Structure Prediction for Gland Segmentation with Hand-Crafted and Deep Convolutional Features

Siyamalan Manivannan, Wenqi Li, Jianguo Zhang, Emanuele Trucco, Stephen McKenna (Lead / Corresponding author)

Research output: Contribution to journalArticle

7 Citations (Scopus)
269 Downloads (Pure)

Abstract

We present a novel method to segment instances of glandular structures from colon histopathology images. We use a structure learning approach which represents local spatial configurations of class labels, capturing structural information normally ignored by sliding-window methods. This allows us to reveal different spatial structures of pixel labels (e.g., locations between adjacent glands, or far from glands), and to identify correctly neighbouring glandular structures as separate instances. Exemplars of label structures are obtained via clustering and used to train support vector machine classifiers. The label structures predicted are then combined and post-processed to obtain segmentation maps. We combine hand-crafted, multi-scale image features with features computed by a deep convolutional network trained to map images to segmentation maps. We evaluate the proposed method on the public domain GlaS dataset, which allows extensive comparisons with recent, alternative methods. Using the GlaS contest protocol, our method achieves the overall best performance.
Original languageEnglish
Pages (from-to)210-221
Number of pages12
JournalIEEE Transactions on Medical Imaging
Volume37
Issue number1
Early online date8 Sep 2017
DOIs
Publication statusPublished - Jan 2018

    Fingerprint

Keywords

  • Molecular and cellular imaging
  • Gastrointestinal tract
  • Segmentation
  • gastrointestinal tract
  • segmentation
  • Histocytochemistry/methods
  • Colorectal Neoplasms/diagnostic imaging
  • Colon/diagnostic imaging
  • Humans
  • Intestinal Mucosa/diagnostic imaging
  • Adenocarcinoma/diagnostic imaging
  • Support Vector Machine
  • Molecular Imaging/methods
  • Image Processing, Computer-Assisted/methods

Cite this