以下是我将如何提出问题的顺序：
- 首先我将向您展示用于在本地主机(flask应用程序(中运行web应用程序的脚本.py。这个网络应用程序是一个分类器，可以显示一个人是否患有病毒性肺炎、细菌性肺炎或正常。因此，从jpeg格式的胸部x光片中可以看到三个类别(病毒、细菌或正常(
- 第二个我将向您展示肺炎二进制分类的不同.py脚本，该脚本将接收原始dicom文件，并在诊断之前将其转换为numpy数组
因此，为了实现诊断，我正试图将我的app.py脚本与肺炎二元分类集成在一起，前者采用jpegs，后者采用dicom文件，以利用第二个脚本的dicom处理功能，但使用我所拥有的病毒和细菌的所有信息和权重，以便在临床设置中使用。临床设置使用dicom文件而不是jpegs，这就是为什么我试图将这两个脚本结合起来以达到目标。
以下是我的病毒性和细菌性肺炎分类的app.py脚本，该脚本包含jpegs，我正试图将其集成到我将在下面进一步附加的另一个脚本上：
#::: Import modules and packages :::
# Flask utils
from flask import Flask, redirect, url_for, request, render_template
from werkzeug.utils import secure_filename
from gevent.pywsgi import WSGIServer
# Import Keras dependencies
from tensorflow.keras.models import model_from_json
from tensorflow.python.framework import ops
ops.reset_default_graph()
from keras.preprocessing import image
# Import other dependecies
import numpy as np
import h5py
from PIL import Image
import PIL
import os
#::: Flask App Engine :::
# Define a Flask app
app = Flask(__name__)
# ::: Prepare Keras Model :::
# Model files
MODEL_ARCHITECTURE = './model/model_adam.json'
MODEL_WEIGHTS = './model/model_100_eopchs_adam_20190807.h5'
# Load the model from external files
json_file = open(MODEL_ARCHITECTURE)
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
# Get weights into the model
model.load_weights(MODEL_WEIGHTS)
print('Model loaded. Check http://127.0.0.1:5000/')
# ::: MODEL FUNCTIONS :::
def model_predict(img_path, model):
'''
Args:
-- img_path : an URL path where a given image is stored.
-- model : a given Keras CNN model.
'''
IMG = image.load_img(img_path).convert('L')
print(type(IMG))
# Pre-processing the image
IMG_ = IMG.resize((257, 342))
print(type(IMG_))
IMG_ = np.asarray(IMG_)
print(IMG_.shape)
IMG_ = np.true_divide(IMG_, 255)
IMG_ = IMG_.reshape(1, 342, 257, 1)
print(type(IMG_), IMG_.shape)
print(model)
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='rmsprop')
predict_x = model.predict(IMG_)
print(predict_x)
prediction = np.argmax(predict_x,axis=1)
print(prediction)
return prediction
# ::: FLASK ROUTES
@app.route('/', methods=['GET'])
def index():
# Main Page
return render_template('index.html')
@app.route('/predict', methods=['GET', 'POST'])
def upload():
# Constants:
classes = {'TRAIN': ['BACTERIA', 'NORMAL', 'VIRUS'],
'VALIDATION': ['BACTERIA', 'NORMAL'],
'TEST': ['BACTERIA', 'NORMAL', 'VIRUS']}
if request.method == 'POST':
# Get the file from post request
f = request.files['file']
# Save the file to ./uploads
basepath = os.path.dirname(__file__)
file_path = os.path.join(
basepath, 'uploads', secure_filename(f.filename))
f.save(file_path)
# Make a prediction
prediction = model_predict(file_path, model)
predicted_class = classes['TRAIN'][prediction[0]]
print('We think that is {}.'.format(predicted_class.lower()))
return str(predicted_class).lower()
if __name__ == '__main__':
app.run(debug = True)`
下面再次是肺炎二元分类的已经运行的脚本，它正在接受dicom文件，我正试图将其与我想要使用的病毒和细菌分类器的权重和预处理信息集成：
## Loading standard modules and libraries
import numpy as np
import pandas as pd
import pydicom
%matplotlib inline
import matplotlib.pyplot as plt
import keras
from keras.models import Sequential
from keras.layers import Dense
from keras.models import model_from_json
from skimage.transform import resize
# This function reads in a .dcm file, checks the important fields for our device, and returns a numpy array
# of just the imaging data
def check_dicom(filename):
print('Loading file {} ...'.format(filename))
ds = pydicom.dcmread(filename)
if (ds.BodyPartExamined !='CHEST') | (ds.Modality !='DX') | (ds.PatientPosition not in ['PA', 'AP']):
print('The image is not valid because the image position, the image type or the body part is not as per standards')
