Biology subjects

Ghaffari Laleh, N.

Publications and source records attributed to Ghaffari Laleh, N..

5 recordsLinked to original sources

bioRxiv2022

Adversarial attacks and adversarial robustness in computational pathology

Artificial Intelligence (AI) can support diagnostic workflows in oncology by aiding diagnosis and providing biomarkers. AI applications are therefore expected to evolve from academic prototypes to commercial products in the coming years. However, AI applications are vulnerable to adversarial attacks, such as malicious interference with test data aiming to cause misclassifications. Therefore, it is essential for the use of AI-based diagnostic devices to secure them against such attacks before widespread use. Unfortunately, no resistant systems exist in computational pathology so far. To address this problem, we investigate the susceptibility of convolutional neural networks (CNNs) to multiple types of white- and black-box attacks. We demonstrate that both attacks can easily confuse CNNs in clinically relevant pathology tasks and impair classification performance. Classical adversarially robust training and dual batch normalization (DBN) are possible mitigation strategies but require precise knowledge of the type of attack used in the inference. We demonstrate that vision transformers (ViTs) perform equally well compared to CNNs at baseline and are orders of magnitude more robust to different types of white-box and black-box attacks. At a mechanistic level, we show that this is associated with a more robust latent representation of clinically relevant categories in ViTs compared to CNNs. Our results are in line with previous theoretical studies. We show that ViTs are robust learners in computational pathology. This implies that large-scale rollout of AI models in computational pathology should rely on ViTs rather than CNN-based classifiers to provide inherent protection against adversaries.

bioinformatics↗

bioRxiv2021

DeepMed: A unified, modular pipeline for end-to-end deep learning in computational pathology

The interpretation of digitized histopathology images has been transformed thanks to artificial intelligence (AI). End-to-end AI algorithms can infer high-level features directly from raw image data, extending the capabilities of human experts. In particular, AI can predict tumor subtypes, genetic mutations and gene expression directly from hematoxylin and eosin (H&E) stained pathology slides. However, existing end-to-end AI workflows are poorly standardized and not easily adaptable to new tasks. Here, we introduce DeepMed, a Python library for predicting any high-level attribute directly from histopathological whole slide images alone, or from images coupled with additional meta-data (https://github.com/KatherLab/deepmed). Unlike earlier computational pipelines, DeepMed is highly developer-friendly: its structure is modular and separates preprocessing, training, deployment, statistics, and visualization in such a way that any one of these processes can be altered without affecting the others. Also, DeepMed scales easily from local use on laptop computers to multi-GPU clusters in cloud computing services and therefore can be used for teaching, prototyping and for large-scale applications. Finally, DeepMed is user-friendly and allows researchers to easily test multiple hypotheses in a single dataset (via cross-validation) or in multiple datasets (via external validation). Here, we demonstrate and document DeepMeds abilities to predict molecular alterations, histopathological subtypes and molecular features from routine histopathology images, using a large benchmark dataset which we release publicly. In summary, DeepMed is a fully integrated and broadly applicable end-to-end AI pipeline for the biomedical research community.

cancer biology↗

bioRxiv2021

Swarm learning for decentralized artificial intelligence in cancer histopathology

Artificial Intelligence (AI) can extract clinically actionable information from medical image data. In cancer histopathology, AI can be used to predict the presence of molecular alterations directly from routine histopathology slides. However, training robust AI systems requires large datasets whose collection faces practical, ethical and legal obstacles. These obstacles could be overcome with swarm learning (SL) where partners jointly train AI models, while avoiding data transfer and monopolistic data governance. Here, for the first time, we demonstrate the successful use of SL in large, multicentric datasets of gigapixel histopathology images comprising over 5000 patients. We show that AI models trained using Swarm Learning can predict BRAF mutational status and microsatellite instability (MSI) directly from hematoxylin and eosin (H&E)-stained pathology slides of colorectal cancer (CRC). We trained AI models on three patient cohorts from Northern Ireland, Germany and the United States of America and validated the prediction performance in two independent datasets from the United Kingdom using SL-based AI models. Our data show that SL enables us to train AI models which outperform most locally trained models and perform on par with models which are centrally trained on the merged datasets. In addition, we show that SL-based AI models are data efficient and maintain a robust performance even if only subsets of local datasets are used for training. In the future, SL can be used to train distributed AI models for any histopathology image analysis tasks, overcoming the need for data transfer and without requiring institutions to give up control of the final AI model.

