Abstract
BackgroundThe purpose of the present work was to test whether quantitative image analysis of circulating cells can provide useful clinical information targeting bone metastasis (BM) and overall survival (OS >30 months) in metastatic breast cancer (MBC).MethodsStarting from cell images of epithelial circulating tumor cells (eCTC) and leukocytes (CD45pos) obtained with DEPArray, we identified the most significant features and applied single-variable and multi-variable methods, screening all combinations of four machine-learning approaches (Naïve Bayes, Logistic regression, Decision Trees, Random Forest).ResultsBest predictive features were circularity (OS) and diameter (BM), in both eCTC and CD45pos. Median difference in OS was 15 vs. 43 (months), p = 0.03 for eCTC and 19 vs. 36, p = 0.16 for CD45pos. Prediction for BM showed low accuracy (64%, 53%) but strong positive predictive value PPV (79%, 91%) for eCTC and CD45, respectively. Best machine learning model was Naïve Bayes, showing 46 vs 11 (months), p <0.0001 for eCTC; 12.5 vs. 45, p = 0.0004 for CD45pos and 11 vs. 45, p = 0.0003 for eCTC + CD45pos. BM prediction reached 91% accuracy with eCTC, 84% with CD45pos and 91% with combined model.ConclusionsQuantitative image analysis and machine learning models were effective methods to predict survival and metastatic pattern, with both eCTC and CD45pos containing significant and complementary information.
Highlights
The purpose of the present work was to test whether quantitative image analysis of circulating cells can provide useful clinical information targeting bone metastasis (BM) and overall survival (OS >30 months) in metastatic breast cancer (MBC)
The study included 45 MBC patients. Each of these patients had a variable number of circulating tumor cells (CTC) and CD45pos cells, and each cell had several parameters provided by CellBrowser software
A total of 2,598 cells belonging to the 45 MBC patients were processed, extracting 846 CD45pos cells and 344 eCTCs
Summary
The purpose of the present work was to test whether quantitative image analysis of circulating cells can provide useful clinical information targeting bone metastasis (BM) and overall survival (OS >30 months) in metastatic breast cancer (MBC). By the analysis of circulating tumor cells (CTC), tumor. DNA (ctDNA) and exosomes, represents one of the most promising approaches to provide a complete and real-time overview of tumor evolution [10,11,12]. The identification and characterization of CTC provide researchers with a goldmine of information that goes beyond mere DNA mutations. Epigenetics, transcriptomics, and phenotypical aspects of cancer can be probed exclusively on CTC. We focused on image analysis of immunostained whole cells, providing morphological and phenotypical information
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have