scholarly journals Proactive Construction of an Annotated Imaging Database for Artificial Intelligence Training

2020 ◽  
Author(s):  
Caroline Bivik Stadler ◽  
Martin Lindvall ◽  
Claes Lundström ◽  
Anna Bodén ◽  
Karin Lindman ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Image Data ◽  
Ground Truth ◽  
Lessons Learned ◽  
Training Data ◽  
Imaging Data ◽  
High Quality ◽  
High Quality Image ◽  
Specific Objective ◽  
Wide Range

Abstract Artificial intelligence (AI) holds much promise for enabling highly desired imaging diagnostics improvements. One of the most limiting bottlenecks for the development of useful clinical-grade AI models is the lack of training data. One aspect is the large amount of cases needed and another is the necessity of high-quality ground truth annotation. The aim of the project was to establish and describe the construction of a database with substantial amounts of detail-annotated oncology imaging data from pathology and radiology. A specific objective was to be proactive, that is, to support undefined subsequent AI training across a wide range of tasks, such as detection, quantification, segmentation, and classification, which puts particular focus on the quality and generality of the annotations. The main outcome of this project was the database as such, with a collection of labeled image data from breast, ovary, skin, colon, skeleton, and liver. In addition, this effort also served as an exploration of best practices for further scalability of high-quality image collections, and a main contribution of the study was generic lessons learned regarding how to successfully organize efforts to construct medical imaging databases for AI training, summarized as eight guiding principles covering team, process, and execution aspects.

scholarly journals Image-based surface reconstruction in geomorphometry – merits, limits and developments

2016 ◽  
Vol 4 (2) ◽  
pp. 359-389 ◽  
Author(s):  
Anette Eltner ◽  
Andreas Kaiser ◽  
Carlos Castillo ◽  
Gilles Rock ◽  
Fabian Neugirg ◽  
...  
Keyword(s):  
High Performance ◽  
Image Data ◽  
Ground Truth ◽  
Limited Range ◽  
Lessons Learned ◽  
Data Sets ◽  
Scale Invariant ◽  
High Quality ◽  
Research Fields ◽  
Wide Range

Abstract. Photogrammetry and geosciences have been closely linked since the late 19th century due to the acquisition of high-quality 3-D data sets of the environment, but it has so far been restricted to a limited range of remote sensing specialists because of the considerable cost of metric systems for the acquisition and treatment of airborne imagery. Today, a wide range of commercial and open-source software tools enable the generation of 3-D and 4-D models of complex geomorphological features by geoscientists and other non-experts users. In addition, very recent rapid developments in unmanned aerial vehicle (UAV) technology allow for the flexible generation of high-quality aerial surveying and ortho-photography at a relatively low cost.The increasing computing capabilities during the last decade, together with the development of high-performance digital sensors and the important software innovations developed by computer-based vision and visual perception research fields, have extended the rigorous processing of stereoscopic image data to a 3-D point cloud generation from a series of non-calibrated images. Structure-from-motion (SfM) workflows are based upon algorithms for efficient and automatic orientation of large image sets without further data acquisition information, examples including robust feature detectors like the scale-invariant feature transform for 2-D imagery. Nevertheless, the importance of carrying out well-established fieldwork strategies, using proper camera settings, ground control points and ground truth for understanding the different sources of errors, still needs to be adapted in the common scientific practice.This review intends not only to summarise the current state of the art on using SfM workflows in geomorphometry but also to give an overview of terms and fields of application. Furthermore, this article aims to quantify already achieved accuracies and used scales, using different strategies in order to evaluate possible stagnations of current developments and to identify key future challenges. It is our belief that some lessons learned from former articles, scientific reports and book chapters concerning the identification of common errors or "bad practices" and some other valuable information may help in guiding the future use of SfM photogrammetry in geosciences.

scholarly journals Seg2pix: Few Shot Training Line Art Colorization with Segmented Image Data

2021 ◽  
Vol 11 (4) ◽  
pp. 1464
Author(s):  
Chang Wook Seo ◽  
Yongduek Seo
Keyword(s):  
Image Data ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Training Data ◽  
High Quality ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Segmented Image ◽  
Image Translation ◽  
Segmentation Image

