% and 61.3% for Ground-Glass-Opacity and Consolidation lesions for COVID-19 segmentation and improves the accuracy by 4.9% points compared to a baseline U-Net.

Design and development of manually operated gladiolus planter

2018 ◽  
Vol 5 (01) ◽  
Author(s):  
TAPAN K. KHURA ◽  
H. L. KUSHWAHA ◽  
SATISH D LANDE ◽  
PKSAHOO . ◽  
INDRA L . KUSHWAHA
Keyword(s):  
Coefficient Of Variation ◽  
Field Capacity ◽  
Power Source ◽  
Forward Speed ◽  
Cereal Crop ◽  
Maximum Coefficient ◽  
Coefficient Of Uniformity ◽  
The Mean ◽  
The Cost ◽  
Immense Potential

Floriculture is an age-old farming activity in India having immense potential for generating selfemployment and income to farmers. However, the cost of cultivation of flower is high as compared to cereal crop. Level of mechanization for different field operations is one but foremost reason for the higher cost of cultivation. As most of the Indian farmers are marginal and small, a need for manually operated gladiolus planter was felt. The geometric properties of gladiolus corm were determined for designing the seed metering system and seed hopper of the planter. The planter was evaluated in the field when pulled by two persons as a power source and guided by a person. The coefficient of variation and highest deviation from the mean spacing was observed as 12.93% and 2.65cm respectively. The maximum coefficient of uniformity of 90.59% was observed for a nominal corm spacing of 15cm at 0.56 kmh-1 forward speed. An average MISS percentage was observed as 2.65 and 2.25 for nominal corm spacing of 15 and 20 cm. The multiple index was zero for two levels corm spacing and forward speed of operation. The QFI was found in the range of 97.2 and 97.9 percent. The average field capacity of the planter was observed as 0.02 hah-1.The average draft requirement of the planter was found as 821 ± 50.3 N.

scholarly journals Overestimation of grey matter atrophy in glioblastoma patients following radio(chemo)therapy

2021 ◽  
Author(s):  
A. Gommlich ◽  
F. Raschke ◽  
J. Petr ◽  
A. Seidlitz ◽  
C. Jentsch ◽  
...  
Keyword(s):  
Brain Tumour ◽  
Contralateral Hemisphere ◽  
Mr Images ◽  
Segmentation Accuracy ◽  
Volume Measurements ◽  
Radiation Induced ◽  
The Mean ◽  
Changes Over Time ◽  
Grey Matter Atrophy ◽  
Abnormal Tissue

Abstract Objective Brain atrophy has the potential to become a biomarker for severity of radiation-induced side-effects. Particularly brain tumour patients can show great MRI signal changes over time caused by e.g. oedema, tumour progress or necrosis. The goal of this study was to investigate if such changes affect the segmentation accuracy of normal appearing brain and thus influence longitudinal volumetric measurements. Materials and methods T1-weighted MR images of 52 glioblastoma patients with unilateral tumours acquired before and three months after the end of radio(chemo)therapy were analysed. GM and WM volumes in the contralateral hemisphere were compared between segmenting the whole brain (full) and the contralateral hemisphere only (cl) with SPM and FSL. Relative GM and WM volumes were compared using paired t tests and correlated with the corresponding mean dose in GM and WM, respectively. Results Mean GM atrophy was significantly higher for full segmentation compared to cl segmentation when using SPM (mean ± std: ΔVGM,full = − 3.1% ± 3.7%, ΔVGM,cl = − 1.6% ± 2.7%; p < 0.001, d = 0.62). GM atrophy was significantly correlated with the mean GM dose with the SPM cl segmentation (r = − 0.4, p = 0.004), FSL full segmentation (r = − 0.4, p = 0.004) and FSL cl segmentation (r = -0.35, p = 0.012) but not with the SPM full segmentation (r = − 0.23, p = 0.1). Conclusions For accurate normal tissue volume measurements in brain tumour patients using SPM, abnormal tissue needs to be masked prior to segmentation, however, this is not necessary when using FSL.

scholarly journals Cotton Stand Counting from Unmanned Aerial System Imagery Using MobileNet and CenterNet Deep Learning Models

2021 ◽  
Vol 13 (14) ◽  
pp. 2822
Author(s):  
Zhe Lin ◽  
Wenxuan Guo
Keyword(s):  
Deep Learning ◽  
Cotton Plant ◽  
Unmanned Aerial System ◽  
Learning Models ◽  
Training Images ◽  
Testing Dataset ◽  
Cotton Plants ◽  
Detection And Counting ◽  
Different Dimensions ◽  
The Mean

