Segmentation of glandular epithelium in colorectal tumours to automatically compartmentalise IHC biomarker quantification: A deep learning approach.

08:00 EDT 12th July 2018 | BioPortfolio

Summary of "Segmentation of glandular epithelium in colorectal tumours to automatically compartmentalise IHC biomarker quantification: A deep learning approach."

In this paper, we propose a method for automatically annotating slide images from colorectal tissue samples. Our objective is to segment glandular epithelium in histological images from tissue slides submitted to different staining techniques, including usual haematoxylin-eosin (H&E) as well as immunohistochemistry (IHC). The proposed method makes use of Deep Learning and is based on a new convolutional network architecture. Our method achieves better performances than the state of the art on the H&E images of the GlaS challenge contest, whereas it uses only the haematoxylin colour channel extracted by colour deconvolution from the RGB images in order to extend its applicability to IHC. The network only needs to be fine-tuned on a small number of additional examples to be accurate on a new IHC dataset. Our approach also includes a new method of data augmentation to achieve good generalisation when working with different experimental conditions and different IHC markers. We show that our methodology enables to automate the compartmentalisation of the IHC biomarker analysis, results concurring highly with manual annotations.


Journal Details

This article was published in the following journal.

Name: Medical image analysis
ISSN: 1361-8423
Pages: 35-45


DeepDyve research library

PubMed Articles [5095 Associated PubMed Articles listed on BioPortfolio]

Tumour Parcellation and Quantification (TuPaQ): a tool for refining biomarker analysis through rapid and automated segmentation of tumour epithelium.

Immunohistochemistry (IHC) is an essential component of biomarker research in cancer. Automated biomarker quantification is hampered by the failure of computational algorithms to discriminate "negativ...

MILD-Net: Minimal information loss dilated network for gland instance segmentation in colon histology images.

The analysis of glandular morphology within colon histopathology images is an important step in determining the grade of colon cancer. Despite the importance of this task, manual segmentation is labor...

Fully automatic segmentation of 4D MRI for cardiac functional measurements.

Segmentation of cardiac medical images, an important step in measuring cardiac function, is usually performed either manually or semi-automatically. Fully automatic segmentation of the left ventricle ...

Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map.

The advent of digital pathology provides us with the challenging opportunity to automatically analyze whole slides of diseased tissue in order to derive quantitative profiles that can be used for diag...

EGFR gene copy number decreases during anti-EGFR antibody therapy in colorectal cancer.

Epidermal growth factor receptor (EGFR) gene copy number (GCN) increase is associated with a favourable anti-EGFR antibody treatment response in RAS wild-type metastatic colorectal cancer. However, th...

Clinical Trials [4938 Associated Clinical Trials listed on BioPortfolio]

Is There a Pancreatic Segmentation Based on the Pancreatic Duct Branching?

Limited pancreatic resections are increasingly performed, but the rate of postoperative fistula is higher than after classical resections. Pancreatic segmentation, anatomically and radiolo...

Prophylactic HIPEC for Colorectal Cancers at High Risk of Developing Peritoneal Metastases

The study investigators hypothesize that prophylactic HIPEC is feasible and well tolerated in patients with colorectal cancers with high-risk of developing peritoneal recurrence. The aim ...

PRESEPT Study: Evaluation of SEPT9 Biomarker Performance for Colorectal Cancer Screening

The purpose of this study is to collect blood specimens and clinical data from screening guideline eligible individuals designated by their physician to receive a screening colonoscopy, an...

Clinicopathological Importance of Colorectal Medullary Carcinoma: Retrospective Cohort Study

Medullary carcinoma (MC) is a rare tumor with solid growth pattern without glandular differentiation and constitute less than 1% of colorectal cancer. Lymph node positivity and distant org...

Evaluation of an Automatic Segmentation Software (Pixyl.Neuro) to Track Lesions in Multiple Sclerosis Patients Via Cerebral MRI

Using an automatic software tool, Pixyl.Neuro, to conduct a retrospective analysis (detection of lesions + segmentation of images + tracking over time) of cerebral MRI images acquired duri...

Medical and Biotech [MESH] Definitions

A carcinoma derived from stratified squamous epithelium. It may also occur in sites where glandular or columnar epithelium is normally present. (From Stedman, 25th ed)

Neoplasms composed of glandular tissue, an aggregation of epithelial cells that elaborate secretions, and of any type of epithelium itself. The concept does not refer to neoplasms located in the various glands or in epithelial tissue.

Benign neoplasms derived from glandular epithelium. (From Stedman, 25th ed)

A malignant neoplasm arising simultaneously or consecutively in mesodermal tissue and glandular epithelium of the same part. (Stedman, 25th ed)

Clusters of colonic crypts that appear different from the surrounding mucosa when visualized after staining. They are of interest as putative precursors to colorectal adenomas and potential biomarkers for colorectal carcinoma.

Quick Search


DeepDyve research library

Relevant Topic

Antiretroviral therapy
Standard antiretroviral therapy (ART) consists of the combination of at least three antiretroviral (ARV) drugs to maximally suppress the HIV virus and stop the progression of HIV disease. Huge reductions have been seen in rates of death and suffering whe...

Searches Linking to this Article