Selected work

Representative Papers

Myelin Distribution at the Optic Nerve Myelination Transition Zone Influences Axonal Biomechanics

Aug 07, 2026

This study investigates the potential role of mechanical discontinuity at the myelination transition zone (MTZ) of the optic nerve in early glaucomatous damage. By developing a multiscale finite element model that integrates the macroscopic globe with the microscopic lamina cribrosa–axon architecture, the work quantifies, for the first time, how different MTZ boundary configurations influence axonal biomechanical responses under intraocular pressures of 15 and 45 mmHg. The results demonstrate that the unmyelinated region endures substantially higher mechanical loads, and posterior displacement of the MTZ markedly exacerbates stress and strain discontinuities across the interface. These findings highlight MTZ geometry as a critical determinant of the local mechanical microenvironment surrounding axons, offering a novel biomechanical perspective on the pathogenesis of glaucoma.

0 citationsRead paper

Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model

Jul 18, 2026

This study challenges the common assumption that explanation stability is an inherent property of deep learning models, demonstrating instead that it emerges from the interaction between the model and the attribution method. Systematically evaluating DenseNet201, ResNet50V2, and InceptionV3 on chest X-ray data using multiple attribution techniques—including LayerCAM and GradCAM++—the authors employ IoU and AUC (both exceeding 99%) as stability metrics. Their results reveal that model stability rankings vary dramatically across attribution methods: for instance, LayerCAM identifies InceptionV3 as the most stable model (IoU = 0.777), whereas GradCAM++ reduces its stability by 17.3%. These findings underscore that attribution method choice critically influences stability assessments and highlight the necessity of cross-method validation to avoid biased conclusions.

0 citationsRead paper

Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification

Apr 09, 2026

This study addresses a critical gap in the evaluation of explainability for medical image classification models, which has predominantly emphasized localization accuracy while overlooking whether models employ consistent spatial reasoning strategies across pathologically similar samples. To bridge this gap, we introduce C-Score (Consistency Score), a novel, annotation-free metric that quantifies intra-class consistency of Class Activation Map (CAM) explanations using confidence-weighted soft Intersection-over-Union with intensity emphasis. Through transfer learning experiments on the Kermany chest X-ray dataset—combining six CAM variants (including Grad-CAM) with DenseNet201, InceptionV3, and ResNet50V2—we uncover three distinct mechanisms by which explanation consistency decouples from AUC performance. Notably, C-Score detects ScoreCAM degradation one checkpoint before a significant AUC drop, offering an early, explanation-quality-based warning signal to inform clinical model selection and deployment.

0 citationsRead paper

When Fine-Tuning Changes the Evidence: Architecture-Dependent Semantic Drift in Chest X-Ray Explanations

Apr 09, 2026

This study addresses the trade-off between accuracy and interpretability in chest X-ray multi-class classification, where fine-tuning improves performance but may induce semantic drift in the visual evidence underpinning model explanations, thereby undermining clinical trust. The authors propose a two-stage training protocol and systematically compare attribution maps generated under transfer learning versus full fine-tuning across DenseNet201, ResNet50V2, and InceptionV3. They demonstrate for the first time that explanation stability is jointly determined by model architecture, optimization phase, and attribution method—with stability rankings even reversing across different attribution techniques. Using LayerCAM and GradCAM++ alongside no-reference metrics such as IoU to assess spatial consistency, they find that coarse-grained anatomical localization remains stable, whereas fine-grained evidential structures are highly architecture-dependent, revealing that high accuracy does not guarantee reliable interpretability.

0 citationsRead paper

Opening the black box of deep learning: Validating the statistical association between explainable artificial intelligence (XAI) and clinical domain knowledge in fundus image-based glaucoma diagnosis

Apr 06, 2025

Deep learning models in medical image diagnosis suffer from limited interpretability, undermining clinical trust. To address this, we conduct the first systematic cross-model, cross-method, and multi-dataset explainable AI (XAI) validation for glaucoma fundus image classification. We evaluate five class activation mapping (CAM) techniques—including Grad-CAM—across four architectures (VGG-11, ResNet-18, DeiT-Tiny, Swin-Tiny) on five publicly available datasets. Attention heatmaps are quantitatively aligned with clinically relevant anatomical structures (optic cup, optic disc, retinal vessels). Paired t-tests and Pearson/Spearman correlation analyses demonstrate that all models significantly attend to these regions (p < 0.001), and the anatomical coverage ratio of attention maps strongly correlates with diagnostic accuracy (r > 0.8, p < 0.001). This work provides the first statistical evidence—spanning multiple models, explanation methods, and datasets—supporting the clinical credibility of XAI in ophthalmic diagnosis.

