A Transformer-ResNet-Integrated Deep Learning Model for Digital Pathology-Based Grading and Risk Stratification of MASLD-Related Liver Fibrosis

INTRODUCTION: Metabolic dysfunction-associated steatotic liver disease (MASLD) affects up to 30% of the global population and drives progression to fibrosis, cirrhosis, and liver cancer, yet early-stage identification remains limited by subjective histopathology and low-sensitivity imaging. We aimed to develop and validate a deep learning model integrating Transformer and ResNet architectures using digital histopathology images of human liver biopsies for MASLD-related fibrosis staging and identification of pathological phenotypes associated with advanced fibrosis, with interpretability analyses to support pathology-assisted decision-making. METHODS: Four hundred sixty-seven Masson-stained liver biopsies from Duke (n=338), MHH (n=72), and BI-int (n=57) repositories were digitized at 20× resolution. Fibrosis was scored 0-4 per Younossi criteria. A four-encoder architecture combining 1×1 strided convolutions, multi-head self-attention Transformer blocks, and ResNet residual units was trained with global average pooling and linear classification. Performance metrics included accuracy, confusion matrices, continuous AI scores, and Grad-CAM visualization; analyses were conducted in Python/Jupyter with pandas, Matplotlib, and PyTorch. RESULTS: Training accuracy reached 0.80 and validation 0.85 without overfitting. Stage-specific accuracy ranged 0.74-0.95, peaking at bridging fibrosis (stage 3). Grad-CAM heatmaps localized model attention to severe fibrotic septa, corroborating advanced fibrotic architectural changes. Continuous AI scores aligned tightly with discrete ground-truth labels, with boundary-adjacent misclassifications reflecting subtle histologic overlap. CONCLUSIONS: The proposed model enables automated and interpretable assessment of MASLD-related fibrosis staging from digital liver biopsy histopathology and provides a quantitative tool for pathology phenotype-based risk stratification. Further clinical translation requires integration of clinical risk factors and validation in longitudinal outcome-based frameworks.