scholarly journals SAR-to-Optical Image Translation Based on Conditional Generative Adversarial Networks—Optimization, Opportunities and Limits

2019 ◽  
Vol 11 (17) ◽  
pp. 2067 ◽  
Author(s):  
Mario Fuentes Reyes ◽  
Stefan Auer ◽  
Nina Merkle ◽  
Corentin Henry ◽  
Michael Schmitt
Keyword(s):  
Remote Sensing ◽  
Optical Image ◽  
Generative Adversarial Networks ◽  
Sar Image ◽  
Image Translation ◽  
Study Results ◽  
Image Representations ◽  
The Impact ◽  
Sar Remote Sensing

Due to its all time capability, synthetic aperture radar (SAR) remote sensing plays an important role in Earth observation. The ability to interpret the data is limited, even for experts, as the human eye is not familiar to the impact of distance-dependent imaging, signal intensities detected in the radar spectrum as well as image characteristics related to speckle or steps of post-processing. This paper is concerned with machine learning for SAR-to-optical image-to-image translation in order to support the interpretation and analysis of original data. A conditional adversarial network is adopted and optimized in order to generate alternative SAR image representations based on the combination of SAR images (starting point) and optical images (reference) for training. Following this strategy, the focus is set on the value of empirical knowledge for initialization, the impact of results on follow-up applications, and the discussion of opportunities/drawbacks related to this application of deep learning. Case study results are shown for high resolution (SAR: TerraSAR-X, optical: ALOS PRISM) and low resolution (Sentinel-1 and -2) data. The properties of the alternative image representation are evaluated based on feedback from experts in SAR remote sensing and the impact on road extraction as an example for follow-up applications. The results provide the basis to explain fundamental limitations affecting the SAR-to-optical image translation idea but also indicate benefits from alternative SAR image representations.

scholarly journals Body Composition in Community-Dwelling Older Adults Before and After SARS-CoV-2 Infection: A Longitudinal Prospective Study in a Rural Village Struck by the Pandemic

2021 ◽  
Vol 12 ◽  
pp. 215013272110477
Author(s):  
Oscar H. Del Brutto ◽  
Robertino M. Mera ◽  
Denisse A. Rumbea ◽  
Pedro Pérez ◽  
Bettsy Y. Recalde ◽  
...  
Keyword(s):  
Physical Activity ◽  
Older Adults ◽  
Body Composition ◽  
Regression Models ◽  
Community Dwelling ◽  
The Body ◽  
Study Results ◽  
The Impact ◽  
Community Dwelling Older Adults

Background: Information on the body composition of inhabitants of remote communities during the SARS-CoV-2 pandemic is limited. Using a longitudinal population-based study design, we assessed the association between SARS-CoV-2 infection and changes in body composition. Methods: Community-dwelling older adults living in a rural Ecuadorian village received body composition determinations before and 1 year after the pandemic as well as serological tests for detection of SARS-CoV-2 antibodies. The independent association between SARS-CoV-2 infection and abnormalities in body composition at follow-up was assessed by fitting linear mixed models for longitudinal data. Results: Of 327 enrolled individuals, 277 (85%) received baseline and follow-up body composition determinations, and 175 (63%) of them became SARS-CoV-2 seropositive. Overall, diet and physical activity deteriorated during the follow-up. Multivariate random-effects generalized least squares regression models that included the impact of time and seropositivity on follow-up body composition, showed that neither variable contributed to a worsening in body composition. Multivariate logistic regression models disclosed that the serological status at follow-up cannot be predicted by differences in body composition and other baseline covariates. Conclusions: Study results suggest no increased susceptibility to SARS-CoV-2 infection among older adults with abnormal body composition and no significant changes as a result of worse physical activity and dietary habits or seropositivity during the length of the study. Together with a previous study in the same population that showed decrease in hand-grip strength after SARS-CoV-2, results confirm that dynapenia (and not sarcopenia) is associated with SARS-CoV-2 infection in older adults.

