AI-based neural decoding reconstructs visual perception by leveraging generative models to map brain activity measured through functional MRI (fMRI) into the observed visual stimulus. Traditionally, ridge linear models transform fMRI into a latent space, which is then decoded using variational autoencoders (VAE) or latent diffusion models (LDM). Owing to the complexity and noisiness of fMRI data, newer approaches split the reconstruction into two sequential stages, the first one providing a rough visual approximation using a VAE, the second one incorporating semantic information through the adoption of LDM guided by contrastive language-image pre-training (CLIP) embeddings. This work addressed some key scientific and technical gaps of the two-stage neural decoding by: 1) implementing a gated recurrent unit (GRU)-based architecture to establish a non-linear mapping between the fMRI signal and the VAE latent space, 2) optimizing the dimensionality of the VAE latent space, 3) systematically evaluating the contribution of the first reconstruction stage, and 4) analyzing the impact of different brain regions of interest (ROIs) on reconstruction quality. Experiments on the Natural Scenes Dataset, containing 73,000 unique natural images, along with fMRI of eight subjects, demonstrated that the proposed architecture maintained competitive performance while reducing the complexity of its first stage by 85%. The sensitivity analysis showcased that the first reconstruction stage is essential for preserving high structural similarity in the final reconstructions. Restricting analysis to semantic ROIs, while excluding early visual areas, diminished visual coherence, preserving semantics though. The inter-subject repeatability across ROIs was about 92 and 98% for visual and sematic metrics, respectively. This study represents a key step toward optimized neural decoding architectures leveraging non-linear models for stimulus prediction. Sensitivity analysis highlighted the interplay between the two reconstruction stages, while ROI-based analysis provided strong evidence that the two-stage AI model reflects the brain's hierarchical processing of visual information.

With the rapid development of artificial intelligence (AI), AI-assisted medical imaging analysis demonstrates remarkable performance in early lung cancer screening. However, the costly annotation process and privacy concerns limit the construction of large-scale medical datasets, hampering the further application of AI in healthcare. To address the data scarcity in lung cancer screening, we propose Lung-DDPM, a thoracic CT image synthesis approach that effectively generates high-fidelity 3D synthetic CT images, which prove helpful in downstream lung nodule segmentation tasks. Our method is based on semantic layout-guided denoising diffusion probabilistic models (DDPM), enabling anatomically reasonable, seamless, and consistent sample generation even from incomplete semantic layouts. Our results suggest that the proposed method outperforms other state-of-the-art (SOTA) generative models in image quality evaluation and downstream lung nodule segmentation tasks. Specifically, Lung-DDPM achieved superior performance on our large validation cohort, with a Fréchet inception distance (FID) of 0.0047, maximum mean discrepancy (MMD) of 0.0070, and mean squared error (MSE) of 0.0024. These results were 7.4×, 3.1×, and 29.5× better than the second-best competitors, respectively. Furthermore, the lung nodule segmentation model, trained on a dataset combining real and Lung-DDPM-generated synthetic samples, attained a Dice Coefficient (Dice) of 0.3914 and sensitivity of 0.4393. This represents 8.8% and 18.6% improvements in Dice and sensitivity compared to the model trained solely on real samples. The experimental results highlight Lung-DDPM's potential for a broader range of medical imaging applications, such as general tumor segmentation, cancer survival estimation, and risk prediction. The code and pretrained models are available at https://github.com/Manem-Lab/Lung-DDPM/.

Multi-Modal Medical Image Fusion (MMMIF) has become increasingly important in clinical applications, as it enables the integration of complementary information from different imaging modalities to support more accurate diagnosis and treatment planning. The primary objective of Medical Image Fusion (MIF) is to generate a fused image that retains the most informative features from the Source Images (SI), thereby enhancing the reliability of clinical decision-making systems. However, due to inherent limitations in individual imaging modalities-such as poor spatial resolution in functional images or low contrast in anatomical scans-fused images can suffer from information degradation or distortion. To address these limitations, this study proposes a novel fusion framework that integrates the Non-Subsampled Shearlet Transform (NSST) with a Convolutional Neural Network (CNN) for effective sub-band enhancement and image reconstruction. Initially, each source image is decomposed into Low-Frequency Coefficients (LFC) and multiple High-Frequency Coefficients (HFC) using NSST. The proposed Concurrent Denoising and Enhancement Network (CDEN) is then applied to these sub-bands to suppress noise and enhance critical structural details. The enhanced LFCs are fused using an AlexNet-based activity-level fusion model, while the enhanced HFCs are combined using a Pulse Coupled Neural Network (PCNN) guided by a Novel Sum-Modified Laplacian (NSML) metric. Finally, the fused image is reconstructed via Inverse-NSST (I-NSST). Experimental results prove that the proposed method outperforms existing fusion algorithms, achieving approximately 16.5% higher performance in terms of the QAB/F (edge preservation) metric, along with strong results across both subjective visual assessments and objective quality indices.

Acute ischemic stroke (AIS) is a leading cause of death and long-term disability worldwide, where rapid reperfusion remains critical for salvaging brain tissue. Although CT perfusion (CTP) imaging provides essential hemodynamic information, its limitations-including extended processing times, additional radiation exposure, and variable software outputs-can delay treatment. In contrast, non-contrast head CT (NCHCT) is ubiquitously available in acute stroke settings. This study explores a generative artificial intelligence approach to predict key perfusion parameters (relative cerebral blood flow [rCBF] and time-to-maximum [Tmax]) directly from NCHCT, potentially streamlining stroke imaging workflows and expanding access to critical perfusion data. We retrospectively identified patients evaluated for AIS who underwent NCHCT, CT angiography, and CTP. Ground truth perfusion maps (rCBF and Tmax) were extracted from VIZ.ai post-processed CTP studies. A modified pix2pix-turbo generative adversarial network (GAN) was developed to translate co-registered NCHCT images into corresponding perfusion maps. The network was trained using paired NCHCT-CTP data, with training, validation, and testing splits of 80%:10%:10%. Performance was assessed on the test set using quantitative metrics including the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and Fréchet inception distance (FID). Out of 120 patients, studies from 99 patients fitting our inclusion and exclusion criteria were used as the primary cohort (mean age 73.3 ± 13.5 years; 46.5% female). Cerebral occlusions were predominantly in the middle cerebral artery. GAN-generated Tmax maps achieved an SSIM of 0.827, PSNR of 16.99, and FID of 62.21, while the rCBF maps demonstrated comparable performance (SSIM 0.79, PSNR 16.38, FID 59.58). These results indicate that the model approximates ground truth perfusion maps to a moderate degree and successfully captures key cerebral hemodynamic features. Our findings demonstrate the feasibility of generating functional perfusion maps directly from widely available NCHCT images using a modified GAN. This cross-modality approach may serve as a valuable adjunct in AIS evaluation, particularly in resource-limited settings or when traditional CTP provides limited diagnostic information. Future studies with larger, multicenter datasets and further model refinements are warranted to enhance clinical accuracy and utility.

Generative artificial intelligence models facilitate open-data sharing by proposing synthetic data as surrogates of real patient data. Despite the promise for healthcare, some of these models are susceptible to patient data memorization, where models generate patient data copies instead of novel synthetic samples, resulting in patient re-identification. Here we assess memorization in unconditional latent diffusion models by training them on a variety of datasets for synthetic data generation and detecting memorization with a self-supervised copy detection approach. We show a high degree of patient data memorization across all datasets, with approximately 37.2% of patient data detected as memorized and 68.7% of synthetic samples identified as patient data copies. Latent diffusion models are more susceptible to memorization than autoencoders and generative adversarial networks, and they outperform non-diffusion models in synthesis quality. Augmentation strategies during training, small architecture size and increasing datasets can reduce memorization, while overtraining the models can enhance it. These results emphasize the importance of carefully training generative models on private medical imaging datasets and examining the synthetic data to ensure patient privacy.

