Automated Histology Analysis: Opportunities for signal processing

Michael T. McCann, John A. Ozolek, Carlos A. Castro, Bahram Parvin, Jelena Kovacevic

Research output: Contribution to journalReview article

Abstract

Histology is the microscopic inspection of plant or animal tissue. It is a critical component in diagnostic medicine and a tool for studying the pathogenesis and biology of processes such as cancer and embryogenesis. Tissue processing for histology has become increasingly automated, drastically increasing the speed at which histology labs can produce tissue slides for viewing. Another trend is the digitization of these slides, allowing them to be viewed on a computer rather than through a microscope. Despite these changes, much of the routine analysis of tissue sections remains a painstaking, manual task that can only be completed by highly trained pathologists at a high cost per hour. There is, therefore, a niche for image analysis methods that can automate some aspects of this analysis. These methods could also automate tasks that are prohibitively time-consuming for humans, e.g., discovering new disease markers from hundreds of whole-slide images (WSIs) or precisely quantifying tissues within a tumor.

Original languageEnglish (US)
Article number6975290
Pages (from-to)78-87
Number of pages10
JournalIEEE Signal Processing Magazine
Volume32
Issue number1
DOIs
StatePublished - Jan 1 2015

Fingerprint

Histology
Signal Processing
Signal processing
Tissue
Embryogenesis
Digitization
Niche
Image Analysis
Microscope
Medicine
Biology
Inspection
Tumor
Animals
Diagnostics
Cancer
Analog to digital conversion
Image analysis
Costs
Tumors

Keywords

  • Biological tissues
  • Biomedical imaging
  • Biomedical signal processing
  • Biopsy
  • Histology
  • Image analysis
  • Image color analysis
  • Microscopy
  • Signal processing
  • Visualization

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

Automated Histology Analysis : Opportunities for signal processing. / McCann, Michael T.; Ozolek, John A.; Castro, Carlos A.; Parvin, Bahram; Kovacevic, Jelena.

In: IEEE Signal Processing Magazine, Vol. 32, No. 1, 6975290, 01.01.2015, p. 78-87.

Research output: Contribution to journalReview article

McCann, Michael T. ; Ozolek, John A. ; Castro, Carlos A. ; Parvin, Bahram ; Kovacevic, Jelena. / Automated Histology Analysis : Opportunities for signal processing. In: IEEE Signal Processing Magazine. 2015 ; Vol. 32, No. 1. pp. 78-87.
@article{7a8cc03849974c2a800808e25c12e016,
title = "Automated Histology Analysis: Opportunities for signal processing",
abstract = "Histology is the microscopic inspection of plant or animal tissue. It is a critical component in diagnostic medicine and a tool for studying the pathogenesis and biology of processes such as cancer and embryogenesis. Tissue processing for histology has become increasingly automated, drastically increasing the speed at which histology labs can produce tissue slides for viewing. Another trend is the digitization of these slides, allowing them to be viewed on a computer rather than through a microscope. Despite these changes, much of the routine analysis of tissue sections remains a painstaking, manual task that can only be completed by highly trained pathologists at a high cost per hour. There is, therefore, a niche for image analysis methods that can automate some aspects of this analysis. These methods could also automate tasks that are prohibitively time-consuming for humans, e.g., discovering new disease markers from hundreds of whole-slide images (WSIs) or precisely quantifying tissues within a tumor.",
keywords = "Biological tissues, Biomedical imaging, Biomedical signal processing, Biopsy, Histology, Image analysis, Image color analysis, Microscopy, Signal processing, Visualization",
author = "McCann, {Michael T.} and Ozolek, {John A.} and Castro, {Carlos A.} and Bahram Parvin and Jelena Kovacevic",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/MSP.2014.2346443",
language = "English (US)",
volume = "32",
pages = "78--87",
journal = "IEEE Signal Processing Magazine",
issn = "1053-5888",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Automated Histology Analysis

T2 - Opportunities for signal processing

AU - McCann, Michael T.

AU - Ozolek, John A.

AU - Castro, Carlos A.

AU - Parvin, Bahram

AU - Kovacevic, Jelena

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Histology is the microscopic inspection of plant or animal tissue. It is a critical component in diagnostic medicine and a tool for studying the pathogenesis and biology of processes such as cancer and embryogenesis. Tissue processing for histology has become increasingly automated, drastically increasing the speed at which histology labs can produce tissue slides for viewing. Another trend is the digitization of these slides, allowing them to be viewed on a computer rather than through a microscope. Despite these changes, much of the routine analysis of tissue sections remains a painstaking, manual task that can only be completed by highly trained pathologists at a high cost per hour. There is, therefore, a niche for image analysis methods that can automate some aspects of this analysis. These methods could also automate tasks that are prohibitively time-consuming for humans, e.g., discovering new disease markers from hundreds of whole-slide images (WSIs) or precisely quantifying tissues within a tumor.

AB - Histology is the microscopic inspection of plant or animal tissue. It is a critical component in diagnostic medicine and a tool for studying the pathogenesis and biology of processes such as cancer and embryogenesis. Tissue processing for histology has become increasingly automated, drastically increasing the speed at which histology labs can produce tissue slides for viewing. Another trend is the digitization of these slides, allowing them to be viewed on a computer rather than through a microscope. Despite these changes, much of the routine analysis of tissue sections remains a painstaking, manual task that can only be completed by highly trained pathologists at a high cost per hour. There is, therefore, a niche for image analysis methods that can automate some aspects of this analysis. These methods could also automate tasks that are prohibitively time-consuming for humans, e.g., discovering new disease markers from hundreds of whole-slide images (WSIs) or precisely quantifying tissues within a tumor.

KW - Biological tissues

KW - Biomedical imaging

KW - Biomedical signal processing

KW - Biopsy

KW - Histology

KW - Image analysis

KW - Image color analysis

KW - Microscopy

KW - Signal processing

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=85032752055&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032752055&partnerID=8YFLogxK

U2 - 10.1109/MSP.2014.2346443

DO - 10.1109/MSP.2014.2346443

M3 - Review article

AN - SCOPUS:85032752055

VL - 32

SP - 78

EP - 87

JO - IEEE Signal Processing Magazine

JF - IEEE Signal Processing Magazine

SN - 1053-5888

IS - 1

M1 - 6975290

ER -