license: apache-2.0
tags:

• 视觉
• 图像分类
  datasets:
• nih-pc-chex-mimic_ch-google-openi-rsna

densenet121-res224-rsna

DenseNet是一种卷积神经网络，通过密集块（Dense Blocks）利用层间的密集连接，将所有层（具有相同特征图尺寸）直接相互连接。为了保持前馈特性，每一层都会接收来自前面所有层的额外输入，并将其自身的特征图传递给后续所有层。

使用方法

以下是如何使用该模型对X光图像进行分类的示例：

注意：每个预训练模型有18个输出。all模型训练了所有输出。但对于其他权重，某些目标未经过训练（因为训练数据集中不存在这些目标），将随机预测。有效的输出仅列在与权重对应的数据集的{dataset}.pathologies字段中。

模型基准测试见：BENCHMARKS.md

import urllib.request  
import skimage  
import torch  
import torch.nn.functional as F  
import torchvision  
import torchvision.transforms  
import torchxrayvision as xrv  

model_name = "densenet121-res224-rsna"  

img_url = "https://huggingface.co/spaces/torchxrayvision/torchxrayvision-classifier/resolve/main/16747_3_1.jpg"  
img_path = "xray.jpg"  
urllib.request.urlretrieve(img_url, img_path)  

model = xrv.models.get_model(model_name, from_hf_hub=True)  

img = skimage.io.imread(img_path)  
img = xrv.datasets.normalize(img, 255)  

# 确保图像是二维数组  
if len(img.shape) > 2:  
    img = img[:, :, 0]  
if len(img.shape) < 2:  
    print("错误：图像维度低于2")  

# 添加颜色通道  
img = img[None, :, :]  

transform = torchvision.transforms.Compose([xrv.datasets.XRayCenterCrop()])  

img = transform(img)  

with torch.no_grad():  
    img = torch.from_numpy(img).unsqueeze(0)  
    preds = model(img).cpu()  
    output = {  
        k: float(v)  
        for k, v in zip(xrv.datasets.default_pathologies, preds[0].detach().numpy())  
    }  
print(output)  

更多代码示例，请参考示例脚本。

引用

TorchXRayVision主要论文：https://arxiv.org/abs/2111.00595

Joseph Paul Cohen, Joseph D. Viviano, Paul Bertin, Paul Morrison, Parsa Torabian, Matteo Guarrera, Matthew P Lungren, Akshay Chaudhari, Rupert Brooks, Mohammad Hashir, Hadrien Bertrand  
TorchXRayVision: 胸部X光数据集和模型库。  
https://github.com/mlmed/torchxrayvision, 2020  

@article{Cohen2020xrv,  
author = {Cohen, Joseph Paul and Viviano, Joseph D. and Bertin, Paul and Morrison, Paul and Torabian, Parsa and Guarrera, Matteo and Lungren, Matthew P and Chaudhari, Akshay and Brooks, Rupert and Hashir, Mohammad and Bertrand, Hadrien},  
journal = {https://github.com/mlmed/torchxrayvision},  
title = {{TorchXRayVision: 胸部X光数据集和模型库}},  
url = {https://github.com/mlmed/torchxrayvision},  
year = {2020}  
arxivId = {2111.00595},  
}  

以及该库开发的初始论文：https://arxiv.org/abs/2002.02497

Joseph Paul Cohen and Mohammad Hashir and Rupert Brooks and Hadrien Bertrand  
关于自动化X光预测中跨域泛化的限制。  
Medical Imaging with Deep Learning 2020 (在线: https://arxiv.org/abs/2002.02497)  

@inproceedings{cohen2020limits,  
  title={关于自动化X光预测中跨域泛化的限制},  
  author={Cohen, Joseph Paul and Hashir, Mohammad and Brooks, Rupert and Bertrand, Hadrien},  
  booktitle={Medical Imaging with Deep Learning},  
  year={2020},  
  url={https://arxiv.org/abs/2002.02497}  
}