Skip to main content
Fig. 5 | BMC Medical Imaging

Fig. 5

From: Machine learning-based MRI radiomics for assessing the level of tumor infiltrating lymphocytes in oral tongue squamous cell carcinoma: a pilot study

Fig. 5

Classification performance of the machine learning models in discriminating between OTSCCs with high and low levels of TILs. Based on the features selected from each sequence alone, the ceT1WI models (b) outperformed the T2WI models (a), with a maximum AUC of 0.820 versus 0.754. Upon combining the two sequences (c), the logistic regression model exhibited the best predictive performance, with an AUC of 0.846. SVM, support vector machine

Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us