论著摘要 |【AI-DR】全自动骨龄评估深度学习系统(双语版)

2018-01-12 11:18:02 admin 0
标签:   人工智能 人工神经网络  计算机视觉 计算机辅助诊断 机器学习 结构化报告 CNN

Fully Automated Deep Learning System for Bone Age Assessment.

发表日期: 2017.03.08   来源:J Digit Imaging. 2017 Aug;30(4):427-441.

作者:

Hyunkwang Lee1, Shahein Tajmir1, Jenny Lee1, Maurice Zissen1 , Bethel Ayele Yeshiwas1, Tarik K. Alkasab1, Garry Choy1, Synho Do1.

作者介绍:

1. Massachusetts General Hospital and Harvard Medical School, Radiology, 25 New Chardon Street, Suite 400B, Boston, MA, 02114, USA.

摘要

骨骼成熟度通过不连续的阶段进行,这是一个常规用于儿科的事实,在评估内分泌和代谢紊乱时将骨龄评估(BAAs)与年龄进行比较。 自1950年推出以来,虽然是许多疾病评估的核心,但改进乏味的过程并没有什么改变。在这项研究中,我们提出了一个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预培训的微调卷积神经网络(CNN),以便在我们提供的测试图像上达到女性和男性队列的57.32和61.40%的精确度。女性测试X线片在1年内被分配了90.39%,在2年内被分配了98.11%的时间。男性测试X线片在1年内分配94.18%,2年内分配99.00%。使用输入遮挡方法,创建了注意图,揭示了训练模型用来执行BAA的特征。这些对应于人工专家在手动执行BAA时所看到的内容。最后,全自动化的BAA系统被部署在临床环境中,作为一个决策支持系统,以比传统方法更快速的解释时间(<2s)更精确和有效的BAAs。

Abstact

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.

关键词:

人工智能;人工神经网络(ANNs);自动测量;自动对象检测;骨年龄;分类;临床工作流程;计算机视觉;计算机辅助诊断(CAD);数据采集;决策支持;数字X线片测量;效率;机器学习;结构化报告

Keywords:

Artificial intelligence; Artificial neural networks (ANNs); Automated measurement; Automated object detection; Bone-age; Classification; Clinical workflow; Computer vision; Computer-aided diagnosis (CAD); Data collection; Decision support; Digital X-ray radiogrammetry; Efficiency; Machine learning; Structured reporting

阅读原文:PMID: 28275919  PMCID: PMC5537090  DOI: 10.1007/s10278-017-9955-8


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片