Quantifying the fine structures of disk galaxies with deep learning: Segmentation of spiral arms in different Hubble types

Context. Spatial correlations between spiral arms and other galactic components such as giant molecular clouds and massive OB stars suggest that spiral arms can play vital roles in various aspects of disk galaxy evolution. Segmentation of spiral arms in disk galaxies is therefore a key task when these correlations are to be investigated. Aims. We therefore decomposed disk galaxies into spiral and nonspiral regions using the code U-Net, which is based on deep-learning algorithms and has been invented for segmentation tasks in biology. Methods. We first trained this U-Net with a large number of synthesized images of disk galaxies with known properties of symmetric spiral arms with radially constant pitch angles and then tested it with entirely unknown data sets. The synthesized images were generated from mathematical models of disk galaxies with various properties of spiral arms, bars, and rings in these supervised-learning tasks. We also applied the trained U-Net to spiral galaxy images synthesized from the results of long-term hydrodynamical simulations of disk galaxies with nonsymmetric spiral arms. Results. We find that U-Net can predict the precise locations of spiral arms with an average prediction accuracy (Fm) of 98%. We also find that Fm does not depend strongly on the numbers of spiral arms, presence or absence of stellar bars and rings, and bulge-to-disk ratios in disk galaxies. These results imply that U-Net is a very useful tool for identifying the locations of spirals arms. However, we find that the U-Net trained on these symmetric spiral arm images cannot predict entirly unknown data sets with the same accuracy that were produced from the results of hydrodynamical simulations of disk galaxies with nonsymmetric irregular spirals and their nonconstant pitch angles across disks. In particular, weak spiral arms in barred-disk galaxies are properly segmented. Conclusions. These results suggest that U-Net can segment more symmetric spiral arms with constant pitch angles in disk galaxies. However, we need to train U-Net with a larger number of more realistic galaxy images with noise, nonsymmetric spirals, and different pitch angles between different arms in order to apply it to real spiral galaxies. It would be a challenge to make a large number of training data sets for such realistic nonsymmetric and irregular spiral arms with nonconstant pitch angles.

Download Full-text

BUILDING GENERALIZATION USING DEEP LEARNING

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-4-565-2018 ◽

2018 ◽

Vol XLII-4 ◽

pp. 565-572 ◽

Cited By ~ 4

Author(s):

M. Sester ◽

Y. Feng ◽

F. Thiemann

Keyword(s):

Computer Vision ◽

Deep Learning ◽

Physical Reality ◽

Training Data ◽

Data Sets ◽

Learning Approaches ◽

Depth Analysis ◽

Map Series ◽

Training Examples ◽

Future Work

Abstract. Cartographic generalization is a problem, which poses interesting challenges to automation. Whereas plenty of algorithms have been developed for the different sub-problems of generalization (e.g. simplification, displacement, aggregation), there are still cases, which are not generalized adequately or in a satisfactory way. The main problem is the interplay between different operators. In those cases the benchmark is the human operator, who is able to design an aesthetic and correct representation of the physical reality.Deep Learning methods have shown tremendous success for interpretation problems for which algorithmic methods have deficits. A prominent example is the classification and interpretation of images, where deep learning approaches outperform the traditional computer vision methods. In both domains &ndash; computer vision and cartography &ndash; humans are able to produce a solution; a prerequisite for this is, that there is the possibility to generate many training examples for the different cases. Thus, the idea in this paper is to employ Deep Learning for cartographic generalizations tasks, especially for the task of building generalization. An advantage of this task is the fact that many training data sets are available from given map series. The approach is a first attempt using an existing network.In the paper, the details of the implementation will be reported, together with an in depth analysis of the results. An outlook on future work will be given.

