scholarly journals Quantitative Phenotyping of Northern Leaf Blight in UAV Images Using Deep Learning

2019 ◽  
Vol 11 (19) ◽  
pp. 2209 ◽  
Author(s):  
Ethan L. Stewart ◽  
Tyr Wiesner-Hanks ◽  
Nicholas Kaczmar ◽  
Chad DeChant ◽  
Harvey Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Throughput ◽  
Plant Disease ◽  
Ground Truth ◽  
Leaf Blight ◽  
Northern Leaf Blight ◽  
Average Precision ◽  
Global Food Security ◽  
Serious Disease ◽  
Uav Images

Plant disease poses a serious threat to global food security. Accurate, high-throughput methods of quantifying disease are needed by breeders to better develop resistant plant varieties and by researchers to better understand the mechanisms of plant resistance and pathogen virulence. Northern leaf blight (NLB) is a serious disease affecting maize and is responsible for significant yield losses. A Mask R-CNN model was trained to segment NLB disease lesions in unmanned aerial vehicle (UAV) images. The trained model was able to accurately detect and segment individual lesions in a hold-out test set. The mean intersect over union (IOU) between the ground truth and predicted lesions was 0.73, with an average precision of 0.96 at an IOU threshold of 0.50. Over a range of IOU thresholds (0.50 to 0.95), the average precision was 0.61. This work demonstrates the potential for combining UAV technology with a deep learning-based approach for instance segmentation to provide accurate, high-throughput quantitative measures of plant disease.

scholarly journals Image-Based Plant Disease Identification by Deep Learning Meta-Architectures

Plants ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1451
Author(s):  
Muhammad Hammad Saleem ◽  
Sapna Khanchi ◽  
Johan Potgieter ◽  
Khalid Mahmood Arif
Keyword(s):  
Deep Learning ◽  
Plant Disease ◽  
State Of The Art ◽  
Mean Average Precision ◽  
Single Shot ◽  
Average Precision ◽  
Crop Monitoring ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
Agricultural Applications

The identification of plant disease is an imperative part of crop monitoring systems. Computer vision and deep learning (DL) techniques have been proven to be state-of-the-art to address various agricultural problems. This research performed the complex tasks of localization and classification of the disease in plant leaves. In this regard, three DL meta-architectures including the Single Shot MultiBox Detector (SSD), Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Networks (RFCN) were applied by using the TensorFlow object detection framework. All the DL models were trained/tested on a controlled environment dataset to recognize the disease in plant species. Moreover, an improvement in the mean average precision of the best-obtained deep learning architecture was attempted through different state-of-the-art deep learning optimizers. The SSD model trained with an Adam optimizer exhibited the highest mean average precision (mAP) of 73.07%. The successful identification of 26 different types of defected and 12 types of healthy leaves in a single framework proved the novelty of the work. In the future, the proposed detection methodology can also be adopted for other agricultural applications. Moreover, the generated weights can be reused for future real-time detection of plant disease in a controlled/uncontrolled environment.

scholarly journals HD Spot: Interpretable Deep Learning Classification of Single Cell Transcript Data

2019 ◽  
Author(s):  
Eric Prince ◽  
Todd C. Hankinson
Keyword(s):  
Deep Learning ◽  
Single Cell ◽  
High Throughput ◽  
Ground Truth ◽  
Sequencing Technologies ◽  
Bioinformatic Tool ◽  
Complex Relationships ◽  
Insight Into ◽  
Generation Sequencing

ABSTRACTHigh throughput data is commonplace in biomedical research as seen with technologies such as single-cell RNA sequencing (scRNA-seq) and other Next Generation Sequencing technologies. As these techniques continue to be increasingly utilized it is critical to have analysis tools that can identify meaningful complex relationships between variables (i.e., in the case of scRNA-seq: genes) in a way such that human bias is absent. Moreover, it is equally paramount that both linear and non-linear (i.e., one-to-many) variable relationships be considered when contrasting datasets. HD Spot is a deep learning-based framework that generates an optimal interpretable classifier a given high-throughput dataset using a simple genetic algorithm as well as an autoencoder to classifier transfer learning approach. Using four unique publicly available scRNA-seq datasets with published ground truth, we demonstrate the robustness of HD Spot and the ability to identify ontologically accurate gene lists for a given data subset. HD Spot serves as a bioinformatic tool to allow novice and advanced analysts to gain complex insight into their respective datasets enabling novel hypotheses development.