To visualize and assess hematoma growth trends by generating follow-up CT images within 24 h based on baseline CT images of spontaneous intracerebral hemorrhage (sICH) using Transformer-integrated Generative Adversarial Networks (GAN). Patients with sICH were retrospectively recruited from two medical centers. The imaging data included baseline non-contrast CT scans taken after onset and follow-up imaging within 24 h. In the test set, the peak signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM) were utilized to quantitatively assess the quality of the predicted images. Pearson's correlation analysis was performed to assess the agreement of semantic features and geometric properties of hematomas between true follow-up CT images and the predicted images. The consistency of hematoma expansion prediction between true and generated images was further examined. The PSNR of the predicted images was 26.73 ± 1.11, and the SSIM was 91.23 ± 1.10. The Pearson correlation coefficients (r) with 95 % confidence intervals (CI) for irregularity, satellite sign number, intraventricular or subarachnoid hemorrhage, midline shift, edema expansion, mean CT value, maximum cross-sectional area, and hematoma volume between the predicted and true follow-up images were as follows: 0.94 (0.91, 0.96), 0.87 (0.81, 0.91), 0.86 (0.80, 0.91), 0.89 (0.84, 0.92), 0.91 (0.87, 0.94), 0.78(0.68, 0.84), 0.94(0.91, 0.96), and 0.94 (0.91, 0.96), respectively. The correlation coefficient (r) for predicting hematoma expansion between predicted and true follow-up images was 0.86 (95 % CI: 0.79, 0.90; P < 0.001). The model constructed using a GAN integrated with Transformer modules can accurately visualize early hematoma changes in sICH.

Iron and myelin are key biomarkers for studying neurodegenerative and demyelinating brain diseases. Multi-contrast MRI techniques, such as R2* and QSM, are commonly used for iron assessment, with histology as the reference standard, but non-invasive myelin assessment remains challenging. To address this, we developed a deep learning model to generate iron and myelin staining images from in vivo multi-contrast MRI data, with a resolution comparable to ex vivo histology macro-scans. A cadaver head was scanned using a 7T MR scanner to acquire T1-weighted and multi-echo GRE data for R2*, and QSM processing, followed by histological staining for myelin and iron. To evaluate the generalizability of the model, a second cadaver head and two in vivo MRI datasets were included. After MRI-to-histology registration in the training subject, a self-attention generative adversarial network (GAN) was trained to synthesize myelin and iron staining images using various combinations of MRI contrast. The model achieved optimal myelin prediction when combining T1w, R2*, and QSM images. Incorporating the synthesized myelin images improved the subsequent prediction of iron staining. The generated images displayed fine details similar to those in histology data and demonstrated generalizability across healthy control subjects. Synthesized myelin images clearly differentiated myelin concentration between white and gray matter, while synthesized iron staining presented distinct patterns such as particularly high deposition in deep gray matter. This study shows that deep learning can transform MRI data into histological feature images, offering ex vivo insights from in vivo data and contributing to advancements in brain histology research.

To evaluate the utility of a deep learning (DL)-based image enhancement for improving the image quality and diagnostic performance of 3D contrast-enhanced T1-weighted black blood (BB) MR imaging for brain metastases. This retrospective study included 126 patients with and 121 patients without brain metastasis who underwent 3-T MRI examinations. Commercially available DL-based MR image enhancement software was utilized for image post-processing. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of enhancing lesions were measured. For qualitative assessment and diagnostic performance evaluation, two radiologists graded the overall image quality, noise, and artifacts of each image and the conspicuity of visible lesions. The Wilcoxon signed-rank test and regression analyses with generalized estimating equations (GEEs) were used for statistical analysis. For MR images that were not previously processed using other DL-based methods, SNR and CNR were higher in the DL-enhanced images than in the standard images (438.3 vs. 661.1, p < 0.01; 173.9 vs. 223.5, p < 0.01). Overall image quality and noise were improved in the DL images (p < 0.01, average score-5 proportion 38% vs. 65%; p < 0.01, 43% vs. 74%), whereas artifacts did not significantly differ (p ≥ 0.07). Sensitivity was increased after post-processing from 79 to 86% (p = 0.02), especially for lesions smaller than 5 mm (69 to 78%, p = 0.03), and changes in specificity (p = 0.24) and average false-positive (FP) count (p = 0.18) were not significant. DL image enhancement improves the image quality and diagnostic performance of 3D contrast-enhanced T1-weighted BB MR imaging for the detection of small brain metastases. Question Can deep learning (DL)-based image enhancement improve the image quality and diagnostic performance of 3D contrast-enhanced T1-weighted black blood (BB) MR imaging for brain metastases? Findings DL-based image enhancement improved image quality of thin slice BB MR images and sensitivity for brain metastasis, particularly for lesions smaller than 5 mm. Clinical relevance DL-based image enhancement on BB images may assist in the accurate diagnosis of brain metastasis by achieving better sensitivity while maintaining comparable specificity.

