Hacker News Reader

Comment by throwaway4220 | Hacker News Reader

I'm a radiologist involved in machine learning research! I lurk on HN to feel like I know how to code :)

Great! Then you're the ideal person to ask something I've been wondering: We see the occasional headline about machine learning algorithms outperforming human radiologists. What's the catch? I'm prepared to believe they aren't really outperforming humans once you take all the unstated factors into account, just wondering what the unstated factors are.

That's surprising, I was sure radiology would be the first medical field to get automated away. What are the main challenges you think?

Most people cite liability as the main reason but I also haven't seen any algorithm that reads chest radiographs better than radiologists. To be fair, rads look at images, correlate with the patient chart and symptoms, and that info is not provided to the algorithms. But also, humans need only one or two examples of a weird diagnosis to find it again and that still can't be tackled by one-shot/few shot learning algorithms (yet!).

https://towardsdatascience.com/why-ai-will-not-replace-radio...

This covers some points, but "never?" I'm not so sure about that... That's why if I can't beat 'em I'm trying to join em

I don't know enough about A.I or radiology but if A.I can drive cars or make investment decisions better than humans I can't see why something as technical as reading photos and recognising patterns can't be done by A.I. Good luck with your research!

The largest system in the human brain is the one responsible for vision. There's a scary amount of computational power involved in a human completing simple-seeming visual tasks, and that's not always easy to reproduce with computer models.

Reply on news.ycombinator.com