A simulation study of loss to follow up: The impact on time to event and prevention.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e14097-e14097
Author(s):  
Donna Elise Levy ◽  
Bingyan Wu ◽  
Daniel Quinn ◽  
Sophie Jentzsch ◽  
Christine Lusk ◽  
...  
Keyword(s):  
Treatment Options ◽  
Patient Treatment ◽  
Future Research ◽  
Time To Event ◽  
Loss To Follow Up ◽  
Study Results ◽  
Patient Attrition ◽  
The Impact ◽  
Future Patient

e14097 Background: Patient attrition during study follow up is a concern in all clinical trials, although its impact on study results has rarely been assessed. In oncology, in particular, where studies are lengthier and may be extended into longitudinal studies, there is an increased likelihood of loss to follow up (LTFU) (Gill et al., 2018). This creates a heightened need to understand how it affects the trial’s validity. The loss of data from patients who have been LTFU can reduce a study’s precision and power. This imprecision not only impacts the results of the current study but can also affect future research as well as future patient treatment options. Studies have found that participant characteristics differ in individuals LTFU as compared to those who remain in follow up (Childs et al., 2011; Geng et al., 2008; Hochheimer et al., 2016). This further emphasizes how attrition can skew study results and their interpretation and supports the need to minimize patient attrition during follow up in order to reduce bias and generate robust study estimates. Methods: This study assessed the impact of LTFU rates on the study estimates through simulations using SAS software. While all endpoints can be affected by LTFU, this study assessed time-to-event endpoints. Exponential distribution was assumed with varying rates of LTFU. In addition, the work covered suggestions for reducing LTFU. Results: Even for low rates of LTFU, biases are introduced in time-to event endpoints. Conclusions: Researchers should make every effort to minimize the extent of LTFU in the design and of and conduct of their trials.

Interim analysis of a phase 2 minimal residual disease (MRD)-adaptive trial of elotuzumab, carfilzomib, lenalidomide, and dexamethasone (Elo-KRd) for newly diagnosed multiple myeloma (MM).

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 8011-8011
Author(s):  
Benjamin Avi Derman ◽  
Jeffrey A. Zonder ◽  
Ankit J. Kansagra ◽  
David L. Grinblatt ◽  
Sunil Narula ◽  
...  
Keyword(s):  
Stem Cell ◽  
High Risk ◽  
Primary Endpoint ◽  
Adaptive Design ◽  
Cell Transplant ◽  
Phase 2 ◽  
Newly Diagnosed ◽  
Study Results ◽  
The Impact

8011 Background: The addition of a monoclonal antibody to triplet induction regimens in patients (pts) with MM with intent for autologous stem cell transplant (ASCT) has resulted in higher overall and deep response rates. In this study we are investigating the impact of the addition of Elo to KRd on complete response (CR) and/or MRD-negative rates in newly diagnosed MM regardless of transplant eligibility. Methods: Pts were enrolled from four MM Research Consortium sites into this phase 2 study. All patients receive 12 cycles of Elo-KRd in 28-day cycles: Elo per standard dosing, K 20/56/70 mg/m2 days 1, 8 and 15, R 25 mg days 1-21, and dexamethasone 40 mg days 1, 8, 15, 22. ASCT eligible candidates can undergo stem cell collection after cycle 4 and then resume treatment; pts who elect to proceed to ASCT are censored for response at that time. Pts MRD(-) (<10-5) by NGS after cycles 8 (C8) and 12 (C12) proceed to Elo-Rd until progression. Patients who convert from MRD(+) to MRD(-) between C8 and C12 receive an additional 6 cycles of Elo-KRd (total 18 cycles) followed by Elo-Rd, and pts MRD(+) after C12 receive an additional 12 cycles of Elo-KRd (total 24) followed by Elo-Rd. The primary endpoint of the study is sCR and/or MRD(-) rate after C8 E-KRd. MRD status was determined by ClonoSEQ next generation sequencing (NGS, <10-5) [Adaptive Biotechnologies]. An improvement in the sCR and/or MRD(-) rate by NGS from a historical 30% to 50% at the end of C8 will be considered promising. Results: 44 pts are enrolled, 39 of whom are evaluable for response (cutoff Jan 10 2021). Median age is 62 years (range 43-81, 23% age >70) and 23 (52%) have high-risk cytogenetic abnormalities (HRCA) including 13 (30%) with >2 high-risk abnormalities (6 pts unknown cytogenetics). 34/39 (87%) have MRD trackable by clonoSEQ. The rate of sCR and/or MRD(-) by NGS at the end of C8 is 19/33 (58%), meeting the statistical threshold for establishing efficacy (2 pts censored for elective ASCT before C8 and 4 pts receiving therapy but have not reached C8). With a median follow-up of 24 months, estimated 2-year progression free survival is 87% (100% for standard risk, 79% for HRCA) and estimated 2-year overall survival is 89% (82% for HRCA). No pt who was MRD(-) by NGS after C8 has progressed, including 6 pts with HRCA. Serious adverse events occurred in 30 pts (68%). 89% experienced treatment emergent AEs, the most common (>10%) of which was pneumonia (14%). One pt had grade 5 myocardial infarction. Conclusions: Elo-KRd demonstrates tolerability consistent with known toxicities of these agents and met the primary endpoint of sCR and/or MRD(-) of >50% after 8 cycles. With longer follow-up, the study results may validate that an MRD-adaptive design for de-escalation of therapy in MM can generate deep responses while reducing treatment exposure. Clinical trial information: NCT02969837.

