Skip to content

Research at St Andrews

Context based interpolation of coarse deep learning prediction maps for the segmentation of fine structures in immunofluorescence images

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Open Access permissions



Nicolas Brieu, Christos Gavriel, David James Harrison, Peter David Caie, Guenter Schmidt

School/Research organisations


The automatic analysis of digital pathology images is becoming of increasing interest for the development of novel therapeutic drugs and of the associated companion diagnostic tests in oncology. A precise quantification of the tumor microenvironment and therefore an accurate segmentation of the tumor extend are critical in this context. In this paper, we present a new approach based on visual context Random Forest to generate high resolution segmentation maps from Deep Learning coarse segmentation maps. Through an example inimmunofluorescence, we show that this method enables an accurate and fast detection of the tumor structures in terms of qualitative and quantitative evaluation against three baseline approaches. For the method to be resilient to the high variability of staining intensity, a novel locally adaptive normalization algorithm is moreover introduced.


Original languageEnglish
Title of host publicationMedical Imaging 2018
Subtitle of host publicationDigital Pathology
EditorsJohn E. Tomaszewski, Metin N. Gurcan
Number of pages6
StatePublished - 6 Mar 2018
EventSymposium: SPIE Medical Imaging : Digital Pathology - Marriott Marquis Houston, Houston, United States
Duration: 10 Feb 201815 Feb 2018
Conference number: 10581

Publication series

NameProceedings of SPIE
PublisherSociety of Photo-optical Instrumentation Engineers
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


ConferenceSymposium: SPIE Medical Imaging
CountryUnited States
Internet address

    Research areas

  • Digital pathology, Whole slide imaging (WSI), Immunofluorescence (IF), Deep learning, Random Forest, Interpolation, Semantic segmentation

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Identifying prognostic structural features in tissue sections of colon cancer patients using point pattern analysis

    Jones-Todd, C. M., Caie, P., Illian, J. B., Stevenson, B. C., Savage, A., Harrison, D. J. & Brown, J. L. 28 Nov 2018 In : Statistics in Medicine. Early View

    Research output: Contribution to journalArticle

  2. Digital Pathology: Path to the Future

    Caie, P. D. & Harrison, D. J. 2 Feb 2018 Tissue Phenomics : Profiling Cancer Patients for Treatment Decisions. Singapore: Pan Stanford Publishing Ltd, p. 185-198 14 p. (Next-Generation Medicine Vol. 1)

    Research output: Chapter in Book/Report/Conference proceedingChapter

  3. Novel histopathologic feature identified through image analysis augments stage II colorectal cancer clinical reporting

    Caie, P. D., Zhou, Y., Turnbull, A., Oniscu, A. & Harrison, D. J. 15 Jun 2016 In : Oncotarget. 7, 28, p. 44381-44394 14 p.

    Research output: Contribution to journalArticle

  4. Next-generation pathology

    Caie, P. D. & Harrison, D. J. 2016 Systems Medicine. Schmitz, U. & Wolkenhauer, O. (eds.). Humana Press, p. 61-72 12 p. (Methods in Molecular Biology; vol. 1386)

    Research output: Chapter in Book/Report/Conference proceedingChapter

ID: 252558377