scholarly journals Mimicry embedding for advanced neural network training of 3D biomedical micrographs

2019 ◽  
Author(s):  
Artur Yakimovich ◽  
Moona Huttunen ◽  
Jerzy Samolej ◽  
Barbara Clough ◽  
Nagisa Yoshida ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Biomedical Imaging ◽  
Three Dimensional ◽  
Network Evolution ◽  
Great Promise ◽  
Parasitic Infections ◽  
General Strategy ◽  
Accurate Analysis

The use of deep neural networks (DNNs) for analysis of complex biomedical images shows great promise but is hampered by a lack of large verified datasets for rapid network evolution. Here we present a novel “mimicry embedding” strategy for rapid application of neural network architecture-based analysis of biomedical imaging datasets. Embedding of a novel biological dataset, such that it mimics a verified dataset, enables efficient deep learning and seamless architecture switching. We apply this strategy across various microbiological phenotypes; from super-resolved viruses toin vivoparasitic infections. We demonstrate that mimicry embedding enables efficient and accurate analysis of three-dimensional microscopy datasets. The results suggest that transfer learning from pre-trained network data may be a powerful general strategy for analysis of heterogeneous biomedical imaging datasets.

scholarly journals TDPP-Net: Achieving three-dimensional path planning via a deep neural network architecture

2019 ◽  
Vol 357 ◽  
pp. 151-162 ◽  
Author(s):  
Keyu Wu ◽  
Mahdi Abolfazli Esfahani ◽  
Shenghai Yuan ◽  
Han Wang
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Three Dimensional ◽  
Neural Network Architecture

Active Noise Control Using Multi-Layered Perceptron Neural Networks

1997 ◽  
Vol 16 (2) ◽  
pp. 109-144 ◽  
Author(s):  
M.O. Tokhi ◽  
R. Wood
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Noise Control ◽  
Learning Algorithm ◽  
Free Field ◽  
Active Noise Control ◽  
Three Dimensional ◽  
Broadband Noise ◽  
Active Noise

This paper presents the development of a neuro-adaptive active noise control (ANC) system. Multi-layered perceptron neural networks with a backpropagation learning algorithm are considered in both the modelling and control contexts. The capabilities of the neural network in modelling dynamical systems are investigated. A feedforward ANC structure is considered for optimum cancellation of broadband noise in a three-dimensional propagation medium. An on-line adaptation and training mechanism allowing a neural network architecture to characterise the optimal controller within the ANC system is developed. The neuro-adaptive ANC algorithm thus developed is implemented within a free-field environment and simulation results verifying its performance are presented and discussed.

scholarly journals Reconstruction of 3D Object Shape Using Hybrid Modular Neural Network Architecture Trained on 3D Models from ShapeNetCore Dataset

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1553 ◽  
Author(s):  
Audrius Kulikajevas ◽  
Rytis Maskeliūnas ◽  
Robertas Damaševičius ◽  
Sanjay Misra
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
A Priori ◽  
Three Dimensional ◽  
Qualitative Evaluation ◽  
3D Models ◽  
Depth Sensors ◽  
The Neural Network ◽  
Artificial Neural Network Ann ◽  
Commercial Applications

Depth-based reconstruction of three-dimensional (3D) shape of objects is one of core problems in computer vision with a lot of commercial applications. However, the 3D scanning for point cloud-based video streaming is expensive and is generally unattainable to an average user due to required setup of multiple depth sensors. We propose a novel hybrid modular artificial neural network (ANN) architecture, which can reconstruct smooth polygonal meshes from a single depth frame, using a priori knowledge. The architecture of neural network consists of separate nodes for recognition of object type and reconstruction thus allowing for easy retraining and extension for new object types. We performed recognition of nine real-world objects using the neural network trained on the ShapeNetCore model dataset. The results evaluated quantitatively using the Intersection-over-Union (IoU), Completeness, Correctness and Quality metrics, and qualitative evaluation by visual inspection demonstrate the robustness of the proposed architecture with respect to different viewing angles and illumination conditions.

scholarly journals Mimicry Embedding Facilitates Advanced Neural Network Training for Image-Based Pathogen Detection

mSphere ◽  
2020 ◽  
Vol 5 (5) ◽  
Author(s):  
Artur Yakimovich ◽  
Moona Huttunen ◽  
Jerzy Samolej ◽  
Barbara Clough ◽  
Nagisa Yoshida ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Network Evolution ◽  
Great Promise ◽  
Data Sets ◽  
Imaging Data ◽  
Data Set ◽  
Novel Strategy

