Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Semantic segmentation of microscopic images of H&E stained prostatic tissue using CNN

Isaksson, Johan LU orcid ; Arvidsson, Ida LU orcid ; Åström, Kalle LU orcid and Heyden, Anders LU orcid (2017) 2017 International Joint Conference on Neural Networks, IJCNN 2017 2017-May. p.1252-1256
Abstract

There is a need for an automatic Gleason scoring system that can be used for prostate cancer diagnosis. Today the diagnoses are determined by pathologists manually, which is both a complex and a time-consuming task. To reduce the pathologists' workload, but also to reduce variations between different pathologists, an automatic classification system would be of great use. Some previous works have aimed for this, but still more work needs to be done. It is probable that such a tool would benefit from having access to individually segmented, pathologically relevant objects from the images. Therefore, we have developed an algorithm for semantic segmentation of the microscopic images of H&E stained prostate tissue into Background,... (More)

There is a need for an automatic Gleason scoring system that can be used for prostate cancer diagnosis. Today the diagnoses are determined by pathologists manually, which is both a complex and a time-consuming task. To reduce the pathologists' workload, but also to reduce variations between different pathologists, an automatic classification system would be of great use. Some previous works have aimed for this, but still more work needs to be done. It is probable that such a tool would benefit from having access to individually segmented, pathologically relevant objects from the images. Therefore, we have developed an algorithm for semantic segmentation of the microscopic images of H&E stained prostate tissue into Background, Stroma, Epithelial Cytoplasm and Nuclei. This algorithm is based on deep learning, or more specifically a convolutional neural network. The network design is inspired by architectures that previously have been proved successful in different applications. It consists of a contracting and an expanding part, which are symmetrical. We have reached an accuracy of 80 %, as measured by the mean of the intersection over union, for segmentation into four classes. Previous works have only investigated nuclei segmentation, and our network performed similar but for the more challenging task of four class segmentation.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings
volume
2017-May
article number
7965996
pages
5 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2017 International Joint Conference on Neural Networks, IJCNN 2017
conference location
Anchorage, United States
conference dates
2017-05-14 - 2017-05-19
external identifiers
  • scopus:85031034057
ISBN
9781509061815
DOI
10.1109/IJCNN.2017.7965996
project
Lund University AI Research
language
English
LU publication?
yes
id
4a850c7f-3019-4750-8030-78fa984a2fcb
date added to LUP
2017-10-30 08:17:31
date last changed
2024-10-14 16:01:56
@inproceedings{4a850c7f-3019-4750-8030-78fa984a2fcb,
  abstract     = {{<p>There is a need for an automatic Gleason scoring system that can be used for prostate cancer diagnosis. Today the diagnoses are determined by pathologists manually, which is both a complex and a time-consuming task. To reduce the pathologists' workload, but also to reduce variations between different pathologists, an automatic classification system would be of great use. Some previous works have aimed for this, but still more work needs to be done. It is probable that such a tool would benefit from having access to individually segmented, pathologically relevant objects from the images. Therefore, we have developed an algorithm for semantic segmentation of the microscopic images of H&amp;E stained prostate tissue into Background, Stroma, Epithelial Cytoplasm and Nuclei. This algorithm is based on deep learning, or more specifically a convolutional neural network. The network design is inspired by architectures that previously have been proved successful in different applications. It consists of a contracting and an expanding part, which are symmetrical. We have reached an accuracy of 80 %, as measured by the mean of the intersection over union, for segmentation into four classes. Previous works have only investigated nuclei segmentation, and our network performed similar but for the more challenging task of four class segmentation.</p>}},
  author       = {{Isaksson, Johan and Arvidsson, Ida and Åström, Kalle and Heyden, Anders}},
  booktitle    = {{2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings}},
  isbn         = {{9781509061815}},
  language     = {{eng}},
  month        = {{06}},
  pages        = {{1252--1256}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Semantic segmentation of microscopic images of H&E stained prostatic tissue using CNN}},
  url          = {{http://dx.doi.org/10.1109/IJCNN.2017.7965996}},
  doi          = {{10.1109/IJCNN.2017.7965996}},
  volume       = {{2017-May}},
  year         = {{2017}},
}