Selective synthetic augmentation with HistoGAN for improved histopathology image classification.
Selective synthetic augmentation with HistoGAN for improved histopathology image classification.
复制标题
与Histogan一起选择性合成增强，以改善组织病理学图像分类。
DOI：
10.1016/j.media.2020.101816
复制
发表时间：
2021-01
影响因子：
10.9
通讯作者：
Huang X
中科院分区：
文献类型：
--
作者：
Xue Y;Ye J;Zhou Q;Long LR;Antani S;Xue Z;Cornwell C;Zaino R;Cheng KC;Huang X
组织病理学分析是目前诊断癌前病变的金标准。从数字图像中实现自动组织病理学分类的目标需要有监督的训练，这需要大量昂贵且耗时的专家注释。同时，准确分类从整张幻灯片图像中裁剪出来的图像斑块是标准的基于滑动窗口的组织病理学切片分类方法的关键。为了缓解这些问题，我们提出了一个精心设计的条件GAN模型，即HistoGAN，用于合成以类别标签为条件的真实组织病理学图像补丁。我们还研究了一种新的合成增强框架，该框架选择性地添加由我们提出的HistoGAN生成的新的合成图像补丁，而不是直接用合成图像扩展训练集。通过基于所分配标签的置信度及其与真实标记图像的特征相似性来选择合成图像，我们的框架为合成增强提供了质量保证。我们的模型在两个数据集上进行了评估：一个是带有有限注释的宫颈组织病理学图像数据集，另一个是带有转移性癌症的淋巴结组织病理学图像数据集。在这里，我们表明，利用HistoGAN生成的图像，选择性增强，对宫颈组织病理学和转移性癌数据集的分类性能有显著和一致的改善（准确率分别提高6.7%和2.8%）。
Histopathological analysis is the present gold standard for precancerous lesion diagnosis. The goal of automated histopathological classification from digital images requires supervised training, which requires a large number of expert annotations that can be expensive and time-consuming. Meanwhile, accurate classification of image patches cropped from whole-slide images are essential for standard sliding window based histopathology slide classification methods. To mitigate these issues, we propose a carefully designed conditional GAN model, namely HistoGAN, for synthesizing realistic histopathology image patches conditioned on class labels. We also investigate a novel synthetic augmentation framework that selectively adds new synthetic image patches generated by our proposed HistoGAN, rather than expanding directly the training set with synthetic images. By selecting synthetic images based on the confidence of their assigned labels and their feature similarity to real labeled images, our framework provides quality assurance to synthetic augmentation. Our models are evaluated on two datasets: a cervical histopathology image dataset with limited annotations, and another dataset of lymph node histopathology images with metastatic cancer. Here, we show that leveraging HistoGAN generated images with selective augmentation results in significant and consistent improvements of classification performance (6.7% and 2.8% higher accuracy, respectively) for cervical histopathology and metastatic cancer datasets.
登录
查看更多内容
影响因子：
6.1
作者：
Chankong, Thanatip;Theera-Umpon, Nipon;Auephanwiriyakul, Sansanee
通讯作者：
Auephanwiriyakul, Sansanee
影响因子：
6
作者：
Frid-Adar, Maayan;Diamant, Idit;Greenspan, Hayit
通讯作者：
Greenspan, Hayit
影响因子：
12.8
作者：
Liu, Yufei;Zhou, Yuan;Wang, Zihong
通讯作者：
Wang, Zihong
DOI：
10.1109/cvpr.2016.266
发表时间：
2016-06
期刊：
Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition
影响因子：
--
作者：
Hou L;Samaras D;Kurc TM;Gao Y;Davis JE;Saltz JH
通讯作者：
Saltz JH
影响因子：
17.6
作者：
Gurcan MN;Boucheron LE;Can A;Madabhushi A;Rajpoot NM;Yener B
通讯作者：
Yener B