[¹⁸F]FDG PET/CT scan combined with [¹⁸F]PSMA-1007 PET/CT scan is commonly conducted for detecting bone metastases in prostate cancer (PCa). However, it is expensive and may expose patients to more radiation hazards. This study explores deep learning (DL) techniques to synthesize [¹⁸F]PSMA-1007 PET bone images from CT bone images for the early detection of bone metastases in PCa, which may reduce additional PET/CT scans and relieve the burden on patients. We retrospectively collected paired whole-body (WB) [¹⁸F]PSMA-1007 PET/CT images from 152 patients with clinical and pathological diagnosis results, including 123 PCa and 29 cases of benign lesions. The average age of the patients was 67.48 ± 10.87 years, and the average lesion size was 8.76 ± 15.5 mm. The paired low-dose CT and PET images were preprocessed and segmented to construct the WB bone structure images. 152 subjects were randomly stratified into training, validation, and test groups in the number of 92:41:19. Two generative adversarial network (GAN) models-Pix2pix and Cycle GAN-were trained to synthesize [¹⁸F]PSMA-1007 PET bone images from paired CT bone images. The performance of two synthesis models was evaluated using quantitative metrics of mean absolute error (MAE), mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index metrics (SSIM), as well as the target-to-background ratio (TBR). The results of DL-based image synthesis indicated that the synthesis of [¹⁸F]PSMA-1007 PET bone images from low-dose CT bone images was highly feasible. The Pix2pix model performed better with an SSIM of 0.97, PSNR of 44.96, MSE of 0.80, and MAE of 0.10, respectively. The TBRs of bone metastasis lesions calculated on DL-synthesized PET bone images were highly correlated with those of real PET bone images (Pearson's r > 0.90) and had no significant differences (p < 0.05). It is feasible to generate synthetic [¹⁸F]PSMA-1007 PET bone images from CT bone images by using DL techniques with reasonable accuracy, which can provide information for early detection of PCa bone metastases.

The progress of artificial intelligence (AI) research in dental medicine is hindered by data acquisition challenges and imbalanced distributions. These problems are especially apparent when planning to develop AI-based diagnostic or analytic tools for various lesions, such as maxillary sinus lesions (MSL) including mucosal thickening and polypoid lesions. Traditional unsupervised generative models struggle to simultaneously control the image realism, diversity, and lesion-type specificity. This study establishes an expert-guided framework to overcome these limitations to elevate AI-based diagnostic accuracy. A StyleGAN2 framework was developed for generating clinically relevant MSL images (such as mucosal thickening and polypoid lesion) under expert control. The generated images were then integrated into training datasets to evaluate their effect on ResNet50's diagnostic performance. Here we show: 1) Both lesion subtypes achieve satisfactory fidelity metrics, with structural similarity indices (SSIM > 0.996) and maximum mean discrepancy values (MMD < 0.032), and clinical validation scores close to those of real images; 2) Integrating baseline datasets with synthetic images significantly enhances diagnostic accuracy for both internal and external test sets, particularly improving area under the precision-recall curve (AUPRC) by approximately 8% and 14% for mucosal thickening and polypoid lesions in the internal test set, respectively. The StyleGAN2-based image generation tool effectively addressed data scarcity and imbalance through high-quality MSL image synthesis, consequently boosting diagnostic model performance. This work not only facilitates AI-assisted preoperative assessment for maxillary sinus lift procedures but also establishes a methodological framework for overcoming data limitations in medical image analysis.

Brain-to-image decoding has been recently propelled by the progress in generative AI models and the availability of large ultra-high field functional Magnetic Resonance Imaging (fMRI). However, current approaches depend on complicated multi-stage pipelines and preprocessing steps that typically collapse the temporal dimension of brain recordings, thereby limiting time-resolved brain decoders. Here, we introduce Dynadiff (Dynamic Neural Activity Diffusion for Image Reconstruction), a new single-stage diffusion model designed for reconstructing images from dynamically evolving fMRI recordings. Our approach offers three main contributions. First, Dynadiff simplifies training as compared to existing approaches. Second, our model outperforms state-of-the-art models on time-resolved fMRI signals, especially on high-level semantic image reconstruction metrics, while remaining competitive on preprocessed fMRI data that collapse time. Third, this approach allows a precise characterization of the evolution of image representations in brain activity. Overall, this work lays the foundation for time-resolved brain-to-image decoding.

