The reliability of computer analysis of ultrasonographic prostate images: the influence of inconsistent histopathology

R. J. Giesen; A. L. Huynen; J. J. de la Rosette; H. E. Schaafsma; M. P. van Iersel; R. G. Aarnink; F. M. Debruyne; H. Wijkstra

doi:10.1016/0301-5629(94)90047-7

The reliability of computer analysis of ultrasonographic prostate images: the influence of inconsistent histopathology

R. J. Giesen
, A. L. Huynen
, J. J. de la Rosette
, H. E. Schaafsma
, M. P. van Iersel
, R. G. Aarnink
, F. M. Debruyne
, H. Wijkstra

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

This article describes a method to investigate the influence of inconsistent histopathology during the development of tissue discrimination algorithms. Review of the pathology is performed on the biopsies used as training set of a computer system for cancer detection in ultrasonographic prostate images. The influence of the discrepancies found between independent pathologists on the discriminating power of the system is investigated. A high diagnostic consistency in histopathology concerning only the categories malignant and nonmalignant is found. Therefore, review of the pathology does not significantly influence the results of tissue discrimination algorithms for cancer detection. However a high interobserver variability is obtained in the differentiation between more histology classes

Original language	English
Pages (from-to)	871-876
Journal	Ultrasound in medicine & biology
Volume	20
Issue number	9
DOIs	https://doi.org/10.1016/0301-5629(94)90047-7
Publication status	Published - 1994

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1016/0301-5629(94)90047-7

Cite this

@article{c2c1c5caafe6461bb00702fcad4962ce,

title = "The reliability of computer analysis of ultrasonographic prostate images: the influence of inconsistent histopathology",

abstract = "This article describes a method to investigate the influence of inconsistent histopathology during the development of tissue discrimination algorithms. Review of the pathology is performed on the biopsies used as training set of a computer system for cancer detection in ultrasonographic prostate images. The influence of the discrepancies found between independent pathologists on the discriminating power of the system is investigated. A high diagnostic consistency in histopathology concerning only the categories malignant and nonmalignant is found. Therefore, review of the pathology does not significantly influence the results of tissue discrimination algorithms for cancer detection. However a high interobserver variability is obtained in the differentiation between more histology classes",

author = "Giesen, \{R. J.\} and Huynen, \{A. L.\} and \{de la Rosette\}, \{J. J.\} and Schaafsma, \{H. E.\} and \{van Iersel\}, \{M. P.\} and Aarnink, \{R. G.\} and Debruyne, \{F. M.\} and H. Wijkstra",

year = "1994",

doi = "10.1016/0301-5629(94)90047-7",

language = "English",

volume = "20",

pages = "871--876",

journal = "Ultrasound in medicine \& biology",

issn = "0301-5629",

publisher = "Elsevier USA",

number = "9",

}

TY - JOUR

T1 - The reliability of computer analysis of ultrasonographic prostate images: the influence of inconsistent histopathology

AU - Giesen, R. J.

AU - Huynen, A. L.

AU - de la Rosette, J. J.

AU - Schaafsma, H. E.

AU - van Iersel, M. P.

AU - Aarnink, R. G.

AU - Debruyne, F. M.

AU - Wijkstra, H.

PY - 1994

Y1 - 1994

N2 - This article describes a method to investigate the influence of inconsistent histopathology during the development of tissue discrimination algorithms. Review of the pathology is performed on the biopsies used as training set of a computer system for cancer detection in ultrasonographic prostate images. The influence of the discrepancies found between independent pathologists on the discriminating power of the system is investigated. A high diagnostic consistency in histopathology concerning only the categories malignant and nonmalignant is found. Therefore, review of the pathology does not significantly influence the results of tissue discrimination algorithms for cancer detection. However a high interobserver variability is obtained in the differentiation between more histology classes

AB - This article describes a method to investigate the influence of inconsistent histopathology during the development of tissue discrimination algorithms. Review of the pathology is performed on the biopsies used as training set of a computer system for cancer detection in ultrasonographic prostate images. The influence of the discrepancies found between independent pathologists on the discriminating power of the system is investigated. A high diagnostic consistency in histopathology concerning only the categories malignant and nonmalignant is found. Therefore, review of the pathology does not significantly influence the results of tissue discrimination algorithms for cancer detection. However a high interobserver variability is obtained in the differentiation between more histology classes

U2 - 10.1016/0301-5629(94)90047-7

DO - 10.1016/0301-5629(94)90047-7

M3 - Article

C2 - 7886847

SN - 0301-5629

VL - 20

SP - 871

EP - 876

JO - Ultrasound in medicine & biology

JF - Ultrasound in medicine & biology

IS - 9

ER -

The reliability of computer analysis of ultrasonographic prostate images: the influence of inconsistent histopathology

Abstract

UN SDGs

Access to Document

Fingerprint

Cite this