Biology subjects

Sheridan, T. B.

Publications and source records attributed to Sheridan, T. B..

4 recordsLinked to original sources

bioRxiv2026

DIANNE: Segmentation-Free Localization of Histology Differential Attributes

Pathologist-guided distinctions within histology and spatial omic images provide insights into health and disease, with digital pathology leveraging artificial intelligence to automate such assessments. To train computational models, current digital pathology methods rely on upfront manual annotations, which are time-consuming to generate. Pre-annotation is poorly suited to investigating novel spatial behaviors--a major need driven by advances in spatial profiling--for which annotation criteria and data needs will be uncertain. To address these challenges, we present DIANNE, a digital pathology annotation support and discovery approach for rapid training and inference of spatial differential attributes, enabled by train-time Positive Class Mixup Augmentation. DIANNE can compute foundation model-derived segmentation-free localization of differential classifiers across whole slide H&E images within seconds on a workstation, enabling interactive investigation of spatial niches. Predictive models can be re-trained in real-time in response to patch or regional annotation changes, clarifying determinative biological attributes across slides from only a few dozen annotated patches. We demonstrate the effectiveness of DIANNE for tumor detection, artifact identification, and exploration of pancreatic, fetal membranes and kidney tissue structures. DIANNE also provides analogous capabilities for IHC, multiplex immunofluorescence, and registered spatial transcriptomic+H&E images. DIANNE is implemented in a Jupyter toolkit, enabling rapid development of high-resolution classifiers from weakly-supervised training. DIANNE provides a practical system to quantitatively understand known and novel spatial phenotypes.

pathology↗

bioRxiv2024

Spatiotemporal profiling defines persistence and resistance dynamics during targeted treatment of melanoma

Resistance of BRAF-mutant melanomas to targeted therapy arises from the ability of cells to enter a persister state, evade treatment with relative dormancy, and repopulate the tumor when reactivated. Using spatial transcriptomics in patient derived xenograft models, we capture clonal lineage evolution during treatment, finding the persister state to show increased oxidative phosphorylation, decreased proliferation, and increased invasive capacity, with central-to-peripheral gradients. Phylogenetic tracing identifies intrinsic- and acquired-resistance mechanisms (e.g. dual specific phosphatases, Reticulon-4, CDK2) and suggests specific temporal windows of potential therapeutic efficacy. Using deep learning to analyze histopathological slides, we find morphological features of specific cell states, demonstrating that juxtaposition of transcriptomics and histology data enables identification of phenotypically-distinct populations using imaging data alone. In summary, we define state change and lineage selection during melanoma treatment with spatiotemporal resolution, elucidating how choice and timing of therapeutic agents will impact the ability to eradicate resistant clones. Statement of SignificanceTumor evolution is accelerated by application of anti-cancer therapy, resulting in clonal expansions leading to dormancy and subsequently resistance, but the dynamics of this process are incompletely understood. Tracking clonal progression during treatment, we identify conserved, global transcriptional changes and local clone-clone and spatial patterns underlying the emergence of resistance.

cancer biology↗

bioRxiv2023

SAMPLER: Empirical distribution representations for rapid analysis of whole slide tissue images

Deep learning has revolutionized digital pathology, allowing for automatic analysis of hematoxylin and eosin (H&E) stained whole slide images (WSIs) for diverse tasks. In such analyses, WSIs are typically broken into smaller images called tiles, and a neural network backbone encodes each tile in a feature space. Many recent works have applied attention based deep learning models to aggregate tile-level features into a slide-level representation, which is then used for slide-level prediction tasks. However, training attention models is computationally intensive, necessitating hyperparameter optimization and specialized training procedures. Here, we propose SAMPLER, a fully statistical approach to generate efficient and informative WSI representations by encoding the empirical cumulative distribution functions (CDFs) of multiscale tile features. We demonstrate that SAMPLER-based classifiers are as accurate or better than state-of-the-art fully deep learning attention models for classification tasks including distinction of: subtypes of breast carcinoma (BRCA: AUC=0.911 {+/-} 0.029); subtypes of non-small cell lung carcinoma (NSCLC: AUC=0.940{+/-}0.018); and subtypes of renal cell carcinoma (RCC: AUC=0.987{+/-}0.006). A major advantage of the SAMPLER representation is that predictive models are >100X faster compared to attention models. Histopathological review confirms that SAMPLER-identified high attention tiles contain tumor morphological features specific to the tumor type, while low attention tiles contain fibrous stroma, blood, or tissue folding artifacts. We further apply SAMPLER concepts to improve the design of attention-based neural networks, yielding a context aware multi-head attention model with increased accuracy for subtype classification within BRCA and RCC (BRCA: AUC=0.921{+/-}0.027, and RCC: AUC=0.988{+/-}0.010). Finally, we provide theoretical results identifying sufficient conditions for which SAMPLER is optimal. SAMPLER is a fast and effective approach for analyzing WSIs, with greatly improved scalability over attention methods to benefit digital pathology analysis.

bioinformatics↗

bioRxiv2021

Deep Learning Features Encode Interpretable Morphologies within Histological Images

Convolutional neural networks (CNNs) are revolutionizing digital pathology by enabling machine learning-based classification of a variety of phenotypes from hematoxylin and eosin (H&E) whole slide images (WSIs), but the interpretation of CNNs remains difficult. Most studies have considered interpretability in a post hoc fashion, e.g. by presenting example regions with strongly predicted class labels. However, such an approach does not explain the biological features that contribute to correct predictions. To address this problem, here we investigate the interpretability of H&E-derived CNN features (the feature weights in the final layer of a transfer-learning-based architecture), which we show can be construed as abstract morphological genes ("mones") with strong independent associations to biological phenotypes. We observe that many mones are specific to individual cancer types, while others are found in multiple cancers especially from related tissue types. We also observe that mone-mone correlations are strong and robustly preserved across related cancers. Importantly, linear mone-based classifiers can very accurately separate 38 distinct classes (19 tumor types and their adjacent normals, AUC=97.1% {+/-} 2.8% for each class prediction), and linear classifiers are also highly effective for universal tumor detection (AUC=99.2% {+/-} 0.12%). This linearity provides evidence that individual mones or correlated mone clusters may be associated with interpretable histopathological features or other patient characteristics. In particular, the statistical similarity of mones to gene expression values allows integrative mone analysis via expression-based bioinformatics approaches. We observe strong correlations between individual mones and individual gene expression values, notably mones associated with collagen gene expression in ovarian cancer. Mone-expression comparisons also indicate that immunoglobulin expression can be identified using mones in colon adenocarcinoma and that immune activity can be identified across multiple cancer types, and we verify these findings by expert histopathological review. Our work demonstrates that mones provide a morphological H&E decomposition that can be effectively associated with diverse phenotypes, analogous to the interpretability of transcription via gene expression values.

bioinformatics↗