I'm looking at your bones and goo

Student radiographer working in a hospital and hoping to become an Advanced Practitioner in. Um. I haven't decided yet. This blog is for education & entertainment, but I am not an authority! I just love the subject.

[radioactiveradley]

Nyello! I'm B.L.Radley, also known as @blradley, also known as 'that person who decided to become a radiographer on a whim literally so they could introduce themselves as Rad the Rad but then got really fucking obsessed with radiography and ology and now wants to commit themselves to several more years of specialised study and student debts to become an Advanced Practitioner in.... MRI, probably, but who the heck knows'

Important info:

They/it/xe pronouns plz.

'Rad' on this blog refers ONLY to radiographers and surfer-slang. Transphobes begone.

I am a student.

This means:

I am not an expert! I might be wrong about stuff! If you know more than me, please feel free to correct me! I love this topic and want to learn more!

I am not qualified to give out medical advice, and will only say 'go see your doctor if this concerns you!' on this blog.

It's also worth noting that, though I do work part-time in a hospital, doin' the ol' radiography, I am not going to provide funny/embarrassing patient stories. Or any patient stories at all, beyond, perhaps, very, very anonymised anecdotes to help illustrate points. I strongly disagree with mocking patients or posting anything about them without their consent - particularly if it could be traced back to them! This is just a blog where I can scream excitedly about how cool it is that I can look at all the Mushy And Bony Stuff inside you without cutting you open!

(Although sometimes you'll get cut open too <3 Just for funsies <3)

Please feel free to ask me anything, and I will do my best to reply!

Or, uh. Infodump about my hyperfixation. Not sorry.

[shialabeowulf]

This is someone dying while having an MRI scan. Before you die, your brain releases tons and tons of endorphines that make you feel a range of emotions. Tragically beautiful.

[official-stormtrooper]

sinterwoldiers

[some-wannabe-zlister]

This is actually from the walking dead. It’s someone dying from the zombie virus. You can even see the amc logo in the bottom corner

[heritageposts]

date of origin: 5th of november, 2012.

[thyrell]

how does this post only have like 3,000 notes this feels like such a classic

[radioactiveradley]

no this is 100% what mris look like

[viralfrog]

[rlyehtaxidermist]

observation: people think fMRI is a meaningful measure of "thought"

observation: people believe ChatGPT is "thinking"

conclusion: we must put the ChatGPT servers inside an fMRI machine. this will work perfectly and have no adverse consequences. trust.

[spyglassrealms]

MRI macine perfec t size for put AI in to "th/ink"! inside very Good and Not Danger AI "think" strongly put AI in MRI Machine. Put AI In MRI Machine. no problems ever in MRI machhine because good Shape and Support for server rack weak of solid state drive. Amri Mahine yes a place for an AI put AI in mri machine can trust machien for giveing good measure of AI "think". friend MRI machine

[fittingoutjane]

I think that putting every ChatGPT server in an fMRI would greatly improve society. Just make sure the operator is behind a solid bullet-proof shield first.

[lassukmiboolelunk]

@radioactiveradley

[beardedmrbean]

[randomramblesofaraven]

[twerklina]

[radioactiveradley]

THE MAGNET IS ALWAYS ON.

Man wearing heavy metallic necklace dies after being sucked into MRI machine

The man entered a room as his wife was having a scan on her knee, according to local media.

I'm not posting this to shame the victim, but the staff. It's absolutely atrocious that anyone was allowed into an active magnet room with a large metal chain around their neck. We go to great lengths to communicate the dangers of MRI to anyone who will be entering the field. This was either a gross failure of communication, or blatant criminal negligence.

[radioactiveradley]

I NEED TO YELL MORE ON THIS BLOG

RGGGGH!!! RGHHHHHHH!!!! I LOVE MEDICAL IMAGING SO MUCH!!!! it makes me feral! it makes me awooga!!!!

I AM LOOKING INSIDE YOUR BODY. I AM LOOKING AT YOUR GOOS AND OOZES AND BONY BITS. I AM LOOKING WITH SOUND AND WITH MAGNETS AND WITH RADIATION.

[chleopatrah]

🤣🤣🤣🤣🤣🤣🤣🤣 this is how passionate I am about the brain LMAOOOOOOO

[radioactiveradley]

HI HELLO I LOVE BRAINS

I've been deeply into neuro stuff lately, looking at AI and how it can speed up imaging of the neurodegnerative brain... but an even more exciting avenue is low-field MRI! It's coming into practice for rapid stroke diagnosis in the field! We're talking about TINY low-field MRI machines that fit in a backpack! They can simply scan the head of a potential stroke patient, differentiate haemorrhagic from ischaemic, and allow for life-saving clotbuster drugs to be given where possible only minutes after paramedics arrive!

