The analysis of histopathology images with artificial intelligence aims to enable clinical decision support systems and precision medicine. The success of such applications depends on the ability to model the diverse patterns observed in pathology images. To this end, we present Virchow, the largest foundation model for computational pathology to date. In addition to the evaluation of biomarker prediction and cell identification, we demonstrate that a large foundation model enables pan-cancer detection, achieving 0.95 specimen-level area under the (receiver operating characteristic) curve across nine common and seven rare cancers. Furthermore, we show that with less training data, the pan-cancer detector built on Virchow can achieve similar performance to tissue-specific clinical-grade models in production and outperform them on some rare variants of cancer. Virchow’s performance gains highlight the value of a foundation model and open possibilities for many high-impact applications with limited amounts of labeled training data.

Data-driven methods for battery lifetime prediction are attracting increasing attention for applications in which the degradation mechanisms are poorly understood and suitable training sets are available. However, while advanced machine learning and deep learning methods promise high performance with minimal data preprocessing, simpler linear models with engineered features often achieve comparable performance, especially for small training sets, while also providing physical and statistical interpretability. In this work, we use a previously published dataset to develop simple, accurate, and interpretable data-driven models for battery lifetime prediction. We first present the “capacity matrix” concept as a compact representation of battery electrochemical cycling data, along with a series of feature representations. We then create a number of univariate and multivariate models, many of which achieve comparable performance to the highest-performing models previously published for this dataset; thus, our work can serve as a comprehensive benchmarking study for this dataset. These models also provide insights into the degradation of these cells. Our approaches can be used both to quickly train models for a new battery cycling dataset and to benchmark the performance of more advanced machine learning methods.

Although oversampling methods are widely used to deal with class imbalance problems, most only utilize observed samples in the minority class and ignore the rich information available in the majority class. In this work, we use an oversampling method that leverages information in both the majority and minority classes to mitigate the class imbalance problem. Experimental results on two clinical datasets with highly imbalanced outcomes demonstrate that prediction models can be significantly improved using data obtained from this oversampling method when the number of minority class samples is very small.

The Hallmarks of Cancer framework has played a seminal role in developing our understanding of cancer biology. By design, these hallmarks abstract cancer into a common set of functional capabilities. The hallmarks thus constitute an intentionally reductionist framework that has unified diverse observations and yielded valuable mechanistic insight, while leaving unresolved how these processes interact across scales. Complementary tools are therefore needed to capture cancer's inherently complex, multimodal, and multiscale nature. Here, we posit that generative models, built on the recent advances of artificial intelligence, are the key technology to capture this complexity and to thereby improve how we diagnose, understand, and intervene in cancer. Specifically, because of their ability to recognize complex patterns, process unstructured inputs, and synthesize multimodal inputs, generative models are poised to usher in a new era of biological discovery and clinical care. Ultimately, we envision a synergistic cycle wherein generative models of cancer and the Hallmarks of Cancer complement one another, the former driving hypothesis generation and discovery and the latter guiding the prioritization and development of new measurement tools.