Transcranial focused ultrasound (tFUS) is an emerging modality for non-invasive brain stimulation and therapeutic intervention, offering millimeter-scale spatial precision and the ability to target deep brain structures. However, the heterogeneous and anisotropic nature of the human skull introduces significant distortions to the propagating ultrasound wavefront, which require time-consuming patient-specific planning and corrections using numerical solvers for accurate targeting. To enable data-driven approaches in this domain, we introduce TFUScapes, the first large-scale, high-resolution dataset of tFUS simulations through anatomically realistic human skulls derived from T1-weighted MRI images. We have developed a scalable simulation engine pipeline using the k-Wave pseudo-spectral solver, where each simulation returns a steady-state pressure field generated by a focused ultrasound transducer placed at realistic scalp locations. In addition to the dataset, we present DeepTFUS, a deep learning model that estimates normalized pressure fields directly from input 3D CT volumes and transducer position. The model extends a U-Net backbone with transducer-aware conditioning, incorporating Fourier-encoded position embeddings and MLP layers to create global transducer embeddings. These embeddings are fused with U-Net encoder features via feature-wise modulation, dynamic convolutions, and cross-attention mechanisms. The model is trained using a combination of spatially weighted and gradient-sensitive loss functions, enabling it to approximate high-fidelity wavefields. The TFUScapes dataset is publicly released to accelerate research at the intersection of computational acoustics, neurotechnology, and deep learning. The project page is available at https://github.com/CAMMA-public/TFUScapes.

This study aims to investigate the feasibility of a single general model to synthesize CT images across body sites, thorax, abdomen, and pelvis, to support treatment planning for MRI-only radiotherapy. A total of 157 patients who received MRI-guided radiation therapy in the thorax, abdomen, and pelvis on a 0.35T MRIdian Linac were included. A subset of 122 cases were used for model training and the remaining 35 cases were used for model validation. All patient datasets had semi-paired CT-simulation image and 0.35T MR image acquired using TrueFISP. A conditional generative adversarial network with a multi-planar method was used to generate synthetic CT images from 0.35T MR images. The effect of preprocessing methods (with and without bias field corrections) on the quality of synthetic CT was evaluated and found to be insignificant. The general models trained on all cases performed comparably to the site-specific models trained on individual body sites. For all models, the peak signal-to-noise ratios ranged from 31.7 to 34.9 and the structural index similarity measures ranged from 0.9547 to 0.9758. For the datasets with bias field corrections, the mean-absolute-errors in HU (general model versus site-specific model) were 49.7 ± 9.4 versus 49.5 ± 8.9, 48.7 ± 7.6 versus 43 ± 7.8 and 32.8 ± 5.5 versus 31.8 ± 5.3 for the thorax, abdomen, and pelvis, respectively. When comparing plans between synthetic CTs and ground truth CTs, the dosimetric difference was on average less than 0.5% (0.2 Gy) for target coverage and less than 2.1% (0.4 Gy) for organ-at-risk metrics for all body sites with either the general or specific models. Synthetic CT plans showed good agreement with mean gamma pass rates of >94% and >99% for 1%/1 mm and 2%/2 mm, respectively. This study has demonstrated the feasibility of using a general model for multiple body sites and the potential of using synthetic CT to support an MRI-guided radiotherapy workflow.

Multimodal medical image fusion plays a crucial role in medical diagnosis by integrating complementary information from different modalities to enhance image readability and clinical applicability. However, existing methods mainly follow computer vision standards for feature extraction and fusion strategy formulation, overlooking the rich semantic information inherent in medical images. To address this limitation, we propose a novel semantic-guided medical image fusion approach that, for the first time, incorporates medical prior knowledge into the fusion process. Specifically, we construct a publicly available multimodal medical image-text dataset, upon which text descriptions generated by BiomedGPT are encoded and semantically aligned with image features in a high-dimensional space via a semantic interaction alignment module. During this process, a cross attention based linear transformation automatically maps the relationship between textual and visual features to facilitate comprehensive learning. The aligned features are then embedded into a text-injection module for further feature-level fusion. Unlike traditional methods, we further generate diagnostic reports from the fused images to assess the preservation of medical information. Additionally, we design a medical semantic loss function to enhance the retention of textual cues from the source images. Experimental results on test datasets demonstrate that the proposed method achieves superior performance in both qualitative and quantitative evaluations while preserving more critical medical information.

Multi-modal medical image fusion (MMIF) is increasingly recognized as an essential technique for enhancing diagnostic precision and facilitating effective clinical decision-making within computer-aided diagnosis systems. MMIF combines data from X-ray, MRI, CT, PET, SPECT, and ultrasound to create detailed, clinically useful images of patient anatomy and pathology. These integrated representations significantly advance diagnostic accuracy, lesion detection, and segmentation. This comprehensive review meticulously surveys the evolution, methodologies, algorithms, current advancements, and clinical applications of MMIF. We present a critical comparative analysis of traditional fusion approaches, including pixel-, feature-, and decision-level methods, and delves into recent advancements driven by deep learning, generative models, and transformer-based architectures. A critical comparative analysis is presented between these conventional methods and contemporary techniques, highlighting differences in robustness, computational efficiency, and interpretability. The article addresses extensive clinical applications across oncology, neurology, and cardiology, demonstrating MMIF's vital role in precision medicine through improved patient-specific therapeutic outcomes. Moreover, the review thoroughly investigates the persistent challenges affecting MMIF's broad adoption, including issues related to data privacy, heterogeneity, computational complexity, interpretability of AI-driven algorithms, and integration within clinical workflows. It also identifies significant future research avenues, such as the integration of explainable AI, adoption of privacy-preserving federated learning frameworks, development of real-time fusion systems, and standardization efforts for regulatory compliance.

