基于LIDC-IDRI肺结节肺癌数据集的人工智能深度学习分类良性和恶性肺癌（Python 全代码）全流程解析（二）
1 环境配置和数据集预处理1.1 环境配置1.1 数据集预处理 2 深度学习模型训练和评估2.1 深度学习模型训练2.1 深度学习模型评估 笑话一则开心一下喽完整代码如下：模型文件如下深度学习模型讲解---待续
第一部分内容的传送门
1 环境配置和数据集预处理
1.1 环境配置
环境配置建议使用anaconda进行配置。核心的配置是keras和tensorflow的版本要匹配。
环境配置如下：
tensorboard 1.13.1
tensorflow 1.13.1
Keras 2.2.4
numpy 1.21.5
opencv-python 4.6.0.66
python 3.7
1.1 数据集预处理
数据集的预处理分为两个关键步骤。首先是图片处理，我们使用cv2库将图片转换为矩阵格式。这些矩阵随后被堆叠，并放入一个列表中，以便于深度学习模型的读取和处理。
其次是标签处理。我们从保存肺癌恶性程度信息的label.csv文件中逐行读取数据。通过切片和提取，我们获取了肺癌的恶性程度评级，这些评级在1到5之间。我们将大于3的评级归类为恶性，小于3的评级归类为良性。为了让模型更好地理解这些标签，我们用1表示良性，0表示恶性，最后将标签数据转换为one-hot编码格式。
输出与处理的函数如下：
import matplotlib.pyplot as pltimport numpy as npimport kerasimport cv2import osfrom keras.preprocessing.image import img_to_arrayfrom keras.utils import to_categorical, plot_modeldef load_data(label_path,data_path): data_x = [] labels = [] f = open(label_path) label = f.readlines() for Pathimg in os.listdir(os.path.join(data_path,'x')): Path = os.path.join(os.path.join(data_path,'x'),Pathimg) #print(Path) image = cv2.imread(Path) image = img_to_array(image) data_x.append(image) #处理label index_num = int(Pathimg.split('.')[0]) # print(labels)用索隐处理， a = label[index_num] label_ = int(a[-3:-2]) label_1 = 1 if label_ > 3 else 0 labels.append(label_1) print(labels) # print(data) #guiyihua data_x = np.array(data_x,dtype='float') / 255.0 labels = np.array(labels) #转化标签为张量 labels = to_categorical(labels) #载入data——y data_y = [] for Pathimg in os.listdir(os.path.join(data_path,'y')): Path = os.path.join(os.path.join(data_path,'y'),Pathimg) #print(Path) image = cv2.imread(Path) image = img_to_array(image) data_y.append(image) #guiyihua data_y = np.array(data_y,dtype='float') / 255.0 #处理Z data_z = [] for Pathimg in os.listdir(os.path.join(data_path,'z')): Path = os.path.join(os.path.join(data_path,'z'),Pathimg) #print(Path) image = cv2.imread(Path) image = img_to_array(image) data_z.append(image) #guiyihua data_z = np.array(data_y,dtype='float') / 255.0 return labels,data_x,data_y,data_z我们定义好数据预处理的函数后读取数据。图片的数据的格式如下：
其中有875个图片，每个图片的大小为50*50和3个通道
label的格式如下：
2 深度学习模型训练和评估
2.1 深度学习模型训练
我们已经在另一个文件中创建了一个深度学习模型，并且定义了一个函数来导入这个模型。在这里，我们将实例化这个函数。该函数会返回模型的结构以及模型训练的记录信息。
这个模型的输入是来自三个不同角度的图像和对应的标签。模型将被训练 5 个周期，每个周期训练 50 个图像。我们将使用 TensorBoard 查看模型的训练记录。
#######搭建模型model,callbacks = create_model()#模型训练H = model.fit([data_x,data_y,data_z],[labels], epochs=5,batch_size=50, callbacks=callbacks)训练结果如下：
我们可以看到训练的准确率还可以为0.7451左右
训练完成后我们将模型储存起来方便对模型进行评估。
#######save model to diskprint('info:saving model.....')model.save(os.path.join(result_path,'model_44.h5'))2.1 深度学习模型评估
模型的评估我们首先使用了，分类模型训练的损失函数和准确率来评估模型的训练过程。之后我们还会介绍模型的评估的其他指标。包括混淆矩阵，ROC曲线，AUC值，等