bioinformatics↗

bioRxiv2021

Improving mathematical models of cancer by including resistance to therapy: a study in non-small cell lung cancer

We examined a dataset of 590 Non-Small Cell Lung Cancer patients treated with either chemotherapy or immunotherapy using a game-theoretic model that includes both the evolution of therapy resistance and a cost of resistance. We tested whether the game-theoretic model provides a better fit than classical mathematical models of population growth (exponential, logistic, classic Bertalanffy, general Bertalanffy, Gompertz, general Gompertz). To our knowledge, this is the first time a large clinical patient cohort (as opposed to only in-vitro data) has been used to apply a game-theoretic cancer model. The game-theoretic model provided a better fit to the tumor dynamics of the 590 Non-Small Cell Lung Cancer patients than any of the non-evolutionary population growth models. This was not simply due to having more parameters in the game-theoretic model. The game-theoretic model was seemingly able to fit more accurately patients whose tumor burden exhibit a U-shaped trajectory over time. We explained how this game-theoretic model provides predictions of future tumor growth based on just a few initial measurements. Using the estimates for treatment-specific parameters, we then explored alternative treatment protocols and their expected impact on tumor growth and patient outcome. As such, the model could possibly be used to suggest patient-specific optimal treatment regimens with the goal of minimizing final tumor burden. Therapeutic protocols based on game-theoretic modeling can help to predict tumor growth, and could potentially improve patient outcome in the future. The model invites evolutionary therapies that anticipate and steer the evolution of therapy resistance.

cancer biology↗

bioRxiv2021

Classical Mathematical Models for Prediction of Response to Chemotherapy and Immunotherapy

Classical mathematical models of tumor growth have shaped our understanding of cancer and have broad practical implications for treatment scheduling and dosage. However, even the simplest textbook models have been barely validated in real world-data of human patients. In this study, we fitted a range of differential equation models to tumor volume measurements of patients undergoing chemotherapy or cancer immunotherapy for solid tumors. We used a large dataset of 1472 patients with three or more measurements per target lesion, of which 652 patients had six or more data points. We show that the early treatment response shows only moderate correlation with the final treatment response, demonstrating the need for nuanced models. We then perform a head-to-head comparison of six classical models which are widely used in the field: the Exponential, Logistic, Classic Bertalanffy, General Bertalanffy, Classic Gompertz and General Gompertz model. Several models provide a good fit to tumor volume measurements, with the Gompertz model providing the best balance between goodness of fit and number of parameters. Similarly, when fitting to early treatment data, the general Bertalanffy and Gompertz models yield the lowest mean absolute error to forecasted data, indicating that these models could potentially be effective at predicting treatment outcome. In summary, we provide a quantitative benchmark for classical textbook models and state-of-the art models of human tumor growth. We publicly release an anonymized version of our original data, providing the first benchmark set of human tumor growth data for evaluation of mathematical models. Author SummaryMathematical oncology uses quantitative models for prediction of tumor growth and treatment response. The theoretical foundation of mathematical oncology is provided by six classical mathematical models: the Exponential, Logistic, Classic Bertalanffy, General Bertalanffy, Classic Gompertz and General Gompertz model. These models have been introduced decades ago, have been used in thousands of scientific articles and are part of textbooks and curricula in mathematical oncology. However, these models have not been systematically tested in clinical data from actual patients. In this study, we have collected quantitative tumor volume measurements from thousands of patients in five large clinical trials of cancer immunotherapy. We use this dataset to systematically investigate how accurately mathematical models can describe tumor growth, showing that there are pronounced differences between models. In addition, we show that two of these models can predict tumor response to immunotherapy and chemotherapy at later time points when trained on early tumor growth dynamics. Thus, our article closes a conceptual gap in the literature and at the same time provides a simple tool to predict response to chemotherapy and immunotherapy on the level of individual patients.

cancer biology↗