Download Full-text

Deep Learning COVID-19 Features on CXR Using Limited Training Data Sets

IEEE Transactions on Medical Imaging ◽

10.1109/tmi.2020.2993291 ◽

2020 ◽

Vol 39 (8) ◽

pp. 2688-2700 ◽

Cited By ~ 41

Author(s):

Yujin Oh ◽

Sangjoon Park ◽

Jong Chul Ye

Keyword(s):

Deep Learning ◽

Training Data ◽

Data Sets

Download Full-text

AltumAge: A Pan-Tissue DNA-Methylation Epigenetic Clock Based on Deep Learning

10.1101/2021.06.01.446559 ◽

2021 ◽

Author(s):

Lucas Paulo de Lima ◽

Louis R Lapierre ◽

Ritambhara Singh

Keyword(s):

Dna Methylation ◽

Deep Learning ◽

Placental Tissue ◽

Training Data ◽

Data Sets ◽

Epigenetic Clock ◽

Neural Network Approach ◽

Cpg Sites ◽

Age Related ◽

Model Predictions

Several age predictors based on DNA methylation, dubbed epigenetic clocks, have been created in recent years. Their accuracy and potential for generalization vary widely based on the training data. Here, we gathered 143 publicly available data sets from several human tissues to develop AltumAge, a highly accurate and precise age predictor based on deep learning. Compared to Horvath's 2013 model, AltumAge performs better across both normal and malignant tissues and is more generalizable to new data sets. Interestingly, it can predict gestational week from placental tissue with low error. Lastly, we used deep learning interpretation methods to learn which methylation sites contributed to the final model predictions. We observed that while most important CpG sites are linearly related to age, some highly-interacting CpG sites can influence the relevance of such relationships. We studied the associated genes of these CpG sites and found literary evidence of their involvement in age-related gene regulation. Using chromatin annotations, we observed that the CpG sites with the highest contribution to the model predictions were related to heterochromatin and gene regulatory regions in the genome. We also found age-related KEGG pathways for genes containing these CpG sites. In general, neural networks are better predictors due to their ability to capture complex feature interactions compared to the typically used regularized linear regression. Altogether, our neural network approach provides significant improvement and flexibility to current epigenetic clocks without sacrificing model interpretability.

Download Full-text

COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings

International Journal of Biomedical Imaging ◽

10.1155/2020/8828855 ◽

2020 ◽

Vol 2020 ◽

pp. 1-7

Author(s):

Mohd Zulfaezal Che Azemin ◽

Radhiana Hassan ◽

Mohd Izzuddin Mohd Tamrin ◽

Mohd Adli Md Ali

Keyword(s):

Deep Learning ◽

Network Architecture ◽

Clinical Findings ◽

Training Data ◽

Receiver Operating Curve ◽

Data Sets ◽

Data Set ◽

X Ray ◽

Chest X Ray ◽

Sensitivity Specificity

The key component in deep learning research is the availability of training data sets. With a limited number of publicly available COVID-19 chest X-ray images, the generalization and robustness of deep learning models to detect COVID-19 cases developed based on these images are questionable. We aimed to use thousands of readily available chest radiograph images with clinical findings associated with COVID-19 as a training data set, mutually exclusive from the images with confirmed COVID-19 cases, which will be used as the testing data set. We used a deep learning model based on the ResNet-101 convolutional neural network architecture, which was pretrained to recognize objects from a million of images and then retrained to detect abnormality in chest X-ray images. The performance of the model in terms of area under the receiver operating curve, sensitivity, specificity, and accuracy was 0.82, 77.3%, 71.8%, and 71.9%, respectively. The strength of this study lies in the use of labels that have a strong clinical association with COVID-19 cases and the use of mutually exclusive publicly available data for training, validation, and testing.

Download Full-text

Deep-CEE I: fishing for galaxy clusters with deep neural nets

Monthly Notices of the Royal Astronomical Society ◽

10.1093/mnras/stz2936 ◽

2019 ◽

Vol 490 (4) ◽

pp. 5770-5787 ◽

Cited By ~ 3

Author(s):

Matthew C Chan ◽

John P Stott

Keyword(s):

