![]() ![]() Some commercial image analysis software already incorporates machine learning algorithms to assist researchers and clinicians in quantifying and segmenting histopathological images. Machine learning can be utilized for various image analysis tasks that are routinely performed during histological analyses including detection, segmentation, and classification. Digital pathology, which is the process of digitizing histopathology images, creates a new “treasure trove of image data” for machine learning (ML). With the widespread adoption of digital slide scanners in both clinical and preclinical settings, it is becoming increasingly common to digitize histology slides into high-resolutions images. For some cancer types, clinicians may decide treatment strategies based on histopathology images coupled with molecular assay data. In clinical settings, histopathology images are a critical source of primary data for pathologists to perform cancer diagnostic. Finally, we will discuss future opportunities of integrating molecular omics data with digital histopathology images for characterizing tumor ecosystem. We will describe some common steps in the workflow of preparing the data, as well as some limitations of this approach. We will provide a perspective of workflow on generating cell-level training data sets using immunohistochemistry markers to “weakly-label” the cell types. We will systematically review the various machine learning methods in these three scales with a focus on cell-level analysis. In this review, we will consider three different scales of histopathological analyses that machine learning can operate within: whole slide image (WSI)-level, region of interest (ROI)-level, and cell-level. In this review we focus on machine learning-based digital histopathology image analysis methods for characterizing tumor ecosystem. Furthermore, some recent approaches have attempted to integrate spatial and molecular omics data to better characterize the TIME. Recently, deep learning approaches have been widely used for digital histopathology images for cancer diagnoses and prognoses. ![]() The spatial organization of these different cell types in TIME could be used as biomarkers for predicting drug responses, prognosis and metastasis. The tumor immune microenvironment (TIME) encompasses many heterogeneous cell types that engage in extensive crosstalk among the cancer, immune, and stromal components. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, United States 4Cancer Biology and Evolution Program, H.3Department of Head and Neck-Endocrine Oncology, H.1Department of Biostatistics and Bioinformatics, H.Lockhart 2 †, Mengyu Xie 1, Ritu Chaudhary 3, Robbert J. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |