Biology subjects

Song, A. H.

Publications and source records attributed to Song, A. H..

7 recordsLinked to original sources

bioRxiv2026

Curvature-based schedule ordering is preserved in homogeneous and heterogeneous tumors

During treatment, dosing protocols with identical total dose may favor one schedule over another depending on how exposure is distributed over time. In homogeneous cell populations, Jensen's inequality has been shown to predict whether continuous or intermittent high-dose followed by low-dose is favored, based on the curvature of the concentration-effect function. Scheduling ordering can be performed based on curvature only: concave functions favor continuous dosing while convex functions favor intermittent dosing schedules with a high time-variance. However, tumors exhibit heterogeneous drug sensitivities, and treatment preferentially eliminates drug-sensitive cells, progressively shifting the surviving population toward greater drug resistance. Whether this treatment-induced selection can reverse curvature-based schedule ordering remains unclear. We develop a mathematical framework in which phenotypes share a common concentration-effect function but differ by fixed, nonnegative sensitivity scales. We prove that the ordering of equal-mean schedules is administrated solely by the scalar cumulative treatment effect, that is, by the curvature of the effect function alone. Consequently, baseline heterogeneity and treatment-induced selection can alter the magnitude of treatment response and the composition of surviving cells, but cannot reverse the ordering of equal-mean schedules predicted by the curvature of the single-cell concentration-effect function. This preservation holds across different temporal dosing profiles and repeated treatment cycles. Our work uncovers a general principle that curvature-based schedule ordering is preserved in heterogeneous tumors despite treatment-induced selection toward resistance.

cancer biology↗

bioRxiv2026

Prototype-based AI triage for 3D pathology

Non-destructive 3D pathology enables high-resolution slide-free imaging of intact clinical specimens, providing comprehensive visualization of tissue structures beyond what conventional slide-based 2D histopathology can provide. However, the scale and complexity of volumetric datasets make exhaustive manual review impractical, motivating AI-assisted triage methods to select a small number of high-risk 2D slices for pathologist review. While prior triage models have shown promise, interpretability is poor and performance can be suboptimal, especially in the nascent field of 3D pathology in which labeled data is limited. We present SCOPE, a Segmentation-guided CrOss-slice PrototypE learning framework for comprehensive risk assessment of 2D levels within 3D pathology datasets. SCOPE combines (i) clustering-based pretraining on large-scale unlabeled volumetric data to initialize morphology-aware prototypes, (ii) segmentation-derived structural priors from publicly available models to guide proto-type learning, and (iii) cross-slice (2.5D) prototype aggregation across neighboring slices to generate slice-level risk predictions. In prostate and esophageal data cohorts, SCOPE consistently outperforms attention-based and prototype-based multiple instance learning baselines for both binary and multiclass prediction tasks, enabling depth-resolved risk profiling for 3D triage based on morphological prototypes that are interpretable to pathologists.

pathology↗

bioRxiv2026

Scalable 3D cell-interaction analysis via supercell graphs for prostate cancer risk stratification

Cellular interactions underlie fundamental biological processes but are not fully represented in conventional 2D histology images. While 3D pathology allows for more-accurate construction of cell-level graphs, machine-learning models are computationally unwieldy and prone to overfitting, especially when dealing with small cohorts. Here, we introduce SCALE3D, a SuperCell graph Analysis framework for LargE 3D pathology datasets. In SCALE3D, spatially adjacent and morphologically similar cells are grouped into functional "supercells." Supercell subtypes are defined via morphology-based clustering and 3D graphs connecting these supercells are used to model their interactions. Validation was performed with 76 radical prostatectomy specimens from patients with known 5-year biochemical recurrence (BCR) outcomes. SCALE3D-derived features achieve higher performance for BCR prediction than established 3D nuclear and glandular morphological features. Combining these complementary features further improves prediction performance. Compared to individual cell-level 3D graphs, SCALE3D maintains comparable prognostic performance with improved noise tolerance while reducing computational times by up to 1,000-fold.

pathology↗

bioRxiv2025

Histology-guided 3D virtual staining of microCT-imaged lung tissue via deep learning

Histologically stained tissue sections are considered the gold standard for studying microscopic anatomy and diagnosing disease in clinical practice. However, the processes of sectioning and staining are laborious, and the overall method relies on two-dimensional (2D) analysis. In contrast, X-ray-based virtual histology offers the advantage of virtual sectioning while retaining the full three-dimensional (3D) volumetric representation of the tissue. Nevertheless, its grayscale nature has prevented it to be readily utilized by pathologists who are accustomed to conventional histological stains. In this work, we present a histology-guided enhancement platform that can integrate the 3D information provided by synchrotron radiation phase-contrast microCT with the rich visual features characteristic of histological stains. We introduce a multi-stage microCT-histology co-registration method combined with a virtual staining deep neural network and demonstrate successful virtual histological staining of microCT human and mouse lung tissue that closely resembles standard histology. We evaluate our strategy on multiple histological stains and apply it to identify 3D collagen-based remodeling of pulmonary arteries in patients with pulmonary hypertension. Overall, this innovative enhancement pipeline has the potential to aid in the incorporation of microCT into clinical practice, and advance non-destructive 3D pathology for improved diagnostic efficiency and accuracy.