Fine-needle aspiration of pancreatic cystic lesions: A randomized study comparing standard and flexible needles with long-term follow-up.

Endoscopy ◽  
2020 ◽  
Author(s):  
Mohammad Al-Haddad ◽  
Michael B Wallace ◽  
William Brugge ◽  
Sundeep Lakhtakia ◽  
Zhaoshen Li ◽  
...  
Keyword(s):  
Diagnostic Accuracy ◽  
Fine Needle Aspiration ◽  
Needle Aspiration ◽  
Cystic Lesions ◽  
Fine Needle ◽  
Cyst Volume ◽  
Study Results ◽  
Consensus Diagnosis ◽  
The Impact

Abstract Background and study aims: Pancreatic cystic lesions (PCLs) are increasingly found on cross-sectional imaging, and a majority have low risk for malignancy. The added value of fine-needle aspiration (FNA) in risk stratification remains unclear. We evaluated the impact of 3 FNA needles on diagnostic accuracy, clinical management, and ability to accrue fluid for tumor markers. Patients and methods: A multicenter prospective trial randomized 250 patients with PCLs≥13mm to 19G Flex(2):19G(1):22G(1) needles with cross-over as repeated FNA procedures. Diagnostic accuracy established at 2-year follow-up with final diagnosis from surgical histopathology or consensus diagnosis by experts based sequentially on clinical presentation, imaging, and aspirate analysis in blinded review. Results: Patients enrolled (36% symptomatic) with PCLs in head (44%), body (28%), and tail (26%). Percentage of cyst volume aspiration is 78% [72%-84%] for 19G Flex, 74% [64%-84%] for 22G, and 73% [63%-83%] for19G (p=.84). Successful FNA was significantly higher for 19G Flex (89% [82%-94%]) and 22G (82% [70%-90%]) compared to 19G (75% [63%-85%]) (p=0.02). Repeated FNA was required more frequently in head/uncinate lesions than body and tail (p<.01). Diagnostic accuracy of cyst aspirate was 84% [73%-91%] against histopathology at 2-year follow-up (n=79), and 77% [70%-83%] against consensus diagnosis among non-resective cases (n=171). Related serious adverse events occurred in 1.2% [0.2%-3.5%] of patients. Conclusions: Our study results demonstrate a statistically significant difference among the three needles in overall success rate of aspiration, but not in percentage of cyst volume aspirated. Flexible needles may be particularly valuable in sampling cystic PCLs in head/uncinate of pancreas.

scholarly journals Edge-Preserving Convolutional Generative Adversarial Networks for SAR-to-Optical Image Translation