There are various challenging issues in automating line art colorization. In this paper, we propose a GAN approach incorporating semantic segmentation image data. Our GAN-based method, named Seg2pix, can automatically generate high quality colorized images, aiming at computerizing one of the most tedious and repetitive jobs performed by coloring workers in the webtoon industry. The network structure of Seg2pix is mostly a modification of the architecture of Pix2pix, which is a convolution-based generative adversarial network for image-to-image translation. Through this method, we can generate high quality colorized images of a particular character with only a few training data. Seg2pix is designed to reproduce a segmented image, which becomes the suggestion data for line art colorization. The segmented image is automatically generated through a generative network with a line art image and a segmentation ground truth. In the next step, this generative network creates a colorized image from the line art and segmented image, which is generated from the former step of the generative network. To summarize, only one line art image is required for testing the generative model, and an original colorized image and segmented image are additionally required as the ground truth for training the model. These generations of the segmented image and colorized image proceed by an end-to-end method sharing the same loss functions. By using this method, we produce better qualitative results for automatic colorization of a particular character’s line art. This improvement can also be measured by quantitative results with Learned Perceptual Image Patch Similarity (LPIPS) comparison. We believe this may help artists exercise their creative expertise mainly in the area where computerization is not yet capable.

scholarly journals Image-based surface reconstruction in geomorphometry – merits, limits and developments of a promising tool for geoscientists

2015 ◽  
Vol 3 (4) ◽  
pp. 1445-1508 ◽  
Author(s):  
A. Eltner ◽  
A. Kaiser ◽  
C. Castillo ◽  
G. Rock ◽  
F. Neugirg ◽  
...  
Keyword(s):  
Structure From Motion ◽  
High Performance ◽  
Scientific Practice ◽  
Low Cost ◽  
Image Data ◽  
Ground Truth ◽  
Scale Invariant ◽  
High Quality ◽  
Promising Tool ◽  
Wide Range

Abstract. Photogrammetry and geosciences are closely linked since the late 19th century. Today, a wide range of commercial and open-source software enable non-experts users to obtain high-quality 3-D datasets of the environment, which was formerly reserved to remote sensing experts, geodesists or owners of cost-intensive metric airborne imaging systems. Complex tridimensional geomorphological features can be easily reconstructed from images captured with consumer grade cameras. Furthermore, rapid developments in UAV technology allow for high quality aerial surveying and orthophotography generation at a relatively low-cost. The increasing computing capacities during the last decade, together with the development of high-performance digital sensors and the important software innovations developed by other fields of research (e.g. computer vision and visual perception) has extended the rigorous processing of stereoscopic image data to a 3-D point cloud generation from a series of non-calibrated images. Structure from motion methods offer algorithms, e.g. robust feature detectors like the scale-invariant feature transform for 2-D imagery, which allow for efficient and automatic orientation of large image sets without further data acquisition information. Nevertheless, the importance of carrying out correct fieldwork strategies, using proper camera settings, ground control points and ground truth for understanding the different sources of errors still need to be adapted in the common scientific practice. This review manuscript intends not only to summarize the present state of published research on structure-from-motion photogrammetry applications in geomorphometry, but also to give an overview of terms and fields of application, to quantify already achieved accuracies and used scales using different strategies, to evaluate possible stagnations of current developments and to identify key future challenges. It is our belief that the identification of common errors, "bad practices" and some other valuable information in already published articles, scientific reports and book chapters may help in guiding the future use of SfM photogrammetry in geosciences.

scholarly journals Unsupervised content-preserving transformation for optical microscopy

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Xinyang Li ◽  
Guoxun Zhang ◽  
Hui Qiao ◽  
Feng Bao ◽  
Yue Deng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Optical Microscopy ◽  
Training Data ◽  
Fluorescence Labeling ◽  
Imaging Data ◽  
Image Transformation ◽  
General Applicability ◽  
Data Annotation ◽  
Biomedical Image ◽  
Wide Range

AbstractThe development of deep learning and open access to a substantial collection of imaging data together provide a potential solution for computational image transformation, which is gradually changing the landscape of optical imaging and biomedical research. However, current implementations of deep learning usually operate in a supervised manner, and their reliance on laborious and error-prone data annotation procedures remains a barrier to more general applicability. Here, we propose an unsupervised image transformation to facilitate the utilization of deep learning for optical microscopy, even in some cases in which supervised models cannot be applied. Through the introduction of a saliency constraint, the unsupervised model, named Unsupervised content-preserving Transformation for Optical Microscopy (UTOM), can learn the mapping between two image domains without requiring paired training data while avoiding distortions of the image content. UTOM shows promising performance in a wide range of biomedical image transformation tasks, including in silico histological staining, fluorescence image restoration, and virtual fluorescence labeling. Quantitative evaluations reveal that UTOM achieves stable and high-fidelity image transformations across different imaging conditions and modalities. We anticipate that our framework will encourage a paradigm shift in training neural networks and enable more applications of artificial intelligence in biomedical imaging.

