Search papers, labs, and topics across Lattice.
This study evaluates the use of CT Foundation model-derived embeddings for predicting distant metastasis (DM) risk in head and neck cancer, comparing their performance against traditional radiomics and deep learning approaches. Utilizing preoperative CT images from 2,327 patients, the foundation model achieved an AUC of 0.791, surpassing the radiomics and deep learning models, which scored 0.772 and 0.753, respectively. The findings suggest that foundation models can streamline the prediction process by minimizing the need for expert knowledge and extensive annotations, making them a viable alternative for clinical applications.
Foundation model embeddings can outperform traditional methods in predicting cancer metastasis, achieving near-state-of-the-art results with less reliance on expert input.
Background: Early prediction of distant metastasis (DM) risk in head and neck cancer (HNC) can enable timely interventions that may improve treatment outcomes. Many current machine learning methods rely on prior knowledge of the region of interest such as tumor segmentations, which require expert knowledge, is time-consuming and introduces user-dependent variability. Medical image-based foundation models have recently been developed for specific imaging modalities to streamline down-stream prediction tasks by extracting modality-relevant features. Purpose: In this study, we evaluate the effectiveness of using a foundation model as the feature extractor to predict DM risk in HNC patients and compare its performance with traditional approaches that require prior knowledge on the regions of interest. Methods: Preoperative CT images of 2327 patients from the RADCURE dataset were used. Three features-sets were created including radiomics, deep-learning based features, and CT Foundation derived features. The feature-sets were used individually in a multi-layer perceptron (MLP) to predict DM risk. Results: The model using CT Foundation embeddings outperformed the radiomics and deep learning-based models, achieving a Receiver Operating Characteristic Area Under the Curve (AUC) of 0.791, compared to AUC values of 0.772 and 0.753 for the radiomics and deep learning-based models, respectively. The CT Foundation based model had similar performance to a model that combined the use of radiomics and deep learning-based features that achieved an AUC of 0.794. Conclusions: Features based on foundation models offer a promising alternative to traditional radiomics while reducing the need for domain expertise and extensively annotated datasets. Their minimal preprocessing requirements also make them a more accessible and scalable option.
