scholarly journals Large-Scale Permanent Slide Imaging and Image Analysis for Diatom Morphometrics

2017 ◽  
Vol 7 (4) ◽  
pp. 330 ◽  
Author(s):  
Michael Kloster ◽  
Oliver Esper ◽  
Gerhard Kauer ◽  
Bánk Beszteri
Keyword(s):  
Image Analysis ◽  
Large Scale ◽  
Permanent Slide

scholarly journals TransMed: Transformers Advance Multi-Modal Medical Image Classification

Diagnostics ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1384
Author(s):  
Yin Dai ◽  
Yifan Gao ◽  
Fayu Liu
Keyword(s):  
Image Analysis ◽  
Image Classification ◽  
Long Range ◽  
Medical Image ◽  
Large Scale ◽  
Medical Images ◽  
Medical Image Analysis ◽  
Lesion Detection ◽  
Tumor Segmentation ◽  
Medical Image Classification

Over the past decade, convolutional neural networks (CNN) have shown very competitive performance in medical image analysis tasks, such as disease classification, tumor segmentation, and lesion detection. CNN has great advantages in extracting local features of images. However, due to the locality of convolution operation, it cannot deal with long-range relationships well. Recently, transformers have been applied to computer vision and achieved remarkable success in large-scale datasets. Compared with natural images, multi-modal medical images have explicit and important long-range dependencies, and effective multi-modal fusion strategies can greatly improve the performance of deep models. This prompts us to study transformer-based structures and apply them to multi-modal medical images. Existing transformer-based network architectures require large-scale datasets to achieve better performance. However, medical imaging datasets are relatively small, which makes it difficult to apply pure transformers to medical image analysis. Therefore, we propose TransMed for multi-modal medical image classification. TransMed combines the advantages of CNN and transformer to efficiently extract low-level features of images and establish long-range dependencies between modalities. We evaluated our model on two datasets, parotid gland tumors classification and knee injury classification. Combining our contributions, we achieve an improvement of 10.1% and 1.9% in average accuracy, respectively, outperforming other state-of-the-art CNN-based models. The results of the proposed method are promising and have tremendous potential to be applied to a large number of medical image analysis tasks. To our best knowledge, this is the first work to apply transformers to multi-modal medical image classification.

Seafloor mapping based on multibeam echosounder bathymetry and backscatter data using Object-Based Image Analysis: a case study from the Rewal site, the Southern Baltic

2018 ◽  
Vol 47 (3) ◽  
pp. 248-259 ◽  
Author(s):  
Łukasz Janowski ◽  
Jarosław Tęgowski ◽  
Jarosław Nowak
Keyword(s):  
Image Analysis ◽  
Large Scale ◽  
Fine Sand ◽  
Empirical Method ◽  
Angular Variable ◽  
Seafloor Mapping ◽  
Multibeam Echosounder ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Southern Baltic

Abstract Seafloor mapping is a fast developing multidisciplinary branch of oceanology that combines geophysics, geostatistics, sedimentology and ecology. One of its objectives is to isolate distinct seabed features in a repeatable, fast and objective way, taking into consideration multibeam echosounder (MBES) bathymetry and backscatter data. A large-scale acoustic survey was conducted by the Maritime Institute in Gdańsk in 2010 using Reson 8125 MBES. The dataset covered over 20 km2 of a shallow seabed area (depth of up to 22 m) in the Polish Exclusive Economic Zone within the Southern Baltic. Determination of sediments was possible based on ground-truth grab samples acquired during the MBES survey. Four classes of sediments were recognized as muddy sand, very fine sand, fine sand and clay. The backscatter mosaic created using the Angular Variable Gain (AVG) empirical method was the primary contribution to the image processing method used in this study. The use of the Object-Based Image Analysis (OBIA) and the Classification and Regression Trees (CART) classifier makes it possible to isolate the backscatter image with 87.5% overall and 81.0% Kappa accuracy. The obtained results confirm the possibility of creating reliable maps of the seafloor based on MBES measurements. Once developed, the OBIA workflow can be applied to other spatial and temporal scenes.

scholarly journals Large-Scale Image Analysis for Investigating Spatio-Temporal Changes in Nuclear DNA Damage Caused by Nitrogen Atmospheric Pressure Plasma Jets

2020 ◽  
Vol 21 (11) ◽  
pp. 4127
Author(s):  
Xu Han ◽  
James Kapaldo ◽  
Yueying Liu ◽  
M. Sharon Stack ◽  
Elahe Alizadeh ◽  
...  
Keyword(s):  
Cell Cycle ◽  
Dna Damage ◽  
Image Analysis ◽  
Cancer Cells ◽  
Atmospheric Pressure ◽  
Large Scale ◽  
Nuclear Dna ◽  
Atmospheric Pressure Plasma ◽  
Plasma Jet ◽  
Spatio Temporal

The effective clinical application of atmospheric pressure plasma jet (APPJ) treatments requires a well-founded methodology that can describe the interactions between the plasma jet and a treated sample and the temporal and spatial changes that result from the treatment. In this study, we developed a large-scale image analysis method to identify the cell-cycle stage and quantify damage to nuclear DNA in single cells. The method was then tested and used to examine spatio-temporal distributions of nuclear DNA damage in two cell lines from the same anatomic location, namely the oral cavity, after treatment with a nitrogen APPJ. One cell line was malignant, and the other, nonmalignant. The results showed that DNA damage in cancer cells was maximized at the plasma jet treatment region, where the APPJ directly contacted the sample, and declined radially outward. As incubation continued, DNA damage in cancer cells decreased slightly over the first 4 h before rapidly decreasing by approximately 60% at 8 h post-treatment. In nonmalignant cells, no damage was observed within 1 h after treatment, but damage was detected 2 h after treatment. Notably, the damage was 5-fold less than that detected in irradiated cancer cells. Moreover, examining damage with respect to the cell cycle showed that S phase cells were more susceptible to DNA damage than either G1 or G2 phase cells. The proposed methodology for large-scale image analysis is not limited to APPJ post-treatment applications and can be utilized to evaluate biological samples affected by any type of radiation, and, more so, the cell-cycle classification can be used on any cell type with any nuclear DNA staining.