An efficient approach to converting three-dimensional image data into highly accurate computational models

2008 ◽  
Vol 366 (1878) ◽  
pp. 3155-3173 ◽  
Author(s):  
P.G Young ◽  
T.B.H Beresford-West ◽  
S.R.L Coward ◽  
B Notarberardino ◽  
B Walker ◽  
...  
Keyword(s):  
Mesh Generation ◽  
Computational Models ◽  
Three Dimensional ◽  
Image Data ◽  
Model Material ◽  
Imaging Data ◽  
Material Inhomogeneity ◽  
Dimensional Image ◽  
Wide Range ◽  
Impact Modelling

Image-based meshing is opening up exciting new possibilities for the application of computational continuum mechanics methods (finite-element and computational fluid dynamics) to a wide range of biomechanical and biomedical problems that were previously intractable owing to the difficulty in obtaining suitably realistic models. Innovative surface and volume mesh generation techniques have recently been developed, which convert three-dimensional imaging data, as obtained from magnetic resonance imaging, computed tomography, micro-CT and ultrasound, for example, directly into meshes suitable for use in physics-based simulations. These techniques have several key advantages, including the ability to robustly generate meshes for topologies of arbitrary complexity (such as bioscaffolds or composite micro-architectures) and with any number of constituent materials (multi-part modelling), providing meshes in which the geometric accuracy of mesh domains is only dependent on the image accuracy (image-based accuracy) and the ability for certain problems to model material inhomogeneity by assigning the properties based on image signal strength. Commonly used mesh generation techniques will be compared with the proposed enhanced volumetric marching cubes (EVoMaCs) approach and some issues specific to simulations based on three-dimensional image data will be discussed. A number of case studies will be presented to illustrate how these techniques can be used effectively across a wide range of problems from characterization of micro-scaffolds through to head impact modelling.

scholarly journals AI-Sketcher : A Deep Generative Model for Producing High-Quality Sketches

2019 ◽  
Vol 33 ◽  
pp. 2564-2571 ◽  
Author(s):  
Nan Cao ◽  
Xin Yan ◽  
Yang Shi ◽  
Chaoran Chen
Keyword(s):  
Artificial Intelligence ◽  
Large Scale ◽  
State Of The Art ◽  
Positional Information ◽  
Generative Model ◽  
Training Data ◽  
Creative Design ◽  
High Quality ◽  
User Input ◽  
Variational Autoencoder

Sketch drawings play an important role in assisting humans in communication and creative design since ancient period. This situation has motivated the development of artificial intelligence (AI) techniques for automatically generating sketches based on user input. Sketch-RNN, a sequence-to-sequence variational autoencoder (VAE) model, was developed for this purpose and known as a state-of-the-art technique. However, it suffers from limitations, including the generation of lowquality results and its incapability to support multi-class generations. To address these issues, we introduced AI-Sketcher, a deep generative model for generating high-quality multiclass sketches. Our model improves drawing quality by employing a CNN-based autoencoder to capture the positional information of each stroke at the pixel level. It also introduces an influence layer to more precisely guide the generation of each stroke by directly referring to the training data. To support multi-class sketch generation, we provided a conditional vector that can help differentiate sketches under various classes. The proposed technique was evaluated based on two large-scale sketch datasets, and results demonstrated its power in generating high-quality sketches.

Brain tumor classification and segmentation using sparse coding and dictionary learning

2016 ◽  
Vol 61 (4) ◽  
pp. 413-429 ◽  
Author(s):  
Saif Dawood Salman Al-Shaikhli ◽  
Michael Ying Yang ◽  
Bodo Rosenhahn
Keyword(s):  
Brain Tumor ◽  
Dictionary Learning ◽  
Sparse Coding ◽  
Image Data ◽  
Ground Truth ◽  
Tumor Classification ◽  
Training Data ◽  
Tumor Segmentation ◽  
Feature Dictionary ◽  
The Brain

