当前位置：首页 > article >正文

深度学习-利用预训练的 ResNet 和 DenseNet 模型进行医学影像诊断

article 2025/2/11 4:02:54

下面将分别展示基于 PyTorch 框架，利用预训练的 ResNet 和 DenseNet 模型进行医学影像诊断以提高准确率的代码实现。以肺炎 X 光影像诊断为例，假设数据集已经按照训练集和测试集划分好，每个类别存放在不同文件夹中。

1. 安装必要的库

pip install torch torchvision numpy matplotlib pandas

2. 使用 ResNet 实现医学影像诊断

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms, models
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
import numpy as np

# 数据预处理
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

# 加载数据集
train_dataset = datasets.ImageFolder(root='path/to/train_data', transform=transform)
test_dataset = datasets.ImageFolder(root='path/to/test_data', transform=transform)

# 创建数据加载器
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False)

# 加载预训练的 ResNet 模型
model = models.resnet18(pretrained=True)
num_ftrs = model.fc.in_features
# 修改最后一层全连接层以适应二分类任务
model.fc = nn.Linear(num_ftrs, 2)

# 定义设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = model.to(device)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
num_epochs = 10
train_losses = []
for epoch in range(num_epochs):
    running_loss = 0.0
    model.train()
    for i, (images, labels) in enumerate(train_loader):
        images, labels = images.to(device), labels.to(device)
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    epoch_loss = running_loss / len(train_loader)
    train_losses.append(epoch_loss)
    print(f'Epoch {epoch + 1}/{num_epochs}, Loss: {epoch_loss:.4f}')

# 绘制训练损失曲线
plt.plot(train_losses)
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.title('Training Loss')
plt.show()

# 评估模型
model.eval()
correct = 0
total = 0
with torch.no_grad():
    for images, labels in test_loader:
        images, labels = images.to(device), labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

accuracy = 100 * correct / total
print(f'Test Accuracy: {accuracy:.2f}%')

3. 使用 DenseNet 实现医学影像诊断

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms, models
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
import numpy as np

# 数据预处理
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

# 加载数据集
train_dataset = datasets.ImageFolder(root='path/to/train_data', transform=transform)
test_dataset = datasets.ImageFolder(root='path/to/test_data', transform=transform)

# 创建数据加载器
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False)

# 加载预训练的 DenseNet 模型
model = models.densenet121(pretrained=True)
num_ftrs = model.classifier.in_features
# 修改最后一层全连接层以适应二分类任务
model.classifier = nn.Linear(num_ftrs, 2)

# 定义设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = model.to(device)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
num_epochs = 10
train_losses = []
for epoch in range(num_epochs):
    running_loss = 0.0
    model.train()
    for i, (images, labels) in enumerate(train_loader):
        images, labels = images.to(device), labels.to(device)
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    epoch_loss = running_loss / len(train_loader)
    train_losses.append(epoch_loss)
    print(f'Epoch {epoch + 1}/{num_epochs}, Loss: {epoch_loss:.4f}')

# 绘制训练损失曲线
plt.plot(train_losses)
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.title('Training Loss')
plt.show()

# 评估模型
model.eval()
correct = 0
total = 0
with torch.no_grad():
    for images, labels in test_loader:
        images, labels = images.to(device), labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

accuracy = 100 * correct / total
print(f'Test Accuracy: {accuracy:.2f}%')