ABSTRACT The use of deep neural networks (DNNs) for analysis of complex biomedical images shows great promise but is hampered by a lack of large verified data sets for rapid network evolution. Here, we present a novel strategy, termed “mimicry embedding,” for rapid application of neural network architecture-based analysis of pathogen imaging data sets. Embedding of a novel host-pathogen data set, such that it mimics a verified data set, enables efficient deep learning using high expressive capacity architectures and seamless architecture switching. We applied this strategy across various microbiological phenotypes, from superresolved viruses to in vitro and in vivo parasitic infections. We demonstrate that mimicry embedding enables efficient and accurate analysis of two- and three-dimensional microscopy data sets. The results suggest that transfer learning from pretrained network data may be a powerful general strategy for analysis of heterogeneous pathogen fluorescence imaging data sets. IMPORTANCE In biology, the use of deep neural networks (DNNs) for analysis of pathogen infection is hampered by a lack of large verified data sets needed for rapid network evolution. Artificial neural networks detect handwritten digits with high precision thanks to large data sets, such as MNIST, that allow nearly unlimited training. Here, we developed a novel strategy we call mimicry embedding, which allows artificial intelligence (AI)-based analysis of variable pathogen-host data sets. We show that deep learning can be used to detect and classify single pathogens based on small differences.

scholarly journals Hydroxyapatite for Biomedical Applications: A Short Overview

Ceramics ◽  
2021 ◽  
Vol 4 (4) ◽  
pp. 542-563
Author(s):  
Elisa Fiume ◽  
Giulia Magnaterra ◽  
Abbas Rahdar ◽  
Enrica Verné ◽  
Francesco Baino
Keyword(s):  
Calcium Phosphates ◽  
Three Dimensional ◽  
Good Alternative ◽  
Great Promise ◽  
Comprehensive Overview ◽  
Current Trends ◽  
Mechanical Performances ◽  
Potential Use

Calcium phosphates (CaPs) are biocompatible and biodegradable materials showing a great promise in bone regeneration as good alternative to the use of auto- and allografts to guide and support tissue regeneration in critically-sized bone defects. This can be certainly attributed to their similarity to the mineral phase of natural bone. Among CaPs, hydroxyapatite (HA) deserves a special attention as it, actually is the main inorganic component of bone tissue. This review offers a comprehensive overview of past and current trends in the use of HA as grafting material, with a focus on manufacturing strategies and their effect on the mechanical properties of the final products. Recent advances in materials processing allowed the production of HA-based grafts in different forms, thus meeting the requirements for a range of clinical applications and achieving enthusiastic results both in vitro and in vivo. Furthermore, the growing interest in the optimization of three-dimensional (3D) porous grafts, mimicking the trabecular architecture of human bone, has opened up new challenges in the development of bone-like scaffolds showing suitable mechanical performances for potential use in load bearing anatomical sites.

scholarly journals Dental Implant Nano-Engineering: Advances, Limitations and Future Directions

Nanomaterials ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 2489
Author(s):  
Yifan Zhang ◽  
Karan Gulati ◽  
Ze Li ◽  
Ping Di ◽  
Yan Liu
Keyword(s):  
Dental Implants ◽  
Three Dimensional ◽  
Antimicrobial Activities ◽  
In Vivo Studies ◽  
Great Promise ◽  
Stimuli Responsive ◽  
Tissue Integration ◽  
Material Choice

Titanium (Ti) and its alloys offer favorable biocompatibility, mechanical properties and corrosion resistance, which makes them an ideal material choice for dental implants. However, the long-term success of Ti-based dental implants may be challenged due to implant-related infections and inadequate osseointegration. With the development of nanotechnology, nanoscale modifications and the application of nanomaterials have become key areas of focus for research on dental implants. Surface modifications and the use of various coatings, as well as the development of the controlled release of antibiotics or proteins, have improved the osseointegration and soft-tissue integration of dental implants, as well as their antibacterial and immunomodulatory functions. This review introduces recent nano-engineering technologies and materials used in topographical modifications and surface coatings of Ti-based dental implants. These advances are discussed and detailed, including an evaluation of the evidence of their biocompatibility, toxicity, antimicrobial activities and in-vivo performances. The comparison between these attempts at nano-engineering reveals that there are still research gaps that must be addressed towards their clinical translation. For instance, customized three-dimensional printing technology and stimuli-responsive, multi-functional and time-programmable implant surfaces holds great promise to advance this field. Furthermore, long-term in vivo studies under physiological conditions are required to ensure the clinical application of nanomaterial-modified dental implants.

