Advanced

Towards Grading Gleason Score using Generically Trained Deep convolutional Neural Networks

Källén, Hanna LU ; Molin, Jesper; Heyden, Anders LU ; Lundström, Claes and Åström, Karl LU (2016) 2016 IEEE International Symposium on Biomedical Imaging In 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)
Abstract
We developed an automatic algorithm with the purpose to assist pathologists to report Gleason score on malignant prostatic adenocarcinoma specimen. In order to detect and classify the cancerous tissue, a deep convolutional neural network that had been pre-trained on a large set of photographic images was used. A specific aim was to support intuitive interaction with the result, to let pathologists adjust and correct the output. Therefore, we have designed an algorithm that makes a spatial classification of the whole slide into the same growth patterns as pathologists do. The 22-layer network was cut at an earlier layer and the output from that layer was used to train both a random forest classifier and a support vector machines... (More)
We developed an automatic algorithm with the purpose to assist pathologists to report Gleason score on malignant prostatic adenocarcinoma specimen. In order to detect and classify the cancerous tissue, a deep convolutional neural network that had been pre-trained on a large set of photographic images was used. A specific aim was to support intuitive interaction with the result, to let pathologists adjust and correct the output. Therefore, we have designed an algorithm that makes a spatial classification of the whole slide into the same growth patterns as pathologists do. The 22-layer network was cut at an earlier layer and the output from that layer was used to train both a random forest classifier and a support vector machines classifier. At a specific layer a small patch of the image was used to calculate a feature vector and an image is represented by a number of those vectors. We have classified both the individual patches and the entire images. The classification results were compared for different scales of the images and feature vectors from two different layers from the network. Testing was made on a dataset consisting of 213 images, all containing a single class, benign tissue or Gleason score 3-5. Using 10-fold cross validation the accuracy per patch was 81 %. For whole images, the accuracy was increased to 89 %. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Prostate Cancer, Gleason Score, Deep Learning, Convolutional Neural Networks
in
2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)
pages
5 pages
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
2016 IEEE International Symposium on Biomedical Imaging
external identifiers
  • Scopus:84978387816
DOI
10.1109/ISBI.2016.7493473
language
English
LU publication?
yes
id
839c04b4-164c-4145-8620-9a6f2e5139c4
date added to LUP
2016-06-01 11:51:33
date last changed
2016-10-13 05:09:39
@misc{839c04b4-164c-4145-8620-9a6f2e5139c4,
  abstract     = {We  developed an automatic algorithm with the purpose to assist pathologists to report Gleason score on malignant prostatic adenocarcinoma specimen. In order to detect and classify the cancerous tissue, a deep convolutional neural network that had been pre-trained on a large set of photographic images was used. A specific aim was to support intuitive interaction with the result, to let pathologists adjust and correct the output. Therefore, we have designed an algorithm that makes a spatial classification of the whole slide into the same growth patterns as pathologists do. The 22-layer network was cut at an earlier layer and the output from that layer was used to train both a random forest classifier and a support vector machines classifier. At a specific layer a small patch of the image was used to calculate a feature vector and an image is represented by a number of those vectors. We have classified both the individual patches and the entire images. The classification results were compared for different scales of the images and feature vectors from two different layers from the network. Testing was made on a dataset consisting of 213 images, all containing a single class, benign tissue or Gleason score 3-5. Using 10-fold cross validation the accuracy per patch was 81 %. For whole images, the accuracy was increased to 89 %.},
  author       = {Källén, Hanna and Molin, Jesper and Heyden, Anders and Lundström, Claes and Åström, Karl},
  keyword      = {Prostate Cancer,Gleason Score,Deep Learning,Convolutional Neural Networks},
  language     = {eng},
  pages        = {5},
  publisher    = {ARRAY(0x8f76898)},
  series       = {2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)},
  title        = {Towards Grading Gleason Score using Generically Trained Deep convolutional Neural Networks},
  url          = {http://dx.doi.org/10.1109/ISBI.2016.7493473},
  year         = {2016},
}