abide

Fader Networks for domain adaptation on fMRI: ABIDE-II study

Automated blind MRI quality assessment using 3D CNN + FC deep learning. Trains on ABIDE-1 (15 sites), achieves SOTA transfer to novel sites and Glioblastoma MRI from TCIA.

Preparatory scripts for BIDS tabular phenotypic data in large neuroimaging datasets.

[MICCAIW 2025 Best Paper Award] BrainNetMLP for functional brain network classification

基于功能脑网络多模版学习的精神疾病辅助诊断算法研究

Multi-task learning of functional connectivity on the ABIDE dataset.

Replication code for 'The IQ-Motion Confound in Multi-Site Autism fMRI May Be Inflated by Site-Correlated Measurement Uncertainty' (Soliman, 2026). Errors-in-variables correction via Probability Cloud Regression on ABIDE-I.

ASD classification from resting-state fMRI using functional brain connectivity using Random Forest and 3D brain visualisation on ABIDE I.

3D CNN classification of Autism Spectrum Disorder from resting-state fMRI (ABIDE I, ReHo maps)

Dual-pathway deep QC for brain MRI: DNN on IQMs + ResNet-18 visual artifact extraction. Validated on ABIDE-1 and DS030 with GradCAM artifact localization.

B.Tech 2023 capstone — CNN vs Vision Transformer for ASD detection from structural MRI (ABIDE-I, 1,067 subjects). Established CNN baseline (AUC 0.978) and documented ViT failure from scratch. Foundation for graduate Phase 2.

Label-efficient learning on brain MRI and fMRI: bilateral self-supervised U-Net for tumour segmentation (BraTS/MSD) and a noise-aware connectome classifier for autism (ABIDE I), with a trust audit, Nextflow, Docker and Rust inference.

Controlled evaluation of complex-valued phase-coherence graph neural networks for autism classification from resting-state fMRI (ABIDE I/II): code, predictions and analysis

Graph-based classification of Autism Spectrum Disorder from resting-state fMRI functional connectivity data (ABIDE dataset, n=303)

Autism Prediciton model based on research paper

💀💭 Tool to visualise resting-state fMRI connectivity

ASD detection system built on the ABIDE neuroimaging dataset — multi-atlas feature extraction, tangent connectivity, and an MLP classifier achieving 76% accuracy and 0.818 AUC. Active development.

Code for Bachelor Thesis "Unveiling Hidden Features: Multimodal Integration Using Cross-Modal Variational Autoencoders for the Identification of Stratification in ABIDE"