A Liver Segmentation Method Based on the Fusion of VNet and WGAN

Accurate segmentation of liver images is an essential step in liver disease diagnosis, treatment planning, and prognosis. In recent years, although liver segmentation methods based on 2D convolutional neural networks have achieved good results, there is still a lack of interlayer information that causes severe loss of segmentation accuracy to a certain extent. Meanwhile, making the best of high-level and low-level features more effectively in a 2D segmentation network is a challenging problem. Therefore, we designed and implemented a 2.5-dimensional convolutional neural network, VNet_WGAN, to improve the accuracy of liver segmentation. First, we chose three adjacent layers of a liver model as the input of our network and adopted two convolution kernels in series connection, which can integrate cross-sectional spatial information and interlayer information of liver models. Second, a chain residual pooling module is added to fuse multilevel feature information to optimize the skip connection. Finally, the boundary loss function in the generator is employed to compensate for the lack of marginal pixel accuracy in the Dice loss function. The effectiveness of the proposed method is verified on two datasets, LiTS and CHAOS. The Dice coefficients are 92% and 90%, respectively, which are better than those of the compared segmentation networks. In addition, the experimental results also show that the proposed method can reduce computational consumption while retaining higher segmentation accuracy, which is significant for liver segmentation in practice and provides a favorable reference for clinicians in liver segmentation.

Download Full-text

M2UNet++

10.4018/978-1-7998-7709-7.ch015 ◽

2022 ◽

pp. 256-273

Author(s):

Devidas Tulshiram Kushnure ◽

Sanjay Nilkanth Talbar

Keyword(s):

Decision Making ◽

Deep Learning ◽

Quantitative Result ◽

Manual Segmentation ◽

Liver Segmentation ◽

Multi Scale ◽

Hepatic Diseases ◽

Segmentation Accuracy ◽

High Level ◽

Result Analysis

Liver segmentation is instrumental for decision making in the medical realm for the diagnosis and treatment planning of hepatic diseases. However, the manual segmentation of the hundreds of CT images is tedious for medical experts. Thus, it hampers the segmentation accuracy and is reliant on opinion of the operator. This chapter presents the deep learning-based modified multi-scale UNet++ (M2UNet++) approach for automatic liver segmentation. The multi-scale features were modified channel-wise using adaptive feature recalibration to improve the representation of the high-level semantic information of the skip pathways and improved the segmentation performance with fewer computational overheads. The experimental results proved the model's efficacy on the publicly available 3DIRCADb dataset, which offers significant complexity and variations. The model's dice coefficient value is 97.28% that is 7.64%, and 2.24% improved from the UNet and UNet++ model. The quantitative result analysis shows that the M2UNet++ model outperforms the state-of-the-art methods proposed for liver segmentation.

Download Full-text

Hubungan antara Asupan Karbohidrat dan Lemak dengan Kadar Trigliserida pada Pesenam Aerobik Wanita

JURNAL NUTRISIA ◽

10.29238/jnutri.v19i2.15 ◽

2017 ◽

Vol 19 (2) ◽

pp. 84-89

Author(s):

Diah Nur Khasanah ◽

Idi Setiyobroto ◽

Weni Kurdanti

Keyword(s):

Coronary Heart Disease ◽

Triglyceride Level ◽

Observational Research ◽

Fat Intake ◽

Cross Sectional ◽

Exact Test ◽

High Carbohydrate ◽

High Consumption ◽

High Level ◽

High Triglyceride

Background: A long-standing association exists between elevated triglyceride levels and coronary heart disease (CHD). High consumption of fat and carbohydrate influences enhancement of triglycerides level. Sport can reduce cholesterol and triglycerides level. Objective: This research aims to analyze relationship between carbohydrates and fat intakes with triglycerides level on female aerobic gymnasts. Method: This is an observational research using cross sectional research design which was held in Miracle Gymnasium on February17- 18th 2017. 30 subjects were selected as subject because fulfill the requirement (older than 20 years and have willingness to be a subjects). Research variable areintakes of carbohydrate, fat, and triglyceride levels. Result: Result shows 53.3% subjects have high level of carbohydrate and fat intakes followed by 20% subjects with high level of triglycerides. Subjects with high level of carbohydrate, fat intakes and high triglyceride level are 28%. Subjects withsufficient carbohydrate, fat intakes and high triglyceride level are 12.5%.Fisher’s exact test was done to prove hypothesis with results there is no significant relationship between carbohydrate and fat intake with triglyceride level. Conclusions: Subjects with high carbohydrate and fat intake is 53.3% and 20% subjects have high triglyceride level. Relationship between carbohydrate and fat intake with triglyceride level on female aerobic gymnasts is not significant (p>0.05). Keywords: Intake, Carbohydrate, Fat, Aerobic Gymnasts, Triglyceride