Brain volume measurement serves as a critical approach for assessing brain health status. Considering the close biological connection between the eyes and brain, this study aims to investigate the feasibility of estimating brain volume through retinal fundus imaging integrated with clinical metadata, and to offer a cost-effective approach for assessing brain health. Based on clinical information, retinal fundus images, and neuroimaging data derived from a multicenter, population-based cohort study, the KaiLuan Study, we proposed a cross-modal correlation representation (CMCR) network to elucidate the intricate co-degenerative relationships between the eyes and brain for 755 subjects. Specifically, individual clinical information, which has been followed up for as long as 12 years, was encoded as a prompt to enhance the accuracy of brain volume estimation. Independent internal validation and external validation were performed to assess the robustness of the proposed model. Root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) metrics were employed to quantitatively evaluate the quality of synthetic brain images derived from retinal imaging data. The proposed framework yielded average RMSE, PSNR, and SSIM values of 98.23, 35.78 dB, and 0.64, respectively, which significantly outperformed 5 other methods: multi-channel Variational Autoencoder (mcVAE), Pixel-to-Pixel (Pixel2pixel), transformer-based U-Net (TransUNet), multi-scale transformer network (MT-Net), and residual vision transformer (ResViT). The two- (2D) and three-dimensional (3D) visualization results showed that the shape and texture of the synthetic brain images generated by the proposed method most closely resembled those of actual brain images. Thus, the CMCR framework accurately captured the latent structural correlations between the fundus and the brain. The average difference between predicted and actual brain volumes was 61.36 cm³, with a relative error of 4.54%. When all of the clinical information (including age and sex, daily habits, cardiovascular factors, metabolic factors, and inflammatory factors) was encoded, the difference was decreased to 53.89 cm³, with a relative error of 3.98%. Based on the synthesized brain MR images from retinal fundus images, the volumes of brain tissues could be estimated with high accuracy. This study provides an innovative, accurate, and cost-effective approach to characterize brain health status through readily accessible retinal fundus images. NCT05453877 ( https://clinicaltrials.gov/ ).

&#xD;Computed tomography perfusion (CTP) imaging is a rapid diagnostic tool for acute stroke but is less robust when tissue time-attenuation curves are truncated. This study proposes an unsupervised learning method for generating perfusion maps from truncated CTP images. Real brain CTP images were artificially truncated to 15% and 30% of the original scan time. Perfusion maps of complete and truncated CTP images were calculated using the proposed method and compared with standard singular value decomposition (SVD), tensor total variation (TTV), nonlinear regression (NLR), and spatio-temporal perfusion physics-informed neural network (SPPINN).&#xD;Main results.&#xD;The NLR method yielded many perfusion values outside physiological ranges, indicating a lack of robustness. The proposed method did not improve the estimation of cerebral blood flow compared to both the SVD and TTV methods, but reduced the effect of truncation on the estimation of cerebral blood volume, with a relative difference of 15.4% in the infarcted region for 30% truncation (20.7% for SVD and 19.4% for TTV). The proposed method also showed better resistance to 30% truncation for mean transit time, with a relative difference of 16.6% in the infarcted region (25.9% for SVD and 26.2% for TTV). Compared to the SPPINN method, the proposed method had similar responses to truncation in gray and white matter, but was less sensitive to truncation in the infarcted region. These results demonstrate the feasibility of using unsupervised learning to generate perfusion maps from CTP images and improve robustness under truncation scenarios.&#xD.