Invasive cervical cancer is preceded by a period of cervical intraepithelial neoplasia (CIN). Cervical abnormalities are typically detected via cytological screening for which patients with abnormal screening results often proceed to colposcopic directed biopsy. Histological evaluation of cervical biopsy tissue for presence or absence of CIN lesions relies predominantly on evaluation of Hemotoxylin and Eosin (H & E) staining. However, the interobserver reproducibility of CIN diagnoses among community pathologists as compared with expert gynecologic pathologists has been documented to be poor. Human papillomavirus (HPV) is the causative agent for cervical cancer. Therefore, we hypothesize that supplemental HPV data in the context of cellular morphology could enable pathologists to more reproducibly distinguish HPV-associated neoplasia (CIN lesions) from other benign entities ("no-CIN") that can closely mimic CIN. We have developed an advanced HPV In Situ Hybridization (ISH) test using molecular probes that include HPV genotypes most commonly associated with CIN lesions. Specifically, this fully automated HPV ISH test stains formalin fixed, paraffin embedded (FFPE) cervical biopsy specimens using Ventana slide stainer instruments. Blue, chromogenic staining at the target site indicates the presence of HPV. Data to be presented later will assess improved reproducibility of H & E interpretation (CIN versus "no-CIN" diagnosis) among community pathologists compared with the expert panel by using adjunctive HPV ISH slides. Six community-based pathologists will evaluate a cohort of 153 H & E stained cervical biopsy specimens for the presence or absence of CIN lesions. Results will be compared with a "gold standard" established by a consensus of three expert gynecologic pathologists. After a "wash-out" period of four weeks, the same set of H & E-stained slides will be re-evaluated by the community-based pathologists in conjunction with the corresponding HPV ISH stained slides. McNemar's test will be used to statistically analyze sensitivity and specificity.