Potential improvement in nodule detection

[totesarana]

Hi lfz,

I have observed one thing during playing with your detector. Looks like your detector performs much better on CTs with smaller slice thickness (i.e., higher resolution on z axis). This is significant as I observed ~500 proposals (before iou step) for higher resolution CTs and around ~2000 ~ 3000 proposals for lower resolution CTs. Do you think it could be beneficial to train two detectors for these two types of CTs?

[lfz]

Thank you for letting me know that, I think firstly any method would perform better with smaller slice thickness because of more information.

but this difference is too big? so maybe you can try that idea. I think it might work

2017-08-05 5:13 GMT+08:00 totesarana [email protected]:

Hi lfz,

I have observed one thing during playing with your detector. Looks like your detector performs much better on CTs with smaller slice thickness (i.e., higher resolution on z axis). This is significant as I observed ~500 proposals (before iou step) for higher resolution CTs and around ~2000 ~ 3000 proposals for lower resolution CTs. Do you think it could be beneficial to train two detectors for these two types of CTs?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/lfz/DSB2017/issues/35, or mute the thread https://github.com/notifications/unsubscribe-auth/AIigQw98a0j9cyQGLQMmle8qEGprvW7Uks5sU4l6gaJpZM4OuMmJ .

-- 廖方舟 清华大学医学院 Liao Fangzhou School of Medicine Tsinghua University Beijing 100084 China