{"slug": "electric-evidential-learning-enhanced-ct-reconstruction-via-iterative-correction", "title": "ELECTRIC: Evidential Learning-Enhanced CT Reconstruction via Iterative Correction", "summary": "Researchers introduced ELECTRIC (Evidential Learning-Enhanced CT Reconstruction via Iterative Correction), a physics-guided Bayesian method that uses an evidential neural network to iteratively reconstruct CT images. In simulations on the AAPM Mayo Clinic Low-Dose CT dataset, the learned prior mean reduced reconstruction error by roughly 70% relative to filtered back-projection, and the adaptive-precision reconstruction matched or exceeded a fixed prior while being more robust to prior-strength misspecification.", "body_md": "arXiv:2608.00060v1 Announce Type: new\nAbstract: Here we introduce ELECTRIC (Evidential Learning-Enhanced CT Reconstruction via Iterative Correction), a physics-guided Bayesian formulation. An evidential neural network provides an image proposal and an error-predictive epistemic-uncertainty surrogate. The latter is converted into an adaptive precision field and inserted into a Poisson-weighted MAP update. The resulting image-evidence-precision-reconstruction loop treats prior confidence as a learned state variable of iterative reconstruction. In addition to the formulation and theoretical analysis, we report two simulation studies on image slices from the AAPM Mayo Clinic Low-Dose CT dataset: a mechanism-validation pilot using transparent surrogate estimators, and a feasibility study in which a trained Normal-Inverse-Gamma evidential network drives the full closed loop. On held-out patients, the learned prior mean reduces reconstruction error by roughly 70 percent relative to filtered back-projection, the learned epistemic uncertainty is error-predictive and supports selective trust, and the physics-guided update restores measurement consistency while the adaptive-precision reconstruction matches or exceeds a validation-tuned fixed prior and remains markedly more robust to prior-strength misspecification. Together these results demonstrate the complete ELECTRIC closed-loop pipeline, while identifying formal uncertainty calibration and joint training as the principal directions for future work.", "url": "https://wpnews.pro/news/electric-evidential-learning-enhanced-ct-reconstruction-via-iterative-correction", "canonical_source": "https://arxiv.org/abs/2608.00060", "published_at": "2026-08-04 04:00:00+00:00", "updated_at": "2026-08-04 04:38:05.434099+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision"], "entities": ["ELECTRIC", "AAPM Mayo Clinic Low-Dose CT dataset"], "alternates": {"html": "https://wpnews.pro/news/electric-evidential-learning-enhanced-ct-reconstruction-via-iterative-correction", "markdown": "https://wpnews.pro/news/electric-evidential-learning-enhanced-ct-reconstruction-via-iterative-correction.md", "text": "https://wpnews.pro/news/electric-evidential-learning-enhanced-ct-reconstruction-via-iterative-correction.txt", "jsonld": "https://wpnews.pro/news/electric-evidential-learning-enhanced-ct-reconstruction-via-iterative-correction.jsonld"}}