PAPNET-directed rescreening of cervicovaginal smears: a study of 101 cases of atypical squamous cells of undetermined significance.

Many women having cervicovaginal smears interpreted as atypical squamous cells of undetermined significance (ASCUS) ultimately prove to harbor squamous intraepithelial lesions (SIL). The question is whether rare cells diagnostic of SIL are present in so-called "atypical" smears, but simply go undetected. To test whether the PAPNET Cytological Screening System, an automated system, can detect the (assumed) presence of such cells, six reviewers independently evaluated PAPNET video images generated for 101 cases conventionally diagnosed as ASCUS. Using PAPNET-identified microscopic coordinates, selected cases were then manually reviewed and reclassified according to consensus opinion. Overall, 35 cases were reclassified as SIL (22 low grade; 13 high grade). Histologic correlations showed 37 of the 101 cases conventionally interpreted as ASCUS carried tissue diagnoses of SIL, (28 low grade; 8 high grade, 1 ungraded). Using PAPNET, 24 of the 37 (65%) corresponding smears were reclassified as SIL (15 low grades; 9 high grade).

[1]  M. Spitzer,et al.  Comparative Utility of Repeat Papanicolaou Smears, Cervicography, and Colposcopy in the Evaluation of Atypical Papanicolaou Smears , 1987, Obstetrics and gynecology.

[2]  M. Boon,et al.  Neural network processing can provide means to catch errors that slip through human screening of pap smears , 1993, Diagnostic cytopathology.

[3]  O A Husain,et al.  An analysis of the variation of human interpretation: Papnet a mini-challenge. , 1994, Analytical cellular pathology : the journal of the European Society for Analytical Cellular Pathology.

[4]  L. Dehner.  Cervicovaginal cytology, false-negative results, and standards of practice. , 1993, American journal of clinical pathology.

[5]  W. Frable.  Litigation cells: Definition and observations on a cell type in cervical vaginal smears not addressed by the Bethesda system , 1994, Diagnostic cytopathology.

[6]  K Schreiber,et al.  Evaluation of the PAPNET cytologic screening system for quality control of cervical smears. , 1994, American journal of clinical pathology.

[7]  L. Mango,et al.  PAPNET analysis of reportedly negative smears preceding the diagnosis of a high-grade squamous intraepithelial lesion or carcinoma. , 1994, Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc.

[8]  M. Boon,et al.  Neural network processing of cervical smears can lead to a decrease in diagnostic variability and an increase in screening efficacy: a study of 63 false-negative smears. , 1994, Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc.

[9]  L. Koss.  The Papanicolaou test for cervical cancer detection. A triumph and a tragedy. , 1989, JAMA.

[10]  G L Wied,et al.  Artificial neural networks and their use in quantitative pathology. , 1990, Analytical and quantitative cytology and histology.

[11]  Raheela Ashfaq,et al.  Evaluation of papnettrade; system for rescreening of negative cervical smears , 1995 .

[12]  W. Creasman,et al.  Evaluation of the atypical Pap smear. , 1987, American journal of obstetrics and gynecology.

[13]  M. Henry,et al.  Atypical cervical cytology. Colposcopic follow-up using the Bethesda System. , 1993, The Journal of reproductive medicine.

[14]  D. Wilbur,et al.  Reactive change and atypical squamous cells of undetermined significance in papanicolaou smears: A cytohistologic correlation , 1993, Diagnostic cytopathology.

[15]  G. Vooijs,et al.  Screening errors in cervical cytologic screening. , 1987, Acta cytologica.