Deep Learning ◽

Galaxy Clusters ◽

Galaxy Evolution ◽

Learning Algorithm ◽

High Redshift ◽

Simulated Data ◽

Galaxy Cluster ◽

Neural Nets ◽

Training Data ◽

Wide Field

ABSTRACT We introduce Deep-CEE (Deep Learning for Galaxy Cluster Extraction and Evaluation), a proof of concept for a novel deep learning technique, applied directly to wide-field colour imaging to search for galaxy clusters, without the need for photometric catalogues. This technique is complementary to traditional methods and could also be used in combination with them to confirm existing galaxy cluster candidates. We use a state-of-the-art probabilistic algorithm, adapted to localize and classify galaxy clusters from other astronomical objects in Sloan Digital Sky Survey imaging. As there is an abundance of labelled data for galaxy clusters from previous classifications in publicly available catalogues, we do not need to rely on simulated data. This means we keep our training data as realistic as possible, which is advantageous when training a deep learning algorithm. Ultimately, we will apply our model to surveys such as Large Synoptic Survey Telescope and Euclid to probe wider and deeper into unexplored regions of the Universe. This will produce large samples of both high-redshift and low-mass clusters, which can be utilized to constrain both environment-driven galaxy evolution and cosmology.

Download Full-text

Generative Adversarial Domain Adaptation for Nucleus Quantification in Images of Tissue Immunohistochemically Stained for Ki-67

JCO Clinical Cancer Informatics ◽

10.1200/cci.19.00108 ◽

2020 ◽

pp. 666-679 ◽

Cited By ~ 2

Author(s):

Xuhong Zhang ◽

Toby C. Cornish ◽

Lin Yang ◽

Tellen D. Bennett ◽

Debashis Ghosh ◽

...

Keyword(s):

Deep Learning ◽

Domain Adaptation ◽

Training Data ◽

Data Sets ◽

Learning Models ◽

Convolutional Network ◽

Ki 67 ◽

Data Set ◽

Target Data ◽

Real Target

PURPOSE We focus on the problem of scarcity of annotated training data for nucleus recognition in Ki-67 immunohistochemistry (IHC)–stained pancreatic neuroendocrine tumor (NET) images. We hypothesize that deep learning–based domain adaptation is helpful for nucleus recognition when image annotations are unavailable in target data sets. METHODS We considered 2 different institutional pancreatic NET data sets: one (ie, source) containing 38 cases with 114 annotated images and the other (ie, target) containing 72 cases with 20 annotated images. The gold standards were manually annotated by 1 pathologist. We developed a novel deep learning–based domain adaptation framework to count different types of nuclei (ie, immunopositive tumor, immunonegative tumor, nontumor nuclei). We compared the proposed method with several recent fully supervised deep learning models, such as fully convolutional network-8s (FCN-8s), U-Net, fully convolutional regression network (FCRN) A, FCRNB, and fully residual convolutional network (FRCN). We also evaluated the proposed method by learning with a mixture of converted source images and real target annotations. RESULTS Our method achieved an F1 score of 81.3% and 62.3% for nucleus detection and classification in the target data set, respectively. Our method outperformed FCN-8s (53.6% and 43.6% for nucleus detection and classification, respectively), U-Net (61.1% and 47.6%), FCRNA (63.4% and 55.8%), and FCRNB (68.2% and 60.6%) in terms of F1 score and was competitive with FRCN (81.7% and 70.7%). In addition, learning with a mixture of converted source images and only a small set of real target labels could further boost the performance. CONCLUSION This study demonstrates that deep learning–based domain adaptation is helpful for nucleus recognition in Ki-67 IHC stained images when target data annotations are not available. It would improve the applicability of deep learning models designed for downstream supervised learning tasks on different data sets.

Download Full-text

The use of deep learning to automate the segmentation of the skeleton from CT volumes of pigs1

Translational Animal Science ◽

10.1093/tas/txy060 ◽

2018 ◽

Vol 2 (3) ◽

pp. 324-335 ◽

Cited By ~ 2

Author(s):

Johannes Kvam ◽

Lars Erik Gangsei ◽

Jørgen Kongsro ◽

Anne H Schistad Solberg

Keyword(s):

Deep Learning ◽

Automatic Segmentation ◽

Large Data ◽

Ct Scanning ◽

Large Data Sets ◽

Training Data ◽

Data Sets ◽

Fully Automatic ◽

Number Of Individuals ◽

Control Accuracy

Abstract Computed tomography (CT) scanning of pigs has been shown to produce detailed phenotypes useful in pig breeding. Due to the large number of individuals scanned and corresponding large data sets, there is a need for automatic tools for analysis of these data sets. In this paper, the feasibility of deep learning for fully automatic segmentation of the skeleton of pigs from CT volumes is explored. To maximize performance, given the training data available, a series of problem simplifications are applied. The deep-learning approach can replace our currently used semiautomatic solution, with increased robustness and little or no need for manual control. Accuracy was highly affected by training data, and expanding the training set can further increase performance making this approach especially promising.