Download Full-text

PENGARUH PEMBERIAN PELAYANAN INFORMASI OBAT DAN KONSELING TERHADAP TINGKAT KEPATUHAN MINUM OBAT PADA PASIEN DIABETES MELITUS DENGAN HIPERTENSI DI RUMAH SAKIT DAERAH IDAMAN BANJARBARU

Jurnal Ilmiah Ibnu Sina (JIIS): Ilmu Farmasi dan Kesehatan ◽

10.36387/jiis.v5i2.462 ◽

2020 ◽

Vol 5 (2) ◽

pp. 240-249

Author(s):

Satrio Wibowo Rahmatullah ◽

◽

Ika Maulida Nurrahma ◽

Adnan Syahrizal

Keyword(s):

Drug Information ◽

Treatment Success ◽

Information Service ◽

Regional Hospital ◽

P Value ◽

Chi Square ◽

Cross Sectional ◽

Quasi Experimental ◽

High Level ◽

Chi Square Analysis

Compliance to achieve treatment success can be improved by providing drug information services (PIO) and counseling to improve understanding of treatment instructions. The general objective of this study was to determine the effect of drug information service and counseling on the level of medication adherence in patients with diabetes mellitus (DM) with hypertension in the Banjarbaru Regional Hospital. This study uses a quasi experimental method with a cross sectional approach and takes patient data prospectively. The results of this study indicate that the group given PIO and counseling showed a high level of adherence as many as 20 respondents (100%). Whereas in the group that was not given PIO and the counseling level of adherence was low, there were 4 respondents (20%). Based on the mann-whitney analysis p-value = 0,000 (<α = 0.05) so that there are differences in the group with PIO and counseling with groups without PIO and counseling, while the chi square analysis p-value = 0.004 (<α = 0 , 05) so that PIO and counseling have a significant effect on the level of adherence to taking medication in patients with DM with hypertension at the Banjarbaru Regional Hospital.

Download Full-text

Comparison of Non-radiographic Axial Spondyloarthritis and Ankylosing Spondyltis from a Single Rheumatology Hospital in Morocco

Current Rheumatology Reviews ◽

10.2174/1573397115666190222195923 ◽

2020 ◽

Vol 16 (3) ◽

pp. 240-244 ◽

Cited By ~ 2

Author(s):

Nessrine Akasbi ◽

Siar Nihad ◽

Zoukal Sofia ◽

El Kohen Khadija ◽

Harzy Taoufik

Keyword(s):

Disease Burden ◽

Axial Spondyloarthritis ◽

Univariate Analysis ◽

Cross Sectional Study ◽

Low Back ◽

New Classification ◽

Cross Sectional ◽

Asas Criteria ◽

History Of ◽

High Level

Background: According to the new classification criteria developed by The Assessment of SpondyloArthritis International Society, patients with axial spondyloarthritis (axSpA) can be classified in 2 subgroups: Patients with radiographic axial spondyloarthritis: ankylosing spondylitis patients (AS) and those with non-radiographic axial spondyloarthritis (nr-axSpA). Objective: The aim of the present study is to describe and discuss the differences and similarities between the two subgroups. Patients and Methods: A cross-sectional study was conducted in a single rheumatology hospital in Morocco. These included patients diagnosed as having axial spondyloarthritis according to ASAS criteria 2010, during a period of 6 years. The AS and the nr-axSpA subgroups were compared for the various axSpA-related variables. Results: Of the 277 patients with a diagnosis of axial SpA who were included in this study, 160 had AS and 117 had nr-axSpA. AS and nr-ax-SpA shared a similar age at diagnosis, similar prevalence of low back pain, lumbar stiffness, extra-articular manifestations, BASDAI and BASFI. In the multivariate analysis, AS patients were mainly male with cervical stiffness, enthesitis, coxitis and high level of ESR (erythrocyte sedimentation rate). The females generally had a family history of SpA and arthritis and were associated to the nr-axSpA form in the univariate analysis. Conclusion: This was the first study to characterise patients with AS and nr-axSpA in Morocco. Consistent with other studies published, this study showed that patients with nr-axSpA and patients with AS shared a comparable degree of disease burden.

