A Deep Learning Approach for Histology-Based Nucleus Segmentation and Tumor Microenvironment Characterization.

Microscopic examination of pathology slides is essential to disease diagnosis and biomedical research. However, traditional manual examination of tissue slides is laborious and subjective. Tumor whole-slide image (WSI) scanning is becoming part of routine clinical procedures and produces massive data that capture tumor histologic details at high resolution. Furthermore, the rapid development of deep learning algorithms has significantly increased the efficiency and accuracy of pathology image analysis. In light of this progress, digital pathology is fast becoming a powerful tool to assist pathologists. Studying tumor tissue and its surrounding microenvironment provides critical insight into tumor initiation, progression, metastasis, and potential therapeutic targets. Nucleus segmentation and classification are critical to pathology image analysis, especially in characterizing and quantifying the tumor microenvironment (TME). Computational algorithms have been developed for nucleus segmentation and TME quantification within image patches. However, existing algorithms are computationally intensive and time consuming for WSI analysis. This study presents Histology-based Detection using Yolo (HD-Yolo), a new method that significantly accelerates nucleus segmentation and TME quantification. We demonstrate that HD-Yolo outperforms existing WSI analysis methods in nucleus detection, classification accuracy, and computation time. We validated the advantages of the system on 3 different tissue types: lung cancer, liver cancer, and breast cancer. For breast cancer, nucleus features by HD-Yolo were more prognostically significant than both the estrogen receptor status by immunohistochemistry and the progesterone receptor status by immunohistochemistry. The WSI analysis pipeline and a real-time nucleus segmentation viewer are available at https://github.com/impromptuRong/hd_wsi.

The plant response to high CO2 levels is heritable and orchestrated by DNA methylation.

Plant responses to abiotic environmental challenges are known to have lasting effects on the plant beyond the initial stress exposure. Some of these lasting effects are transgenerational, affecting the next generation. The plant response to elevated carbon dioxide (CO2 ) levels has been well studied. However, these investigations are typically limited to plants grown for a single generation in a high CO2 environment while transgenerational studies are rare. We aimed to determine transgenerational growth responses in plants after exposure to high CO2 by investigating the direct progeny when returned to baseline CO2 levels. We found that both the flowering plant Arabidopsis thaliana and seedless nonvascular plant Physcomitrium patens continue to display accelerated growth rates in the progeny of plants exposed to high CO2 . We used the model species Arabidopsis to dissect the molecular mechanism and found that DNA methylation pathways are necessary for heritability of this growth response. More specifically, the pathway of RNA-directed DNA methylation is required to initiate methylation and the proteins CMT2 and CMT3 are needed for the transgenerational propagation of this DNA methylation to the progeny plants. Together, these two DNA methylation pathways establish and then maintain a cellular memory to high CO2 exposure.