使用掩码条件潜在扩散模型与大规模慢性伤口数据集迁移学习的合成麻风病图像生成
Synthetic Leprosy Image Generation Using Mask-Conditioned Latent Diffusion and Transfer Learning from Large Chronic Wound Datasets
浏览论文内容
中文总结 AI 辅助
本研究利用慢性伤口图像训练掩码条件潜在扩散模型，迁移至低数据麻风病图像生成，验证了跨域迁移可行性，并指出主要瓶颈是语义控制而非图像质量。
中文摘要 AI 辅助
被忽视热带病的机器学习受限于数据而非算法：公开的麻风病（汉森病）标注图像集仅有数百张，比生成模型所需的数据量低数个数量级。我们探究在丰富的慢性伤口摄影图像上训练的模型能否迁移到这一低数据场景。我们构建了一个三阶段流程。首先，一个DeepLabV3-ResNet50分割网络（验证Dice系数0.876，IoU 0.799）为两个未附带掩码的伤口数据集提供病灶掩码。其次，我们利用Stable Diffusion 1.5组件组装了一个掩码条件潜在扩散模型，并在3,280个伤口感兴趣区域裁剪块上训练，将UNet输入卷积从4通道扩展至11通道，以接纳三个掩码特征图和一个模糊的低频上下文潜在向量。第三，我们在来自约150名患者的764张图像中选取的708对麻风病图像-掩码对上微调该模型。我们使用LPIPS感知距离进行评估，并以在相同242张锚定图像上计算的真实-真实基线作为参照；若无此参照，跨数据集距离将无法解释。生成集未出现模式坍塌：其内部感知多样性（0.662）与真实麻风病集（0.672，95%置信区间[0.664, 0.680]）在统计上无显著差异。生成图像与真实分布的距离为0.044 LPIPS——可测量地分开，但不到半个标准差。微调仅使输出分布发生微小变化，我们将其归因于病灶几何仅通过输入拼接到达网络。因此，慢性伤口摄影是麻风病病灶合成的可行供体领域：低级外观迁移良好，剩余障碍在于语义控制而非图像质量。
英文摘要
Machine learning for neglected tropical diseases is limited by data, not algorithms: public annotated image sets for leprosy (Hansen's disease) number in the hundreds, orders of magnitude below what generative models require. We ask whether a model trained on abundant chronic wound photography transfers to this low-data regime. We build a three-stage pipeline. First, a DeepLabV3-ResNet50 segmentation network (validation Dice 0.876, IoU 0.799) supplies lesion masks for two wound datasets that ship without them. Second, we assemble a mask-conditioned latent diffusion model from Stable Diffusion 1.5 components and train it on 3,280 region-of-interest wound crops, widening the UNet input convolution from 4 to 11 channels to admit three mask feature maps and a blurred low-frequency context latent. Third, we fine-tune this model on 708 leprosy image-mask pairs drawn from 764 images of approximately 150 patients. We evaluate with LPIPS perceptual distance, anchored by a real-versus-real baseline computed on the same 242 anchor images as the cross-set comparisons; without that reference the cross-set distances cannot be interpreted. The generated set shows no mode collapse: its internal perceptual diversity (0.662) is statistically indistinguishable from that of the real leprosy set (0.672, 95% CI [0.664, 0.680]). Generated images sit 0.044 LPIPS outside the real distribution - measurably apart, but under half of one standard deviation. Fine-tuning shifted the output distribution only marginally, which we trace to lesion geometry reaching the network through input concatenation alone. Chronic wound photography is therefore a viable donor domain for leprosy lesion synthesis: low-level appearance transfers well, and the remaining barrier is semantic control rather than image quality.
发表机构
- Poolesville High School（普尔斯维尔高中）
机构由 AI 辅助整理，请以论文原文为准。