AbstractThis paper presents a novel fully automatic framework for multi-class brain tumor classification and segmentation using a sparse coding and dictionary learning method. The proposed framework consists of two steps: classification and segmentation. The classification of the brain tumors is based on brain topology and texture. The segmentation is based on voxel values of the image data. Using K-SVD, two types of dictionaries are learned from the training data and their associated ground truth segmentation: feature dictionary and voxel-wise coupled dictionaries. The feature dictionary consists of global image features (topological and texture features). The coupled dictionaries consist of coupled information: gray scale voxel values of the training image data and their associated label voxel values of the ground truth segmentation of the training data. For quantitative evaluation, the proposed framework is evaluated using different metrics. The segmentation results of the brain tumor segmentation (MICCAI-BraTS-2013) database are evaluated using five different metric scores, which are computed using the online evaluation tool provided by the BraTS-2013 challenge organizers. Experimental results demonstrate that the proposed approach achieves an accurate brain tumor classification and segmentation and outperforms the state-of-the-art methods.

WAVELET DE-NOISING OF OPTICAL TERAHERTZ PULSE IMAGING DATA

2001 ◽  
Vol 01 (02) ◽  
pp. L65-L69 ◽  
Author(s):  
BRADLEY FERGUSON ◽  
DEREK ABBOTT
Keyword(s):  
Image Data ◽  
Imaging Data ◽  
Terahertz Pulse ◽  
Spectroscopic Measurements ◽  
Wide Range ◽  
Terahertz Pulse Imaging

Terahertz pulse imaging (TPI) systems are used to obtain sub-millimeter spectroscopic measurements for a wide range of applications. This letter highlights the use of wavelet de-noising to markedly improve the SNR of the obtained data, increasing the SNR by up to 10 dB. A comparison of different wavelet families and properties is presented and the results demonstrated on THz image data of an oak leaf and an Australian $100 note.

scholarly journals Facing small and biased data dilemma in drug discovery with federated learning

2020 ◽  
Author(s):  
Zhaoping Xiong ◽  
Ziqiang Cheng ◽  
Chi Xu ◽  
Xinyuan Lin ◽  
Xiaohong Liu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Drug Discovery ◽  
Aqueous Solubility ◽  
Training Data ◽  
Small Data ◽  
Sensitive Information ◽  
Distributed Data ◽  
High Quality ◽  
Different Sources ◽  
Striking Contrast

AbstractArtificial intelligence (AI) models usually require large amounts of high-quality training data, which is in striking contrast to the situation of small and biased data faced by current drug discovery pipelines. The concept of federated learning has been proposed to utilize distributed data from different sources without leaking sensitive information of these data. This emerging decentralized machine learning paradigm is expected to dramatically improve the success of AI-powered drug discovery. We here simulate the federated learning process with 7 aqueous solubility datasets from different sources, among which there are overlapping molecules with high or low biases in the recorded values. Beyond the benefit of gaining more data, we also demonstrate federated training has a regularization effect making it superior than centralized training on the pooled datasets with high biases. Further, two more cases are studied to test the usability of federated learning in drug discovery. Our work demonstrates the application of federated learning in predicting drug related properties, but also highlights its promising role in addressing the small data and biased data dilemma in drug discovery.

scholarly journals LAND COVER CLASSIFICATION FROM FULL-WAVEFORM LIDAR DATA BASED ON SUPPORT VECTOR MACHINES

2016 ◽  
Vol XLI-B3 ◽  
pp. 447-452
Author(s):  
M. Zhou ◽  
C. R. Li ◽  
L. Ma ◽  
H. C. Guan
Keyword(s):  
Support Vector Machines ◽  
Land Cover ◽  
Prediction Model ◽  
Image Data ◽  
Ground Truth ◽  
Land Cover Classification ◽  
Training Data ◽  
Support Vector ◽  
Vector Machines ◽  
Waveform Lidar

In this study, a land cover classification method based on multi-class Support Vector Machines (SVM) is presented to predict the types of land cover in Miyun area. The obtained backscattered full-waveforms were processed following a workflow of waveform pre-processing, waveform decomposition and feature extraction. The extracted features, which consist of distance, intensity, Full Width at Half Maximum (FWHM) and back scattering cross-section, were corrected and used as attributes for training data to generate the SVM prediction model. The SVM prediction model was applied to predict the types of land cover in Miyun area as ground, trees, buildings and farmland. The classification results of these four types of land covers were obtained based on the ground truth information according to the CCD image data of Miyun area. It showed that the proposed classification algorithm achieved an overall classification accuracy of 90.63%. In order to better explain the SVM classification results, the classification results of SVM method were compared with that of Artificial Neural Networks (ANNs) method and it showed that SVM method could achieve better classification results.

Sign in / Sign up

Export Citation Format

Share Document