return
else:
print('ID:', ds.PatientID,
'Age:', ds.PatientAge,
'Modality:', ds.Modality,
'Postion: ', ds.PatientPosition,
'Body Part: ', ds.BodyPartExamined,
'Study Desc: ', ds.StudyDescription)
img = ds.pixel_array
return img
# This function takes the numpy array output by check_dicom and
# runs the appropriate pre-processing needed for our model input
def preprocess_image(img,img_mean,img_std,img_size):
# todo
img = resize(img, (224,224))
img = img / 255.0
grey_img = (img - img_mean) / img_std
proc_img = np.zeros((224,224,3))
proc_img[:, :, 0] = grey_img
proc_img[:, :, 1] = grey_img
proc_img[:, :, 2] = grey_img
proc_img = np.resize(proc_img, img_size)
return proc_img
# This function loads in our trained model w/ weights and compiles it
def load_model(model_path, weight_path):
# todo
json_file = open(model_path, 'r')
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
model.load_weights(weight_path)
return model
# This function uses our device's threshold parameters to predict whether or not
# the image shows the presence of pneumonia using our trained model
def predict_image(model, img, thresh):
# todo
result = model.predict(img)
print('Predicted value:', result)
predict=result[0]
prediction = "Negative"
if(predict > thresh):
prediction = "Positive"
return prediction
# This function uses our device's threshold parameters to predict whether or not
# the image shows the presence of pneumonia using our trained model
def predict_image(model, img, thresh):
# todo
result = model.predict(img)
print('Predicted value:', result)
predict=result[0]
prediction = "Negative"
if(predict > thresh):
prediction = "Positive"
return prediction
test_dicoms = ['test1.dcm','test2.dcm','test3.dcm','test4.dcm','test5.dcm','test6.dcm']
model_path = "my_model2.json" #path to saved model
weight_path = "xray_class_my_model2.best.hdf5" #path to saved best weights
IMG_SIZE=(1,224,224,3) # This might be different if you did not use vgg16
img_mean = 0.49262813 # mean image value from Build and train model line 22
img_std = 0.24496286 # loads the std dev from Build and train model line 22
my_model = load_model(model_path, weight_path) #loads model
thresh = 0.62786263 #threshold value for New Model2 from Build and train model line 66 at 80% Precision
# use the .dcm files to test your prediction
for i in test_dicoms:
img = np.array([])
img = check_dicom(i)
if img is None:
continue
img_proc = preprocess_image(img,img_mean,img_std,IMG_SIZE)
pred = predict_image(my_model,img_proc,thresh)
print('Model Classification:', pred , 'for Pneumonia' )
print('--------------------------------------------------------------------------------------------------------')
上述脚本的输出：
Loading file test1.dcm ...
ID: 2 Age: 81 Modality: DX Postion: PA Body Part: CHEST Study Desc: No Finding
Predicted value: [[0.4775539]]
Model Classification: Negative for Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test2.dcm ...
ID: 1 Age: 58 Modality: DX Postion: AP Body Part: CHEST Study Desc: Cardiomegaly
Predicted value: [[0.47687072]]
Model Classification: Negative for Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test3.dcm ...
ID: 61 Age: 77 Modality: DX Postion: AP Body Part: CHEST Study Desc: Effusion
Predicted value: [[0.47764364]]
Model Classification: Negative for Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test4.dcm ...
The image is not valid because the image position, the image type or the body part is not as per standards
Loading file test5.dcm ...
The image is not valid because the image position, the image type or the body part is not as per standards
Loading file test6.dcm ...
