Skip to main content
 
Notice: Users may be experiencing issues with displaying some pages on stanfordhealthcare.org. We are working closely with our technical teams to resolve the issue as quickly as possible. Thank you for your patience.
 

See our updated masking policy »

Stanford Health Care

Predicting lymph node metastasis from primary tumor histology and clinicopathologic factors in colorectal cancer using deep learning. Communications medicine Krogue, J. D., Azizi, S., Tan, F., Flament-Auvigne, I., Brown, T., Plass, M., Reihs, R., Müller, H., Zatloukal, K., Richeson, P., Corrado, G. S., Peng, L. H., Mermel, C. H., Liu, Y., Chen, P. C., Gombar, S., Montine, T., Shen, J., Steiner, D. F., Wulczyn, E. 2023; 3 (1): 59

Abstract

Presence of lymph node metastasis (LNM) influences prognosis and clinical decision-making in colorectal cancer. However, detection of LNM is variable and depends on a number of external factors. Deep learning has shown success in computational pathology, but has struggled to boost performance when combined with known predictors.Machine-learned features are created by clustering deep learning embeddings of small patches of tumor in colorectal cancer via k-means, and then selecting the top clusters that add predictive value to a logistic regression model when combined with known baseline clinicopathological variables. We then analyze performance of logistic regression models trained with and without these machine-learned features in combination with the baseline variables.The machine-learned extracted features provide independent signal for the presence of LNM (AUROC: 0.638, 95% CI: [0.590, 0.683]). Furthermore, the machine-learned features add predictive value to the set of 6 clinicopathologic variables in an external validation set (likelihood ratio test, p?

View details for DOI 10.1038/s43856-023-00282-0

View details for PubMedID 37095223

View details for PubMedCentralID 5069274