search

microsoft / Recursive-Cascaded-Networks

[ICCV 2019] Recursive Cascaded Networks for Unsupervised Medical Image Registration
https://arxiv.org/abs/1907.12353
MIT License
362 stars 87 forks source link

what's the format of the deformation field? #8

Closed mvoofan closed 4 years ago

mvoofan commented 4 years ago

Thanks for you kindly sharing your codes. It is very nice work and it canbe excuted directly.

I get the deformation field (128128128*3 matrix) by adding "real_flow" in the variable "keys" (in eval.py). However, I cannot get the right warped image using the floating image and the deformation field (I used the SimpleITK.Warp function). I wonder whether you can added some explanation to the deformation field.

mvoofan commented 4 years ago

Sorry. Maybe I use the wrong displacement variable in SimpleITK.

Hoodini-Gzj commented 2 years ago

Thanks for you kindly sharing your codes. It is very nice work and it canbe excuted directly.

I get the deformation field (128_128_128*3 matrix) by adding "real_flow" in the variable "keys" (in eval.py). However, I cannot get the right warped image using the floating image and the deformation field (I used the SimpleITK.Warp function). I wonder whether you can added some explanation to the deformation field.

How do you get the deformation field? Could you tell me more about it.Looking forward to your reply. I am a newbie, can you share your part of the code?

mvoofan commented 2 years ago

Thanks for you kindly sharing your codes. It is very nice work and it canbe excuted directly. I get the deformation field (128_128_128*3 matrix) by adding "real_flow" in the variable "keys" (in eval.py). However, I cannot get the right warped image using the floating image and the deformation field (I used the SimpleITK.Warp function). I wonder whether you can added some explanation to the deformation field.

How do you get the deformation field? Could you tell me more about it.Looking forward to your reply. I am a newbie, can you share your part of the code?

Just add "real_flow" in the variable "keys" (in eval.py), then u can get a dict varibale return (maybe named "results").

Hoodini-Gzj commented 2 years ago

Thanks for you kindly sharing your codes. It is very nice work and it canbe excuted directly. I get the deformation field (128_128_128*3 matrix) by adding "real_flow" in the variable "keys" (in eval.py). However, I cannot get the right warped image using the floating image and the deformation field (I used the SimpleITK.Warp function). I wonder whether you can added some explanation to the deformation field.

How do you get the deformation field? Could you tell me more about it.Looking forward to your reply. I am a newbie, can you share your part of the code?

Just add "real_flow" in the variable "keys" (in eval.py), then u can get a dict varibale return (maybe named "results").

Thank u for ur reply. I have successfully obtained the result according to ur suggestion. Wish everything goes well with your work! :)