Fully Automated Deep Learning System for Bone Age Assessment.

Fully Automated Deep Learning System for Bone Age Assessment.
复制标题

DOI:
10.1007/s10278-017-9955-8
复制
发表时间:
2017-08
影响因子:
4.4
通讯作者:
Do S
Do S
中科院分区:
工程技术2区
文献类型:
--
作者:
Lee H;Tajmir S;Lee J;Zissen M;Yeshiwas BA;Alkasab TK;Choy G;Do S

文献摘要

参考文献

被引文献

相似文献

骨骼成熟度通过离散阶段进展,这是儿科中常规使用的一个事实,其中骨龄评估(BAA)与实际年龄在内分泌和代谢疾病的评估中进行比较。虽然对许多疾病评估至关重要,但自1950年引入以来,几乎没有改变以改善繁琐的过程。在这项研究中,我们提出了一个完全自动化的深度学习管道来分割感兴趣的区域,标准化和预处理输入射线照片,并执行BAA。我们的模型使用ImageNet预训练,微调的卷积神经网络(CNN),在我们的测试图像上为女性和男性群体实现了57.32%和61.40%的准确率。女性受试者的X线片在1年内被指定为BAA的比例为90.39%,在2年内被指定为BAA的比例为98.11%。男性试验X线片1年内分配率为94.18%,2年内分配率为99.00%。使用输入遮挡方法,创建了注意力图,揭示了训练模型用于执行BAA的特征。这些对应于人类专家在手动执行BAA时看到的内容。最后,全自动BAA系统被部署在临床环境中作为决策支持系统,以比传统方法更快的解释时间(<2 s)获得更准确和有效的BAA。
Skeletal maturity progresses through discrete phases, a fact that is used routinely in pediatrics where bone age assessments (BAAs) are compared to chronological age in the evaluation of endocrine and metabolic disorders. While central to many disease evaluations, little has changed to improve the tedious process since its introduction in 1950. In this study, we propose a fully automated deep learning pipeline to segment a region of interest, standardize and preprocess input radiographs, and perform BAA. Our models use an ImageNet pretrained, fine-tuned convolutional neural network (CNN) to achieve 57.32 and 61.40% accuracies for the female and male cohorts on our held-out test images. Female test radiographs were assigned a BAA within 1 year 90.39% and within 2 years 98.11% of the time. Male test radiographs were assigned 94.18% within 1 year and 99.00% within 2 years. Using the input occlusion method, attention maps were created which reveal what features the trained model uses to perform BAA. These correspond to what human experts look at when manually performing BAA. Finally, the fully automated BAA system was deployed in the clinical environment as a decision supporting system for more accurate and efficient BAAs at much faster interpretation time (<2 s) than the conventional method.
DOI: 10.1007/s11263-015-0816-y
发表时间: 2015-12-01
影响因子: 19.5
作者:
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者: Fei-Fei, Li
DOI: 10.1109/tmi.2016.2528162
发表时间: 2016-05
影响因子: 10.6
作者:
Shin HC;Roth HR;Gao M;Lu L;Xu Z;Nogues I;Yao J;Mollura D;Summers RM
通讯作者: Summers RM
DOI: 10.1016/s0895-6111(00)00026-4
发表时间: 2000-09-01
影响因子: 5.7
作者:
Cao, F;Huang, HK;Gilsanz, V
通讯作者: Gilsanz, V
DOI: 10.1109/tpami.2015.2439285
发表时间: 2016-04-01
影响因子: 23.6
作者:
Deng, Jia;Krause, Jonathan;Fei-Fei, Li
通讯作者: Fei-Fei, Li
DOI: 10.1109/tmi.2016.2535865
发表时间: 2016-05-01
影响因子: 10.6
作者:
Anthimopoulos, Marios;Christodoulidis, Stergios;Mougiakakou, Stavroula
通讯作者: Mougiakakou, Stavroula