Deep learning based medical image recognition systems often require a
substantial amount of training data with expert annotations, which can be
expensive and time-consuming to obtain. Recently, synthetic augmentation
techniques have been proposed to mitigate the issue by generating realistic
images conditioned on class labels. However, the effectiveness of these methods
heavily depends on the representation capability of the trained generative
model, which cannot be guaranteed without sufficient labeled training data. To
further reduce the dependency on annotated data, we propose a synthetic
augmentation method called HistoDiffusion, which can be pre-trained on
large-scale unlabeled datasets and later applied to a small-scale labeled
dataset for augmented training. In particular, we train a latent diffusion
model (LDM) on diverse unlabeled datasets to learn common features and generate
realistic images without conditional inputs. Then, we fine-tune the model with
classifier guidance in latent space on an unseen labeled dataset so that the
model can synthesize images of specific categories. Additionally, we adopt a
selective mechanism to only add synthetic samples with high confidence of
matching to target labels. We evaluate our proposed method by pre-training on
three histopathology datasets and testing on a histopathology dataset of
colorectal cancer (CRC) excluded from the pre-training datasets. With
HistoDiffusion augmentation, the classification accuracy of a backbone
classifier is remarkably improved by 6.4% using a small set of the original
labels. Our code is available at this https URL

通过在大规模无标签数据集上预训练潜在扩散模型（LDM），我们提出了一种名为 HistoDiffusion 的合成增强方法，然后在未见过的有标签数据集上通过分类器引导在潜在空间中微调模型，以合成特定类别的图像，并采用选择性机制只添加与目标标签匹配度较高的合成样本，通过 HistoDiffusion 增强，使用少量原始标签，我们大幅提高了骨干分类器的分类准确率 6.4%。

大规模无条件预训练的合成增强

Synthetic Augmentation with Large-scale Unconditional Pre-training

Integrating deep learning with clinical expertise holds great potential for
addressing healthcare challenges and empowering medical professionals with
improved diagnostic tools. However, the need for annotated medical images is
often an obstacle to leveraging the full power of machine learning models. Our
research demonstrates that by combining synthetic images, generated using
diffusion models, with real images, we can enhance nonalcoholic fatty liver
disease (NAFLD) classification performance. We evaluate the quality of the
synthetic images by comparing two metrics: Inception Score (IS) and Fr\'{e}chet
Inception Distance (FID), computed on diffusion-generated images and generative
adversarial networks (GANs)-generated images. Our results show superior
performance for the diffusion-generated images, with a maximum IS score of
$1.90$ compared to $1.67$ for GANs, and a minimum FID score of $69.45$ compared
to $99.53$ for GANs. Utilizing a partially frozen CNN backbone (EfficientNet
v1), our synthetic augmentation method achieves a maximum image-level ROC AUC
of $0.904$ on a NAFLD prediction task.

综合临床专业知识和深度学习技术，通过利用扩散模型生成的合成图像和真实图像相结合，文中通过基于 NAFLD 分类的实验表明，综合使用效果明显优于仅使用生成对抗网络（GANs）进行图像增广，达到了 0.904 的最佳图像级别 ROC AUC 性能。