scholarly journals Resolving Clinicians’ Queries Across a Grid’s Infrastructure

2005 ◽  
Vol 44 (02) ◽  
pp. 149-153 ◽  
Author(s):  
F. Estrella ◽  
C. del Frate ◽  
T. Hauer ◽  
M. Odeh ◽  
D. Rogulin ◽  
...  
Keyword(s):  
Image Analysis ◽  
Data Storage ◽  
Medical Image ◽  
Large Scale ◽  
Medical Image Analysis ◽  
Large Data ◽  
Computing Power ◽  
European Database ◽  
Order Of Magnitude ◽  
Network Speed

Summary Objectives: The past decade has witnessed order of magnitude increases in computing power, data storage capacity and network speed, giving birth to applications which may handle large data volumes of increased complexity, distributed over the internet. Methods: Medical image analysis is one of the areas for which this unique opportunity likely brings revolutionary advances both for the scientist’s research study and the clinician’s everyday work. Grids [1] computing promises to resolve many of the difficulties in facilitating medical image analysis to allow radiologists to collaborate without having to co-locate. Results: The EU-funded MammoGrid project [2] aims to investigate the feasibility of developing a Grid-enabled European database of mammograms and provide an information infrastructure which federates multiple mammogram databases. This will enable clinicians to develop new common, collaborative and co-operative approaches to the analysis of mammographic data. Conclusion: This paper focuses on one of the key requirements for large-scale distributed mammogram analysis: resolving queries across a grid-connected federation of images.

scholarly journals ZF-AutoML: An Easy Machine-Learning-Based Method to Detect Anomalies in Fluorescent-Labelled Zebrafish

Inventions ◽  
2019 ◽  
Vol 4 (4) ◽  
pp. 72
Author(s):  
Ryota Sawaki ◽  
Daisuke Sato ◽  
Hiroko Nakayama ◽  
Yuki Nakagawa ◽  
Yasuhito Shimada
Keyword(s):  
Machine Learning ◽  
Image Analysis ◽  
High Throughput ◽  
High Throughput Screening ◽  
Large Scale ◽  
Fluorescent Protein ◽  
Learning Program ◽  
High Throughput Analysis ◽  
Easy Method ◽  
High Fecundity

Background: Zebrafish are efficient animal models for conducting whole organism drug testing and toxicological evaluation of chemicals. They are frequently used for high-throughput screening owing to their high fecundity. Peripheral experimental equipment and analytical software are required for zebrafish screening, which need to be further developed. Machine learning has emerged as a powerful tool for large-scale image analysis and has been applied in zebrafish research as well. However, its use by individual researchers is restricted due to the cost and the procedure of machine learning for specific research purposes. Methods: We developed a simple and easy method for zebrafish image analysis, particularly fluorescent labelled ones, using the free machine learning program Google AutoML. We performed machine learning using vascular- and macrophage-Enhanced Green Fluorescent Protein (EGFP) fishes under normal and abnormal conditions (treated with anti-angiogenesis drugs or by wounding the caudal fin). Then, we tested the system using a new set of zebrafish images. Results: While machine learning can detect abnormalities in the fish in both strains with more than 95% accuracy, the learning procedure needs image pre-processing for the images of the macrophage-EGFP fishes. In addition, we developed a batch uploading software, ZF-ImageR, for Windows (.exe) and MacOS (.app) to enable high-throughput analysis using AutoML. Conclusions: We established a protocol to utilize conventional machine learning platforms for analyzing zebrafish phenotypes, which enables fluorescence-based, phenotype-driven zebrafish screening.

Large-scale evaluation of plant growth in Arabidopsis thaliana by non-invasive image analysis

1999 ◽  
Vol 37 (9) ◽  
pp. 671-678 ◽  
Author(s):  
Dario Leister ◽  
Claudio Varotto ◽  
Paolo Pesaresi ◽  
Alexandra Niwergall ◽  
Francesco Salamini
Keyword(s):  
Arabidopsis Thaliana ◽  
Image Analysis ◽  
Plant Growth ◽  
Large Scale ◽  
Scale Evaluation ◽  
Non Invasive

scholarly journals Large-Scale Biomedical Image Analysis in Grid Environments

2008 ◽  
Vol 12 (2) ◽  
pp. 154-161 ◽  
Author(s):  
V.S. Kumar ◽  
B. Rutt ◽  
T. Kurc ◽  
U.V. Catalyurek ◽  
T.C. Pan ◽  
...  
Keyword(s):  
Image Analysis ◽  
Large Scale ◽  
Biomedical Image Analysis ◽  
Biomedical Image ◽  
Grid Environments

scholarly journals Large-Scale Integer Programs in Image Analysis

2002 ◽  
Vol 50 (3) ◽  
pp. 490-500 ◽  
Author(s):  
Geir Dahl ◽  
Geir Storvik ◽  
Alice Fadnes
Keyword(s):  
Image Analysis ◽  
Large Scale ◽  
Integer Programs
Sign in / Sign up

Export Citation Format

Share Document