#准确率损失曲线绘制plt.style.use('ggplot')plt.figure()N = 5fig = plt.plot(np.arange(0, N), H.history["loss"], label="train_loss")#plt.plot(np.arange(0, N), H.history["val_loss"], label="val_loss")plt.plot(np.arange(0, N), H.history["acc"], label="train_acc")#plt.plot(np.arange(0, N), H.history["val_acc"], label="val_acc")plt.title("Training Loss and Accuracy on traffic-sign classifier")plt.xlabel("Epoch #")plt.ylabel("Loss/Accuracy")plt.legend(loc="lower left")#plt.show()plt.savefig('a.jpg',dpi=800)训练结果如下：
笑话一则开心一下喽
今天去买水果，我问一个摊主：别人家的瓜都写着不甜包退，你怎么不敢写呢，瓜不好吧。摊主：不买滚，我他么卖的是苦瓜……
深度学习，医学图像处理，机器学习精通，需要帮助的联系我（有偿哦）
完整代码如下：
import matplotlib.pyplot as pltimport numpy as npimport kerasimport cv2import osos.chdir('F:\工作\博客\sort_lung')from models import create_modelfrom load_datas import load_datalabel_path = r'F:\test\data\label.txt'data_path = r'F:\test\data\train'result_path = r'F:\test\result'#读取预处理数据labels,data_x,data_y,data_z = load_data(label_path,data_path)#######搭建模型model,callbacks = create_model()#模型训练H = model.fit([data_x,data_y,data_z],[labels], epochs=5,batch_size=50, callbacks=callbacks)#save model to diskprint('info:saving model.....')model.save(os.path.join(result_path,'model_44.h5'))#准确率损失曲线绘制plt.style.use('ggplot')plt.figure()N = 5fig = plt.plot(np.arange(0, N), H.history["loss"], label="train_loss")#plt.plot(np.arange(0, N), H.history["val_loss"], label="val_loss")plt.plot(np.arange(0, N), H.history["acc"], label="train_acc")#plt.plot(np.arange(0, N), H.history["val_acc"], label="val_acc")plt.title("Training Loss and Accuracy on traffic-sign classifier")plt.xlabel("Epoch #")plt.ylabel("Loss/Accuracy")plt.legend(loc="lower left")#plt.show()plt.savefig('a.jpg',dpi=800)模型文件如下
深度学习模型讲解—待续
# -*- coding: utf-8 -*-"""Created on Sun Apr 14 21:08:01 2024@author: dell"""from keras.preprocessing.image import ImageDataGeneratorfrom keras.optimizers import Adamfrom sklearn.model_selection import train_test_splitfrom keras.preprocessing.image import img_to_arrayfrom keras.utils import to_categorical, plot_modelfrom keras.models import Model#from imutils import pathsimport matplotlib.pyplot as pltimport numpy as npimport kerasimport cv2import os#定义模型from keras.models import Sequentialfrom keras.layers import Conv2D, MaxPooling2Dfrom keras.layers import Activation, Dropout, Flatten, Dense, Input,Concatenatedef create_model(): model = Sequential() #############定义多输入 input1 = Input(shape=(50,50,3),name = 'input1') input2 = Input(shape=(50,50,3),name = 'input2') input3 = Input(shape=(50,50,3),name = 'input3') #############定义多输入 x1 = Conv2D(32, (3, 3),padding='same' )(input1)#input is height,width,deep x1 = Activation('relu')(x1) x1 = Conv2D(32, (3, 3),padding='same')(x1) x1 = Activation('relu')(x1) x1 = MaxPooling2D(pool_size=(2, 2),strides = (2, 2))(x1) x1 = Conv2D(48, (3, 3),padding='same')(x1) x1 = Activation('relu')(x1) x1 = Conv2D(48, (3, 3),padding='same')(x1) x1 = Activation('relu')(x1) x1 = MaxPooling2D(pool_size=(2, 2),strides = (2, 2))(x1) x1 = Conv2D(64, (3, 3),padding='same')(x1) x1 = Activation('relu')(x1) x1 = Conv2D(64, (3, 3),padding='same')(x1) x1 = Activation('relu')(x1) x1 = MaxPooling2D(pool_size=(2, 2),strides = (2, 2))(x1) # the model so far outputs 3D feature maps (height, width, features) #base_model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors x1 = Flatten()(x1) x1 = Dense(256)(x1) x1 = Activation('relu')(x1) x1 = Dropout(0.5)(x1) category_predict1 = Dense(100, activation='softmax', name='category_predict1')(x1) # Three loss functions#定义三个全连接层 x2 = Conv2D(32, (3, 3),padding='same' )(input2)#input is height,width,deep x2 = Activation('relu')(x2) x2 = Conv2D(32, (3, 3),padding='same')(x2) x2 = Activation('relu')(x2) x2 = MaxPooling2D(pool_size=(2, 2),strides = (2, 2))(x2) x2 = Conv2D(48, (3, 3),padding='same')(x2) x2 = Activation('relu')(x2) x2 = Conv2D(48, (3, 3),padding='same')(x2) x2 = Activation('relu')(x2) x2 = MaxPooling2D(pool_size=(2, 2),strides = (2, 2))(x2) x2 = Conv2D(64, (3, 3),padding='same')(x2) x2 = Activation('relu')(x2) x2 = Conv2D(64, (3, 3),padding='same')(x2) x2 = Activation('relu')(x2) x2 = MaxPooling2D(pool_size=(2, 2),strides = (2, 2))(x2) # the model so far outputs 3D feature maps (height, width, features) #base_model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors x2 = Flatten()(x2) x2 = Dense(256)(x2) x2 = Activation('relu')(x2) x2 = Dropout(0.5)(x2) category_predict2 = Dense(100, activation='relu', name='category_predict2')(x2) x3 = Conv2D(32, (3, 3),padding='same' )(input3)#input is height,width,deep x3 = Activation('relu')(x3) x3 = Conv2D(32, (3, 3),padding='same')(x3) x3 = Activation('relu')(x3) x3 = MaxPooling2D(pool_size=(2, 2),strides = (2, 2))(x3) x3 = Conv2D(48, (3, 3),padding='same')(x3) x3 = Activation('relu')(x3) x3 = Conv2D(48, (3, 3),padding='same')(x3) x3 = Activation('relu')(x3) x3 = MaxPooling2D(pool_size=(2, 2),strides = (2, 2))(x3) x3 = Conv2D(64, (3, 3),padding='same')(x3) x3 = Activation('relu')(x3) x3 = Conv2D(64, (3, 3),padding='same')(x3) x3 = Activation('relu')(x3) x3 = MaxPooling2D(pool_size=(2, 2),strides = (2, 2))(x3) # the model so far outputs 3D feature maps (height, width, features) #base_model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors x3 = Flatten()(x3) x3 = Dense(256)(x3) x3 = Activation('relu')(x3) x3 = Dropout(0.5)(x3) category_predict3 = Dense(100, activation='relu', name='category_predict3')(x3) #融合全连接层 merge = Concatenate()([category_predict1,category_predict2,category_predict3]) #定义输出 output = Dense(2,activation='sigmoid', name='output')(merge) model = Model(inputs=[input1, input2, input3], outputs=[output]) callbacks = [keras.callbacks.TensorBoard( log_dir='my_log_dir', )] model.compile(optimizer=Adam(lr=0.001,decay=0.01), loss='binary_crossentropy', metrics=['accuracy'], ) return model,callbacks