• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Medical Image Computing and Computer-Assisted Intervention;International Workshop on Ophthalmic Medical Image Analysis >Automated Stage Analysis of Retinopathy of Prematurity Using Joint Segmentation and Multi-instance Learning
【24h】

Automated Stage Analysis of Retinopathy of Prematurity Using Joint Segmentation and Multi-instance Learning

机译：利用关节分割和多实例学习对早产儿视网膜病变进行自动阶段分析

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Retinopathy of prematurity (ROP) is the primary cause of childhood blindness. Prior works have demonstrated the remarkable performances of deep learning (DL) in detecting plus disease and classification between ROP or Normal with retinal images. However, few studies are focused on identifying the 'stage' of ROP disease, which is an important factor to evaluate the severity of the disease. In general, only a small region (typical less than 5% of the image) of a fundus image contributes its being classified as different stages of ROP. Therefore, traditional convolutional neural network (CNN) classifier may be ineffective when it is applied to a global feature extraction while the ROP features are localized with a limited number of labeled images. To address this issue, we combine the segmentation and staging, using both fully convolutional network (FCN) and multi-instance learning (MIL) to achieve integrated task of ROP staging and lesions localization. The proposed network is evaluated on 7330 retinal images (2000 Normal, 630 Stagel, 980 Stage2, 870 Stage3 and 250 Stage4) obtained by RetCam3. Experimental results show that the proposed network achieves 0.93 area under the curve (AUC) on the test dataset (accuracy 92.25%, sensitivity 90.53% and specificity 92.35%), and ROP lesions such as demarcation lines, ridges can be accurately located in the fundus images.
机译：早产儿视网膜病变（ROP）是儿童失明的主要原因。先前的工作已经证明了深度学习（DL）在检测视网膜病变和正常视网膜之间的疾病和分类方面的卓越性能。但是，很少有研究致力于确定ROP疾病的“阶段”，这是评估该疾病严重程度的重要因素。通常，仅眼底图像的一小部分区域（通常小于图像的5％）有助于将其分类为ROP的不同阶段。因此，传统的卷积神经网络（CNN）分类器在将ROP特征定位在有限数量的标记图像中而应用于全局特征提取时可能无效。为了解决这个问题，我们使用完全卷积网络（FCN）和多实例学习（MIL）结合了分段和分期，以实现ROP分期和病变定位的综合任务。在RetCam3获得的7330个视网膜图像（2000正常，630 Stagel，980 Stage2、870 Stage3和250 Stage4）上评估了建议的网络。实验结果表明，该网络在测试数据集上的曲线下面积（AUC）达到0.93（准确度为92.25％，灵敏度为90.53％，特异性为92.35％），并且ROP病变（例如分界线，脊等）可以准确地位于眼底图片。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号