Towards automated brain aneurysm detection in tof-mra: open data, weak labels, and anatomical knowledge

HIGHLIGHTS

SUMMARY

And lead to subarachnoid hemorrhages which have a mortality rate of 40% and usually cause severe disability for patients (Frösen et_al, 2012). Manually assessing a TOF-MRA is a costly process: radiologists detect aneurysms by selectively scrolling through the TOF-MRA volumes in different planes-for instance, they check in the axial plane the most recurrent locations where aneurysms can occur. The authors develop a fully automated DL network for UIA detection and propose to mitigate the data availability bottleneck as follows: the authors explore the use of "weak" labels (Abousamra et_al, 2020 . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or Email

Password

Remember me

Lost your password?

If you don't have an account, you can create one here.