scholarly journals Habitat-Net: Segmentation of habitat images using deep learning

2018 ◽  
Author(s):  
Jesse F. Abrams ◽  
Anand Vashishtha ◽  
Seth T. Wong ◽  
An Nguyen ◽  
Azlan Mohamed ◽  
...  
Keyword(s):  
Deep Learning ◽  
Forest Health ◽  
Data Interpretation ◽  
Input Image ◽  
Computer Assisted ◽  
Binary Segmentation ◽  
Manual Processing ◽  
Study Sites ◽  
Time Required ◽  
High Level

ABSTRACTUnderstanding environmental factors that influence forest health, as well as the occurrence and abundance of wildlife, is a central topic in forestry and ecology. However, the manual processing of field habitat data is time-consuming and months are often needed to progress from data collection to data interpretation. Computer-assisted tools, such as deep-learning applications can significantly shortening the time to process the data while maintaining a high level of accuracy. Here, we propose Habitat-Net: a novel method based on Convolutional Neural Networks (CNN) to segment habitat images of tropical rainforests. Habitat-Net takes color images as input and after multiple layers of convolution and deconvolution, produces a binary segmentation of the input image. We worked on two different types of habitat datasets that are widely used in ecological studies to characterize the forest conditions: canopy closure and understory vegetation. We trained the model with 800 canopy images and 700 understory images separately and then used 149 canopy and 172 understory images to test the performance of Habitat-Net. We compared the performance of Habitat-Net with a simple threshold based method, a manual processing by a second researcher and a CNN approach called U-Net upon which Habitat-Net is based. Habitat-Net, U-Net and simple thresholding reduced total processing time to milliseconds per image, compared to 45 seconds per image for manual processing. However, the higher mean Dice coefficient of Habitat-Net (0.94 for canopy and 0.95 for understory) indicates that accuracy of Habitat-Net is higher than that of both the simple thresholding (0.64, 0.83) and U-Net (0.89, 0.94). Habitat-Net will be of great relevance for ecologists and foresters, who need to monitor changes in their forest structures. The automated workflow not only reduces the time, it also standardizes the analytical pipeline and, thus, reduces the degree of uncertainty that would be introduced by manual processing of images by different people (either over time or between study sites). Furthermore, it provides the opportunity to collect and process more images from the field, which might increase the accuracy of the method. Although datasets from other habitats might need an annotated dataset to first train the model, the overall time required to process habitat photos will be reduced, particularly for large projects.

GPR data interpretation by the deep learning with coloring data

2019 ◽  
Vol 72 (0) ◽  
pp. 68-77
Author(s):  
Shinichiro Iso ◽  
Kazuya Ishitsuka ◽  
Kyosuke Onishi ◽  
Toshifumi Matsuoka
Keyword(s):  
Deep Learning ◽  
Data Interpretation

scholarly journals Towards 6G IoT: Tracing Mobile Sensor Nodes with Deep Learning Clustering in UAV Networks

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3936
Author(s):  
Yannis Spyridis ◽  
Thomas Lagkas ◽  
Panagiotis Sarigiannidis ◽  
Vasileios Argyriou ◽  
Antonios Sarigiannidis ◽  
...  
Keyword(s):  
Deep Learning ◽  
Heuristic Method ◽  
Sensor Nodes ◽  
Convolutional Network ◽  
Received Signal Strength Indicator ◽  
Anchor Nodes ◽  
Time Required ◽  
Rf Signal ◽  
Deep Learning Model

Unmanned aerial vehicles (UAVs) in the role of flying anchor nodes have been proposed to assist the localisation of terrestrial Internet of Things (IoT) sensors and provide relay services in the context of the upcoming 6G networks. This paper considered the objective of tracing a mobile IoT device of unknown location, using a group of UAVs that were equipped with received signal strength indicator (RSSI) sensors. The UAVs employed measurements of the target’s radio frequency (RF) signal power to approach the target as quickly as possible. A deep learning model performed clustering in the UAV network at regular intervals, based on a graph convolutional network (GCN) architecture, which utilised information about the RSSI and the UAV positions. The number of clusters was determined dynamically at each instant using a heuristic method, and the partitions were determined by optimising an RSSI loss function. The proposed algorithm retained the clusters that approached the RF source more effectively, removing the rest of the UAVs, which returned to the base. Simulation experiments demonstrated the improvement of this method compared to a previous deterministic approach, in terms of the time required to reach the target and the total distance covered by the UAVs.