Download Full-text

Burnout Determinants among Nurses Working in Palliative Care during the Coronavirus Disease 2019 Pandemic

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18073358 ◽

2021 ◽

Vol 18 (7) ◽

pp. 3358

Author(s):

José Vítor Gonçalves ◽

Luísa Castro ◽

Guilhermina Rêgo ◽

Rui Nunes

Keyword(s):

Palliative Care ◽

Health Care Professionals ◽

Online Survey ◽

Three Dimensions ◽

Linear Regression Models ◽

Perceived Health Status ◽

Cross Sectional ◽

National Network ◽

Work Related ◽

High Level

Nurses working in palliative care are at risk of burnout. The Copenhagen Burnout Inventory was used to determine burnout levels of nurses working in the Portuguese national network of palliative care. We evaluated the contribution of personal, work, and COVID-19 variables in three burnout subclasses: personal, work, and patient-related. A cross-sectional, exploratory, and quantitative design was employed and participants were sampled using convenience and snowball technique. An online survey was conducted and 153 nurses participated in our study. Socio-demographic characterization was conducted, levels of burnout and determinants were explored through multiple linear regression models for its three dimensions. High levels of personal, working, and patient burnout were present in 71 (46%), 68 (44%), and 33 nurses (22%), respectively. Most of them agreed that COVID-19 had an impact on their activities. Significant personal and work related burnout factors found were specialization in palliative care, self-perceived health status, unit type, weekly hours of work, and allocation to COVID-19 units. Gender was found to be a significant factor in patient-related burnout. There is a high level of burnout among nurses working in the Portuguese national network of palliative care. Measures for identification and mitigation of burnout are necessary to protect health care professionals.

Download Full-text

Burnout and Its Relationship with Demographic and Job-Related Variables among Dentists in Lithuania: A Cross-Sectional Study

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18083968 ◽

2021 ◽

Vol 18 (8) ◽

pp. 3968

Author(s):

Eglė Slabšinskienė ◽

Andrej Gorelik ◽

Aistė Kavaliauskienė ◽

Apolinaras Zaborskis

Keyword(s):

Job Satisfaction ◽

Emotional Exhaustion ◽

Maslach Burnout Inventory ◽

Cross Sectional Study ◽

Personal Accomplishment ◽

Cross Sectional ◽

Satisfaction Index ◽

Sum Score ◽

Sum Scores ◽

High Level

Although burnout has been described as a serious hazard for personal and professional lives and has been surveyed among dentists in many countries, no study has been published regarding burnout among dentists in Lithuania. This study aimed to evaluate the burnout level among Lithuanian dentists and its association with demographic variables, job satisfaction, and other job-related variables. The data were collected among dentists online or during professional conferences while using an anonymous questionnaire (n = 380). The Maslach Burnout Inventory (MBI) was used to evaluate the burnout level. A Poisson regression was applied for the analysis of relationships between variables. We observed that 42.3% of the respondents had a high emotional exhaustion (EE) (95% confidence interval (CI): 37.4–42.3%), while 18.7% (95% CI: 15.0–22.9%) and 28,2% (95% CI: 23.4–32.6%) had high depersonalization (DP) and low personal accomplishment (PA), respectively. Nonetheless, 15.3% (95% CI: 11.8–18.9%) of the study population experienced a high level of overall burnout. An original job satisfaction index was elaborated. It was significantly associated with sum scores of all burnout dimensions: with the EE sum score (Ratio of Sum Score Means (RSSM) 1.54; 95% CI: 1.46–1.62), DP sum score (RSSM 1.59; 95% CI: 1.45–1.74), and PA sum score (RSSM 0.88; 95% CI: 0.84–0.92). It was concluded that Lithuanian dentists can be characterised by high burnout intensity and high prevalence of burnout, being especially evident in emotional exhaustion. The dentist with low job satisfaction appeared to be the most vulnerable to all burnout dimensions.

Download Full-text

Boundary Loss-Based 2.5D Fully Convolutional Neural Networks Approach for Segmentation: A Case Study of the Liver and Tumor on Computed Tomography

Algorithms ◽

10.3390/a14050144 ◽

2021 ◽

Vol 14 (5) ◽

pp. 144

Author(s):

Yuexing Han ◽

Xiaolong Li ◽

Bing Wang ◽

Lu Wang

Keyword(s):

