A convolutional attention model for predicting response to chemo-immunotherapy from ultrasound elastography in mouse tumor models

In the era of personalized cancer treatment, understanding the intrinsic heterogeneity of tumors is crucial. Despite some patients responding favorably to a particular treatment, others may not benefit, leading to the varied efficacy observed in standard therapies. This study focuses on the prediction of tumor response to chemo-immunotherapy, exploring the potential of tumor mechanics and medical imaging as predictive biomarkers. We have extensively studied “desmoplastic” tumors, characterized by a dense and very stiff stroma, which presents a substantial challenge for treatment. The increased stiffness of such tumors can be restored through pharmacological intervention with mechanotherapeutics. We developed a deep learning methodology based on shear wave elastography (SWE) images, which involved a convolutional neural network (CNN) model enhanced with attention modules. The model was developed and evaluated as a predictive biomarker in the setting of detecting responsive, stable, and non-responsive tumors to chemotherapy, immunotherapy, or the combination, following mechanotherapeutics administration. A dataset of 1365 SWE images was obtained from 630 tumors from our previous experiments and used to train and successfully evaluate our methodology. SWE in combination with deep learning models, has demonstrated promising results in disease diagnosis and tumor classification but their potential for predicting tumor response prior to therapy is not yet fully realized. We present strong evidence that integrating SWE-derived biomarkers with automatic tumor segmentation algorithms enables accurate tumor detection and prediction of therapeutic outcomes. This approach can enhance personalized cancer treatment by providing non-invasive, reliable predictions of therapeutic outcomes. Voutouri, Englezos et al. present a convolutional attention model utilizing ultrasound elastography for predicting chemo-immunotherapy responses in mouse tumors. Through training optimization on a large number of images, this approach highlights the potential of combining shear wave elastography with deep learning to enhance personalized cancer treatment. In personalized cancer treatment, it is important to understand that not all tumors respond the same way to therapy. While some patients may benefit from a particular treatment, others may not, leading to different outcomes. This study focuses on predicting how tumors will respond to a combination of chemotherapy and immunotherapy. Specifically, we looked at difficult-to-treat tumors with very stiff structures. These tumors can be softened with certain drugs making them more responsive to treatment. We developed a computer method to analyze medical images that measure the stiffness of tumors. Our method was trained on a large set of tumor images and was able to predict how well a tumor would respond to treatment. Overall, this approach could improve personalized cancer treatment using non-invasive medical imaging to predict which therapies will be most effective for each patient.