The biggest goal remains the same:
Keep learning and keep moving toward where the brain meets technology.
One month down. More to build.
https://t.co/1xTmAgR6aS
Day 30 of 30:
30 days of sharing my journey through neuroscience, research, and technology.
Projects worked on.
Papers read.
Skills developed.
Problems solved.
Mistakes made.
Lessons learned.
Day 29
What research problem are you currently working on?
It could be a scientific question, technical challenge, dataset, method, or research idea you're still developing.
I'd like to hear what researchers in my network are currently trying to solve.
https://t.co/KBYTTHzngB
Instead of immediately blaming the tool, I investigated the data, the assumptions, and the processing steps.
It taught me to understand the failure before looking for a fix.
https://t.co/JUBnskUuwU
Day 28: Research failure that improved my work
One research failure that improved my work:
Some MRI-derived 3D meshes weren't watertight enough for my downstream workflow.
Day 27: Open source tools every neuroscience researcher should know
Five open-source tools worth knowing in neuroscience:
1. FreeSurfer
2. https://t.co/GGnNn3IZ4g
3. NeuroJSON
4. iso2mesh
5. MNE-Python
Learn to troubleshoot.
Understand what you're measuring.
And don't rush to interpret an interesting pattern as a biological finding.
https://t.co/JyMgGG7Jfe
Day 26: What I wish I knew before starting MRI research
If I could go back to the beginning of my MRI research journey, I'd tell myself:
The scan is only the beginning.
Data quality matters.
Automated tools still need QC.
The workflow can be harder than the analysis.
Day 25: My roadmap toward graduate research
My long-term goal is simple:
Work where the brain meets technology.
I'm building toward it through neuroscience, neuroimaging, programming, AI, and computational research.
and hadn't done so in a long time.
That experience changed how I manage code.
Git started as a backup solution.
It became a development tool.
https://t.co/VYND9C9Pjw
Day 24: How I organize research projects using Git
I didn't start using Git because I understood version control.
I started because I lost my code.
A hard drive problem wiped out most of my early projects because I had been manually backing them up
where AI could reduce repetitive work.
But AI can find a pattern without understanding its biological meaning.
Scientific judgment still matters.
https://t.co/aaZVNsbRgH
Day 23: The future of AI in Neuroimaging π€
I don't think AI will replace neuroimaging researchers.
I think it will change what they spend their time doing.
Segmentation, quality control, pattern detection, metadata, and workflow automation are all areas
You don't need to master all five immediately.
But developing them alongside your neuroscience knowledge can make you a much more independent researcher.
https://t.co/QciOk9FYdo
Day 22: Five skills every neuroscience student should learn
Five skills I think every neuroscience student should develop:
1. Scientific reading
2. Statistics
3. Programming
4. Data visualization
5. Scientific communication
Check the input. Check the previous output. Check the environment. Check the dependency.
A workaround solves today's problem.
Understanding the cause can prevent tomorrow's.
https://t.co/63XbRUyLee
Day 21: One challenge I overcame
One research lesson I've learned from debugging neuroimaging workflows:
Don't just fix the error.
Find where the error actually came from.
Day 20: What neuroscience outreach taught me
Neuroscience outreach taught me that understanding something and explaining it are different skills.
The challenge isn't to remove the science.
It's to make the science understandable without making it inaccurate.