Automated colitis detection from endoscopic biopsies as a tissue screening tool in diagnostic pathology

Michael T. McCann, Ramamurthy Bhagavatula, Matthew C. Fickus, John A. Ozolek, Jelena Kovacevic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a method for identifying colitis in colon biopsies as an extension of our framework for the automated identification of tissues in histology images. Histology is a critical tool in both clinical and research applications, yet even mundane histological analysis, such as the screening of colon biopsies, must be carried out by highly-trained pathologists at a high cost per hour, indicating a niche for potential automation. To this end, we build upon our previous work by extending the histopathology vocabulary (a set of features based on visual cues used by pathologists) with new features driven by the colitis application. We use the multiple-instance learning framework to allow our pixel-level classifier to learn from image-level training labels. The new system achieves accuracy comparable to state-of-the-art biological image classifiers with fewer and more intuitive features.

Original languageEnglish (US)
Title of host publication2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings
Pages2809-2812
Number of pages4
DOIs
StatePublished - Dec 1 2012
Event2012 19th IEEE International Conference on Image Processing, ICIP 2012 - Lake Buena Vista, FL, United States
Duration: Sep 30 2012Oct 3 2012

Other

Other2012 19th IEEE International Conference on Image Processing, ICIP 2012
CountryUnited States
CityLake Buena Vista, FL
Period9/30/1210/3/12

Fingerprint

Histology
Biopsy
Pathology
Screening
Classifiers
Tissue
Labels
Automation
Pixels
Costs

Keywords

  • colitis
  • histology
  • image classification

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

McCann, M. T., Bhagavatula, R., Fickus, M. C., Ozolek, J. A., & Kovacevic, J. (2012). Automated colitis detection from endoscopic biopsies as a tissue screening tool in diagnostic pathology. In 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings (pp. 2809-2812). [6467483] https://doi.org/10.1109/ICIP.2012.6467483

Automated colitis detection from endoscopic biopsies as a tissue screening tool in diagnostic pathology. / McCann, Michael T.; Bhagavatula, Ramamurthy; Fickus, Matthew C.; Ozolek, John A.; Kovacevic, Jelena.

2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. p. 2809-2812 6467483.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

McCann, MT, Bhagavatula, R, Fickus, MC, Ozolek, JA & Kovacevic, J 2012, Automated colitis detection from endoscopic biopsies as a tissue screening tool in diagnostic pathology. in 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings., 6467483, pp. 2809-2812, 2012 19th IEEE International Conference on Image Processing, ICIP 2012, Lake Buena Vista, FL, United States, 9/30/12. https://doi.org/10.1109/ICIP.2012.6467483
McCann MT, Bhagavatula R, Fickus MC, Ozolek JA, Kovacevic J. Automated colitis detection from endoscopic biopsies as a tissue screening tool in diagnostic pathology. In 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. p. 2809-2812. 6467483 https://doi.org/10.1109/ICIP.2012.6467483
McCann, Michael T. ; Bhagavatula, Ramamurthy ; Fickus, Matthew C. ; Ozolek, John A. ; Kovacevic, Jelena. / Automated colitis detection from endoscopic biopsies as a tissue screening tool in diagnostic pathology. 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. pp. 2809-2812
@inproceedings{079191a96aab43d0a93780e44c051c0c,
title = "Automated colitis detection from endoscopic biopsies as a tissue screening tool in diagnostic pathology",
abstract = "We present a method for identifying colitis in colon biopsies as an extension of our framework for the automated identification of tissues in histology images. Histology is a critical tool in both clinical and research applications, yet even mundane histological analysis, such as the screening of colon biopsies, must be carried out by highly-trained pathologists at a high cost per hour, indicating a niche for potential automation. To this end, we build upon our previous work by extending the histopathology vocabulary (a set of features based on visual cues used by pathologists) with new features driven by the colitis application. We use the multiple-instance learning framework to allow our pixel-level classifier to learn from image-level training labels. The new system achieves accuracy comparable to state-of-the-art biological image classifiers with fewer and more intuitive features.",
keywords = "colitis, histology, image classification",
author = "McCann, {Michael T.} and Ramamurthy Bhagavatula and Fickus, {Matthew C.} and Ozolek, {John A.} and Jelena Kovacevic",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ICIP.2012.6467483",
language = "English (US)",
isbn = "9781467325332",
pages = "2809--2812",
booktitle = "2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings",

}

TY - GEN

T1 - Automated colitis detection from endoscopic biopsies as a tissue screening tool in diagnostic pathology

AU - McCann, Michael T.

AU - Bhagavatula, Ramamurthy

AU - Fickus, Matthew C.

AU - Ozolek, John A.

AU - Kovacevic, Jelena

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We present a method for identifying colitis in colon biopsies as an extension of our framework for the automated identification of tissues in histology images. Histology is a critical tool in both clinical and research applications, yet even mundane histological analysis, such as the screening of colon biopsies, must be carried out by highly-trained pathologists at a high cost per hour, indicating a niche for potential automation. To this end, we build upon our previous work by extending the histopathology vocabulary (a set of features based on visual cues used by pathologists) with new features driven by the colitis application. We use the multiple-instance learning framework to allow our pixel-level classifier to learn from image-level training labels. The new system achieves accuracy comparable to state-of-the-art biological image classifiers with fewer and more intuitive features.

AB - We present a method for identifying colitis in colon biopsies as an extension of our framework for the automated identification of tissues in histology images. Histology is a critical tool in both clinical and research applications, yet even mundane histological analysis, such as the screening of colon biopsies, must be carried out by highly-trained pathologists at a high cost per hour, indicating a niche for potential automation. To this end, we build upon our previous work by extending the histopathology vocabulary (a set of features based on visual cues used by pathologists) with new features driven by the colitis application. We use the multiple-instance learning framework to allow our pixel-level classifier to learn from image-level training labels. The new system achieves accuracy comparable to state-of-the-art biological image classifiers with fewer and more intuitive features.

KW - colitis

KW - histology

KW - image classification

UR - http://www.scopus.com/inward/record.url?scp=84875822433&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875822433&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6467483

DO - 10.1109/ICIP.2012.6467483

M3 - Conference contribution

AN - SCOPUS:84875822433

SN - 9781467325332

SP - 2809

EP - 2812

BT - 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings

ER -