Look at this shit brah!! Subacute ischaemic infarct on a 0.3T scanner showing a FLAIR that isn't exactly diagnostic quality on an anatomical detail level, but sure as fuck is diagnostic quality for 'is this person's stroke caused by a) bleeding into the brain, or b) not enough blood reaching the brain'!

[lassukmiboolelunk]

holy fish, you weren't joking, how cute is that!

[radioactiveradley]

he's just a lil guy!!!! now everyone can have the experience of popping their head in a li'l microwave~

I keep telling my coworkers we next need to develop the MRI hulahoop, which is just a hulahoop that scans your torso as you hula up and down, but no one has yet seen my vision, alas

[radioactiveradley]

I NEED TO YELL MORE ON THIS BLOG

RGGGGH!!! RGHHHHHHH!!!! I LOVE MEDICAL IMAGING SO MUCH!!!! it makes me feral! it makes me awooga!!!!

I AM LOOKING INSIDE YOUR BODY. I AM LOOKING AT YOUR GOOS AND OOZES AND BONY BITS. I AM LOOKING WITH SOUND AND WITH MAGNETS AND WITH RADIATION.

[chleopatrah]

🤣🤣🤣🤣🤣🤣🤣🤣 this is how passionate I am about the brain LMAOOOOOOO

[radioactiveradley]

HI HELLO I LOVE BRAINS

I've been deeply into neuro stuff lately, looking at AI and how it can speed up imaging of the neurodegnerative brain... but an even more exciting avenue is low-field MRI! It's coming into practice for rapid stroke diagnosis in the field! We're talking about TINY low-field MRI machines that fit in a backpack! They can simply scan the head of a potential stroke patient, differentiate haemorrhagic from ischaemic, and allow for life-saving clotbuster drugs to be given where possible only minutes after paramedics arrive!

Look at this shit brah!! Subacute ischaemic infarct on a 0.3T scanner showing a FLAIR that isn't exactly diagnostic quality on an anatomical detail level, but sure as fuck is diagnostic quality for 'is this person's stroke caused by a) bleeding into the brain, or b) not enough blood reaching the brain'!

[chleopatrah]

WTH THATS actually SO DOPE THANKS 4 SHARING HOMIE

[radioactiveradley]

NAH PRAHBLEM NAH PRAHBLEM I could happily yell about brain imaging for hours! Thank you for giving me an excuse!

[radioactiveradley]

I NEED TO YELL MORE ON THIS BLOG

RGGGGH!!! RGHHHHHHH!!!! I LOVE MEDICAL IMAGING SO MUCH!!!! it makes me feral! it makes me awooga!!!!

I AM LOOKING INSIDE YOUR BODY. I AM LOOKING AT YOUR GOOS AND OOZES AND BONY BITS. I AM LOOKING WITH SOUND AND WITH MAGNETS AND WITH RADIATION.

[chleopatrah]

🤣🤣🤣🤣🤣🤣🤣🤣 this is how passionate I am about the brain LMAOOOOOOO

[radioactiveradley]

HI HELLO I LOVE BRAINS

I've been deeply into neuro stuff lately, looking at AI and how it can speed up imaging of the neurodegnerative brain... but an even more exciting avenue is low-field MRI! It's coming into practice for rapid stroke diagnosis in the field! We're talking about TINY low-field MRI machines that fit in a backpack! They can simply scan the head of a potential stroke patient, differentiate haemorrhagic from ischaemic, and allow for life-saving clotbuster drugs to be given where possible only minutes after paramedics arrive!

Look at this shit brah!! Subacute ischaemic infarct on a 0.3T scanner showing a FLAIR that isn't exactly diagnostic quality on an anatomical detail level, but sure as fuck is diagnostic quality for 'is this person's stroke caused by a) bleeding into the brain, or b) not enough blood reaching the brain'!

[radioactiveradley]

I NEED TO YELL MORE ON THIS BLOG

RGGGGH!!! RGHHHHHHH!!!! I LOVE MEDICAL IMAGING SO MUCH!!!! it makes me feral! it makes me awooga!!!!

I AM LOOKING INSIDE YOUR BODY. I AM LOOKING AT YOUR GOOS AND OOZES AND BONY BITS. I AM LOOKING WITH SOUND AND WITH MAGNETS AND WITH RADIATION.

[pulpfanfiction]

[thoracs]

[worldheritagepostorganization]

World Heritage Post

[nighthaunting]

thought too hard about MRI machines today and had this come to me in a vision

[randomramblesofaraven]

Hi! I've seen you talking in the tags about genAI's use for medical imaging - would you up for giving a more detailed explanation? Because I don't really understand how you can have a "predictive" quality to the scan without losing necessary accuracy

So, in MRI we use 'sequences' - i.e., we test the different magnetic properties of the tissues in your body, and how they react to stimuli. I've written a more in-depth explanation here.