scholarly journals Robust Three-dimensional (3D) Expansion of Bovine Intestinal Stem Cells: A Model for Replacement of Animal Experiments

2021 ◽  
Author(s):  
Bo Ram Lee ◽  
Hyeon Yang ◽  
Sang In Lee ◽  
Inamul Haq ◽  
Sun A Ock ◽  
...  
Keyword(s):  
Stem Cells ◽  
Small Intestine ◽  
Functional Characterization ◽  
Animal Experiments ◽  
Three Dimensional ◽  
Intestinal Stem Cells ◽  
Great Promise ◽  
Intestinal Organoids

Abstract Background Intestinal organoids offer great promise for disease modelling based host-pathogen interactions and nutritional research for feed efficiency measurement in livestock as well as regenerative medicine for therapeutic purposes. However, very limited studies are available on the functional characterization and three-dimensional (3D) expansion of adult stem cells in livestock species compared to mammals. Therefore, we characterized intestinal stem cells derived from small intestine in adult bovine and cultivated intestinal organoids under in vitro 3D culture system.Results In this study, we successfully established intestinal organoids in bovine. Intestinal organoids were long-term cultivated over several passages of culture without loss of the recapitulating capacity of crypts and they had the specific expression of several specific markers involved in intestinal stem cells, intestinal epithelium and nutrient absorption. In addition, they showed the key functionality with regard to a high permeability for compounds of up to FITC-dextran 4 kDa, while FITC-dextran 40 kDa failed to enter the organoid lumen. Furthermore, the genetic properties of intestinal organoids were highly similar to those of in vivo based on QuantSeq 3’ mRNA-Seq. data.Conclusions Collectively, these results provide a reliable method for efficient isolation of intestinal crypts from small intestine and robust 3D expansion of intestinal stem cells in adult bovine and demonstrate the in vitro 3D organoids mimics the in vivo tissue topology and functionality. Finally, intestinal organoids are potential alternatives to in vivo system and will facilitate the practical use of a model to replace animal experiments in the fields of animal biotechnology for various purposes.

scholarly journals Robust Three-Dimensional (3D) Expansion of Bovine Intestinal Organoids: An In Vitro Model as a Potential Alternative to an In Vivo System

Animals ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 2115
Author(s):  
Bo-Ram Lee ◽  
Hyeon Yang ◽  
Sang-In Lee ◽  
Inamul Haq ◽  
Sun-A Ock ◽  
...  
Keyword(s):  
Stem Cells ◽  
Small Intestine ◽  
Adult Stem Cells ◽  
Three Dimensional ◽  
3D Culture ◽  
Great Promise ◽  
Specific Expression ◽  
Intestinal Organoids

Intestinal organoids offer great promise for disease-modelling-based host–pathogen interactions and nutritional research for feed efficiency measurement in livestock and regenerative medicine for therapeutic purposes. However, very limited studies are available on the functional characterisation and three-dimensional (3D) expansion of adult stem cells in livestock species compared to other species. Intestinal crypts derived from intestinal organoids under a 3D culture system from the small intestine in adult bovine were successfully established and characterised for functionality testing, including the cellular potentials and genetic properties based on immunohistochemistry, immunocytochemistry, epithelial barrier permeability assay, QuantSeq 3′ mRNA-Seq. data and quantitative reverse transcription-polymerase chain reaction. Intestinal organoids were long-term cultivated over several passages of culture without loss of the recapitulating capacity of crypts, and they had the specific expression of several specific markers involved in intestinal stem cells, intestinal epithelium, and nutrient absorption. In addition, they showed the key functionality with regard to a high permeability for compounds of up to FITC-dextran 4 kDa, while FITC-dextran 40 kDa failed to enter the organoid lumen and revealed that the genetic properties of bovine intestinal organoids were highly similar to those of in vivo. Collectively, these results provide a reliable method for efficient isolation of intestinal crypts from the small intestine and robust 3D expansion of intestinal organoids in adult bovine and demonstrate the in vitro 3D organoids mimics the in vivo tissue topology and functionality. Finally, intestinal organoids are potential alternatives to in vivo systems and will be facilitated as the practical model to replace animal experiments for various purposes in the fields of animal biotechnology.

Sign in / Sign up

Export Citation Format

Share Document