scholarly journals High-throughput phenotyping with deep learning gives insight into the genetic architecture of flowering time in wheat

2019 ◽  
Author(s):  
Xu Wang ◽  
Hong Xuan ◽  
Byron Evers ◽  
Sandesh Shrestha ◽  
Robert Pless ◽  
...  
Keyword(s):  
Deep Learning ◽  
Flowering Time ◽  
High Throughput ◽  
Developmental Stages ◽  
Expert Knowledge ◽  
Plant Traits ◽  
Plant Morphology ◽  
Ground Truth ◽  
Plant Phenotyping ◽  
High Throughput Phenotyping

ABSTRACTBackgroundPrecise measurement of plant traits with precision and speed on large populations has emerged as a critical bottleneck in connecting genotype to phenotype in genetics and breeding. This bottleneck limits advancements in understanding plant genomes and the development of improved, high-yielding crop varieties.ResultsHere we demonstrate the application of deep learning on proximal imaging from a mobile field vehicle to directly score plant morphology and developmental stages in wheat under field conditions. We developed and trained a convolutional neural network with image datasets labeled from expert visual scores and used this ‘breeder-trained’ network to directly score wheat morphology and developmental stages. For both morphological (awned) and phenological (flowering time) traits, we demonstrate high heritability and extremely high accuracy against the ‘ground-truth’ values from visual scoring. Using the traits scored by the network, we tested genotype-to-phenotype association using the deep learning phenotypes and uncovered novel epistatic interactions for flowering time. Enabled by the time-series high-throughput phenotyping, we describe a new phenotype as the rate of flowering and show heritable genetic control.ConclusionsWe demonstrated a field-based high-throughput phenotyping approach using deep learning that can directly score morphological and developmental phenotypes in genetic populations. Most powerfully, the deep learning approach presented here gives a conceptual advancement in high-throughput plant phenotyping as it can potentially score any trait in any plant species through leveraging expert knowledge from breeders, geneticist, pathologists and physiologists.

scholarly journals Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Huu-Giao Nguyen ◽  
Annika Blank ◽  
Heather E. Dawson ◽  
Alessandro Lugli ◽  
Inti Zlobec
Keyword(s):  
Deep Learning ◽  
High Throughput ◽  
Predictive Accuracy ◽  
Ensemble Methods ◽  
Ground Truth ◽  
Tissue Microarrays ◽  
Tissue Classification ◽  
Ground Truth Data ◽  
Colorectal Tissue ◽  
Core Evaluations

AbstractTissue microarray (TMA) core images are a treasure trove for artificial intelligence applications. However, a common problem of TMAs is multiple sectioning, which can change the content of the intended tissue core and requires re-labelling. Here, we investigate different ensemble methods for colorectal tissue classification using high-throughput TMAs. Hematoxylin and Eosin (H&E) core images of 0.6 mm or 1.0 mm diameter from three international cohorts were extracted from 54 digital slides (n = 15,150 cores). After TMA core extraction and color enhancement, five different flows of independent and ensemble deep learning were applied. Training and testing data with 2144 and 13,006 cores included three classes: tumor, normal or “other” tissue. Ground-truth data were collected from 30 ngTMA slides (n = 8689 cores). A test augmentation is applied to reduce the uncertain prediction. Predictive accuracy of the best method, namely Soft Voting Ensemble of one VGG and one CapsNet models was 0.982, 0.947 and 0.939 for normal, “other” and tumor, which outperformed to independent or ensemble learning with one base-estimator. Our high-accuracy algorithm for colorectal tissue classification in high-throughput TMAs is amenable to images from different institutions, core sizes and stain intensity. It helps to reduce error in TMA core evaluations with previously given labels.

