Margin-Consistent Deep Subtyping of Invasive Lung Adenocarcinoma via Perturbation Fidelity in Whole-Slide Image Analysis

TL;DR

This work proposes a margin consistency framework evaluated on 203,226 patches from 143 whole-slide images spanning five adenocarcinoma subtypes in the BMIRDS-LUAD dataset, demonstrating cross-institutional generalizability despite approximately 15-20% domain-shift-related degradation and identifying opportunities for future adaptation research.

Abstract

Whole-slide image classification for invasive lung adenocarcinoma subtyping remains vulnerable to real-world imaging perturbations that undermine model reliability at the decision boundary. We propose a margin consistency framework evaluated on 203,226 patches from 143 whole-slide images spanning five adenocarcinoma subtypes in the BMIRDS-LUAD dataset. By combining attention-weighted patch aggregation with margin-aware training, our approach achieves robust feature-logit space alignment measured by Kendall correlations of 0.88 during training and 0.64 during validation. Contrastive regularization, while effective at improving class separation, tends to over-cluster features and suppress fine-grained morphological variation; to counteract this, we introduce Perturbation Fidelity (PF) scoring, which imposes structured perturbations through Bayesian-optimized parameters. Vision Transformer-Large achieves 95.20 +/- 4.65% accuracy, representing a 40% error reduction from the 92.00 +/- 5.36% baseline, while ResNet101 with an attention mechanism reaches 95.89 +/- 5.37% from 91.73 +/- 9.23%, a 50% error reduction. All five subtypes exceed an area under the receiver operating characteristic curve (AUC) of 0.99. On the WSSS4LUAD external benchmark, ResNet50 with an attention mechanism attains 80.1% accuracy, demonstrating cross-institutional generalizability despite approximately 15-20% domain-shift-related degradation and identifying opportunities for future adaptation research.

Figures (3)

• Figure 1: Proposed attention-based robust histopathology subtyping framework integrating cross-entropy and contrastive learning with margin consistency. Whole-slide images (WSIs) are divided into fixed-size patches and normalized before passing through a patch encoder and an attention-based feature extractor $h_{\psi_a}(x)$. The resulting feature representation $z$ is used for both classification via a linear classifier $f_{\theta_a}(x) = w^\top z + b$ and representation learning via supervised contrastive loss. Cross-entropy loss $\mathcal{L}_{CE}$, contrastive loss $\mathcal{L}_{CON}$, and Perturbation Fidelity loss $\mathcal{L}_{PF}$ are combined as total loss $\mathcal{L}_T$. Margin consistency is computed using logit differences and feature margins to guide robust decision boundaries. This multitask learning scheme enhances feature discriminability, maintains high-margin consistency, and improves robustness against subtyping brittleness.
• Figure 2: Domain shift analysis for external validation on WSSS4LUAD. (a) Per-subtype accuracy comparison. (b) Domain shift sources. (c) External confusion matrix. (d) Error sources by subtype.
• Figure 3: Bootstrap confidence intervals (95%) demonstrating accuracy improvements and enhanced model stability across architectures. Our method (green) shows consistently higher accuracy with reduced variance compared to baseline (red).