Search

Purpose: Two types of macrophages are present in tumor microenvironment. M1 macrophages exhibit potent anti-tumor properties, while M2 macrophages play the pro-tumoral roles. The presence of M2 macrophages is associated with worsened overall survival in triple-negative breast carcinoma (TNBC) patients. However, the relationship between M2 macrophages and response to neoadjuvant chemotherapy (NAC) is unknown. Methods: M2 macrophages were investigated on biopsy whole sections from 66 TNBCs treated with NAC by CD163 together with other immune checkpoint markers (PD1, PD-L1 and CD8) using a multi-color immunohistochemical multiplex assay. Results: Incomplete response was significantly associated with older age, lower PD-L1 expression (tumor and stroma), lower levels of CD8-positive TILs in stroma, but higher level of CD163-positive macrophages, with the level of CD163-positive M2 macrophages in peritumoral area as the strongest factor. Conclusions: Our data have demonstrated that the level of CD163-positive M2 macrophages was significantly higher in TNBC patients with incomplete response than patients with complete response, suggesting M2 macrophages' important role in predicting TNBC patients' response to NAC. [ABSTRACT FROM AUTHOR]

Automatic identification of tissue structures in the analysis of digital tissue biopsies remains an ongoing problem in digital pathology. Common barriers include lack of reliable ground truth due to inter- and intra- reader variability, class imbalances, and inflexibility of discriminative models. To overcome these barriers, we are developing a framework that benefits from a reliable immunohistochemistry ground truth during labeling, overcomes class imbalances through single task learning, and accommodates any number of classes through a minimally supervised, modular model-per-class paradigm. This study explores an initial application of this framework, based on conditional generative adversarial networks, to automatically identify tumor from non-tumor regions in colorectal H&E slides. The average precision, sensitivity, and F1 score during validation was 95.13 ± 4.44%, 93.05 ± 3.46%, and 94.02 ± 3.23% and for an external test dataset was 98.75 ± 2.43%, 88.53 ± 5.39%, and 93.31 ± 3.07%, respectively. With accurate identification of tumor regions, we plan to further develop our framework to establish a tumor front, from which tumor buds can be detected in a restricted region. This model will be integrated into a larger system which will quantitatively determine the prognostic significance of tumor budding. [ABSTRACT FROM AUTHOR]

An amendment to this paper has been published and can be accessed via a link at the top of the paper. [ABSTRACT FROM AUTHOR]