An accurate stand count is a prerequisite to determining the emergence rate, assessing seedling vigor, and facilitating site-specific management for optimal crop production. Traditional manual counting methods in stand assessment are labor intensive and time consuming for large-scale breeding programs or production field operations. This study aimed to apply two deep learning models, the MobileNet and CenterNet, to detect and count cotton plants at the seedling stage with unmanned aerial system (UAS) images. These models were trained with two datasets containing 400 and 900 images with variations in plant size and soil background brightness. The performance of these models was assessed with two testing datasets of different dimensions, testing dataset 1 with 300 by 400 pixels and testing dataset 2 with 250 by 1200 pixels. The model validation results showed that the mean average precision (mAP) and average recall (AR) were 79% and 73% for the CenterNet model, and 86% and 72% for the MobileNet model with 900 training images. The accuracy of cotton plant detection and counting was higher with testing dataset 1 for both CenterNet and MobileNet models. The results showed that the CenterNet model had a better overall performance for cotton plant detection and counting with 900 training images. The results also indicated that more training images are required when applying object detection models on images with different dimensions from training datasets. The mean absolute percentage error (MAPE), coefficient of determination (R2), and the root mean squared error (RMSE) values of the cotton plant counting were 0.07%, 0.98 and 0.37, respectively, with testing dataset 1 for the CenterNet model with 900 training images. Both MobileNet and CenterNet models have the potential to accurately and timely detect and count cotton plants based on high-resolution UAS images at the seedling stage. This study provides valuable information for selecting the right deep learning tools and the appropriate number of training images for object detection projects in agricultural applications.

scholarly journals Seasonal Influenza and Low Flu Vaccination Coverage as Important Factors Modifying the Costs and Availability of Hospital Services in Poland: A Retrospective Comparative Study

2021 ◽  
Vol 18 (10) ◽  
pp. 5173
Author(s):  
Robert Susło ◽  
Piotr Pobrotyn ◽  
Lidia Brydak ◽  
Łukasz Rypicz ◽  
Urszula Grata-Borkowska ◽  
...  
Keyword(s):  
Influenza Season ◽  
Influenza Infection ◽  
Hospital Staff ◽  
University Hospital ◽  
Control Group ◽  
Admission Rates ◽  
Risk Of Death ◽  
The Mean ◽  
Retrospective Comparative Study ◽  
The Cost

Introduction: Influenza infection is associated with potential serious complications, increased hospitalization rates, and a higher risk of death. Materials and Methods: A retrospective comparative analysis of selected indicators of hospitalization from the University Hospital in Wroclaw, Poland, was carried out on patients with confirmed influenza infection in comparison to a control group randomly selected from among all other patients hospitalized on the respective wards during the 2018–2019 influenza season. Results: The mean laboratory testing costs for the entire hospital were 3.74-fold higher and the mean imaging test costs were 4.02-fold higher for patients with confirmed influenza than for the control group; the hospital expenses were additionally raised by the cost of antiviral therapy, which is striking when compared against the cost of a single flu vaccine. During the 2018–2019 influenza season, influenza infections among the hospital patients temporarily limited the healthcare service availability in the institution, which resulted in reduced admission rates to the departments related to internal medicine; the mean absence among the hospital staff totaled approximately 7 h per employee, despite 7.3% of the staff having been vaccinated against influenza at the hospital’s expense. Conclusions: There were significant differences in the hospitalization indicators between the patients with confirmed influenza and the control group, which markedly increased the hospital care costs in this multi-specialty university hospital.

scholarly journals Application of Fast Non-Local Means Algorithm for Noise Reduction Using Separable Color Channels in Light Microscopy Images

2021 ◽  
Vol 18 (6) ◽  
pp. 2903
Author(s):  
Seong-Hyeon Kang ◽  
Ji-Youn Kim
Keyword(s):  
Light Microscopy ◽  
Noise Reduction ◽  
Natural Image ◽  
Search Window ◽  
Local Means ◽  
Image Characteristics ◽  
Non Local ◽  
Spatial Quality ◽  
Evaluation Parameters ◽  
Color Channels

The purpose of this study is to evaluate the various control parameters of a modeled fast non-local means (FNLM) noise reduction algorithm which can separate color channels in light microscopy (LM) images. To achieve this objective, the tendency of image characteristics with changes in parameters, such as smoothing factors and kernel and search window sizes for the FNLM algorithm, was analyzed. To quantitatively assess image characteristics, the coefficient of variation (COV), blind/referenceless image spatial quality evaluator (BRISQUE), and natural image quality evaluator (NIQE) were employed. When high smoothing factors and large search window sizes were applied, excellent COV and unsatisfactory BRISQUE and NIQE results were obtained. In addition, all three evaluation parameters improved as the kernel size increased. However, the kernel and search window sizes of the FNLM algorithm were shown to be dependent on the image processing time (time resolution). In conclusion, this work has demonstrated that the FNLM algorithm can effectively reduce noise in LM images, and parameter optimization is important to achieve the algorithm’s appropriate application.

Sign in / Sign up

Export Citation Format

Share Document