scholarly journals Deep Learning-Based Congestion Detection at Urban Intersections

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2052
Author(s):  
Xinghai Yang ◽  
Fengjiao Wang ◽  
Zhiquan Bai ◽  
Feifei Xun ◽  
Yulin Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Optical Flow ◽  
Traffic Congestion ◽  
Detection Algorithm ◽  
Input Image ◽  
Vehicle Speed ◽  
Position Information ◽  
Traffic State ◽  
State Discrimination ◽  
Discrimination Method

In this paper, a deep learning-based traffic state discrimination method is proposed to detect traffic congestion at urban intersections. The detection algorithm includes two parts, global speed detection and a traffic state discrimination algorithm. Firstly, the region of interest (ROI) is selected as the road intersection from the input image of the You Only Look Once (YOLO) v3 object detection algorithm for vehicle target detection. The Lucas-Kanade (LK) optical flow method is employed to calculate the vehicle speed. Then, the corresponding intersection state can be obtained based on the vehicle speed and the discrimination algorithm. The detection of the vehicle takes the position information obtained by YOLOv3 as the input of the LK optical flow algorithm and forms an optical flow vector to complete the vehicle speed detection. Experimental results show that the detection algorithm can detect the vehicle speed and traffic state discrimination method can judge the traffic state accurately, which has a strong anti-interference ability and meets the practical application requirements.

scholarly journals De Novo Drug Design Using Artificial Intelligence Applied on SARS-CoV-2 Viral Proteins ASYNT-GAN

BioChem ◽  
2021 ◽  
Vol 1 (1) ◽  
pp. 36-48
Author(s):  
Ivan Jacobs ◽  
Manolis Maragoudakis
Keyword(s):  
Deep Learning ◽  
Small Molecules ◽  
Natural Product ◽  
De Novo ◽  
Viral Proteins ◽  
Computer Assisted ◽  
De Novo Drug Design ◽  
Learning Techniques ◽  
Latent Space ◽  
Synthetic Molecule

Computer-assisted de novo design of natural product mimetics offers a viable strategy to reduce synthetic efforts and obtain natural-product-inspired bioactive small molecules, but suffers from several limitations. Deep learning techniques can help address these shortcomings. We propose the generation of synthetic molecule structures that optimizes the binding affinity to a target. To achieve this, we leverage important advancements in deep learning. Our approach generalizes to systems beyond the source system and achieves the generation of complete structures that optimize the binding to a target unseen during training. Translating the input sub-systems into the latent space permits the ability to search for similar structures, and the sampling from the latent space for generation.

scholarly journals Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

2021 ◽  
pp. 002203452110053
Author(s):  
H. Wang ◽  
J. Minnema ◽  
K.J. Batenburg ◽  
T. Forouzanfar ◽  
F.J. Hu ◽  
...  
Keyword(s):  
Gold Standard ◽  
Orthodontic Treatment ◽  
3D Models ◽  
Similarity Coefficient ◽  
Patient Specific ◽  
Dice Similarity Coefficient ◽  
Surface Deviations ◽  
Surface Deviation ◽  
Binary Segmentation ◽  
Time Required

Accurate segmentation of the jaw (i.e., mandible and maxilla) and the teeth in cone beam computed tomography (CBCT) scans is essential for orthodontic diagnosis and treatment planning. Although various (semi)automated methods have been proposed to segment the jaw or the teeth, there is still a lack of fully automated segmentation methods that can simultaneously segment both anatomic structures in CBCT scans (i.e., multiclass segmentation). In this study, we aimed to train and validate a mixed-scale dense (MS-D) convolutional neural network for multiclass segmentation of the jaw, the teeth, and the background in CBCT scans. Thirty CBCT scans were obtained from patients who had undergone orthodontic treatment. Gold standard segmentation labels were manually created by 4 dentists. As a benchmark, we also evaluated MS-D networks that segmented the jaw or the teeth (i.e., binary segmentation). All segmented CBCT scans were converted to virtual 3-dimensional (3D) models. The segmentation performance of all trained MS-D networks was assessed by the Dice similarity coefficient and surface deviation. The CBCT scans segmented by the MS-D network demonstrated a large overlap with the gold standard segmentations (Dice similarity coefficient: 0.934 ± 0.019, jaw; 0.945 ± 0.021, teeth). The MS-D network–based 3D models of the jaw and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models (0.390 ± 0.093 mm, jaw; 0.204 ± 0.061 mm, teeth). The MS-D network took approximately 25 s to segment 1 CBCT scan, whereas manual segmentation took about 5 h. This study showed that multiclass segmentation of jaw and teeth was accurate and its performance was comparable to binary segmentation. The MS-D network trained for multiclass segmentation would therefore make patient-specific orthodontic treatment more feasible by strongly reducing the time required to segment multiple anatomic structures in CBCT scans.

