Federated Deep Learning to More Reliably Detect Body Part for Hanging Protocols, Relevant Priors, and Workflow Optimization

2022 ◽  
Author(s):  
Ross W. Filice ◽  
Anouk Stein ◽  
Ian Pan ◽  
George Shih
Keyword(s):  
Deep Learning ◽  
Body Part ◽  
Workflow Optimization ◽  
Hanging Protocols

scholarly journals Analysis of COVID-19 Chest X-ray Data using an Ensemble of Different Convolutional Architectures

2021 ◽  
Vol 9 (10) ◽  
pp. 1830-1835
Author(s):  
Gaurav Sharma
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Oxygen Saturation ◽  
Common Cold ◽  
Body Part ◽  
X Ray ◽  
Proposed Model ◽  
Unique Model ◽  
Viral Influenza ◽  
Chest X Ray

Abstract: After every 100 years, a pandemic comes and takes a great toll on the global civilization. This time its COVID-19 and the aftereffects are terrifying. As the symptoms for the disease are very common and are similar to common cold and viral influenza, the detection from symptoms is quite difficult. Although there are many methods devised but the detection of COVID19 has been a problem since the start, and we are still struggling to identify whether a person has the disease. This study proposes a unique model to identify the positive and negative cases using X-ray images of an individual as lungs are the first and most critical body part which gets affected by the virus which causes a deprecation in oxygen saturation. The proposed model is an ensemble of different CNN architectures which are Dense Net, NasNet-Large, Resnet-50, Inception Net, EfficientNetB0 and EfficientNetB1. The results show that the model reaches an accuracy of 99.6% on the tested dataset. Keywords: Deep learning, Convolutional Neural Networks, COVID-19, Ensemble Learning, EfficientNet

scholarly journals Fast body part segmentation and tracking of neonatal video data using deep learning

2020 ◽  
Vol 58 (12) ◽  
pp. 3049-3061
Author(s):  
Christoph Hoog Antink ◽  
Joana Carlos Mesquita Ferreira ◽  
Michael Paul ◽  
Simon Lyra ◽  
Konrad Heimann ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Neonatal Intensive Care ◽  
Near Infrared ◽  
Data Augmentation ◽  
Region Of Interest ◽  
Semantic Segmentation ◽  
Body Part ◽  
Video Data ◽  
Computational Time

AbstractPhotoplethysmography imaging (PPGI) for non-contact monitoring of preterm infants in the neonatal intensive care unit (NICU) is a promising technology, as it could reduce medical adhesive-related skin injuries and associated complications. For practical implementations of PPGI, a region of interest has to be detected automatically in real time. As the neonates’ body proportions differ significantly from adults, existing approaches may not be used in a straightforward way, and color-based skin detection requires RGB data, thus prohibiting the use of less-intrusive near-infrared (NIR) acquisition. In this paper, we present a deep learning-based method for segmentation of neonatal video data. We augmented an existing encoder-decoder semantic segmentation method with a modified version of the ResNet-50 encoder. This reduced the computational time by a factor of 7.5, so that 30 frames per second can be processed at 960 × 576 pixels. The method was developed and optimized on publicly available databases with segmentation data from adults. For evaluation, a comprehensive dataset consisting of RGB and NIR video recordings from 29 neonates with various skin tones recorded in two NICUs in Germany and India was used. From all recordings, 643 frames were manually segmented. After pre-training the model on the public adult data, parts of the neonatal data were used for additional learning and left-out neonates are used for cross-validated evaluation. On the RGB data, the head is segmented well (82% intersection over union, 88% accuracy), and performance is comparable with those achieved on large, public, non-neonatal datasets. On the other hand, performance on the NIR data was inferior. By employing data augmentation to generate additional virtual NIR data for training, results could be improved and the head could be segmented with 62% intersection over union and 65% accuracy. The method is in theory capable of performing segmentation in real time and thus it may provide a useful tool for future PPGI applications.

scholarly journals Private Body Part Detection using Deep Learning

2020 ◽  
Author(s):  
André Tabone ◽  
Alexandra Bonnici ◽  
Stefania Cristina ◽  
Reuben Farrugia ◽  
Kenneth Camilleri
Keyword(s):  
Deep Learning ◽  
Body Part

scholarly journals Localization and Classification of Brain Tumor using Machine Learning & Deep Learning Techniques

2019 ◽  
Vol 8 (9S) ◽  
pp. 59-66
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Brain Tumor ◽  
State Of The Art ◽  
Body Part ◽  
X Rays ◽  
Meaningful Information ◽  
Learning Techniques ◽  
The Brain

Digital image processing is a rising field for the investigation of complicated diseases such as brain tumor, breast cancer, kidney stones, lung cancer, ovarian cancer, and cervix cancer and so on. The recognition of the brain tumor is considered to be a very critical task. A number of approaches are used for the scanning of a particular body part like CT scan, X-rays, and Magnetic Resonance Image (MRI). These pictures are then examined by the surgeons for the removal of the problem. The main objective of examining these MRI images (mainly) is to extract the meaningful information with high accuracy. Machine Learning and Deep Learning algorithms are mainly used for analysing the medical images which can identify, localize and classify the brain tumor into sub categories, according to which the diagnosis would be done by the professionals. In this paper, we have discussed the different techniques that are used for tumor pre-processing, segmentation, localization, extraction of features and classification and summarize more than 30 contributions to this field. Also, we discussed the existing state-of-the-art, literature gaps, open challenges and future scope in this area.

