Evaluation of esophageal cytology using a neural net-based interactive scanning system (the PAPNET system)

Its possible role in screening for esophageal and gastric carcinoma

Leopold G. Koss, Nora Morgenstern, Naveed Tahir-Kheli, Mark J. Suhrland, Klaus Schreiber, Ellen Greenebaum

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

A neural net-based, semiautomated, interactive computerized cell analysis system (The PAPNET system, Neuromedical Systems, Suffern, NY) was used to examine cells from 138 esophageal smears obtained by lavage, brushings, or balloon from as many patients. From each smear, trained human observers examined 128 cell images selected by the machine. Abnormal cells were identified in all 35 patients with cancer, whether esophageal, gastric, oral, or metastatic. Further, in 11 smears, the displayed images allowed the recognition of effects of radiotherapy and, in 14 smears, the diagnosis of a specific tumor type, such as squamous cell carcinoma (8 patients) or adenocarcinoma (6 patients). In 3 additional cases, the diagnosis of 'carcinoma, not further specified,' was established. One care of esophageal carcinoma in situ, not previously recognized on a smear or in the biopsy specimen, and one case of gastric adenocarcinoma, not recognized in the smear, were identified in PAPNET-generated images. The possible application of the apparatus to the triage of smears and population screening for esophageal and gastric carcinoma precursors is discussed.

Original languageEnglish (US)
Pages (from-to)549-557
Number of pages9
JournalAmerican Journal of Clinical Pathology
Volume109
Issue number5
StatePublished - May 1998

Fingerprint

Cell Biology
Stomach
Carcinoma
Adenocarcinoma
Triage
Therapeutic Irrigation
Carcinoma in Situ
Esophageal Neoplasms
Squamous Cell Carcinoma
Radiotherapy
Biopsy
Population
Neoplasms

Keywords

  • Esophageal balloon sampling
  • Esophageal brushing
  • Esophageal carcinoma
  • Esophageal washings
  • Gastric carcinoma
  • Neural net-based scanning system
  • PAPNET

ASJC Scopus subject areas

  • Pathology and Forensic Medicine

Cite this

Evaluation of esophageal cytology using a neural net-based interactive scanning system (the PAPNET system) : Its possible role in screening for esophageal and gastric carcinoma. / Koss, Leopold G.; Morgenstern, Nora; Tahir-Kheli, Naveed; Suhrland, Mark J.; Schreiber, Klaus; Greenebaum, Ellen.

In: American Journal of Clinical Pathology, Vol. 109, No. 5, 05.1998, p. 549-557.

Research output: Contribution to journalArticle

@article{0cfa479f78174814b2493c76d415aadf,
title = "Evaluation of esophageal cytology using a neural net-based interactive scanning system (the PAPNET system): Its possible role in screening for esophageal and gastric carcinoma",
abstract = "A neural net-based, semiautomated, interactive computerized cell analysis system (The PAPNET system, Neuromedical Systems, Suffern, NY) was used to examine cells from 138 esophageal smears obtained by lavage, brushings, or balloon from as many patients. From each smear, trained human observers examined 128 cell images selected by the machine. Abnormal cells were identified in all 35 patients with cancer, whether esophageal, gastric, oral, or metastatic. Further, in 11 smears, the displayed images allowed the recognition of effects of radiotherapy and, in 14 smears, the diagnosis of a specific tumor type, such as squamous cell carcinoma (8 patients) or adenocarcinoma (6 patients). In 3 additional cases, the diagnosis of 'carcinoma, not further specified,' was established. One care of esophageal carcinoma in situ, not previously recognized on a smear or in the biopsy specimen, and one case of gastric adenocarcinoma, not recognized in the smear, were identified in PAPNET-generated images. The possible application of the apparatus to the triage of smears and population screening for esophageal and gastric carcinoma precursors is discussed.",
keywords = "Esophageal balloon sampling, Esophageal brushing, Esophageal carcinoma, Esophageal washings, Gastric carcinoma, Neural net-based scanning system, PAPNET",
author = "Koss, {Leopold G.} and Nora Morgenstern and Naveed Tahir-Kheli and Suhrland, {Mark J.} and Klaus Schreiber and Ellen Greenebaum",
year = "1998",
month = "5",
language = "English (US)",
volume = "109",
pages = "549--557",
journal = "American Journal of Clinical Pathology",
issn = "0002-9173",
publisher = "American Society of Clinical Pathologists",
number = "5",

}

TY - JOUR

T1 - Evaluation of esophageal cytology using a neural net-based interactive scanning system (the PAPNET system)

T2 - Its possible role in screening for esophageal and gastric carcinoma

AU - Koss, Leopold G.

AU - Morgenstern, Nora

AU - Tahir-Kheli, Naveed

AU - Suhrland, Mark J.

AU - Schreiber, Klaus

AU - Greenebaum, Ellen

PY - 1998/5

Y1 - 1998/5

N2 - A neural net-based, semiautomated, interactive computerized cell analysis system (The PAPNET system, Neuromedical Systems, Suffern, NY) was used to examine cells from 138 esophageal smears obtained by lavage, brushings, or balloon from as many patients. From each smear, trained human observers examined 128 cell images selected by the machine. Abnormal cells were identified in all 35 patients with cancer, whether esophageal, gastric, oral, or metastatic. Further, in 11 smears, the displayed images allowed the recognition of effects of radiotherapy and, in 14 smears, the diagnosis of a specific tumor type, such as squamous cell carcinoma (8 patients) or adenocarcinoma (6 patients). In 3 additional cases, the diagnosis of 'carcinoma, not further specified,' was established. One care of esophageal carcinoma in situ, not previously recognized on a smear or in the biopsy specimen, and one case of gastric adenocarcinoma, not recognized in the smear, were identified in PAPNET-generated images. The possible application of the apparatus to the triage of smears and population screening for esophageal and gastric carcinoma precursors is discussed.

AB - A neural net-based, semiautomated, interactive computerized cell analysis system (The PAPNET system, Neuromedical Systems, Suffern, NY) was used to examine cells from 138 esophageal smears obtained by lavage, brushings, or balloon from as many patients. From each smear, trained human observers examined 128 cell images selected by the machine. Abnormal cells were identified in all 35 patients with cancer, whether esophageal, gastric, oral, or metastatic. Further, in 11 smears, the displayed images allowed the recognition of effects of radiotherapy and, in 14 smears, the diagnosis of a specific tumor type, such as squamous cell carcinoma (8 patients) or adenocarcinoma (6 patients). In 3 additional cases, the diagnosis of 'carcinoma, not further specified,' was established. One care of esophageal carcinoma in situ, not previously recognized on a smear or in the biopsy specimen, and one case of gastric adenocarcinoma, not recognized in the smear, were identified in PAPNET-generated images. The possible application of the apparatus to the triage of smears and population screening for esophageal and gastric carcinoma precursors is discussed.

KW - Esophageal balloon sampling

KW - Esophageal brushing

KW - Esophageal carcinoma

KW - Esophageal washings

KW - Gastric carcinoma

KW - Neural net-based scanning system

KW - PAPNET

UR - http://www.scopus.com/inward/record.url?scp=0031945510&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031945510&partnerID=8YFLogxK

M3 - Article

VL - 109

SP - 549

EP - 557

JO - American Journal of Clinical Pathology

JF - American Journal of Clinical Pathology

SN - 0002-9173

IS - 5

ER -