论著摘要 |【AI-CT】多任务特征手段的多语义属性自动评分对肺结节CT图像进行研究(双语版)

2018-01-25 15:09:33 admin 0
标签:   人工智能 计算机辅助诊断 语义特征 影像特征 肺结节

Automatic Scoring of Multiple Semantic Attributes With Multi-Task Feature Leverage: A Study on Pulmonary Nodules in CT Images.

发表日期: 2016.11.16   来源:IEEE Trans Med Imaging. 2017 Mar;36(3):802-814.

作者:

Sihong Chen1, Jing Qin2, Xing Ji1, Baiying Lei1 , Tianfu Wang1, Dong Ni1, Jie-Zhi Cheng1.

作者介绍:

1. Department of Biomedical Engineering, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Medicine, Shenzhen University, Shenzhen, China

2. Smart Health, School of Nursing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong

摘要

计算和语义特征之间的差距是计算机辅助诊断(CAD)与临床使用相矛盾的主要因素之一。为弥补这一差距,我们利用三种多任务学习(MTL)方案来影响来自堆叠去噪自动编码器(SDAE)和卷积神经网络(CNN)的深度学习模型的异构计算特征,以及手工的Haar样和HoG特征,用于描述CT图像中9个肺结节的语义特征。我们认为可以通过MTL来探讨“毛刺征”,“纹理”,“边缘”等语义特征之间的关系。本研究采用肺图像数据库联盟(LIDC)数据作为丰富的注释资源。 LIDC结节量化评分美国几个研究机构的12位放射科医师的9个w.r.t.语义特征。通过将每个语义特征视为一项单独的任务,MTL方案利用交叉验证评估方案,从LIDC随机选择的2400个结节中选择和映射放射科医师评级的异构计算特征数据集。实验结果表明,3种MTL方案的预测语义评分比单任务LASSO和弹性网络回归方法的评分更接近放射科医师的评分。所提出的语义属性评分方案可以提供更丰富的结节定量评估以更好地支持诊断决策和管理。同时,医学图像内容与临床语义的自动关联能力也有助于医学搜索引擎的发展。

Abstact

The gap between the computational and semantic features is the one of major factors that bottlenecks the computer-aided diagnosis (CAD) performance from clinical usage. To bridge this gap, we exploit three multi-task learning (MTL) schemes to leverage heterogeneous computational features derived from deep learning models of stacked denoising autoencoder (SDAE) and convolutional neural network (CNN), as well as hand-crafted Haar-like and HoG features, for the description of 9 semantic features for lung nodules in CT images. We regard that there may exist relations among the semantic features of "spiculation","texture", "margin", etc., that can be explored with the MTL. The Lung Image Database Consortium (LIDC) data is adopted in this study for the rich annotation resources. The LIDC nodules were quantitatively scored w.r.t. 9 semantic features from 12 radiologists of several institutes in U.S.A. By treating each semantic feature as an individual task, the MTL schemes select and map the heterogeneous computational features toward the radiologists' ratings with cross validation evaluation schemes on the randomly selected 2400 nodules from the LIDC dataset. The experimental results suggest that the predicted semantic scores from the three MTL schemes are closer to the radiologists' ratings than the scores from single-task LASSO and elastic net regression methods. The proposed semantic attribute scoring scheme may provide richer quantitative assessments of nodules for better support of diagnostic decision and management. Meanwhile, the capability of the automatic association of medical image contents with the clinical semantic terms by our method may also assist the development of medical search engine.

阅读原文:PMID: 28113928  DOI: 10.1109/TMI.2016.2629462


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