uu.seUppsala University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Convolutional neural networks for false positive reduction of automatically detected cilia in low magnification TEM images
Tallinn Univ Technol, TJ Seebeck Dept Elect, Tallinn, Estonia.ORCID iD: 0000-0003-3557-4947
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Serbian Acad Arts & Sci, Math Inst, Belgrade, Serbia.ORCID iD: 0000-0001-7312-8222
Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Immunology, Genetics and Pathology, Clinical and experimental pathology. (Fredrik Pontén)ORCID iD: 0000-0003-2777-8114
Show others and affiliations
2017 (English)In: Image Analysis: Part I, Springer, 2017, p. 407-418Conference paper, Published paper (Refereed)
Abstract [en]

Automated detection of cilia in low magnification transmission electron microscopy images is a central task in the quest to relieve the pathologists in the manual, time consuming and subjective diagnostic procedure. However, automation of the process, specifically in low magnification, is challenging due to the similar characteristics of non-cilia candidates. In this paper, a convolutional neural network classifier is proposed to further reduce the false positives detected by a previously presented template matching method. Adding the proposed convolutional neural network increases the area under Precision-Recall curve from 0.42 to 0.71, and significantly reduces the number of false positive objects.

Place, publisher, year, edition, pages
Springer, 2017. p. 407-418
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 10269
National Category
Computer Vision and Robotics (Autonomous Systems) Clinical Laboratory Medicine
Research subject
Computerized Image Processing; Pathology
Identifiers
URN: urn:nbn:se:uu:diva-334218DOI: 10.1007/978-3-319-59126-1_34ISI: 000454359300034ISBN: 978-3-319-59125-4 (print)OAI: oai:DiVA.org:uu-334218DiVA, id: diva2:1159082
Conference
SCIA 2017, June 12–14, Tromsø, Norway
Funder
Vinnova, 2016-02329Available from: 2017-05-19 Created: 2017-11-21 Last updated: 2020-01-08Bibliographically approved
In thesis
1. Methods for Processing and Analysis of Biomedical TEM Images
Open this publication in new window or tab >>Methods for Processing and Analysis of Biomedical TEM Images
2019 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Transmission Electron Microscopy (TEM) has the high resolving capability and high clinical significance; however, the current manual diagnostic procedure using TEM is complicated and time-consuming, requiring rarely available expertise for analyzing TEM images of the biological specimen. This thesis addresses the bottlenecks of TEM-based analysis by proposing image analysis methods to automate and improve critical time-consuming steps of currently manual diagnostic procedures. The automation is demonstrated on the computer-assisted diagnosis of Primary Ciliary Dyskinesia (PCD), a genetic condition for which TEM analysis is considered the gold standard.

The methods proposed for the automated workflow mimic the manual procedure performed by the pathologists to detect objects of interest – diagnostically relevant cilia instances – followed by a computational step to combine information from multiple detected objects to enhance the important structural details. The workflow includes an approach for efficient search through a sample to identify objects and locate areas with a high density of objects of interest in low-resolution images, to perform high-resolution imaging of the identified areas. Subsequently, high-quality objects in high-resolution images are detected, processed, and the extracted information is combined to enhance structural details.

This thesis also addresses the challenges typical for TEM imaging, such as sample drift and deformation, or damage due to high electron dose for long exposure times. Two alternative paths are investigated: (i) different strategies combining short exposure imaging with suitable denoising techniques, including conventional approaches and a proposed deep learning based method, are explored; (ii) conventional interpolation approaches and a proposed deep learning based method are analyzed for super-resolution reconstruction using a single image. For both explored directions, in the best case scenario, the processing time is nearly 20 times faster as compared to the acquisition time for a single long exposure high illumination image. Moreover, the reconstruction approach (ii) requires nearly 16 times lesser data (storage space) and overcomes the need for high-resolution image acquisition.

Finally, the thesis addresses critical needs to enable objective and reliable evaluation of TEM image denoising approaches. A method for synthesizing realistic noise-free TEM reference images is proposed, and a denoising benchmark dataset is generated and made publicly available. The proposed dataset consists of noise-free references along with masks encompassing the critical diagnostic structures. This enables performance evaluation based on the capability of denoising methods to preserve structural details, instead of merely grading them based on the signal to noise ratio improvement and preservation of gross structures.

Place, publisher, year, edition, pages
Uppsala: Acta Universitatis Upsaliensis, 2019. p. 49
Series
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 1807
Keywords
image analysis, image processing, deep learning, transmission electron microscopy, denoising, super-resolution reconstruction, registration, detection
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-381800 (URN)978-91-513-0653-7 (ISBN)
Public defence
2019-06-05, Room 2446, ITC, Lägerhyddsvägen 2, Uppsala, 10:15 (English)
Opponent
Supervisors
Available from: 2019-05-15 Created: 2019-04-17 Last updated: 2019-06-18

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records BETA

Gupta, AnindyaSuveer, AmitLindblad, JoakimDragomir, AncaSintorn, Ida-Maria

Search in DiVA

By author/editor
Gupta, AnindyaSuveer, AmitLindblad, JoakimDragomir, AncaSintorn, Ida-MariaSladoje, Nataša
By organisation
Division of Visual Information and InteractionComputerized Image Analysis and Human-Computer InteractionClinical and experimental pathology
Computer Vision and Robotics (Autonomous Systems)Clinical Laboratory Medicine

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 106 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf