34P Investigating morphological heterogeneity in luminal breast cancer integrating artificial intelligence and spatial transcriptomics
نویسندگان
چکیده
Hormone receptor-positive (HR+), HER2-negative (HER2-) breast cancer (BC) accounts for around 65% of all BCs. Invasive lobular and ductal carcinoma (ILC, IDC) show distinct histology clinical presentation. In this study, our goal is to exploit morphological differences between IDC ILC by combining artificial intelligence spatial transcriptomics (ST) characterize intra-tumor heterogeneity. We analyzed 131 H&E whole slide images (WSIs) from frozen HR+, HER2- BC samples, which 43 were 88 IDC. Images morphologically annotated using QuPath. performed ST (Visium 10X Genomics®) on the samples. A neural network (NN) was trained perform classification WSIs detect most relevant tissue regions such classification. Gene expression data used these regions. The NN achieved 0.95 ROC AUC in predicting (ILC vs IDC). Interestingly, 36/43 adipose had highest relative importance assessing histological subtype, suggesting crucial adipocytes Of note, we observed intra-sample heterogeneity levels tumor areas, with just 13% overall cells showing high mapped spots (for ILC). Pathway enrichment analysis differentially expressed genes (DEG) revealed metabolic adipogenesis-related pathways (padj < 0.05). When limiting composed more than 30% cells, DEG metabolic-related Adipose morphology be a key feature distinguishing subtypes BC. Importantly, increased metabolism showed classification, ILC. Further validation needed.
منابع مشابه
Mammographic findings in different breast cancer subtypes (luminal, Her2 positive, triple negative)
Background: Prognosis and management of breast cancer are defined by different variables including histological type, grading, clinical stage, Her2+, estrogen and progesterone receptor conditions. Generally, mammography is one of the most important imaging which is done in breast cancer patients. The aim of this research was to evaluate different mammographic patterns in different breast cancer...
متن کاملHeterogeneity in breast cancer.
Breast cancer is a heterogeneous disease. There is a high degree of diversity between and within tumors as well as among cancer-bearing individuals, and all of these factors together determine the risk of disease progression and therapeutic resistance. Advances in technologies such as whole-genome sequencing and functional viability screens now allow us to analyze tumors at unprecedented depths...
متن کاملHeterogeneity in Breast cancer
Breast cancer is malignant tumor occurred on breast epithelial tissue, although the mortality rate of breast cancer decreases, it remains one of the highest mortality rate diseases. Ignoring few exceptions, almost all tumors are derived from one single cancer cell. However, in clinical diagnosis, most human tumors demonstrate amazing heterogeneity in many morphological and physical characterist...
متن کاملGenomic profiling in luminal breast cancer.
The developments in gene expression analysis have made it possible to sub-classify hormone receptor-positive (luminal) breast cancer in different prognostic subgroups. This sub-classification is currently used in clinical routine as prognostic signature (e.g. 21-gene Onoctype DX®, 70-gene Mammaprint®). As yet, the optimal method for sub-classification has not been defined. Moreover, there is no...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ESMO open
سال: 2023
ISSN: ['2059-7029']
DOI: https://doi.org/10.1016/j.esmoop.2023.101258