Abstract Rationale: Tissue microarrays (TMAs) have become a valuable resource for biomarker expression in translational research. Immunohistochemical (IHC) assessment of TMAs is the principal method for analyzing protein expression in large numbers of patient samples efficient with conservation of tissue. However, manual IHC assessment of TMAs remains a challenging and laborious task. With advances in image analysis, computer generated analyses of TMAs have the potential to lessen the burden of expert pathologist review. Computerized ER scoring relies on tumor localization. Aim: The objective of this study was to compare the effectiveness of a locally developed automated invasive tumor location system with the skills of specialist breast pathologists. Methods: In this study, tumor localization for estrogen receptor (ER) scoring was evaluated comparing computer- generated segmentation masks with those of two specialist breast pathologists. Automated tumor localization was achieved using a novel image analysis algorithm, which labeled compact groups of pixels called superpixels. Machine learning techniques were adopted to model color, shape and textural properties of superpixels in a rotation invariant manner, suitable for histopathology images. The resulting automatically and manually-obtained segmentation masks were used to obtain IHC scores for thirty-two ER stained invasive breast cancer TMA samples using FDA-approved IHC scoring software. Results: Pixel-level comparisons showed lower agreement between automated and manual segmentation masks (κ = 0.84) than between pathologists' masks (κ = 0.91). However, this had little impact on computed IHC scores (Allred method; κ = 0.91, Quickscore method; κ = 0.92). Conclusion: The automated system provides sufficiently consistent measurements for standardized IHC analysis of nuclear staining in TMAs from large clinical trials. Citation Format: Jordan LB, Akbar S, Purdie CA, Thompson AM, McKenna SJ. Breast cancer estrogen receptor scoring in tissue microarrays: Specialist breast pathologist versus automation. [abstract]. In: Proceedings of the Thirty-Eighth Annual CTRC-AACR San Antonio Breast Cancer Symposium: 2015 Dec 8-12; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2016;76(4 Suppl):Abstract nr P5-07-15.