arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.02248cs.LGcs.CVstat.ML
收藏

用于骨病变病理数据增强的生成式图像翻译

Generative Image Translation for Data Augmentation of Bone Lesion Pathology

Courant Institute, New York University(纽约大学库朗研究所);Imagen Technologies(伊马根科技公司)

Anant Gupta, Srivas Venkatesh, Sumit Chopra, Christian Ledig

摘要:

在开发用于罕见疾病分类的机器学习模型时,训练数据不足和严重的类别不平衡往往是限制因素。在这项工作中,我们解决了从X射线图像中的骨病变的分类问题,通过增加少量的阳性样本的训练集。我们提出了一种基于周期一致的生成对抗网络的生成数据增强方法,该网络在没有病理的图像上合成骨病变。我们提出的生成任务作为一个图像补丁的翻译问题,我们专门针对不同的骨骼(肱骨,胫骨,股骨)进行优化。在实验结果中,我们确认所描述的方法减轻了骨病变检测的二进制分类任务中的类不平衡问题。我们表明,增强的训练集,使训练的优秀分类器实现更好的性能上举行了测试集。此外,我们证明了迁移学习的可行性,并将在一个身体部位上训练的生成模型应用于另一个身体部位。

英文摘要:

Insufficient training data and severe class imbalance are often limiting factors when developing machine learning models for the classification of rare diseases. In this work, we address the problem of classifying bone lesions from X-ray images by increasing the small number of positive samples in the training set. We propose a generative data augmentation approach based on a cycle-consistent generative adversarial network that synthesizes bone lesions on images without pathology. We pose the generative task as an image-patch translation problem that we optimize specifically for distinct bones (humerus, tibia, femur). In experimental results, we confirm that the described method mitigates the class imbalance problem in the binary classification task of bone lesion detection. We show that the augmented training sets enable the training of superior classifiers achieving better performance on a held-out test set. Additionally, we demonstrate the feasibility of transfer learning and apply a generative model that was trained on one body part to another.

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。

↑