Image Segmentation ◽

Spatial Information ◽

Medical Images ◽

Tumor Segmentation ◽

Convolutional Networks ◽

Learning Framework ◽

Fully Convolutional Networks ◽

Segmentation Accuracy ◽

Boundary Information

Image segmentation plays an important role in the field of image processing, helping to understand images and recognize objects. However, most existing methods are often unable to effectively explore the spatial information in 3D image segmentation, and they neglect the information from the contours and boundaries of the observed objects. In addition, shape boundaries can help to locate the positions of the observed objects, but most of the existing loss functions neglect the information from the boundaries. To overcome these shortcomings, this paper presents a new cascaded 2.5D fully convolutional networks (FCNs) learning framework to segment 3D medical images. A new boundary loss that incorporates distance, area, and boundary information is also proposed for the cascaded FCNs to learning more boundary and contour features from the 3D medical images. Moreover, an effective post-processing method is developed to further improve the segmentation accuracy. We verified the proposed method on LITS and 3DIRCADb datasets that include the liver and tumors. The experimental results show that the performance of the proposed method is better than existing methods with a Dice Per Case score of 74.5% for tumor segmentation, indicating the effectiveness of the proposed method.

Download Full-text

Utterance Level Feature Aggregation with Deep Metric Learning for Speech Emotion Recognition

Sensors ◽

10.3390/s21124233 ◽

2021 ◽

Vol 21 (12) ◽

pp. 4233

Author(s):

Bogdan Mocanu ◽

Ruxandra Tapu ◽

Titus Zaharia

Keyword(s):

Emotion Recognition ◽

Loss Function ◽

State Of The Art ◽

Disease Diagnosis ◽

Data Representation ◽

Speech Emotion Recognition ◽

Audio Features ◽

Global Accuracy ◽

Space Data ◽

Art Techniques

Emotion is a form of high-level paralinguistic information that is intrinsically conveyed by human speech. Automatic speech emotion recognition is an essential challenge for various applications; including mental disease diagnosis; audio surveillance; human behavior understanding; e-learning and human–machine/robot interaction. In this paper, we introduce a novel speech emotion recognition method, based on the Squeeze and Excitation ResNet (SE-ResNet) model and fed with spectrogram inputs. In order to overcome the limitations of the state-of-the-art techniques, which fail in providing a robust feature representation at the utterance level, the CNN architecture is extended with a trainable discriminative GhostVLAD clustering layer that aggregates the audio features into compact, single-utterance vector representation. In addition, an end-to-end neural embedding approach is introduced, based on an emotionally constrained triplet loss function. The loss function integrates the relations between the various emotional patterns and thus improves the latent space data representation. The proposed methodology achieves 83.35% and 64.92% global accuracy rates on the RAVDESS and CREMA-D publicly available datasets, respectively. When compared with the results provided by human observers, the gains in global accuracy scores are superior to 24%. Finally, the objective comparative evaluation with state-of-the-art techniques demonstrates accuracy gains of more than 3%.

Download Full-text

AB0564 RHEUMATOLOGISTS’ VIEWS AND EXPERIENCES IN MANAGING PsA PATIENTS BASED ON TREATING TO TARGET STRATEGY: A CROSS-SECTIONAL STUDY IN CHINA

Annals of the Rheumatic Diseases ◽

10.1136/annrheumdis-2021-eular.3438 ◽

2021 ◽

Vol 80 (Suppl 1) ◽

pp. 1318.2-1319

Author(s):

L. Xu ◽

Z. Wang ◽

J. Xue ◽

M. Bai ◽

H. Zhong ◽

...

Keyword(s):

