ayush1997 / xvision Goto Github PK

Chest Xray image analysis using Deep learning !

Python 64.56% Jupyter Notebook 35.44%

deep-learning vggnet computer-vision medical-imaging chest-xray-images transfer-learning tensorflow python

xvision's Introduction

Xvision

Chest Xray image analysis using Deep Learning and exploiting Deep Transfer Learning technique for it with Tensorflow.

The maxpool-5 layer of a pretrained VGGNet-16(Deep Convolutional Neural Network) model has been used as the feature extractor here and then further trained on a 2-layer Deep neural network with SGD optimizer and Batch Normalization for classification of Normal vs Nodular Chest Xray Images.

Nodular vs Normal Chest Xray

Some specifications

Property	Values
Pretrained Model	VggNet-16
Optimizer used	stochastic gradient descent(SGD)
Learning rate	0.01
Mini Batch Size	20
Epochs	20
2 Layers	512x512
GPU trained on	Nvidia GEFORCE 920M

Evaluation

Confusion Matrix and Training Error Graph

	Normal	Nodule
Precision	0.7755102	0.55555556
Recall	0.76	0.57692308

Accuracy : 69.3333 %

DataSet

openi.nlm.nih.gov has a large base of Xray,MRI, CT scan images publically available.Specifically Chest Xray Images have been scraped, Normal and Nodule labbeled images are futher extrated for this task.

How to use ?

The above code can be used for Deep Transfer Learning on any Image dataset to train using VggNet as the PreTrained network.

Steps to follow

Download Data- the script download images and saves corresponding disease label in json format.

python scraper.py <path/to/folder/to/save/images>

Follow the scraper/process.ipynb notebook for Data processing and generate

Training images folder - All images for training
Testing images Folder - All images for testing
Training image labels file - Pickled file with training labels
Testing image labels file - Pickled file with testing labels

Extract features(CNN Codes) from the maxpool:5 layer of PreTrained CovNet(VggNet) and save them beforehand for faster training of Neural network.

python train.py <Training images folder> <Testing image folder> <Train images codes folder > <Test images codes folder>
- Train images codes folder - Path where training images codes will be stored
- Test images codes folder - Path where testing images codes will be stored
The extracted features are now used for training our 2-Layer Neural Network from scratch.The computed models are saved as tensorflow checkpoint after every Epoch.

python train_model.py <Training images folder> <Train images codes folder> <Training image labels file> <Folder to save models>
Finally the saved models are used for making predictions.Confusion Matrix is used as the Performance Metrics for this classifcation task.

python test_model.py <Testing images folder> <Test images codes folder> <Testing image labels file> <Folder with saved models>

Some Predictions

References

Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

Contribute

If you want to contribute and add new feature feel free to send Pull request here :D

To report any bugs or request new features, head over to the Issues page

To-do

Implement saliency map or use Deconv for better visualizations.

xvision's People

Contributors

Stargazers

Watchers

Forkers

kkhanh89 mariankh pandeydivesh15 cadrev andandandand jmrinaldi matrix-revolution ctjohnson alexeyantonov serialforbreakfast codeaudit ieyer y12uc231 ashishpahwa7 achillessaxby manniru benjamesbabala dagangwood163 vyraun projectafey jdc08161063 2php fancyerii jjdblast haroldss mnrmja007 guanlongtianzi allensmile lyk125 joshianuj v-italy antriv lifematrix lijian8 rjbashar meta-machine mtal3t richy666666 zizai110 laoniu2020 liviust vunb linxpsoft gb-it top501 yu0089 ajroas aomiit rbunn80110 rituge prateeknepaliya09 chenrongjing zhencang jiandanjinxin paranoidw obendidi rafemcbeth liu3xing3long lisha0803 prernakakkar95 solversa dilaw2007 zbxzc35 yangliu0198 guendeli ruslankosarev bit200 sagorikadas liuyh17 ramana459 dancingonair sonyeric psych0cat lyukan samching jacksu20160407 bastinrobin ieee820 heavyflavor raka747 tobywangel jingzhizhang tomaszrewak sbawani2007 afcarl wedoso aspiringguru gaurav-b98 xjohnxjohn ascent101 abhishek1605 aman229 sucrerouge github4210 chirjot furuolan vaibhav11sajnani zhouliyan111111 stevenji anupam42

