| Summary: | Purpose: A woman should be able to trust that the steroid receptor status of her cancer is reported correctly. Immunohistochemistry (IHC) allows for specific assessment of tumour cells and the role of automated image analysis (IA) in the assessment of receptor IHC in breast cancer is topical. We compared ER and PR status assessed visually and by IA, and their respective abilities to predict cancer-specific survival and recurrence in a cohort with mature follow up.Patients and methods: Patients (n=525) treated for primary symptomatic operable breast cancer in Glasgow during 1995-8 were studied in triplicate tissue microarray using ER (Dako 6F11/12) and PR (Leica R636) IHC. Allred and weighted Histoscores were assigned visually (v-H Scores) and weighted H-scores by IA (ia-H Scores; Slidepath nuclear protocol). Interclass correlation coefficients, univariate and multivariate analyses were performed in SPSS v18.Results: Minimum follow up was 11.8 years (median 13.8). There was excellent agreement between steroid receptor v-H and ia-H Scores and both methods predicted cancer-specific survival equally well overall and in the 384 patients who received endocrine treatment. Allred score was also effective.Conclusions: Automated analysis of ER and PR status gave results in excellent agreement with visual analysis and equally effective (but not better) prediction of survival and tumour recurrence. Visual confirmation that the cells being analysed are representative of the invasive carcinoma remains essential and no quality asssurance requirements are made redundant by image analysis if disasters like the Newfoundland ER testing debacle (Hede, K: JNCI 2008;100:837-) are to be avoided.
|
|---|