There are typically multiple sequences per scan, which is why the scans take sooooooo very long. The basic sequences, like T1/T2, take a couple minutes each. The highly specialised sequences, like NEX-5 neuromelanin sensitive scanning for Parkinson's Disease, can take 16 minutes each (imagine trying to lie still for the duration of that whole scan... which might get up to 90 minutes.... as a patient with a motor disorder that causes involuntary movement 🙃).

Plus, we use 'contrast' - a sort of dye - to better describe pathology, and that contrast is, um. A toxic heavy metal. That can kill you.

(DON'T WORRY IF YOU'RE GOING FOR AN MR SCAN. It's very, very rare that this happens, and only if your renal function is through the floor. But like. Still not ideal!)

So, we want to reduce scan time and contrast use. Thankfully, there is a lot of information contained in a basic-bitch T1/T2/FLAIR sequence that we cannot see with human eyes. The human eye can only differentiate about 50 shades of grey (hahaha) but the subtle differentiations in magnetic resonance that comprise an MR image can number significantly higher.

(In CT, we use a similar theory to select different window widths so we only irradiate you once... but it hasn't been applied to MR yet for various complex reasons)

If you feed a paired 'generator' CNN and a 'discriminator' CNN (typical GAN structure) like, a thousand T1 images and their GBCA counterparts when you're looking at, say, cerebral blood volume in Alzheimer's, the GAN can learn to add the contrast synthetically with very high (90%+!) sensitivity for this disease!

The application of this technology is in its infancy. It's currently limited to specific pathologies. But it's coming along massively, and could hugely improve the lives of anyone who needs frequent MR scans!

[podcastwizard]

if you're in the throes of cosmic despair i cannot recommend museums enough. art or science or history it doesn't matter. oh we're all connected, all of us and everything, throughout all time and space, and no one, no one, no one is alone? awesome. that's what i thought i just wanted to make sure.

[rumade]

The wall of kidney stones at London's science museum always helps put things in perspective. Some of them are the size of fruit, and i don't mean a blueberry...

[radioactiveradley]

staghorn calculi, baby!!

[acti-veg]

‘While bats can only sense the outer shapes and textures of their targets, dolphins can peer inside theirs. If a dolphin echolocates on you, it will perceive your lungs and your skeleton. It can likely sense shrapnel in war veterans and fetuses in pregnant women. It can pick out the air-filled swim bladders that allow fish, their main prey, to control their buoyancy.

It can almost certainly tell different species apart based on the shape of those air bladders. And it can tell if a fish has something weird inside it, like a metal hook. In Hawaii, false killer whales often pluck tuna off fishing lines, and “they’ll know where the hook is inside that fish,” Aude Pacini, who studies these animals, tells me. “They can ‘see’ things that you and I would never consider unless we had an X-ray machine or an MRI scanner.”

This penetrating perception is so unusual that scientists have barely begun to consider its implications. The beaked whales, for example, are odontocetes that look dolphin-esque on the outside—but on the inside, their skulls bear a strange assortment of crests, ridges, and bumps, many of which are only found in males.

Pavel Gol’din has suggested that these structures might be the equivalent of deer antlers—showy ornaments that are used to attract mates. Such ornaments would normally protrude from the body in a visible and conspicuous way, but that’s unnecessary for animals that are living medical scanners.’

-Ed Yong, An Immense World

[aiweirdness]

They trained an AI model on a widely used knee osteoarthritis dataset to see if it would be able to make nonsensical predictions - whether the patient ate refried beans, or drank beer. It did, in part by somehow figuring out where the x-ray was taken.

AI thought X-rays of your knees show if you drink beer—they don’t.

Dartmouth Health study shows how easily AI models can give right answers for wrong reasons

The authors point out that AI models base their predictions on sneaky shortcut effects all the time; they're just easier to identify when the conclusions (beer drinking) are clearly spurious.

Algorithmic shortcutting is tough to avoid. Sometimes it's based on something easy to identify - like rulers in images of skin cancer, or sicker patients getting their chest x-rays while lying down.

But as they found here, often it's a subtle mix of non-obvious correlations. They eliminated as many differences between x-ray machines at different sites as they could find, and the model could still tell where the x-ray was taken - and whether the patient drank beer.

AI models are not approaching the problem like a human scientist would - they'll latch onto all sorts of unintended information in an effort to make their predictions.

This is one reason AI models often end up amplifying the racism and gender discrimination in their training data.

When I wrote a book on AI in 2019, it focused on AIs making sneaky shortcuts.

Book: You Look Like A Thing — Janelle Shane

Aside from the vintage generative text (Pumpkin Trash Break ice cream, anyone?), the algorithmic shortcutting is still completely recognizable today.