xvision's Issues

Problem with process.ipynb

Hey Ayush,
While using your code I ran into a problem and saw that your training image list in your jupyter notebook was looping for only 177 images and not the whole dataset and I couldn't find any solution regarding it. If you could help me with this it would be a very big help.

Thank you.

Code does not run as it is

Is there a version dependency of "process.ipynb". When try to run the code as it is I get lots of errors in
Jupiter with Python 3, eg, following code does not run:
"c.items().sort(key=lambda x: x[0])"
has to be changed to ,
"sorted(c.items(), key=lambda x: x[0])"
No Print statements runs

train_model.py, test_model.py reversed

input image size

Hello Mate ,

Greate job done !, can you please tell me how are you dealing with the input ?, as the xray jpg are single color Channel images and VGG input tensor is i think of 3 channels .
[email protected]
Thanks

how can I run ?

Dear
I cannot understand the file/folders.

In DeepLearning folder, I made two folder : normal and abnormal. And I copyied image files to each folder.

How can I label ? The labels (normal and abnormal) are folder name.

Thank you.
Sincerely.

train.py has issue with tensorflow 0.12

Hi Ayush,
I got an error when parse VGGNet-16 with tensorflow V 0.12. Any idea about tensorflow version that you use?

Thanks
TSW

train_model.py and test_model.py are reversed

Files train_model.py and test_model.py are reversed. Right now (despite what readme says) one has to run test_model.py first and then train_model.py to validate the model. It seems that the content of these files is simply swapped.

Error while running test_model.py : Incompatible shapes

Hi Ayush,

I am getting below error while running test_model.py. Could you help me on this please ? I have Python 3.2.5 and tensorflow 1.0 on Windows platform.

Traceback (most recent call last):
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\client\session.py", line 1022, in _do_call
return fn(*args)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\client\session.py", line 1004, in run_fn
status, run_metadata)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\contextlib.py", li
ne 66, in exit
next(self.gen)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\framework\errors_impl.py", line 469, in raise_exception_on_not_ok
status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shape
s: [9] vs. [25]
[[Node: Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/tas
k:0/cpu:0"](ArgMax_1, ArgMax_2)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "test_model.py", line 189, in
acc,pred,s,actual = sess1.run([accuracy,predicted_y,soft,actual_y], feed_dic
t={x: content_features,y: test_label})
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\client\session.py", line 767, in run
run_metadata_ptr)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\client\session.py", line 965, in _run
feed_dict_string, options, run_metadata)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\client\session.py", line 1015, in _do_run
target_list, options, run_metadata)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\client\session.py", line 1035, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shape
s: [9] vs. [25]
[[Node: Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/tas
k:0/cpu:0"](ArgMax_1, ArgMax_2)]]

Caused by op 'Equal', defined at:
File "test_model.py", line 153, in
correct_prediction = tf.equal(predicted_y, actual_y)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\ops\gen_math_ops.py", line 721, in equal
result = _op_def_lib.apply_op("Equal", x=x, y=y, name=name)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\framework\op_def_library.py", line 763, in apply_op
op_def=op_def)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tens
orflow\python\framework\ops.py", line 2395, in create_op
original_op=self._default_original_op, op_def=op_def)
File "C:\Users\goyalr\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1264, in init self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Incompatible shapes: [9] vs. [25]
[[Node: Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"](ArgMax_1, ArgMax_2)]]

Can not run train_model.py

Hello PHD,
I am trying to
python train_model.py

The problem is :
['DeepLearning/train_model.py', 'final_train_images_calc_nodule_only/', 'train-code/', 'training_labels_calc_nodule_only', 'xx.models']
train_labels 177
161
Traceback (most recent call last):
File "DeepLearning/train_model.py", line 174, in
sess2.run(tf.initialize_all_variables())

Thanks!

data

can't download the data because of failed connection

Anyone run this against NIH dataset?

i.e. the official NIH chest xray dataset.. any results people can publish?

