search

IBBM / Cascaded-FCN

Source code for the MICCAI 2016 Paper "Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworks and 3D Conditional Random Fields"
Other
304 stars 127 forks source link

Question:The results for the code are error #29

Open wwlaoxi opened 6 years ago

wwlaoxi commented 6 years ago 
    1、I downloaded the 3Dircadb database.
    2、I downloaded the Cascaded-FCN code from https://github.com/IBBM/Cascaded-FCN.
    3、I downloaded the step1_weights.caffemodel(https://www.dropbox.com/s/aoykiiuu669igxa/step1_weights.caffemodel?dl=1) and step2_weights.caffemodel(https://www.dropbox.com/s/ql10c37d7ura23l/step2_weights.caffemodel?dl=1).
   I run the cascaded_unet_inference.ipynb in the  Cascaded-FCN code. I find that the prediction is error, so I want to know why。The attachment is result of prediction.

3dircadb

VincentXWD commented 6 years ago

@wwlaoxi Hi, have you solved this problems ?

michaelschwier commented 6 years ago

Same problem here. I'm running the notebook in an official Caffe release docker in CPU mode.

liversegerror

@mohamed-ezz @PatrickChrist @FelixGruen Any help/hints towards solving this would be appreciated!

lidaryani commented 6 years ago

I also achieved the same result. The predicted slice was not a satisfactory result. With regard to the previous issue (#31 ), I tested it in CPU mode and was unacceptable again. @mohamed-ezz @PatrickChrist @FelixGruen Do we have to consider a particular item in the implementation?

mohamed-ezz commented 6 years ago

Hello @lidaryani , please see this note about the Caffe version and the crop layer https://github.com/IBBM/Cascaded-FCN/issues/3#issuecomment-272343778

michaelschwier commented 6 years ago

@lidaryani I got it working by building Jonlong's caffe version and running Cascaded-FCN with that one. See also the Cascaded-FCN jupyter notebook and issue #3

keesh0 commented 5 years ago

I used the docker image (Jon Long) on new CT volumes. The inference was impressive. Using Caffe 1.0.0, I am getting identical results to the above Prediction screenshot.

Could somebody please provide an example of updating the model r/e the crop layer-- https://github.com/IBBM/Cascaded-FCN/issues/3#issuecomment-272343778

keesh0 commented 5 years ago

I used the docker image (Jon Long) on new CT volumes. The inference was impressive. Using Caffe 1.0.0, I am getting identical results to the above Prediction screenshot.

Could somebody please provide an example of updating the model r/e the crop layer-- #3 (comment)

Here is my updated crop layers which appeared to work under Cafe 1.0.0 (AWS Python 3 configured)

layer { name: "crop_d3c-d3cc" type: "Crop" bottom: "d3c" current blob size (1, 512, 64, 64) bottom: "u3a" desired blob size (1, 512, 56, 56) top: "d3cc" crop_param { axis: 2 offset: 4 offset: 4 } } layer {

type: "Crop" bottom: "d2c" (1, 256, 136, 136) bottom: "u2a" desired blob size (1, 256, 104, 104) top: "d2cc" crop_param { axis: 2 offset: 16 offset: 16 } } layer { name: "crop_d1c-d1cc" type: "Crop" bottom: "d1c" (1, 128, 280, 280) bottom: "u1a" desired blob size (1, 128, 200, 200) top: "d1cc" crop_param { axis: 2 offset: 40 offset: 40 } } layer { name: "crop_d0c-d0cc" type: "Crop" bottom: "d0c" (1, 64, 568, 568) bottom: "u0a" *desired blob size (1, 64, 392, 392) top: "d0cc" crop_param { axis: 2 offset: 88 offset: 88 } }

offset = (current blob size - desired blob size) / 2

I am down to just the following warning which I hope are related to training and not inference: I0610 23:47:14.142359 4565 net.cpp:744] Ignoring source layer bn_d0b (batch normalization?) I0610 23:47:14.169219 4565 net.cpp:744] Ignoring source layer loss (loss for training?))

tobimichigan commented 4 years ago

@keesh0 , please could you share the source of the new CT volumes you used? Thank you.

keesh0 commented 4 years ago

Sure.

  1. 3DIRCAD dataset-- 20 venous phase enhanced CT volumes from various European hospitals with different CT scanners [test#0, training cfcn network]

  2. TCGA-LIHC is The Cancer Genome Atlas Liver Hepatocellular Carcinoma (TCGA-LIHC) [test set] https://wiki.cancerimagingarchive.net/display/Public/TCGA-LIHC

tobimichigan commented 4 years ago

@keesh0 , very many thanks. Besides, I encountered some bugs whilst trying out this repo, I have opened an issue on it here: https://github.com/IBBM/Cascaded-FCN/issues/34 and I hope the owner will proffer solution to it. Where you able to plot accuracy curve for the predicted images?

keesh0 commented 4 years ago

I did not try to plot the accuracy curve. Here is my wrapper code-- https://github.com/keesh0/cfcn_test_inference/blob/master/python/test_cascaded_unet_inference.py