The image is not valid because the image position, the image type or the body part is not as per standards
Threshold of 0.62786263 is considered at 80% Precision
以下是我迄今为止所做的尝试，但我得到的诊断始终是每个双子叶植物样本上的病毒：
## Loading standard modules and libraries
import numpy as np
import pandas as pd
import pydicom
from PIL import Image
#%matplotlib inline
import matplotlib.pyplot as plt
import keras
from keras.models import Sequential
from keras.layers import Dense
from keras.models import model_from_json
from keras.preprocessing import image
from skimage.transform import resize
# This function reads in a .dcm file, checks the important fields for our device, and returns a numpy array
# of just the imaging data
def check_dicom(filename):
print('Loading file {} ...'.format(filename))
ds = pydicom.dcmread(filename)
if (ds.BodyPartExamined !='CHEST'): #| (ds.Modality !='DX'): #| (ds.PatientPosition not in ['PA', 'AP']):
print('The image is not valid because the image position, the image type or the body part is not as per standards')
return
else:
print('ID:', ds.PatientID,
'Age:', ds.PatientAge,
'Modality:', ds.Modality,
'Postion: ', ds.PatientPosition,
'Body Part: ', ds.BodyPartExamined,
'Study Desc: ', ds.StudyDescription)
img = ds.pixel_array
return img
# This function takes the numpy array output by check_dicom and
# runs the appropriate pre-processing needed for our model input
def preprocess_image(img):
# todo
#im = np.reshape(img, (342,257 ))
#im = np.arange(257)
#img = Image.fromarray(im)
#img = image.load_img(img).convert('L')
img = resize(img, (342,257))
grey_img = img / 255.0
#grey_img = (img - img_mean) / img_std
proc_img = np.zeros((1,342,257,1))
proc_img[:, :, :, 0] = grey_img
#proc_img[:, :, :, 1] = grey_img
#proc_img[:, :, :, 2] = grey_img
proc_img = proc_img.reshape(1, 342, 257, 1)
return proc_img
# This function loads in our trained model w/ weights and compiles it
def load_model(model_path, weight_path):
# todo
json_file = open(model_path, 'r')
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
model.load_weights(weight_path)
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='rmsprop')
return model
# This function uses our device's threshold parameters to predict whether or not
# the image shows the presence of pneumonia using our trained model
def predict_image(model, img):
# todo
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='rmsprop')
#x = np.expand_dims(img, axis=0)
predict_x= model.predict(img)
print(predict_x)
prediction = np.argmax(predict_x,axis=1)
print(prediction)
return prediction
test_dicoms = ['test3.dcm','test2.dcm','test1.dcm','test4.dcm','test5.dcm','test6.dcm']
model_path = "model_adam.json" #path to saved model
weight_path = "model.h5" #path to saved best weights
#IMG_SIZE=(1,342,257,1) # This might be different if you did not use vgg16
#img_mean = 0.49262813 # mean image value from Build and train model line 22
#img_std = 0.24496286 # loads the std dev from Build and train model line 22
#my_model = load_model(model_path, weight_path) #loads model
#thresh = 0.62786263 #threshold value for New Model2 from Build and train model line 66 at 80% Precision
# use the .dcm files to test your prediction
for i in test_dicoms:
img = np.array([])
img = check_dicom(i)
if img is None:
continue
classes = {'TRAIN': ['BACTERIAL', 'NORMAL', 'VIRAL'],
'VALIDATION': ['BACTERIA', 'NORMAL'],
'TEST': ['BACTERIA', 'NORMAL', 'VIRUS']}
img_proc = preprocess_image(img)
prediction = predict_image(load_model(model_path, weight_path),img_proc)
predicted_class = classes['TRAIN'][int(prediction[0])]
print('Model Classification:', predicted_class, 'Pneumonia' )
print('--------------------------------------------------------------------------------------------------------')
以下是输出：
2022-01-02 10:50:00.817561: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2022-01-02 10:50:00.817601: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Loading file test3.dcm ...
