Tag Archives: radiology informatics

DICOM Processing and Segmentation in Python – Radiology Data Quest

There is something strangely satisfying about being able to take things apart and putting it back together.  Inspired by the popularity of Lego sets in our childhoods, Minecraft brought this sense of wonder to video games.

For those of us who are life-long tinkerers who happen to be radiologists, I published in Radiology Data Quest a DIY on how one take DICOM apart and manipulate it.  All in Python, no less.


DICOM is a pain in the neck.  It also happens to be very helpful.  As clinical radiologists, we expect post-processing, even taking them for granted. However, the magic that occurs behind the scene…

Source: DICOM Processing and Segmentation in Python – Radiology Data Quest

Is your niche too narrow? Too wide? It doesn’t matter.

Academics care about being in a niche.  A person only has 24 hours a day and 7 days a week.  It’s practically impossible to be the world expert in everything.

Some days I worry that my interest in informatics is too narrow.  So tell me again, why wouldn’t anyone just hire either a dedicated radiologist or a dedicated informaticist?  What’s the point of you?

Some days I worry my niche is too broad. Because that’s basically all of radiology, you dimwit!  That inner voice in my head would scream.   How can you expect to understand all of what makes my profession tick, all the intricacies behind every segmentation algorithm, every big-data challenge, every line of code?  Give it up.

And then there are days when I spend 8 hours doing something I want to do, and the day feels 20 minutes long.  Days when I feel tired but satisfied, proud to have made those career choices.

These are the days when that voice doesn’t speak.