scholarly journals Investigating the Impact of the Bit Depth of Fluorescence-Stained Images on the Performance of Deep Learning-Based Nuclei Instance Segmentation

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 967
Author(s):  
Amirreza Mahbod ◽  
Gerald Schaefer ◽  
Christine Löw ◽  
Georg Dorffner ◽  
Rupert Ecker ◽  
...  
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Computer Assisted ◽  
Important Criterion ◽  
Histological Image ◽  
Computer Mediated ◽  
Image Patches ◽  
Processing Techniques ◽  
The Impact ◽  
Instance Segmentation

Nuclei instance segmentation can be considered as a key point in the computer-mediated analysis of histological fluorescence-stained (FS) images. Many computer-assisted approaches have been proposed for this task, and among them, supervised deep learning (DL) methods deliver the best performances. An important criterion that can affect the DL-based nuclei instance segmentation performance of FS images is the utilised image bit depth, but to our knowledge, no study has been conducted so far to investigate this impact. In this work, we released a fully annotated FS histological image dataset of nuclei at different image magnifications and from five different mouse organs. Moreover, by different pre-processing techniques and using one of the state-of-the-art DL-based methods, we investigated the impact of image bit depth (i.e., eight bits vs. sixteen bits) on the nuclei instance segmentation performance. The results obtained from our dataset and another publicly available dataset showed very competitive nuclei instance segmentation performances for the models trained with 8 bit and 16 bit images. This suggested that processing 8 bit images is sufficient for nuclei instance segmentation of FS images in most cases. The dataset including the raw image patches, as well as the corresponding segmentation masks is publicly available in the published GitHub repository.

scholarly journals Evaluation of the Consistency of Simultaneously Acquired Sentinel-2 and Landsat 8 Imagery on Plastic Covered Greenhouses

2020 ◽  
Vol 12 (12) ◽  
pp. 2015 ◽  
Author(s):  
Manuel Ángel Aguilar ◽  
Rafael Jiménez-Lao ◽  
Abderrahim Nemmaoui ◽  
Fernando José Aguilar ◽  
Dilek Koc-San ◽  
...  
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Coefficient Of Determination ◽  
Landsat 8 ◽  
Surface Reflectance ◽  
Remote Sensing Techniques ◽  
Image Pairs ◽  
Study Sites ◽  
High Level ◽  
Sentinel 2

Remote sensing techniques based on medium resolution satellite imagery are being widely applied for mapping plastic covered greenhouses (PCG). This article aims at testing the spectral consistency of surface reflectance values of Sentinel-2 MSI (S2 L2A) and Landsat 8 OLI (L8 L2 and the pansharpened and atmospherically corrected product from L1T product; L8 PANSH) data in PCG areas located in Spain, Morocco, Italy and Turkey. The six corresponding bands of S2 and L8, together with the normalized difference vegetation index (NDVI), were generated through an OBIA approach for each PCG study site. The coefficient of determination (r2) and the root mean square error (RMSE) were computed in sixteen cloud-free simultaneously acquired image pairs from the four study sites to evaluate the coherence between the two sensors. It was found that the S2 and L8 correlation (r2 > 0.840, RMSE < 9.917%) was quite good in most bands and NDVI. However, the correlation of the two sensors fluctuated between study sites, showing occasional sun glint effects on PCG roofs related to the sensor orbit and sun position. Moreover, higher surface reflectance discrepancies between L8 L2 and L8 PANSH data, mainly in the visible bands, were always observed in areas with high-level aerosol values derived from the aerosol quality band included in the L8 L2 product (SR aerosol). In this way, the consistency between L8 PANSH and S2 L2A was improved mainly in high-level aerosol areas according to the SR aerosol band.

scholarly journals Lung Cancer Screening by Low-Dose Computed Tomography: Part 2 – Key Elements for Programmatic Implementation of Lung Cancer Screening

2020 ◽  
Author(s):  
Stefan Delorme ◽  
Rudolf Kaaks
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
Low Dose ◽  
Lung Cancer Screening ◽  
Cancer Registries ◽  
Computer Assisted ◽  
Management Algorithm ◽  
Epidemiologic Surveillance ◽  
Set Up ◽  
High Level

