Biology subjects

Hewitt, K. J.

Publications and source records attributed to Hewitt, K. J..

4 recordsLinked to original sources

bioRxiv2026

An Integrated Preclinical Platform for Lethal Neuroendocrine Prostate Cancer from Rapid Autopsy Bone and Liver Metastases.

Treatment-emergent neuroendocrine prostate cancer (NEPC) is an aggressive, therapy-resistant disease arising in up to 20% of castration resistant prostate cancers, yet robust biologically relevant preclinical models remain scarce. Here, we describe a technical blueprint for establishing an integrated platform of patient-derived models from visceral and bone metastases collected through a prostate cancer rapid autopsy program (PC RAP). We report the establishment and characterization of patient-derived xenograft (PDX) models from liver metastasis tissue, liver and bone metastasis-derived organoid lines (PDOs), and corresponding patient-derived organoid xenograft (PDOX) models. In addition, we established, to our knowledge, the first mesenchymal stem cell (MSC) cultures derived from neuroendocrine prostate cancer (NEPC) bone metastases. The PDOs preserved intratumoral heterogeneity, displaying both CRPC-NE and CRPC-adenocarcinoma features. These organoids retained neuroendocrine identity across multiple passages, with transcriptomic profiles concordant with the original patient tissue and matched PDX models generated at our institution and at the National Cancer Institute (NCI Patient-Derived Models Repository). To model the bone metastatic microenvironment, we generated novel organoid-based New Approach Methodologies (NAMs) by co-culturing PDOs with iPSC-derived bone marrow organoids, establishing a physiologically relevant vascularized organotypic model of PC bone metastasis. To extend our studies in vivo, we established preclinical models using the liver and bone metastasis-derived organoid models. The PDOX models were tumorigenic and developed spontaneous lymph node metastases, providing clinically relevant models for investigating lethal NEPC biology. Together, these complementary patient-derived models provide a robust and versatile platform for investigating NEPC biology, metastatic progression, and evaluating new therapeutic strategies. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=184 SRC="FIGDIR/small/740121v1_ufig1.gif" ALT="Figure 1"> View larger version (57K): org.highwire.dtl.DTLVardef@1c641f1org.highwire.dtl.DTLVardef@113696aorg.highwire.dtl.DTLVardef@16dcc72org.highwire.dtl.DTLVardef@1898d9f_HPS_FORMAT_FIGEXP M_FIG C_FIG HighlightsO_LINovel preclinical models of visceral and bone metastases established from a prostate cancer rapid autopsy program. C_LIO_LIThis study is the first to establish mesenchymal stem cell cultures from NEPC bone metastases. C_LIO_LIPDOs preserve heterogeneity, showing both CRPC-NE and CRPC-Adeno features, with transcriptomic profiles concordant with originator tissue and PDX models. C_LIO_LIPC RAP-derived organoids are tumorigenic in vivo and generate spontaneous lymph node metastases. C_LI

cancer biology↗

bioRxiv2024

Counterfactual Diffusion Models for Mechanistic Explainability of Artificial Intelligence Models in Pathology

Deep learning can extract predictive and prognostic biomarkers from histopathology whole slide images. However, explainable artificial intelligence approaches widely used in digital pathology, such as attention heatmaps and class activation mapping, offer only limited interpretability regarding the features captured by classifiers. Here, we present MoPaDi (Morphing histoPathology Diffusion), a framework for generating counterfactual explanations for histopathology images that reveal which morphological or style features drive classifier predictions. MoPaDi combines diffusion autoencoders with task-specific multiple instance learning classifiers to manipulate images and flip predictions by modifying relevant features. We evaluated the framework on multiple datasets spanning colorectal, breast, liver, and lung cancers, including tissue type, cancer subtype, and biomarker (microsatellite instability) classification tasks. We assessed counterfactual explanations through quantitative analyses, pathologists evaluations, and independent foundation model-based classifiers. We found that MoPaDi was able to generate realistic counterfactual histopathology images, enabling pathologists to identify morphological features associated with the change in model predictions. Unlike conventional reviews of highly attended regions typical in digital pathology, MoPaDi explanations enabled pathologists to directly identify morphological features driving the classifiers predictions from a limited number of top-contributing tiles. Consistent with the literature, our biomarker classifier associated high microsatellite instability with mucinous differentiation, glandular patterns, and lymphocytic infiltration. Furthermore, MoPaDi revealed that changes in classifier predictions were mainly driven by morphological alterations rather than staining differences. Overall, MoPaDi is a practical framework for counterfactual explanations in computational pathology that reveals model-specific drivers of classification and increases trust in deep learning models.

bioinformatics↗

bioRxiv2022

Self-supervised deep learning for pan-cancer mutation prediction from histopathology

The histopathological phenotype of tumors reflects the underlying genetic makeup. Deep learning can predict genetic alterations from tissue morphology, but it is unclear how well these predictions generalize to external datasets. Here, we present a deep learning pipeline based on self-supervised feature extraction which achieves a robust predictability of genetic alterations in two large multicentric datasets of seven tumor types.

cancer biology↗

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↗