五类医学图像分类 深度学习

import matplotlib.pyplot as plt
import numpy as np
import PIL
import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential

读取图片

import pathlib
data_dir = r'C:\Users\86188\TensorFlow机器学习\CNN图像分类\五类图像'
data_dir = pathlib.Path(data_dir)
print(data_dir)

image_count = len(list(data_dir.glob('*/*.jpeg')))
print(image_count)

查看图片：

腹部CT = list(data_dir.glob('腹部CT/*'))
PIL.Image.open(str(腹部CT[0]))

脑部CT = list(data_dir.glob('脑部CT/*'))
PIL.Image.open(str(脑部CT[0]))

手X光片 = list(data_dir.glob('手X光片/*'))
PIL.Image.open(str(手X光片[0]))

胸部CT = list(data_dir.glob('胸部CT/*'))
PIL.Image.open(str(胸部CT[0]))

胸部X光片 = list(data_dir.glob('胸部X光片/*'))
PIL.Image.open(str(胸部X光片[0]))

定义一些参数：

#为加载器定义一些参数
batch_size = 32
img_height = 90
img_width = 90

使用 80% 的图像进行训练，使用 20% 的图像进行验证：

train_ds = tf.keras.utils.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="training",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

val_ds = tf.keras.utils.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="validation",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

class_names = train_ds.class_names
print(class_names)

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']

plt.figure(figsize=(10, 10))
for images, labels in train_ds.take(1):
  for i in range(9):
    ax = plt.subplot(5, 5,i+1)
    plt.imshow(images[i].numpy().astype("uint8"))
    plt.title(class_names[labels[i]])
    plt.axis("off")

for image_batch, labels_batch in train_ds:
  print(image_batch.shape)
  print(labels_batch.shape)
  break

image_batch是形状的张量(32, 90, 90, 3)。这是一批 32 张形状的图像90x90x3（最后一个维度是指颜色通道 RGB）。label_batch是 shape 的张量，(32,)这些是 32 幅图像的对应标签。

AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

normalization_layer = layers.Rescaling(1./255)
normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
image_batch, labels_batch = next(iter(normalized_ds))
first_image = image_batch[0]
print(np.min(first_image), np.max(first_image)) 

划分数据集并构建模型（CNN模型搭建）：

num_classes = len(class_names)

model = Sequential([
  layers.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
  layers.Conv2D(16, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),  #最大池化层
  layers.Conv2D(32, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(64, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes)
])

 调用compile()方法指定损失函数和要使用的优化器（选择 Adam）：

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])
model.summary()

模型训练：

epochs=10  #迭代次数
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

从训练集和验证集可以看出，该模型在验证集和测试的准确率高达100%，不存在过拟合的情况，也不需要再使用数据增强或dropout等方法了。

绘制准确率和损失值曲线：

acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(epochs)

plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('训练集和验证集的准确度')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('训练集和验证集的损失值')
plt.show()

评估模型：

loss,accuracy = model.evaluate(train_ds, verbose=1)  #verbose = 1 为输出进度条记录

print('损失值:',loss)
print('准确度:', accuracy )

进行预测：

手X光片_path = r"C:/Users/86188/TensorFlow机器学习/datasets/5ClassMedicalImg/手X光片/001017.jpeg"

img = tf.keras.utils.load_img(
    手X光片_path, target_size=(img_height, img_width)
)

img_array = tf.keras.utils.img_to_array(img)
img_array = tf.expand_dims(img_array, 0) # Create a batch


predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])

print(
    "这个图片大概属于 {} 有着 {:.2f}%准确度."
    .format(class_names[np.argmax(score)], 100 * np.max(score))
)