Deep-learning background field removal (BFRnet): a 3D dual-frequency octave-convolution U-net trained to predict the background field of the brain — including brains with significant pathological susceptibility sources (haemorrhage, calcification). Consumes the total field (ppm) and predicts the background field; the local tissue field is total − background, masked. The authors' trained MATLAB network was exported to ONNX and is run here with ONNX Runtime — no MATLAB Runtime — reproducing the MATLAB output to ~1e-8 at a fraction of the memory and image size. QSM-CI reconstruction method bfrnet. Browse and run it at https://qsmxt.github.io/QSM-CI/submission.html?method=bfrnet.
INR-QSM — a subject-specific UNSUPERVISED deep-learning dipole inversion using an implicit neural representation. No pretrained weights: a sine-activated coordinate MLP (SIREN) is OPTIMIZED per-subject so that the susceptibility it represents, pushed through the QSM dipole forwar…
This record provides the complete code, frozen configurations, calibration and test seeds, raw episode- and step-level logs, processed tables, statistical outputs, figures, environment manifests, checksums, and a self-contained Google Colab workflow for a reviewer-requested compa…
Background. Post-marketing pharmacovigilance depends on the timely identification of serious individual case safety reports (ICSRs) from large spontaneous-reporting databases such as the FDA Adverse Event Reporting System (FAERS). Machine-learning triage has been proposed to prio…
These are the data and results reported in the paper "A probabilistic digital twin framework for corrosion-fatigue prognosis of floating offshore wind turbines".
Personalized learning is increasingly essential in higher education due to variations in student abilities, learning pace, and academic preparedness. This paper presents EduMentor-AI, a hybrid adaptive intelligence model designed to support personalized learning through the integ…
Self-supervised deep learning has emerged as a powerful method for image enhancement when a priori ground-truth references are not available. Stemming from Noise2Noise , it was shown that a convolutional neural network (CNN) can be trained from a noisy input and target pair of th…