0 citationsRead paper

Recent publications

Latest Papers

Myelin Distribution at the Optic Nerve Myelination Transition Zone Influences Axonal Biomechanics

Aug 07, 2026

This study investigates the potential role of mechanical discontinuity at the myelination transition zone (MTZ) of the optic nerve in early glaucomatous damage. By developing a multiscale finite element model that integrates the macroscopic globe with the microscopic lamina cribrosa–axon architecture, the work quantifies, for the first time, how different MTZ boundary configurations influence axonal biomechanical responses under intraocular pressures of 15 and 45 mmHg. The results demonstrate that the unmyelinated region endures substantially higher mechanical loads, and posterior displacement of the MTZ markedly exacerbates stress and strain discontinuities across the interface. These findings highlight MTZ geometry as a critical determinant of the local mechanical microenvironment surrounding axons, offering a novel biomechanical perspective on the pathogenesis of glaucoma.

0 citationsRead paper

Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model

Jul 18, 2026

This study challenges the common assumption that explanation stability is an inherent property of deep learning models, demonstrating instead that it emerges from the interaction between the model and the attribution method. Systematically evaluating DenseNet201, ResNet50V2, and InceptionV3 on chest X-ray data using multiple attribution techniques—including LayerCAM and GradCAM++—the authors employ IoU and AUC (both exceeding 99%) as stability metrics. Their results reveal that model stability rankings vary dramatically across attribution methods: for instance, LayerCAM identifies InceptionV3 as the most stable model (IoU = 0.777), whereas GradCAM++ reduces its stability by 17.3%. These findings underscore that attribution method choice critically influences stability assessments and highlight the necessity of cross-method validation to avoid biased conclusions.

0 citationsRead paper

Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification

Apr 09, 2026

This study addresses a critical gap in the evaluation of explainability for medical image classification models, which has predominantly emphasized localization accuracy while overlooking whether models employ consistent spatial reasoning strategies across pathologically similar samples. To bridge this gap, we introduce C-Score (Consistency Score), a novel, annotation-free metric that quantifies intra-class consistency of Class Activation Map (CAM) explanations using confidence-weighted soft Intersection-over-Union with intensity emphasis. Through transfer learning experiments on the Kermany chest X-ray dataset—combining six CAM variants (including Grad-CAM) with DenseNet201, InceptionV3, and ResNet50V2—we uncover three distinct mechanisms by which explanation consistency decouples from AUC performance. Notably, C-Score detects ScoreCAM degradation one checkpoint before a significant AUC drop, offering an early, explanation-quality-based warning signal to inform clinical model selection and deployment.

0 citationsRead paper

When Fine-Tuning Changes the Evidence: Architecture-Dependent Semantic Drift in Chest X-Ray Explanations

Apr 09, 2026

This study addresses the trade-off between accuracy and interpretability in chest X-ray multi-class classification, where fine-tuning improves performance but may induce semantic drift in the visual evidence underpinning model explanations, thereby undermining clinical trust. The authors propose a two-stage training protocol and systematically compare attribution maps generated under transfer learning versus full fine-tuning across DenseNet201, ResNet50V2, and InceptionV3. They demonstrate for the first time that explanation stability is jointly determined by model architecture, optimization phase, and attribution method—with stability rankings even reversing across different attribution techniques. Using LayerCAM and GradCAM++ alongside no-reference metrics such as IoU to assess spatial consistency, they find that coarse-grained anatomical localization remains stable, whereas fine-grained evidential structures are highly architecture-dependent, revealing that high accuracy does not guarantee reliable interpretability.

0 citationsRead paper

Opening the black box of deep learning: Validating the statistical association between explainable artificial intelligence (XAI) and clinical domain knowledge in fundus image-based glaucoma diagnosis

Apr 06, 2025

Deep learning models in medical image diagnosis suffer from limited interpretability, undermining clinical trust. To address this, we conduct the first systematic cross-model, cross-method, and multi-dataset explainable AI (XAI) validation for glaucoma fundus image classification. We evaluate five class activation mapping (CAM) techniques—including Grad-CAM—across four architectures (VGG-11, ResNet-18, DeiT-Tiny, Swin-Tiny) on five publicly available datasets. Attention heatmaps are quantitatively aligned with clinically relevant anatomical structures (optic cup, optic disc, retinal vessels). Paired t-tests and Pearson/Spearman correlation analyses demonstrate that all models significantly attend to these regions (p < 0.001), and the anatomical coverage ratio of attention maps strongly correlates with diagnostic accuracy (r > 0.8, p < 0.001). This work provides the first statistical evidence—spanning multiple models, explanation methods, and datasets—supporting the clinical credibility of XAI in ophthalmic diagnosis.

0 citationsRead paper