Download Full-text

A Surrogate Data-Based Approach for Validating Deep Learning Model Used in Healthcare

Applications of Deep Learning and Big IoT on Personalized Healthcare Services - Advances in Medical Technologies and Clinical Practice ◽

10.4018/978-1-7998-2101-4.ch009 ◽

2020 ◽

pp. 132-146

Author(s):

Meenakshi Srivastava

Keyword(s):

Deep Learning ◽

Predictive Modelling ◽

Surrogate Data ◽

Learning Model ◽

Training Data ◽

Data Sets ◽

Data Set ◽

Huge Data ◽

Small Data Sets ◽

Deep Learning Model

IoT-based communication between medical devices has encouraged the healthcare industry to use automated systems which provide effective insight from the massive amount of gathered data. AI and machine learning have played a major role in the design of such systems. Accuracy and validation are considered, since copious training data is required in a neural network (NN)-based deep learning model. This is hardly feasible in medical research, because the size of data sets is constrained by complexity and high cost experiments. The availability of limited sample data validation of NN remains a concern. The prediction of outcomes on a NN trained on a smaller data set cannot guarantee performance and exhibits unstable behaviors. Surrogate data-based validation of NN can be viewed as a solution. In the current chapter, the classification of breast tissue data by a NN model has been detailed. In the absence of a huge data set, a surrogate data-based validation approach has been applied. The discussed study can be applied for predictive modelling for applications described by small data sets.

Download Full-text

MVP: predicting pathogenicity of missense variants by deep learning

10.1101/259390 ◽

2018 ◽

Cited By ~ 10

Author(s):

Hongjian Qi ◽

Chen Chen ◽

Haicang Zhang ◽

John J. Long ◽

Wendy K. Chung ◽

...

Keyword(s):

Deep Learning ◽

Developmental Disorders ◽

De Novo ◽

Prediction Method ◽

Training Data ◽

Data Sets ◽

Clinical Genetic ◽

Missense Variants ◽

Clinical Genetic Testing ◽

Pathogenicity Prediction

AbstractAccurate pathogenicity prediction of missense variants is critical to improve power in genetic studies and accurate interpretation in clinical genetic testing. Here we describe a new prediction method, MVP, which uses a deep learning approach to leverage large training data sets and many correlated predictors. Using cancer mutation hotspots and de novo germline mutations from developmental disorders for benchmarking, MVP achieved better performance in prioritizing pathogenic missense variants than previous methods.

Download Full-text

Sentiment Analysis from Tweets using Convolutional Neural Networks

The Journal of CIEES ◽

10.48149/jciees.2021.1.1.2 ◽

2021 ◽

Vol 1 (1) ◽

pp. 12-16

Author(s):

M. Pek ◽

M. Turan

Keyword(s):

Social Media ◽

Deep Learning ◽

Political Parties ◽

Sentiment Analysis ◽

Success Rate ◽

Training Data ◽

Data Sets ◽

Success Rates ◽

Wide Spread ◽

Learning Techniques

By current improvements of web technology nowadays, usage of social media has increased. Twitter is a web site where millions share their opinions. Political parties, firms and other establishments has been examining data at these social media sites to learn person’s opinions about themselves. Reporting the sharing of millions of persons instantly is done more easily by using machine and deep learning techniques. In this work, sentiment analysis is done by the Convolutional Neural Network which has wide-spread usage in deep learning. Besides other known works, improvements in feature selection have been applied in order to meet higher success rate. Model has been trained by the different data sets and tested in other data sets. The model has reached to 97% success rate by the training data. 90% and 89% success rates have been achieved on the tests applied to other data sets.

Download Full-text