AI-Driven 2D Electric Field Distribution Estimation in a Human Breast Model Formed by a Line Source

AI-Driven Estimation of Electric Field Values from Reference Models via KNN algorithm

In this study, we examine the challenges of electromagnetic dosimetry, which are related to the accurate determination of the electric field distribution within biological phantoms. Traditional calculation methods lead to high measurement uncertainties. These uncertainties are due to the geometric complexity and the distribution of electromagnetic properties within these phantoms, which constitute significant obstacles. We propose a machine learning framework using k-nearest neighbor (KNN) regression to estimate and validate field values in cylindrical phantoms modeling human tissue structures. The results we obtain for intra-geometric predictions using multiple datasets demonstrate exceptional performance ( R 2 ≈ 0.99) for phantoms with the same elliptical cylindrical geometry, thanks to robust 5-fold cross-validation. This proves a near-perfect reconstruction of the complex components of the field when trained within identical geometric boundaries. However, inter-geometric extrapolation predicting fields from datasets combining different geometries, including ellipses and cylinders, reveals fundamental limitations. Indeed, the coefficient of determination ( R 2 ) drops significantly to approximately ≈ 0.55 due to intrinsic geometric dissimilarities that hinder the model's transferability. Exhaustive validation, using error analysis such as residual histograms and the superposition of predicted and measured values, consistently confirms these geometry-specific field characteristics. Our results highlight critical constraints in the development of universal dosimetry models. In particular, they underscore the need for geometry-adaptive machine learning architectures, which maintain excellent prediction accuracy for a given geometry while improving cross-domain generalization capabilities.

Fast and Robust IVIM Parameter Estimation in Breast MRI Using Physics-Informed Deep Learning

Lesion-Aware Adaptive Fourier Neural Operator for CT-to-PSMA PET Synthesis in Prostate Cancer

Deep learning models that synthesize PET from CT or MRI can reduce patient dose and scanner demand, but are typically optimized with global losses such as L1 or mean squared error (MSE) that treat all voxels similarly. In whole-body PSMA-PET, tumor voxels occupy only a small fraction of the volume, yet carry the clinically relevant activity signal; as a result, models can achieve high structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) while still underestimating lesion activity or failing to preserve tumor-specific structure. Radiomics provides biologically meaningful descriptors of tumor intensity and texture, but direct radiomics conditioning is time-consuming because it requires feature extraction from delineated lesion regions. We propose LAFNO, a Lesion-Aware Adaptive Fourier Neural Operator for CT-to-PSMA-PET synthesis that replaces high-dimensional radiomics conditioning with two efficient CT-derived proxy channels. Motivated by radiomics analysis of PSMA-avid tumor core and peritumoral regions, LAFNO uses a contrast proxy for local density variation and a disorder proxy for local texture heterogeneity, both injected into the model bottleneck. LAFNO combines whole-volume reconstruction with lesion-level total lesion activity (TLA), tumor-core contrast, and peritumoral supervision. We evaluated LAFNO against four baseline architectures on the TCIA PSMA-PET-CT-Lesions dataset. LAFNO remained competitive on whole-volume image quality, achieving SSIM of 0.960 and 0.938 for 18F- and 68Ga-PSMA, respectively, while reducing per-patient TLA error to 48.3% and 64.0% for 18F- and 68Ga-PSMA, respectively, and achieving the highest tumor-core radiomics reproducibility across all feature classes for both tracers. Peritumoral reproducibility remained tracer-dependent, indicating that biological fidelity in synthetic PSMA-PET remains challenging.

