MYMuhammad Nabi Yasinzai

Muhammad Nabi Yasinzai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Muhammad Nabi Yasinzai has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Synthesis with Modality and Metadata Conditioning

    by Muhammad Nabi Yasinzai, Remika Mito, Mangor Pedersen

    Multimodal MRI provides complementary information for neuroimaging analysis, with different modalities capturing distinct anatomical, tissue, and pathological features relevant to downstream artificial intelligence (AI) applications. Although large-scale structural MRI resources are increasingly available, modality coverage remains uneven across public and pooled neuroimaging datasets. Large pooled datasets span heterogeneous sites, scanners, and acquisition protocols and often contain incomplete or inconsistent demographic and clinical metadata. Synthetic MRI can supplement missing or underrepresented modalities and support metadata-conditioned synthetic cohorts. However, many existing approaches use limited modality combinations or relatively homogeneous datasets, limiting their applicability to heterogeneous pooled neuroimaging data. Diffusion models can generate high-fidelity, diverse MRI, but direct 3D voxel-space sampling is computationally expensive. Latent diffusion reduces this cost by generating in a compressed space, although information loss during compression can limit synthesis fidelity. We develop the Wavelet-Fusion Diffusion Model (WFDM), a 3D latent diffusion framework for multimodal brain MRI synthesis with target-modality and metadata conditioning. WFDM combines a Wavelet-Fusion variational autoencoder (WF-VAE) compressor with a conditional 3D U-Net diffusion model trained in the latent space. Training and evaluation use 45,880 preprocessed T1w, T2w, T1Gd, and FLAIR scans from 157 BrainScape datasets. Compared with the BrainScape-trained MAISI (Medical AI for Synthetic Imaging) baseline, WFDM reduced pooled MedicalNet feature-space Fréchet distance (FID) from 0.00550 to 0.00404 and pooled Maximum Mean Discrepancy (MMD) from 0.1918 to 0.1471 while maintaining comparable sample diversity. WFDM achieved lower FID and MMD for T1w, T2w, and FLAIR, whereas MAISI achieved lower values for T1Gd. Rectified Flow sampling with 50 steps was 12.4–13.4 times faster than 1000-step DDPM sampling while achieving the lowest pooled FID and MMD in the sampler ablation. In T1w MRI, WFDM also more closely preserved age- and sex-associated morphometric patterns, including age-group morphometric separation, regional age–volume associations, and male–female differences. We release BrainMint for brain MRI synthesis workflows and medmetric for standardized evaluation of 3D medical image synthesis models.

  • Open Access

    BrainScape: An open-source framework for integrating and preprocessing anatomical MRI datasets

    by Muhammad Nabi Yasinzai, Remika Mito, Mangor Pedersen

    MRI has revolutionized our ability to investigate and understand brain structure and function in health and disease. A large amount of MRI data is widely available to researchers, both from large-scale multi-site consortia and smaller site-specific datasets. This wealth of MRI data offers opportunities to advance our understanding of the brain, particularly through machine learning and deep learning approaches that rely on large sample sizes to reveal complex associations between brain organization and its behavioral and clinical associations. Many large-scale initiatives provide extensive datasets with sufficient statistical power to support reproducibility, but reproducibility alone does not ensure clinical relevance or broad generalizability due to narrow demographic representations and minimized dataset variability. Recent work highlights the need to embrace dataset variability and open-science collaborations for pooling heterogeneous datasets. Nevertheless, effectively integrating these diverse resources remains a significant challenge. Inconsistencies in organization, data formatting, acquisition protocols, and metadata remain, especially for smaller, site-specific datasets, despite ongoing efforts within the neuroimaging community to standardize data sharing practices. To address these issues, we introduce BrainScape: a curated collection of 160 publicly available MRI datasets packaged with an open-source, plugin-based Python framework that automates the download, organization, preprocessing, and demographic attachment of the MRI data. Each individual dataset includes a detailed configuration file capturing all dataset-specific parameters, enabling other researchers to regenerate the BrainScape dataset. The current BrainScape dataset integrates 160 datasets, encompassing a total of 27227 subjects and 46583 multimodal MRI scans after quality control. The BrainScape framework’s pipeline effectively aggregates these heterogeneous datasets while preserving the original dataset structure and demographic details. Its modular design allows integration into data pipelines, supporting large-scale studies involving diverse cohorts and targeted research on rare phenotypes. BrainScape framework employs an easy-to-use plugin-based architecture with distinct modules for data downloading, file mapping, validation, preprocessing, and demographics attachment. Furthermore, each MR image can be traced to its source project and repository, and subjects excluded from datasets are documented in dedicated dataset-specific configuration files, providing transparent and reproducible exclusion criteria. BrainScape dataset includes multiple MRI modalities such as T1-weighted (T1w), T2-weighted (T2w), gadolinium-enhanced T1-weighted (T1Gd), and fluid-attenuated inversion recovery (FLAIR) from diverse sources and integrates key demographic fields, such as age, sex, and handedness, for large-scale studies. This unified workflow reduces manual labor and minimizes the risk of data duplication and biases. By providing automated, transparent, and configurable workflows, BrainScape hopes to address open science challenges, accelerate data-driven investigations, and promote inclusivity and reproducibility in neuroscience research.

  • New approach for designing cVEP BCI stimuli based on superposition of edge responses

    by Muhammad Nabi Yasinzai, Yusuf Ziya Ider

    The purpose of this study is to develop a new methodology for designing stimulus sequences for Brain Computer Interfaces that utilize code modulated Visually Evoked Potentials (cVEP BCIs), based on experimental results regarding the behavior and the properties of the actual EEG responses of the visual system to binary-coded visual stimuli, such that training time is reduced and possible number of targets is increased. EEG from 8 occipital sites is recorded with 2000 sps, in response to visual stimuli presented on a computer monitor with 60 Hz refresh rate. EEG responses of the visual system to black-to-white and white-to-black transitions of a target area on the monitor are recorded for 500 ms, for 160 trials, and signal-averaged to obtain the onset (positive edge) and offset (negative edge) responses, respectively. It is found that both edge responses are delayed by 50 ms and wane completely within 350 ms. These edge responses are then used to generate (predict) the EEG responses to arbitrary binary stimulus sequences using the superposition principle. It is found that the generated and the measured EEG responses to certain (16) simple short sequences (16.67–350 ms) are highly correlated. These ‘optimal short patterns’ are then randomly combined to design the long (120 bit, 2 sec) ‘Superposition Optimized Pulse (SOP)’ sequences, and their EEG response templates are obtained by superposition of the edge responses. A SOP sequence-based Visual Speller BCI application yielded higher accuracy (95.9%) and Information Transfer Rate (ITR) (57.2 bpm), compared to when superposition principle is applied to conventional m-sequences and randomly generated sequences. Training for the BCI application involves only the acquisition of the edge responses and takes less than 4 min. This is the first study in which the EEG templates for cVEP BCI sequences are obtained by the superposition of edge responses.