scholarly journals Segmentation Trachea and Bronchial Branches in Chest Computed Tomography Image by Deep Learning - preliminary results -

10.29007/r6cd ◽  
2022 ◽  
Author(s):  
Hoang Nhut Huynh ◽  
My Duyen Nguyen ◽  
Thai Hong Truong ◽  
Quoc Tuan Nguyen Diep ◽  
Anh Tu Tran ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Medical Images ◽  
Semantic Segmentation ◽  
Body Part ◽  
Medical Image Segmentation ◽  
Superior Performance ◽  
Research Issues ◽  
Tomography Image ◽  
Computed Tomography Image

Segmentation is one of the most common methods for analyzing and processing medical images, assisting doctors in making accurate diagnoses by providing detailed information about the required body part. However, segmenting medical images presents a number of challenges, including the need for medical professionals to be trained, the fact that it is time-consuming and prone to errors. As a result, it appears that an automated medical image segmentation system is required. Deep learning algorithms have recently demonstrated superior performance for segmentation tasks, particularly semantic segmentation networks that provide a pixel-level understanding of images. U- Net for image segmentation is one of the modern complex networks in the field of medical imaging; several segmentation networks have been built on its foundation with the advancements of Recurrent Residual convolutional units and the construction of recurrent residual convolutional neural network based on U-Net (R2U-Net). R2U-Net is used to perform trachea and bronchial segmentation on a dataset of 36,000 images. With a variety of experiments, the proposed segmentation resulted in a dice-coefficient of 0.8394 on the test dataset. Finally, a number of research issues are raised, indicating the need for future improvements.

scholarly journals Human body part estimation from depth images via spatially-constrained deep learning

2014 ◽  
Vol 50 ◽  
pp. 122-129 ◽  
Author(s):  
Mingyuan Jiu ◽  
Christian Wolf ◽  
Graham Taylor ◽  
Atilla Baskurt
Keyword(s):  
Deep Learning ◽  
Human Body ◽  
Body Part ◽  
Depth Images ◽  
Human Body Part

Behavioral Factors Impact Impairment and Disability Evaluation

2011 ◽  
Vol 16 (5) ◽  
pp. 5-7
Author(s):  
Lee Ensalada
Keyword(s):  
Social History ◽  
Standardized Test ◽  
Somatoform Disorders ◽  
Disability Evaluation ◽  
Body Part ◽  
Emotional Reactions ◽  
Illness Behavior ◽  
Validity Testing ◽  
Symptom Validity Testing ◽  
Disease Pattern

Abstract Illness behavior refers to the ways in which symptoms are perceived, understood, acted upon, and communicated and include facial grimacing, holding or supporting the affected body part, limping, using a cane, and stooping while walking. Illness behavior can be unconscious or conscious: In the former, the person is unaware of the mental processes and content that are significant in determining behavior; conscious illness behavior may be voluntary and conscious (the two are not necessarily associated). The first broad category of inappropriate illness behavior is defensiveness, which is characterized by denial or minimization of symptoms. The second category includes somatoform disorders, factitious disorders, and malingering and is characterized by exaggerating, fabricating, or denying symptoms; minimizing capabilities or positive traits; or misattributing actual deficits to a false cause. Evaluators can detect the presence of inappropriate illness behaviors based on evidence of consistency in the history or examination; the likelihood that the reported symptoms make medical sense and fit a reasonable disease pattern; understanding of the patient's current situation, personal and social history, and emotional predispositions; emotional reactions to symptoms; evaluation of nonphysiological findings; results obtained using standardized test instruments; and tests of dissimulation, such as symptom validity testing. Unsupported and insupportable conclusions regarding inappropriate illness behavior represent substandard practice in view of the importance of these conclusions for the assessment of impairment or disability.

Letter to the Editor: The Continuing Challenge of Evaluating RSD Impairment and Disability

1998 ◽  
Vol 3 (5) ◽  
pp. 8-10
Author(s):  
Robert L. Knobler ◽  
Charles N. Brooks ◽  
Leon H. Ensalada ◽  
James B. Talmage ◽  
Christopher R. Brigham
Keyword(s):  
Disability Evaluation ◽  
Body Part ◽  
Loss Of Function ◽  
Regulatory Requirements ◽  
Major Cardiac Event ◽  
Clinical Scenarios ◽  
Impairment Score ◽  
Occupational Activities ◽  
The Difference

Abstract The author of the two-part article about evaluating reflex sympathetic dystrophy (RSD) responds to criticisms that a percentage impairment score may not adequately reflect the disability of an individual with RSD. The author highlights the importance of recognizing the difference between impairment and disability in the AMA Guides to the Evaluation of Permanent Impairment (AMA Guides): impairment is the loss, loss of use, or derangement of any body part, system, or function; disability is a decrease in or the loss or absence of the capacity to meet personal, social, or occupational demands or to meet statutory or regulatory requirements because of an impairment. The disparity between impairment and disability can be encountered in diverse clinical scenarios. For example, a person's ability to resume occupational activities following a major cardiac event depends on medical, social, and psychological factors, but nonmedical factors appear to present the greatest impediment and many persons do not resume work despite significant improvements in functional capacity. A key requirement according to the AMA Guides is objective documentation, and the author agrees that when physicians consider the disability evaluation of people, more issues than those relating to the percentage loss of function should be considered. More study of the relationships among impairment, disability, and quality of life in patients with RSD are required.

Deep Learning

2009 ◽  
Author(s):  
Stellan Ohlsson
Keyword(s):  
Deep Learning
Sign in / Sign up

Export Citation Format

Share Document