2021 ◽  
Vol 13 (18) ◽  
pp. 3575
Author(s):  
Jie Guo ◽  
Chengyu He ◽  
Mingjin Zhang ◽  
Yunsong Li ◽  
Xinbo Gao ◽  
...  
Keyword(s):  
Speckle Noise ◽  
Optical Image ◽  
Optical Methods ◽  
Generative Adversarial Networks ◽  
Feature Maps ◽  
Sar Images ◽  
Generative Adversarial Network ◽  
Edge Preserving ◽  
Image Translation ◽  
Content Adaptive

With the ability for all-day, all-weather acquisition, synthetic aperture radar (SAR) remote sensing is an important technique in modern Earth observation. However, the interpretation of SAR images is a highly challenging task, even for well-trained experts, due to the imaging principle of SAR images and the high-frequency speckle noise. Some image-to-image translation methods are used to convert SAR images into optical images that are closer to what we perceive through our eyes. There exist two weaknesses in these methods: (1) these methods are not designed for an SAR-to-optical translation task, thereby losing sight of the complexity of SAR images and the speckle noise. (2) The same convolution filters in a standard convolution layer are utilized for the whole feature maps, which ignore the details of SAR images in each window and generate images with unsatisfactory quality. In this paper, we propose an edge-preserving convolutional generative adversarial network (EPCGAN) to enhance the structure and aesthetics of the output image by leveraging the edge information of the SAR image and implementing content-adaptive convolution. The proposed edge-preserving convolution (EPC) decomposes the content of the convolution input into texture components and content components and then generates a content-adaptive kernel to modify standard convolutional filter weights for the content components. Based on the EPC, the EPCGAN is presented for SAR-to-optical image translation. It uses a gradient branch to assist in the recovery of structural image information. Experiments on the SEN1-2 dataset demonstrated that the proposed method can outperform other SAR-to-optical methods by recovering more structures and yielding a superior evaluation index.

scholarly journals COVID-PCD – a participatory research study on the impact of COVID-19 in people with Primary Ciliary Dyskinesia

2020 ◽  
Author(s):  
Eva SL Pedersen ◽  
Eugénie NR Collaud ◽  
Rebeca Mozun ◽  
Cristina Ardura-Garcia ◽  
Yin Ting Lam ◽  
...  
Keyword(s):  
Support Groups ◽  
Social Contact ◽  
Epidemiological Data ◽  
Course Of Disease ◽  
Baseline Questionnaire ◽  
Study Results ◽  
Contact Behaviour ◽  
The Impact ◽  
Ciliary Dyskinesia

AbstractIntroductionCOVID-PCD is a participatory study initiated by people with PCD who have an essential vote in all stages of the research from the design of the study to the recruitment of participants, and interpretation and communication of the study results. COVID-PCD aims to collect epidemiological data in real time from people with PCD throughout the pandemic to describe incidence of COVID-19, symptoms, and course of disease; identify risk factors for prognosis; and assess experiences, wishes, and needs.MethodsThe study is advertised through patient support groups and participants register online on the study website (www.covid19pcd.ispm.ch). The study invites persons of any age from anywhere in the world with a suspected or confirmed PCD. A baseline questionnaire assesses details on PCD diagnosis, habitual symptoms, and COVID-19 episodes that occurred before study entry. Afterwards, participants receive a weekly follow-up questionnaire with questions on incident SARS-CoV-2 infections, current symptoms, social contact behaviour, and physical activity. Occasional thematic questionnaires are sent out focusing on emerging questions of interest chosen by people with PCD. In case of hospitalisation, patients or family members are asked to obtain a hospital report. Results are continuously analysed and summaries put online.ConclusionThe study started recruitment on April 30, 2020, and 556 people with PCD completed the baseline questionnaire by November 2, 2020. The COVID-PCD study is a participatory study that follows people with PCD during the COVID-19 pandemic, helps to empower affected persons, and serves as a platform for communication between patients, physicians, and researchers.

scholarly journals A COMPARATIVE ANALYSIS OF UNSUPERVISED AND SEMI-SUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CATEGORIZATION