pathology↗

bioRxiv2025

Deep-learning triage of 3D pathology datasets for comprehensive and efficient pathologist assessments

Standard-of-care slide-based 2D histopathology severely undersamples spatially heterogeneous tissue specimens, with each thin 2D section representing <1% of the entire tissue volume (in the case of a biopsy). Recent advances in non-destructive 3D pathology, such as open-top light-sheet microscopy (OTLS), enable comprehensive high-resolution imaging of large clinical specimens. While fully automated computational analyses of such 3D pathology datasets are being explored, a potential low-risk route for accelerated clinical adoption would be to continue to rely upon pathologists to provide final diagnoses. Since manual review of these massive and complex 3D datasets is infeasible for routine clinical practice, we present CARP3D, a deep learning triage framework that identifies high-risk 2D cross sections within large 3D pathology datasets to enable time-efficient pathologist evaluation. CARP3D assigns risk scores to all 2D levels within a tissue volume by leveraging context from a subset of neighboring depth levels, outperforming models in which predictions are based on isolated 2D levels. In two use cases - risk stratification based on prostate cancer biopsies and screening for dysplasia/cancer in endoscopic biopsies of Barretts esophagus - AI-triaged 3D pathology, enabled by CARP3D, demonstrates the potential to improve the detection of high-risk diseases in comparison to slide-based 2D histopathology while optimizing pathologist workloads.

pathology↗

bioRxiv2024

AI-driven Discovery of Morphomolecular Signatures in Toxicology

Early identification of drug toxicity is essential yet challenging in drug development. At the preclinical stage, toxicity is assessed with histopathological examination of tissue sections from animal models to detect morphological lesions. To complement this analysis, toxicogenomics is increasingly employed to understand the mechanism of action of the compound and ultimately identify lesion-specific safety biomarkers for which in vitro assays can be designed. However, existing works that aim to identify morphological correlates of expression changes rely on qualitative or semi-quantitative morphological characterization and remain limited in scale or morphological diversity. Artificial intelligence (AI) offers a promising approach for quantitatively modeling this relationship at an unprecedented scale. Here, we introduce GEESE, an AI model designed to impute morphomolecular signatures in toxicology data. Our model was trained to predict 1,536 gene targets on a cohort of 8,231 hematoxylin and eosin-stained liver sections from Rattus norvegicus across 127 preclinical toxicity studies. The model, evaluated on 2,002 tissue sections from 29 held-out studies, can yield pseudo-spatially resolved gene expression maps, which we correlate with six key drug-induced liver injuries (DILI). From the resulting 25 million lesion-expression pairs, we established quantitative relations between up and downregulated genes and lesions. Validation of these signatures against toxicogenomic databases, pathway enrichment analyses, and human hepatocyte cell lines asserted their relevance. Overall, our study introduces new methods for characterizing toxicity at an unprecedented scale and granularity, paving the way for AI-driven discovery of toxicity biomarkers. Live demo: https://mahmoodlab.github.io/tox-discovery-ui/

bioinformatics↗

bioRxiv2024

Deep Learning-based Modeling for Preclinical Drug Safety Assessment

In drug development, assessing the toxicity of candidate compounds is crucial for successfully transitioning from preclinical research to early-stage clinical trials. Drug safety is typically assessed using animal models with a manual histopathological examination of tissue sections to characterize the dose-response relationship of the compound - a timeintensive process prone to inter-observer variability and predominantly involving tedious review of cases without abnormalities. Artificial intelligence (AI) methods in pathology hold promise to accelerate this assessment and enhance reproducibility and objectivity. Here, we introduce TRACE, a model designed for toxicologic liver histopathology assessment capable of tackling a range of diagnostic tasks across multiple scales, including situations where labeled data is limited. TRACE was trained on 15 million histopathology images extracted from 46,734 digitized tissue sections from 157 preclinical studies conducted on Rattus norvegicus. We show that TRACE can perform various downstream toxicology tasks spanning histopathological response assessment, lesion severity scoring, morphological retrieval, and automatic dose-response characterization. In an independent reader study, TRACE was evaluated alongside ten board-certified veterinary pathologists and achieved higher concordance with the consensus opinion than the average of the pathologists. Our study represents a substantial leap over existing computational models in toxicology by offering the first framework for accelerating and automating toxicological pathology assessment, promoting significant progress with faster, more consistent, and reliable diagnostic processes. Live Demo: https://mahmoodlab.github.io/tox-foundation-ui/

bioinformatics↗