Celebrating Neurodiversity Through Aesthetic Data Visualization
summary
Project claims that cortical-volume patterns separate by sex and by ASD status and that an interaction may mark female-specific differences. Analysis uses multidimensional scaling (MDS) then linear discriminant analysis (LDA) with Wilks’ lambda tests and intracranial-volume normalization to isolate diagnosis effects. Top contributing regions map to face, language, social and emotion areas. Workflow links FreeSurfer-derived atlases to R, exports models through PrusaSlicer and Houdini, and yields 300+ 3D-printed brain models as tangible visualizations for further biomarker and classifier development.
AI-written summary · about
chapters (19)
- 0:00Neurodiversity and brain data
- 0:49Autism and gender diagnosis gap
- 3:19Brain volume analysis goals
- 4:04Multidimensional scaling of brain data
- 6:11Linear discriminant analysis for classification
- 7:35IGEN values and gender differences
- 9:00Adjusting for cranial volume
- 10:473D printing brain models
- 13:36Process of brain model printing
- 14:22Brain regions in ASD diagnosis
- 15:27Discriminant weights to brain regions
- 16:11Gender differences in brain structure
- 16:55ASD brain regions and language
- 17:40Gender and ASD interaction
- 18:223D visualizations with age
- 19:11Future research and clinical uses
- 22:43Biases in ASD diagnosis data
- 23:48Data points to 3D brain models
- 26:20Q&A
related talks
01h 00mData, visualization, and designing AI
24mHow Enables Real Time Data With Event Driven Architecture
24mExploratory Data Analysis (EDA) and Visualization Techniques..
01h 20mMRI Brain Scan Classification Guide | FastSurfer, XGBoost, 3D CNNs
40mFrom healthcare.hospital import datascience
50mThe Shape of Data: Machine Learning and Topology
49mBuilding AI That Learns and Adapts: A Case Study in MRI Diagnostics
42mBuilding AI That Learns and Adapts: A Case Study in MRI Diagnostics