Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Artificial intelligence methods are been increasingly used for analysis of pathology slides. In this issue of the Journal, Sandbank et al. describe the validation and utility of a robust second reader system that can distinguish in situ and standfirst invasive carcinomas from non-neoplastic lesions of the breast.