Clinical Practice ◽

Psoriatic Arthritis ◽

Disease Activity ◽

Western Medicine ◽

Work Experience ◽

Tertiary Hospital ◽

Treat To Target ◽

Cross Sectional ◽

Activity Assessment ◽

High Level

Background:Psoriatic arthritis (PsA) is a chronic inflammatory arthritis with progressive, erosive destruction associated with functional impairment. Principles of treat-to-target (T2T) have been widely used in rheumatoid arthritis, which has powerfully improved patient outcomes. In 2017, the concept of T2T has proposed to apply in PsA patients. However, the awareness and implementation of evidence-based T2T treatment guidelines varies across different geographical regions of China, hospital grades, professional status and specialities.Objectives:The study aimed to investigate Rheumatologists’ views and experiences in managing PsA patients with T2T strategy in china.Methods:A cross-sectional questionnaire survey of Rheumatologists in China from 5 August to 15 August 2020 was conducted for this study. Rheumatologists were contacted by WeChat (a Chinese cell/web app) and asked to complete a web-based questionnaire anonymously. The electronic questionnaire was sent out by the internet platform of WenJuanXing via WeChat (https://www.wjx.cn/). The questionnaire was designed to collect: (a) demographic information; (b) patient management in clinical practice for Rheumatologists; (c) familiarity and application of T2T strategy in Rheumatologists. P values ≤0.05 were considered significant.Results:(1) A total of 823 rheumatologists (69.87% female, 30.13% male) provided valid answers to the questionnaire. 71.09% of the participants major in Modern Western Medicine, 28.91% major in traditional chinese medicine. A total of 75.94% worked in Grade-A Tertiary Hospital. A total of 52.73% had more than 10 years of work experience and 63.55% had High-level title. (2) More than half of the patients were followed up by 69% Rheumatologists in their daily practice. The proportion of follow-up patients increased powerfully in the group of Rheumatologists who major in Modern Western Medicine (P=0.014), work in Grade-A Tertiary Hospital (P<0.001), have more than 10 years of work experience (P<0.001) and High-level title (P<0.001). (3) 36.45% Rheumatologist thought the frequency for patient disease activity assessment was every 1 month and 53.1% was every 3 months. And 41.7% Rheumatologist prefer to use PASDAS for disease activity criteria, and only 3.6% choose MDA. (4) A total of 62.43% thought they were familiar with T2T strategy, and 83.6% Rheumatologists applied T2T strategy in clinical practice. Among 135 Rheumatologists who did not apply T2T strategy, 62.2% of Rheumatologists thought that the main barrier to T2T application was that they did not fully understand the strategy. The frequency of application of T2T strategy in clinical practice was significantly different between Rheumatologists who major in Modern Western Medicine (60.75%) and traditional chinese medicine (22.84%) (P=0.023).Conclusion:In china, the management of PsA patients need to be standardized to improve patient outcomes. And the promotion of T2T strategy in PsA need to be further strengthened.References:[1]Smolen JS, Schöls M, Braun J,et al. Treating axial spondyloarthritis and peripheral spondyloarthritis, especially psoriatic arthritis, to target: 2017 update of recommendations by an international task force. Ann Rheum Dis. 2018 Jan;77(1):3-17.[2]Tucker LJ, Ye W, Coates LC. Novel Concepts in Psoriatic Arthritis Management: Can We Treat to Target? Curr Rheumatol Rep. 2018 Sep 18;20(11):71.[3]Coates LC, Helliwell PS. Treating to target in psoriatic arthritis: how to implement in clinical practice. Ann Rheum Dis. 2016;75(4):640-643.Figure 1A. Rheumatologist priority of frequency for patient follow-up in different disease status. B. Rheumatologist priority of frequency for patient disease activity assessment in clinical practice. C. Rheumatologist priority of disease activity criteria for PsA patients.Disclosure of Interests:None declared.

Download Full-text

COVID-19 Vaccine Acceptance in Azuay Province, Ecuador: A Cross-Sectional Online Survey

Vaccines ◽

10.3390/vaccines9060678 ◽

2021 ◽

Vol 9 (6) ◽

pp. 678

Author(s):

Julio Jaramillo-Monge ◽

Michael Obimpeh ◽

Bernardo Vega ◽

David Acurio ◽

Annelies Boven ◽

...

Keyword(s):

Rural Areas ◽

Online Survey ◽

Vaccination Campaign ◽

Postgraduate Education ◽

Effective Vaccine ◽

Cross Sectional ◽

Lower Education Level ◽

Vaccination Acceptance ◽

History Of ◽

High Level

We investigated the COVID-19 vaccination acceptance level in Azuay province, Ecuador through an online survey from 12th to 26th February (before the start of the COVID-19 vaccination campaign in Ecuador). Overall, 1219 respondents participated in the survey. The mean age was 32 ± 13 years; 693 participants (57%) were female. In total, 1109 (91%) of the participants indicated they were willing to be vaccinated with a COVID-19 vaccine, if the vaccine is at least 95% effective; 835 (68.5%) if it is 90% effective and 493 (40.5%) if it is 70% effective; 676 (55.5%) participants indicated they feared side effects and 237 (19.4%) thought the vaccine was not effective. Older age, having had a postgraduate education, a history of a negative COVID-19 test, a high level of worry of contracting COVID-19, believing that COVID-19 infection can be prevented with a vaccine and understanding there is currently an effective vaccine against COVID-19 were associated with higher vaccination acceptance. A vaccination education campaign will be needed to increase the knowledge of Ecuadorians about the COVID-19 vaccine and to increase their trust in the vaccine. People with a lower education level and living in rural areas may need to be targeted during such a campaign.

Download Full-text