AI-Enhanced Hybrid Optimization and Deep Network Architecture for Noise Reduction in Low-Dose Medical Imaging

Low-dose computed tomography (LDCT) is a significant non-invasive imaging modality for disease diagnosis in early stages and clinical oncology. However, the reduction of radiation dose unavoidably introduces severe quantum noise, photon starvation and Poisson-Gaussian noise, which degrade contrast-to-noise ratio (CNR) and obscure subtle anatomical details. Recent advances in Artificial Intelligence (AI) have shown great promise in medical image restoration. However, pure deep learning methods often suffer from over-smoothing of fine structures and poor interpretability, while traditional non-convex variational models can preserve global edges, but are sensitive to the choice of parameters and produce staircasing artifacts. We propose an AI-empowered hybrid restoration framework that combines non-convex Total Variation (TV) optimization and a deep convolutional residual network within the Plug-and-Play (PnP) Alternating Direction Method of Multipliers (ADMM) framework to enjoy the complementary merits of the two paradigms. The AI based deep residual network can learn complex noise features and image priors efficiently. The optimization part keeps the structural fidelity and ensures the stable reconstruction. The proposed framework is tested on clinical lung CT slices from LIDC-IDRI benchmark dataset, and the experimental results show that the proposed framework achieves 33.97dB of Peak Signal-to-Noise Ratio (PSNR) and 0.918 of Structural Similarity Index Measure (SSIM) at noise level of σ=25. The experimental results show that the proposed AI-enabled hybrid model can better preserve structure edges, recover fine anatomical details and suppress noise compared with the traditional optimization methods and deep learning alone, which shows the effectiveness for low-dose medical image denoising.

Simulation-Based Imaging: Learning Acoustic Inverse Problems from Simulated Data

We introduce Simulation-Based Imaging (SBI), a framework for non-destructive acoustic imaging in which machine learning models trained entirely on simulated data serve as real-time solvers for the acoustic inverse problem. A high-fidelity nodal Discontinuous Galerkin forward solver generates large training datasets by randomizing inclusion geometry within a unit-cube domain; a 2D convolutional neural network then learns a direct mapping from boundary pressure measurements to a 32 by 32 by 32 voxel reconstruction of the interior. The trained model reliably recovers inclusion position and size from 144 boundary sensors with no prior knowledge of inclusion count or geometry. Reconstruction error degrades by only 13% under 5% additive measurement noise, and just 17% of the sensor array (24 of 144 sensors) suffices for quality within 4% of full coverage. These results establish SBI as a viable proof-of-concept imaging device whose complexity resides in software rather than hardware, opening a path toward cheap, portable, deployable imaging systems.

UNetrDose: a fast and accurate transformer-based dose prediction model for radiotherapy

Objective. To develop and validate UNetrDose, a Transformer-based deep learning model designed for fast and accurate photon beamlet dose prediction. The study aims to achieve Monte Carlo (MC)-level dosimetric accuracy using only CT-derived electron density images and beamlet coordinates as input, enabling the efficient reconstruction of complete 3D dose distributions for intensity-modulated radiation therapy (IMRT) plans. Approach. For each beamlet, a fixed-size 3D image patch was extracted along its propagation path, centered on the beamlet trajectory. The geometric information, defined as the beamlet’s relative position within the beam field, was used alongside the image patch as model input. The ground-truth dose distributions were generated using MC simulations. The proposed UNetrDose model combined convolutional layers for local feature extraction with Transformer modules to capture long-range dependencies. A total of 90 fixed-beam IMRT plans (51 esophageal and 39 rectal cases) were used for model training, validation, and testing. Model performance was comprehensively assessed, evaluating spatial accuracy with 3D gamma pass rates and clinical acceptability through dose-volume histogram comparisons and other dosimetric parameters. Main results. UNetrDose demonstrated high fundamental accuracy at the individual beamlet level, where pass rates for the stringent γ(1 mm, 1%) criterion exceeded 96% for both esophageal and rectal cases. This translated to excellent clinical performance on full IMRT plans, where the model achieved mean γ(2 mm, 2%) pass rates ranging from 97.06±2.05% for esophageal cases to 98.75±0.78% for rectal cases. The model was also highly efficient, with an average inference time of approximately 28 ms per beamlet. Significance. UNetrDose offers a promising alternative to traditional dose calculation engines by providing a balance between high dosimetric accuracy and fast computation. Its ability to predict dose distributions using only electron density images and beamlet positions simplifies the workflow, making it highly applicable for time-sensitive clinical scenarios.