Purpose For screening with low-dose CT (LDCT) to be effective, the benefits must outweigh the potential risks. In large lung cancer screening studies, a mortality reduction of approx. 20 % has been reported, which requires several organizational elements to be achieved in practice. Materials and Methods The elements to be set up are an effective invitation strategy, uniform and quality-assured assessment criteria, and computer-assisted evaluation tools resulting in a nodule management algorithm to assign each nodule the needed workup intensity. For patients with confirmed lung cancer, immediate counseling and guideline-compliant treatment in tightly integrated regional expert centers with expert skills are required. First, pulmonology contacts as well as CT facilities should be available in the participant’s neighborhood. IT infrastructure, linkage to clinical cancer registries, quality management as well as epidemiologic surveillance are also required. Results An effective organization of screening will result in an articulated structure of both widely distributed pulmonology offices as the participants’ primary contacts and CT facilities as well as central expert facilities for supervision of screening activities, individual clarification of suspicious findings, and treatment of proven cancer. Conclusion In order to ensure that the benefits of screening more than outweigh the potential harms and that it will be accepted by the public, a tightly organized structure is needed to ensure wide availability of pulmonologists as first contacts and CT facilities with expert skills and high-level equipment concentrated in central facilities. Key Points:  Citation Format

scholarly journals High-Intensity Focused Ultrasound Circular Cyclocoagulation in Glaucoma: A Step Forward for Cyclodestruction?

2017 ◽  
Vol 2017 ◽  
pp. 1-14 ◽  
Author(s):  
Rodolfo Mastropasqua ◽  
Vincenzo Fasanella ◽  
Alessandra Mastropasqua ◽  
Marco Ciancaglini ◽  
Luca Agnifili
Keyword(s):  
High Intensity ◽  
Ciliary Body ◽  
Focused Ultrasound ◽  
Current Knowledge ◽  
High Intensity Focused Ultrasound ◽  
High Rate ◽  
Dose Effect ◽  
Computer Assisted ◽  
Refractory Glaucoma ◽  
High Level

The ciliary body ablation is still considered as a last resort treatment to reduce the intraocular pressure (IOP) in uncontrolled glaucoma. Several ablation techniques have been proposed over the years, all presenting a high rate of complications, nonselectivity for the target organ, and unpredictable dose-effect relationship. These drawbacks limited the application of cyclodestructive procedures almost exclusively to refractory glaucoma. High-intensity focused ultrasound (HIFU), proposed in the early 1980s and later abandoned because of the complexity and side effects of the procedure, was recently reconsidered in a new approach to destroy the ciliary body. Ultrasound circular cyclocoagulation (UC3), by using miniaturized transducers embedded in a dedicated circular-shaped device, permits to selectively treat the ciliary body in a one-step, computer-assisted, and non-operator-dependent procedure. UC3 shows a high level of safety along with a predictable and sustained IOP reduction in patients with refractory glaucoma. Because of this, the indication of UC3 was recently extended also to naïve-to-surgery patients, thus reconsidering the role and timing of ciliary body ablation in the surgical management of glaucoma. This article provides a review of the most used cycloablative techniques with particular attention to UC3, summarizing the current knowledge about this procedure and future possible developments.

scholarly journals Deep-Framework: A Distributed, Scalable, and Edge-Oriented Framework for Real-Time Analysis of Video Streams

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4045
Author(s):  
Alessandro Sassu ◽  
Jose Francisco Saenz-Cogollo ◽  
Maurizio Agelli
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Video Data ◽  
Video Analytics ◽  
Web Based ◽  
Real Time Analysis ◽  
Open Source Framework ◽  
Cluster Configuration ◽  
Time Requirements ◽  
High Level

Edge computing is the best approach for meeting the exponential demand and the real-time requirements of many video analytics applications. Since most of the recent advances regarding the extraction of information from images and video rely on computation heavy deep learning algorithms, there is a growing need for solutions that allow the deployment and use of new models on scalable and flexible edge architectures. In this work, we present Deep-Framework, a novel open source framework for developing edge-oriented real-time video analytics applications based on deep learning. Deep-Framework has a scalable multi-stream architecture based on Docker and abstracts away from the user the complexity of cluster configuration, orchestration of services, and GPU resources allocation. It provides Python interfaces for integrating deep learning models developed with the most popular frameworks and also provides high-level APIs based on standard HTTP and WebRTC interfaces for consuming the extracted video data on clients running on browsers or any other web-based platform.

Sign in / Sign up

Export Citation Format

Share Document