Cant not download the VGG15.tfmodel

Hello sir,
I am trying to extract features from train.py using VGG16. When i tried to download the file vgg16.tfmodel from https://s3.amazonaws.com/cadl/models/vgg16.tfmodel, seems like the link doesnt work for me. Would you mind providing alternative link for that file ?

can not run train.py

Hi,
I'm trying to run train.py and getting following error

161
j= 0
(20, 224, 224, 3) Image Shape
Traceback (most recent call last):
File train.py", line 131, in
content_features =get_content_feature(img_4d).reshape((get_content_feature(img_4d).shape[0],77512))
File "train.py", line 87, in get_content_feature 'vgg/dropout/random_uniform:0': [[1.0]]
File "tensorflow\python\framework\ops.py", line 575, in eval return _eval_using_default_session(self, feed_dict, self.graph, session)
File "tensorflow\python\framework\ops.py", line 3633, in _eval_using_default_session return session.run(tensors, feed_dict)
File "tensorflow\python\client\session.py", line 766, in run run_metadata_ptr)
File "tensorflow\python\client\session.py", line 943, in _run % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (1, 1) for Tensor 'vgg/dropout/random_uniform:0', which has shape '(?, 4096)'

Could you help me with this. I'm new to python.

Thanks.

Error when running train_model.py

I got the error as below:

2017-08-07 16:24:09.904701: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-07 16:24:09.904717: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-08-07 16:24:09.904732: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-07 16:24:09.904735: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2017-08-07 16:24:10.154733: W tensorflow/core/framework/op_kernel.cc:1158] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
2017-08-07 16:24:10.154797: W tensorflow/core/framework/op_kernel.cc:1158] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
2017-08-07 16:24:10.154878: W tensorflow/core/framework/op_kernel.cc:1158] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
2017-08-07 16:24:10.154962: W tensorflow/core/framework/op_kernel.cc:1158] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
2017-08-07 16:24:10.155013: W tensorflow/core/framework/op_kernel.cc:1158] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
2017-08-07 16:24:10.155095: W tensorflow/core/framework/op_kernel.cc:1158] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
2017-08-07 16:24:10.155153: W tensorflow/core/framework/op_kernel.cc:1158] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
2017-08-07 16:24:10.155203: W tensorflow/core/framework/op_kernel.cc:1158] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
Traceback (most recent call last):
File "train_model.py", line 174, in
saver.restore(sess1, os.getcwd()+"/"+sys.argv[4]+"/"+"my-model-"+str(epoch-1)+".ckpt")
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1548, in restore
{self.saver_def.filename_tensor_name: save_path})
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 789, in run
run_metadata_ptr)
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 997, in _run
feed_dict_string, options, run_metadata)
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1132, in _do_run
target_list, options, run_metadata)
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1152, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
[[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]

Caused by op u'save/RestoreV2', defined at:
File "train_model.py", line 161, in
saver = tf.train.Saver()
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1139, in init
self.build()
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1170, in build
restore_sequentially=self._restore_sequentially)
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 691, in build
restore_sequentially, reshape)
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 407, in _AddRestoreOps
tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 247, in restore_op
[spec.tensor.dtype])[0])
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/gen_io_ops.py", line 640, in restore_v2
dtypes=dtypes, name=name)
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/Users/min.jiang/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1269, in init
self._traceback = _extract_stack()

NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /Users/min.jiang/Documents/DEEPLEARNING/CODE/Xvision/DeepLearning/../xvision_test/model//my-model-19.ckpt
[[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]

Can't crawl the dataset

Hi， @ayush1997 I can't get your whole train dataset from your scraper.py. Could you share your dataset, Thanks