Empirical investigation of 3D CT Foundation Models and Unsupervised Adaptation for Head and Neck Cancer Recurrence Prediction

The rapid emergence of 3D CT foundation models has opened new avenues for predictive modeling from CT imaging, offering a compelling alternative to traditional radiomics which is known to suffer from reproducibility issues and sensitivity to acquisition protocol variations. Yet, as these models grow in availability, a critical need arises to evaluate how well their learned representations generalize across diverse clinical settings and whether adaptation to specific downstream tasks is necessary to unlock their full potential. To address these questions, we benchmarked several 3D CT foundation models for predicting recurrence-free survival in head and neck cancer across two public datasets totaling 3,644 patients, evaluating various adaptation strategies and modality fusion mechanisms. Our findings reveal persistent difficulty in identifying features that generalize consistently across different imaging distributions, as evidenced by significant performance drops on external validation cohorts. Ultimately, the integration of imaging features with clinical data remains the most accurate approach for prognostic prediction, though achieving universal generalization across varied clinical contexts continues to represent a substantial challenge for the current generation of models.

Histopathology image embedding based on foundation models features aggregation for patient treatment response prediction

Predicting the response of a patient to a cancer treatment is of high interest. Nonetheless, this task is still challenging from a medical point of view due to the complexity of the interaction between the patient organism and the considered treatment. Recent works on foundation models pre-trained with self-supervised learning on large-scale unlabeled histopathology datasets have opened a new direction towards the development of new methods for cancer diagnosis related tasks. In this article, we propose a novel methodology for predicting Diffuse Large B-Cell Lymphoma patients treatment response from Whole Slide Images. Our method exploits several foundation models as feature extractors to obtain a local representation of the image corresponding to a small region of the tissue, then, a global representation of the image is obtained by aggregating these local representations using attention-based Multiple Instance Learning. Our experimental study conducted on a dataset of 152 patients, shows the promising results of our methodology, notably by highlighting the advantage of using foundation models compared to conventional ImageNet pre-training. Moreover, the obtained results clearly demonstrates the potential of foundation models for characterizing histopathology images and generating more suited semantic representation for this task.

A vision transformer-based framework for knowledge transfer from multi-modal to mono-modal lymphoma subtyping models

Determining lymphoma subtypes is a crucial step for better patients treatment targeting to potentially increase their survival chances. In this context, the existing gold standard diagnosis method, which is based on gene expression technology, is highly expensive and time-consuming making difficult its accessibility. Although alternative diagnosis methods based on IHC (immunohistochemistry) technologies exist (recommended by the WHO), they still suffer from similar limitations and are less accurate. WSI (Whole Slide Image) analysis by deep learning models showed promising new directions for cancer diagnosis that would be cheaper and faster than existing alternative methods. In this work, we propose a vision transformer-based framework for distinguishing DLBCL (Diffuse Large B-Cell Lymphoma) cancer subtypes from high-resolution WSIs. To this end, we propose a multi-modal architecture to train a classifier model from various WSI modalities. We then exploit this model through a knowledge distillation mechanism for efficiently driving the learning of a mono-modal classifier. Our experimental study conducted on a dataset of 157 patients shows the promising performance of our mono-modal classification model, outperforming six recent methods from the state-of-the-art dedicated for cancer classification. Moreover, the power-law curve, estimated on our experimental data, shows that our classification model requires a reasonable number of additional patients for its training to potentially reach identical diagnosis accuracy as IHC technologies.