scholarly journals Evaluating the Deep Learning accuracy in data extraction from synthetic image sequences

2019 ◽  
Vol 10 (3) ◽  
Author(s):  
André Franceschi de Angelis ◽  
Thaı́s Rocha
Keyword(s):  
Deep Learning ◽  
Data Extraction ◽  
Image Sequences ◽  
Synthetic Image

scholarly journals Data augmentation for computed tomography angiography via synthetic image generation and neural domain adaptation

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Malte Seemann ◽  
Lennart Bargsten ◽  
Alexander Schlaefer
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Deep Learning ◽  
Medical Imaging ◽  
Computed Tomography Angiography ◽  
Data Augmentation ◽  
Domain Adaptation ◽  
Synthetic Image ◽  
Wide Range ◽  
The Impact

AbstractDeep learning methods produce promising results when applied to a wide range of medical imaging tasks, including segmentation of artery lumen in computed tomography angiography (CTA) data. However, to perform sufficiently, neural networks have to be trained on large amounts of high quality annotated data. In the realm of medical imaging, annotations are not only quite scarce but also often not entirely reliable. To tackle both challenges, we developed a two-step approach for generating realistic synthetic CTA data for the purpose of data augmentation. In the first step moderately realistic images are generated in a purely numerical fashion. In the second step these images are improved by applying neural domain adaptation. We evaluated the impact of synthetic data on lumen segmentation via convolutional neural networks (CNNs) by comparing resulting performances. Improvements of up to 5% in terms of Dice coefficient and 20% for Hausdorff distance represent a proof of concept that the proposed augmentation procedure can be used to enhance deep learning-based segmentation for artery lumen in CTA images.

scholarly journals Deep learning-based recognition of cell structures in fluorescence microscopy sequences with respect to their morphology on cells infected with Marburg virus

2020 ◽  
Vol 6 (3) ◽  
pp. 501-504
Author(s):  
Dennis Schmidt ◽  
Andreas Rausch ◽  
Thomas Schanze
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Infected Cell ◽  
Network Architecture ◽  
Image Sequences ◽  
Marburg Virus ◽  
Microscopic Image ◽  
Cell Structures ◽  
Fast Recognition ◽  
Subviral Particles

AbstractThe Institute of Virology at the Philipps-Universität Marburg is currently researching possible drugs to combat the Marburg virus. This involves classifying cell structures based on fluoroscopic microscopic image sequences. Conventionally, membranes of cells must be marked for better analysis, which is time consuming. In this work, an approach is presented to identify cell structures in images that are marked for subviral particles. It could be shown that there is a correlation between the distribution of subviral particles in an infected cell and the position of the cell’s structures. The segmentation is performed with a "Mask-R-CNN" algorithm, presented in this work. The model (a region-based convolutional neural network) is applied to enable a robust and fast recognition of cell structures. Furthermore, the network architecture is described. The proposed method is tested on data evaluated by experts. The results show a high potential and demonstrate that the method is suitable.

scholarly journals Synthetic Image Rendering Solves Annotation Problem in Deep Learning Nanoparticle Segmentation

Small Methods ◽  
2021 ◽  
pp. 2100223
Author(s):  
Leonid Mill ◽  
David Wolff ◽  
Nele Gerrits ◽  
Patrick Philipp ◽  
Lasse Kling ◽  
...  
Keyword(s):  
Deep Learning ◽  
Synthetic Image ◽  
Image Rendering

scholarly journals Technical Note: Quantifying music-dance synchrony with the application of a deep learning-based 2D pose estimator

2020 ◽  
Author(s):  
Filip Potempski ◽  
Andrea Sabo ◽  
Kara K Patterson
Keyword(s):  
Deep Learning ◽  
Motor Performance ◽  
Data Extraction ◽  
Effective Means ◽  
Technical Note ◽  
Novel Method ◽  
Synchronous Condition ◽  
The Mean ◽  
Repeated Training

AbstractDance interventions are more effective at improving gait and balance outcomes than other rehabilitation interventions. Repeated training may culminate in superior motor performance compared to other interventions without synchronization. This technical note will describe a novel method using a deep learning-based 2D pose estimator: OpenPose, alongside beat analysis of music to quantify movement-music synchrony during salsa dancing. This method has four components: i) camera setup and recording, ii) tempo/downbeat analysis and waveform cleanup, iii) OpenPose estimation and data extraction, and iv) synchronization analysis. Two trials were recorded: one in which the dancer danced synchronously to the music and one where they did not. The salsa dancer performed a solo basic salsa step continuously for 90 seconds to a salsa track while their movements and the music were recorded with a webcam. This data was then extracted from OpenPose and analyzed. The mean synchronization value for both feet was significantly lower in the synchronous condition than the asynchronous condition, indicating that this is an effective means to track and quantify a dancer’s movement and synchrony while performing a basic salsa step.