ID: 61 Age: 77 Modality: DX Postion: AP Body Part: CHEST Study Desc: Effusion
2022-01-02 10:50:02.652828: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2022-01-02 10:50:02.652859: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
2022-01-02 10:50:02.652899: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (Wisdom-HP-250-G3-Notebook-PC): /proc/driver/nvidia/version does not exist
2022-01-02 10:50:02.653123: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
[[0.01132523 0.00254696 0.98612785]]
[2]
Model Classification: VIRAL Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test2.dcm ...
ID: 1 Age: 58 Modality: DX Postion: AP Body Part: CHEST Study Desc: Cardiomegaly
[[0.01112939 0.00251635 0.9863543 ]]
[2]
Model Classification: VIRAL Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test1.dcm ...
ID: 2 Age: 81 Modality: DX Postion: PA Body Part: CHEST Study Desc: No Finding
[[0.01128576 0.00255111 0.9861631 ]]
[2]
Model Classification: VIRAL Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test4.dcm ...
The image is not valid because the image position, the image type or the body part is not as per standards
Loading file test5.dcm ...
ID: 2 Age: 81 Modality: CT Postion: PA Body Part: CHEST Study Desc: No Finding
[[0.01128576 0.00255111 0.9861631 ]]
[2]
Model Classification: VIRAL Pneumonia
--------------------------------------------------------------------------------------------------------
Loading file test6.dcm ...
ID: 2 Age: 81 Modality: DX Postion: XX Body Part: CHEST Study Desc: No Finding
WARNING:tensorflow:5 out of the last 5 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7fba38ed19d0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.
[[0.01128576 0.00255111 0.9861631 ]]
[2]
Model Classification: VIRAL Pneumonia
---------------------------------------
我的怀疑是，当我集成了这两个脚本时，我在图像预处理步骤上做得不对(记住：目标是利用第二个脚本的Dicom读取功能(。因此，当我集成了这两个脚本时，由于尝试预处理时阵列排列错误，模型完全接受并预测了错误的输入。如果需要一些关于参数的信息，请在jupyter模型的训练演示中突出显示。
当分类器在训练/测试中工作正常，但在生产中进行推理时工作不正常时，一个非常常见的原因是训练数据与生产数据的处理方式不同。解决方法是确保它得到相同的处理，最好使用相同的代码位。
-
分类器训练的jpegs是如何处理的？最初是来自双子叶植物吗？如果是，转换的确切代码是什么？
-
训练期间jpegs的负载情况如何？要特别注意修改数据而不仅仅是复制数据的位，例如gray_img=(img-img_mean(/img_std和代码中其他注释掉的行(可能在训练过程中没有注释掉(
-
如果您复制dicom->jpeg从1转换，jpeg从2加载，你可能会有一个工作预测
下面的dicom到jpeg转换函数为我完成了任务：
def take_dicom(dicomname):
ds = read_file('Dicom_files/' + dicomname)
im = fromarray(ds.pixel_array)
final_img = im.save('./Jpeg/' + dicomname + '.jpg')
pure_jpg = dicomname + '.jpg'
return pure_jpg
只需要使用os函数将我的预测函数指向在预处理和诊断这些jpeg之前应该选择的位置：
def preprocess_image(pure_jpg):
'''
Args:
-- img_path : an URL path where a given image is stored.
-- model : a given Keras CNN model.
'''
#print(pure_jpg)
basepath = os.path.dirname('./Jpeg/')
file_path = os.path.join(
basepath, img)
#image = take_dicom(file_path)
#print(str(image))
IMG = image.load_img(file_path).convert('L')
#print(IMG)
#print(type(IMG))
# Pre-processing the image
IMG_ = IMG.resize((257, 342))
#print(type(IMG_))
IMG_ = np.asarray(IMG_)
#print(IMG_.shape)
IMG_ = np.true_divide(IMG_, 255)
IMG_ = IMG_.reshape(1, 342, 257, 1)
#print(type(IMG_), IMG_.shape)
return IMG_
然而，问题是它只适用于以下两种dicom成像模式：
- DX(数字X射线(
- CT(计算机Tormography(
CR(计算机射线照相(dicom图像无法转换。