Interpretability and Individuality in Knee MRI: Patient-Specific Radiomic Fingerprint with Reconstructed Healthy Personas
Yaxi Chen, Simin Ni, Shuai Li, Shaheer U. Saeed, Aleksandra Ivanova, Rikin Hargunani, Jie Huang, Chaozong Liu, Yipeng Hu
TL;DR
This work tackles the challenge of interpretable knee MRI analysis by introducing patient-specific radiomic fingerprints and healthy personas. It combines an image-conditioned feature-usage predictor with population-level logistic coefficients to produce a transparent, subject-adaptive decision rule, formalized as $p(\mathbf{c}=1|\mathcal{I})=\sigma\left(\sum_{n=1}^N \beta_n \, u_n \, r_n\right)$. A diffusion-model-based healthy persona provides a per-ROI baseline for direct deviation analysis, with ROI-wise radiomic features extracted from pathologic, persona, and residual ROIs. Empirically, the approach achieves comparable or superior performance to state-of-the-art DL models while enabling multi-level interpretability; ablations reveal trade-offs between interpretability and sensitivity when incorporating higher-order texture features or the persona. The framework offers practical benefits for human-explainable biomarker discovery and localized pathology interpretation in knee MRI, with potential for adaptive view/patch strategies and broader clinical adoption.
Abstract
For automated assessment of knee MRI scans, both accuracy and interpretability are essential for clinical use and adoption. Traditional radiomics rely on predefined features chosen at the population level; while more interpretable, they are often too restrictive to capture patient-specific variability and can underperform end-to-end deep learning (DL). To address this, we propose two complementary strategies that bring individuality and interpretability: radiomic fingerprints and healthy personas. First, a radiomic fingerprint is a dynamically constructed, patient-specific feature set derived from MRI. Instead of applying a uniform population-level signature, our model predicts feature relevance from a pool of candidate features and selects only those most predictive for each patient, while maintaining feature-level interpretability. This fingerprint can be viewed as a latent-variable model of feature usage, where an image-conditioned predictor estimates usage probabilities and a transparent logistic regression with global coefficients performs classification. Second, a healthy persona synthesises a pathology-free baseline for each patient using a diffusion model trained to reconstruct healthy knee MRIs. Comparing features extracted from pathological images against their personas highlights deviations from normal anatomy, enabling intuitive, case-specific explanations of disease manifestations. We systematically compare fingerprints, personas, and their combination across three clinical tasks. Experimental results show that both approaches yield performance comparable to or surpassing state-of-the-art DL models, while supporting interpretability at multiple levels. Case studies further illustrate how these perspectives facilitate human-explainable biomarker discovery and pathology localisation.