2019 ◽  
Vol IV-2/W7 ◽  
pp. 167-173 ◽  
Author(s):  
P. J. Soto ◽  
J. D. Bermudez ◽  
P. N. Happ ◽  
R. Q. Feitosa
Keyword(s):  
Remote Sensing ◽  
Representation Learning ◽  
Fine Tuning ◽  
Generative Adversarial Networks ◽  
Image Categorization ◽  
Absolute Value ◽  
Adversarial Networks ◽  
Novel Approach ◽  
Public Datasets ◽  
The Impact

<p><strong>Abstract.</strong> This work aims at investigating unsupervised and semi-supervised representation learning methods based on generative adversarial networks for remote sensing scene classification. The work introduces a novel approach, which consists in a semi-supervised extension of a prior unsupervised method, known as MARTA-GAN. The proposed approach was compared experimentally with two baselines upon two public datasets, <i>UC-MERCED</i> and <i>NWPU-RESISC45</i>. The experiments assessed the performance of each approach under different amounts of labeled data. The impact of fine-tuning was also investigated. The proposed method delivered in our analysis the best overall accuracy under scarce labeled samples, both in terms of absolute value and in terms of variability across multiple runs.</p>

scholarly journals Quality Assessment of SAR-to-Optical Image Translation

2020 ◽  
Vol 12 (21) ◽  
pp. 3472
Author(s):  
Jiexin Zhang ◽  
Jianjiang Zhou ◽  
Minglei Li ◽  
Huiyu Zhou ◽  
Tianzhu Yu
Keyword(s):  
Quality Assessment ◽  
Image Quality Assessment ◽  
Speckle Noise ◽  
Optical Image ◽  
Visual Interpretation ◽  
Translation Quality ◽  
Evaluation Approach ◽  
Image Translation ◽  
Optical Modes ◽  
Image Representations

Synthetic aperture radar (SAR) images contain severe speckle noise and weak texture, which are unsuitable for visual interpretation. Many studies have been undertaken so far toward exploring the use of SAR-to-optical image translation to obtain near optical representations. However, how to evaluate the translation quality is a challenge. In this paper, we combine image quality assessment (IQA) with SAR-to-optical image translation to pursue a suitable evaluation approach. Firstly, several machine-learning baselines for SAR-to-optical image translation are established and evaluated. Then, extensive comparisons of perceptual IQA models are performed in terms of their use as objective functions for the optimization of image restoration. In order to study feature extraction of the images translated from SAR to optical modes, an application in scene classification is presented. Finally, the attributes of the translated image representations are evaluated using visual inspection and the proposed IQA methods.

scholarly journals Psychological Ethical Climate in Schools and Teachers’ Performance: Analyzing the Effect on Government and Private Teachers

2021 ◽  
Vol 9 (3) ◽  
pp. 309-316
Author(s):  
Syed Zubair Haider ◽  
Rafaquat Ali ◽  
Syeda Sidra Nosheen
Keyword(s):  
Private Schools ◽  
Private School ◽  
Ethical Climate ◽  
Government Schools ◽  
Descriptive Research ◽  
Study Results ◽  
Climate Scale ◽  
The Impact ◽  
Performance Scale

The present research examined the impact of psychological ethical climate on teachers’ performance in government and private schools of Bahawalpur. In this study, the descriptive research design was used, and data were collected through two scales, such as the psychological ethical climate scale developed by Schwepker, Ferrell, and Ingram (1997) and the teachers’ job performance scale developed by Akhtar and Haider (2017). The simple random and convenient sampling techniques were used to select government ESEs and private school teachers and their principals to rate their performance. Total 280 questionnaires were distributed among teachers, and 60 questionnaires were provided to principals, and the response rate was 100% due to vigorous follow-up by the researchers. Researchers applied different statistical techniques to the collected data to get accurate results. This study revealed that both government and private teachers highly displayed a psychological ethical climate in their schools. The study results showed that psychological ethical climate has a statistically significant effect on teachers’ performance in private schools. At the same time, the effect was insignificant in government schools.

Sign in / Sign up

Export Citation Format

Share Document