Synthetic MRI (SyMRI) is a technique used to estimate tissue properties and generate multiple MR sequence contrasts from a single acquisition. However, image quality can be suboptimal. To evaluate a neural network approach using artificial intelligence-based direct contrast synthesis (AI-DCS) of the multi-contrast weighted images to improve image quality. This prospective, IRB approved study enrolled 50 pediatric patients undergoing clinical brain MRI. In addition to the standard of care (SOC) clinical protocol, 2D multi-delay multi-echo (MDME) sequence was obtained. SOC 3D T1-weighted (T1W), 2D T2-weighted (T2W) and 2D T2W fluid-attenuated inversion recovery (FLAIR) images from 35 patients were used to train a neural network generating synthetic T1W, T2W, and FLAIR images. Quantitative analysis of grey matter (GM) and white matter (WM) apparent signal to noise (aSNR) and grey-white matter (GWM) apparent contrast to noise (aCNR) ratios was performed. 8 patients were evaluated. When compared to SyMRI, T1W AI-DCS had better overall image quality, reduced noise/artifacts, and better subjective SNR in 100 % (16/16) of evaluations. When compared to SyMRI, T2W AI-DCS overall image quality and diagnostic confidence was better in 93.8 % (15/16) and 87.5 % (14/16) of evaluations, respectively. When compared to SyMRI, FLAIR AI-DCS was better in 93.8 % (15/16) of evaluations in overall image quality and in 100 % (16/16) of evaluations for noise/artifacts and subjective SNR. Quantitative analysis revealed higher WM aSNR compared with SyMRI (p < 0.05) for T1W, T2W and FLAIR. AI-DCS demonstrates better overall image quality than SyMRI on T1W, T2W and FLAIR.

We introduce CheXGenBench, a rigorous and multifaceted evaluation framework for synthetic chest radiograph generation that simultaneously assesses fidelity, privacy risks, and clinical utility across state-of-the-art text-to-image generative models. Despite rapid advancements in generative AI for real-world imagery, medical domain evaluations have been hindered by methodological inconsistencies, outdated architectural comparisons, and disconnected assessment criteria that rarely address the practical clinical value of synthetic samples. CheXGenBench overcomes these limitations through standardised data partitioning and a unified evaluation protocol comprising over 20 quantitative metrics that systematically analyse generation quality, potential privacy vulnerabilities, and downstream clinical applicability across 11 leading text-to-image architectures. Our results reveal critical inefficiencies in the existing evaluation protocols, particularly in assessing generative fidelity, leading to inconsistent and uninformative comparisons. Our framework establishes a standardised benchmark for the medical AI community, enabling objective and reproducible comparisons while facilitating seamless integration of both existing and future generative models. Additionally, we release a high-quality, synthetic dataset, SynthCheX-75K, comprising 75K radiographs generated by the top-performing model (Sana 0.6B) in our benchmark to support further research in this critical domain. Through CheXGenBench, we establish a new state-of-the-art and release our framework, models, and SynthCheX-75K dataset at https://raman1121.github.io/CheXGenBench/

Positron emission tomography with 2-deoxy-2-[fluorine-18]fluoro-D-glucose integrated with computed tomography (18F-FDG PET-CT) is a multi-modality medical imaging technique widely used for screening and diagnosis of lesions and tumors, in which, CT can provide detailed anatomical structures, while PET can show metabolic activities. Nevertheless, it has disadvantages such as long scanning time, high cost, and relatively high radiation doses.&#xD;&#xD;Purpose: We propose a deep learning model for the whole-body CT-to-PET synthesis task, generating high-quality synthetic PET images that are comparable to real ones in both clinical relevance and diagnostic value.&#xD;&#xD;Material: We collect 102 pairs of 3D CT and PET scans, which are sliced into 27,240 pairs of 2D CT and PET images ( training: 21,855 pairs, validation: 2,810, testing: 2,575 pairs).&#xD;&#xD;Methods: We propose a Transformer-enhanced Generative Adversarial Network (GAN) for whole-body CT-to-PET synthesis task. The CPGAN model uses residual blocks and Fully Connected Transformer Residual (FCTR) blocks to capture both local features and global contextual information. A customized loss function incorporating structural consistency is designed to improve the quality of synthesized PET images.&#xD;&#xD;Results: Both quantitative and qualitative evaluation results demonstrate effectiveness of the CPGAN model. The mean and standard variance of NRMSE,PSNR and SSIM values on test set are (16.90 ± 12.27) × 10-4, 28.71 ± 2.67 and 0.926 ± 0.033, respectively, outperforming other seven state-of-the-art models. Three radiologists independently and blindly evaluated and gave subjective scores to 100 randomly chosen PET images (50 real and 50 synthetic). By Wilcoxon signed rank test, there are no statistical differences between the synthetic PET images and the real ones.&#xD;&#xD;Conclusions: Despite the inherent limitations of CT images to directly reflect biological information of metabolic tissues, CPGAN model effectively synthesizes satisfying PET images from CT scans, which has potential in reducing the reliance on actual PET-CT scans.