scholarly journals Automated data extraction software for medical summary using text mining (T-Library)

2019 ◽  
Author(s):  
Tomohide Yamada ◽  
Yoshinobu Kondo ◽  
Ryo Momosaki
Keyword(s):  
Clinical Trials ◽  
Deep Learning ◽  
Clinical Research ◽  
Data Extraction ◽  
Healthcare Providers ◽  
Clinical Information ◽  
Patient Records ◽  
Unstructured Text ◽  
Risk Engine ◽  
Easy Operation

The electronic medical record (EMR) is a source of clinical information and is used for clinical research. Clinical researchers leverage this information by employing staffs to manually extracting data from the unstructured text. This process can be both error-prone and labor-intensive. This software (T-Library) is a software which automatically extracts key clinical data from patient records and can potentially help healthcare providers and researchers save money, make treatment decisions and manage clinical trials. This software saves labor for data transcription in clinical research. This is a vital step toward getting researchers rapid access to the information they need. This is also the attempt to cluster patients’ morbid states and establish accurate and constantly updated risk engine of complications’ crises, using deep learning. Strengths: 1) Quick and Easy operation URL: http://www.picoron.com/tlibrary/

Chemical Named Entity Recognition Using Deep Learning Techniques

2021 ◽  
pp. 59-73
Author(s):  
Hema R. ◽  
Ajantha Devi
Keyword(s):  
Deep Learning ◽  
Chemical Elements ◽  
Data Extraction ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Related Data ◽  
Named Entity ◽  
Chemical Structures ◽  
Learning Techniques ◽  
Chemical Named Entity Recognition

Chemical entities can be represented in different forms like chemical names, chemical formulae, and chemical structures. Because of the different classification frameworks for chemical names, the task of distinguishing proof or extraction of chemical elements with less ambiguous is considered a major test. Compound named entity recognition (NER) is the initial phase in any chemical-related data extraction strategy. The majority of the chemical NER is done utilizing dictionary-based, rule-based, and machine learning procedures. Recently, deep learning methods have evolved, and, in this chapter, the authors sketch out the various deep learning techniques applied for chemical NER. First, the authors introduced the fundamental concepts of chemical named entity recognition, the textual contents of chemical documents, and how these chemicals are represented in chemical literature. The chapter concludes with the strengths and weaknesses of the above methods and also the types of the chemical entities extracted.

scholarly journals Botanical Digitization: Application of MorphoLeaf in 2D Shape Visualization, Digital Morphometrics, and Species Delimitation, using Homologous Landmarks of Cucurbitaceae Leaves as a Model

2020 ◽  
Author(s):  
Oluwatobi A. Oso ◽  
Adeniyi A. Jayeola
Keyword(s):  
Deep Learning ◽  
Species Delimitation ◽  
Data Extraction ◽  
High Variability ◽  
Plant Leaves ◽  
Pca Analysis ◽  
Digital Identification ◽  
Plant Groups ◽  
Blade Area ◽  
Outline Analysis

ABSTRACTMorphometrics has been applied in several fields of science including botany. Plant leaves are been one of the most important organs in the identification of plants due to its high variability across different plant groups. The differences between and within plant species reflect variations in genotypes, development, evolution, and environment. While traditional morphometrics has contributed tremendously to reducing the problems that come with the identification of plants and delimitation of species based on morphology, technological advancements have led to the creation of deep learning digital solutions that made it easy to study leaves and detect more characters to complement already existing leaf datasets. In this study, we demonstrate the use of MorphoLeaf in generating morphometric dataset from 140 leaf specimens from seven Cucurbitaceae species via scanning of leaves, extracting landmarks, data extraction, landmarks data quantification, and reparametrization and normalization of leaf contours. PCA analysis revealed that blade area, blade perimeter, tooth area, tooth perimeter, height of (each position of the) tooth from tip, and the height of each (position of the) tooth from base are important and informative landmarks that contribute to the variation within the species studied. Our results demonstrate that MorphoLeaf can quantitatively track diversity in leaf specimens, and it can be applied to functionally integrate morphometrics and shape visualization in the digital identification of plants. The success of digital morphometrics in leaf outline analysis presents researchers with opportunities to apply and carry out more accurate image-based researches in diverse areas including, but not limited to, plant development, evolution, and phenotyping.

Sign in / Sign up

Export Citation Format

Share Document