CleftGAN：调整基于风格的生成对抗网络以创建描绘唇裂畸形的图像
CleftGAN: Adapting A Style-Based Generative Adversarial Network To Create Images Depicting Cleft Lip Deformity
AI总结：
针对唇裂图像数据稀缺问题，提出基于StyleGAN-ADA的CleftGAN生成模型，通过迁移学习和ADA技术，以少量训练图像生成高保真、多样化的唇裂图像，并验证其有效性。
摘要：
在尝试训练机器学习系统评估面部唇裂时，一个主要障碍是缺乏高质量、经伦理委员会批准的患者图像的大型数据集。为此，我们构建了一个基于深度学习的唇裂生成器，旨在产生几乎无限数量的、具有高保真度且变异广泛的唇裂模拟人工图像。我们采用迁移学习协议，测试了不同版本的StyleGAN-ADA（一种结合自适应数据增强（ADA）的生成对抗网络图像生成器）作为基础模型。对描绘多种唇裂畸形的训练图像进行预处理，以调整旋转、缩放、颜色和背景模糊。主算法的ADA修改使得我们能够构建新的生成模型，同时只需输入相对较少的训练图像。使用514张唇裂面部正面照片进行对抗训练，以调整基于70,000张正常面孔的预训练模型。采用弗雷歇初始距离（FID）来衡量新生成面部图像与唇裂训练数据集的相似性，同时使用感知路径长度（PPL）和新的严重度直方图散度指数（DISH）来评估我们称之为CleftGAN的图像生成器的性能。我们发现具有平移不变性的StyleGAN3（StyleGAN3-t）作为基础模型表现最佳。生成的图像实现了低FID，反映出与真实唇裂图像训练输入数据集的紧密相似性。低PPL和DISH值分别反映了通过迁移学习过程图像插值的平滑性和语义有效性，以及训练和生成图像中严重程度的相似分布。
英文摘要：
A major obstacle when attempting to train a machine learning system to evaluate facial clefts is the scarcity of large datasets of high-quality, ethics board-approved patient images. In response, we have built a deep learning-based cleft lip generator designed to produce an almost unlimited number of artificial images exhibiting high-fidelity facsimiles of cleft lip with wide variation. We undertook a transfer learning protocol testing different versions of StyleGAN-ADA (a generative adversarial network image generator incorporating adaptive data augmentation (ADA)) as the base model. Training images depicting a variety of cleft deformities were pre-processed to adjust for rotation, scaling, color adjustment and background blurring. The ADA modification of the primary algorithm permitted construction of our new generative model while requiring input of a relatively small number of training images. Adversarial training was carried out using 514 unique frontal photographs of cleft-affected faces to adapt a pre-trained model based on 70,000 normal faces. The Frechet Inception Distance (FID) was used to measure the similarity of the newly generated facial images to the cleft training dataset, while Perceptual Path Length (PPL) and the novel Divergence Index of Severity Histograms (DISH) measures were also used to assess the performance of the image generator that we dub CleftGAN. We found that StyleGAN3 with translation invariance (StyleGAN3-t) performed optimally as a base model. Generated images achieved a low FID reflecting a close similarity to our training input dataset of genuine cleft images. Low PPL and DISH measures reflected a smooth and semantically valid interpolation of images through the transfer learning process and a similar distribution of severity in the training and generated images, respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