scholarly journals Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images

Agronomy ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1458
Author(s):  
Adel Ammar ◽  
Anis Koubaa ◽  
Bilel Benjdira
Keyword(s):  
Deep Learning ◽  
Geographical Location ◽  
Network Models ◽  
Aerial Images ◽  
Palm Tree ◽  
Average Precision ◽  
Neural Network Models ◽  
Learning Framework ◽  
Palm Trees ◽  
Uav Images

In this paper, we propose an original deep learning framework for the automated counting and geolocation of palm trees from aerial images using convolutional neural networks. For this purpose, we collected aerial images from two different regions in Saudi Arabia, using two DJI drones, and we built a dataset of around 11,000 instances of palm trees. Then, we applied several recent convolutional neural network models (Faster R-CNN, YOLOv3, YOLOv4, and EfficientDet) to detect palms and other trees, and we conducted a complete comparative evaluation in terms of average precision and inference speed. YOLOv4 and EfficientDet-D5 yielded the best trade-off between accuracy and speed (up to 99% mean average precision and 7.4 FPS). Furthermore, using the geotagged metadata of aerial images, we used photogrammetry concepts and distance corrections to automatically detect the geographical location of detected palm trees. This geolocation technique was tested on two different types of drones (DJI Mavic Pro and Phantom 4 pro) and was assessed to provide an average geolocation accuracy that attains 1.6 m. This GPS tagging allows us to uniquely identify palm trees and count their number from a series of drone images, while correctly dealing with the issue of image overlapping. Moreover, this innovative combination between deep learning object detection and geolocalization can be generalized to any other objects in UAV images.

scholarly journals FiberAI: A Deep Learning model for automated analysis of nascent DNA Fibers

2020 ◽  
Author(s):  
Azam Mohsin ◽  
Stephen Arnovitz ◽  
Aly A Khan ◽  
Fotini Gounari
Keyword(s):  
Deep Learning ◽  
Dna Replication ◽  
High Throughput ◽  
Genome Stability ◽  
Molecular Mechanisms ◽  
Quantitative Information ◽  
Average Precision ◽  
Extrinsic Factors ◽  
Replication Process ◽  
Microscopy Images

AbstractAll life forms undergo cell division and are dependent on faithful DNA replication to maintain the stability of their genomes. Both intrinsic and extrinsic factors can stress the replication process and multiple checkpoint mechanisms have evolved to ensure genome stability. Understanding these molecular mechanisms is crucial for preventing and treating genomic instability associated diseases including cancer. DNA replicating fiber fluorography is a powerful technique that directly visualizes the replication process and a cell’s response to replication stress. Analysis of DNA-fiber microscopy images provides quantitative information about replication fitness. However, a bottleneck for high throughput DNA-fiber studies is that quantitative measurements are laborious when performed manually. Here we introduce FiberAI, which uses state-of-the art deep learning frameworks to detect and quantify DNA-fibers in high throughput microscopy images. FiberAI efficiently detects DNA fibers, achieving a bounding box average precision score of 0.91 and a segmentation average precision score of 0.90. We then use FiberAI to measure the integrity of replication checkpoints. FiberAI is publicly available and allows users to view model predicted selections, add their own manual selections, and easily analyze multiple image sets. Thus, FiberAI can help elucidate DNA replication processes by streamlining DNA-fiber analyses.

Convolutional Neural Network of Atomic Surface Structures to Predict Binding Energies for High-Throughput Screening of Catalysts

2019 ◽  
Author(s):  
Seoin Back ◽  
Junwoong Yoon ◽  
Nianhan Tian ◽  
Wen Zhong ◽  
Kevin Tran ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
High Throughput ◽  
High Throughput Screening ◽  
Binding Energies ◽  
Surface Structures ◽  
Voronoi Polyhedra ◽  
Atomic Surface

We present an application of deep-learning convolutional neural network of atomic surface structures using atomic and Voronoi polyhedra-based neighbor information to predict adsorbate binding energies for the application in catalysis.

Sign in / Sign up

Export Citation Format

Share Document