Uncertainty-gated refinement boosts depression diagnosis from MRI scans
Uncertainty-Gated SHAP-Dirichlet Refinement for MRI-Based Depression Classification
Machine Learning
Summary
Diagnosing major depressive disorder from brain scans is difficult because changes in the brain are subtle and varied. The authors propose a method that improves existing computer predictions by double-checking and adjusting uncertain cases using explanations of similar cases, without retraining the original model. This approach also identifies which cases are unreliable and need expert review, improving overall accuracy, especially for low-confidence predictions. Their tests on brain scan data showed the method helps some types of classifiers work better and makes their confidence scores more trustworthy.
What this means in practice
- •For medical imaging teams: Improve MRI-based depression prediction accuracy by refining uncertain model outputs without retraining.
- •For clinical decision support teams: Enable triage of uncertain MRI cases by deferring low-confidence predictions for expert review to increase reliability.
Authors
Phuc Truong Loc Nguyen, Nguyen Truong Toan To, Truong Thanh Hung Nguyen, Hoang-Loc Cao, Hung Cao
Abstract
Structural MRI-based classification of major depressive disorder (MDD) remains challenging due to subtle, heterogeneous anatomical changes. We propose uncertainty-gated SHAP-Dirichlet refinement, a post-hoc reliability layer that improves predictions without retraining the classifier. The method retrieves similar labeled SHAP explanations, constructs Dirichlet class evidence, and selectively refines uncertain predictions through probabilistic fusion, while allowing unreliable cases to be deferred for expert review. We evaluate five classifiers on 504 SRPBS subjects (252 controls and 252 MDD patients) using 159 anatomical features and repeated nested cross-validation. Refinement improved accuracy across all 8 repetitions for TabM and ResNet, yielding mean gains of 1.04 and 0.45 percentage points (sign test p=0.008), while modifying at most 8.3% of predictions. Gains were concentrated among low-confidence cases, with significant improvements in calibration. The method also benefited an RBF support vector machine but not logistic regression or random forests. Ablations confirmed the importance of uncertainty gating and soft fusion. Dirichlet evidence identified baseline errors (AUROC 0.62), while deferring 50% of cases increased retained-case accuracy to approximately 75%. These findings support selective explanation-guided refinement as a practical approach to improving prediction reliability and facilitating expert triage in MDD classification.