The morphological features that pathologists use to differentiate neoplasms from normal tissue are nonspecific to tissue type. For example, if given a Ki67 stained biopsy of neuroendocrine or breast tumor, a pathologist would be able to correctly identify morphologically abnormal cells in both samples but may struggle to identify the origin of both samples. This is also true for other pathological malignancies such as carcinomas, sarcomas, and leukemia. This implies that computer algorithms trained to recognize tumor from one site should be able to identify tumor from other sites with similar tumor subtypes. Here, we present the results of an experiment that supports this hypothesis. We train a deep learning system to distinguish tumor from non-tumor regions in Ki67 stained neuroendocrine tumor digital slides. Then, we test the same, unmodified, deep learning model to distinguish breast cancer from non-cancer regions. When applied to a sample of 96 high power fields, our system achieved a cumulative pixel-wise accuracy of 86% across these high-power fields. To our knowledge, our results are the first to formally demonstrate generalized segmentation of tumors from different sites of origin through image analysis. This paradigm has the potential to help with the design of tumor identification algorithms as well as the composition of the datasets they draw from.
Immunohistochemical staining (IHC) of tissue sections is routinely used in pathology to diagnose and characterize malignant tumors. Unfortunately, in the majority of cases, IHC stain interpretation is completed by a trained pathologist using a manual method, which consists of counting each positively and negatively stained cell under a microscope. Even in the hands of expert pathologists, the manual enumeration suffers from poor reproducibility. In this study, we propose a novel method to create artificial datasets in silico with known ground truth, allowing us to analyze the accuracy, precision, and intra- and inter-observer variability in a systematic manner and compare different computer analysis approaches. Our approach employs conditional Generative Adversarial Networks. We created our dataset by using 32 different breast cancer patients' Ki67 stained tissues. Our experiments indicated that synthetic images are indistinguishable from real images: The accuracy of five experts (3 pathologists and 2 image analysts) in distinguishing between 15 real and 15 synthetic images was only 47.3% (±8.5%).