结合目标检测与匹配修正的手腕骨兴趣区域提取  

Hand-wrist region of interest extraction based on object detection and matching correction

作　　者：毛科技[1] 汪敏豪 陈立建[1,2] 陆伟 武坤秀 陈庆章[1] 赵小敏[1] Mao Keji;Wang Minhao;Chen Lijian;Lu Wei;Wu Kunxiu;Chen Qingzhang;Zhao Xiaomin(College of Computer Science&Technology,Zhejiang University of Technology,Hangzhou 310023,China;Xiaoshan College,Zhejiang Radio and Television University,Hangzhou 312000,China)

机构地区：[1]浙江工业大学计算机科学与技术学院,杭州310023 [2]浙江广播电视大学萧山学院,杭州312000

出　　处：《中国图象图形学报》2022年第3期973-987,共15页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62072410);浙江省重点研发计划项目(2018C01082);浙江省公益性技术应用研究项目(LGG22F020014,LGG20F020018)。

摘　　要：目的在骨龄智能评估研究中,如何准确地提取手腕参照骨的兴趣区域(region of interest,ROI)是保证骨龄精确评估的关键。基于传统深度学习的方法用于手腕骨ROI提取,存在个别参照骨漏判、误判等情况,导致平均提取准确率较低。本文结合目标检测强大的定位和识别能力,以准确提取所有手腕骨ROI为目的,提出了一种参照骨自动匹配与修正方法。方法针对不同参照骨形状、位置等特征表现出的规律性和关联性,本文采集了大量不同性别、不同年龄段的人手腕图谱作为参照骨样本匹配,然后分多个阶段提取参照骨ROI:1)基于目标检测算法初步提取出所有参照骨候选ROI,并根据一定的阈值剔除置信度较低的区域;2)结合参照骨的大数据样本构建位置点匹配模型,对剔除区域进行自动匹配与填补,保证ROI提取的完整性;3)通过多尺度滑动窗口以及ROI分类模型,对填补得到的ROI位置进行滑动修正,进一步保证提取准确率。结果实验结果表明,本文结合目标检测与匹配修正的方法优于现有绝大多数方法。其中,匹配修正方法在目标检测算法的提取结果基础上,提升了约1.42%的平均准确率,当结合Faster R-CNN(region-convolutional neural network)算法时能达到最高98.45%的交并比(intersection-over-union,IoU)准确率。结论本文方法利用手腕骨的位置特征,对个别提取困难的参照骨类型进行重新匹配与修正,有效地弥补了传统方法泛化能力不足的缺点。本文方法能够同时面向人手腕中所有参照骨ROI提取,具备良好的扩展性和易操作性。Objective The regions of interest(ROI)extrancted correction in hand-wrist reference bones is the essential method to target accurate bone age.Current image processing methods have high time complexity and operation difficulty,which cannot meet the requirement of large-scale clinical use.Deep learning technology has its feature extraction priority but the missing and misjudgment of individual reference bones will lead to low average extraction accuracy when it is used to extract ROIs of hand-wrist reference bones.The intensive positioning and classification capability of object detection algorithms is analyzed to demonstrate an automatic reference bone matching and correction method for the purpose of extracting all hand-wrist ROIs accurately.Method The amount of reference bones in the human hand-wrist is clear in common.The identified illustration strict regularity and correlation for the time-scaled bone age.Based on this,a large quantity of human hand-wrist X-ray images have been collected as the benchmark in genders and age scales.As for the evaluation,the reference bone sample orientation can be easily identified to calibrate the reference bone ROI and improve the extraction accuracy further based on matching the position similarity between the sample and the standard atlas.This demonstration is mainly divided into 3 steps:1)All reference bone candidate ROIs are extracted in preliminary based on the object detection algorithm.Due to the insufficient generalization capability of most deep learning models,the accuracy rate is low when extracting some complicated reference bones.Based on the results of the reference bone candidate ROIs generated,this research adds a series of post-processing procedures,including replicated ROIs of the same reference bone category deduction,and filter regions alteration with low confidence in terms of the threshold set by the algorithm;2)In order to guarantee the overall capability of the reference bone ROI extraction,it is necessary to match automatically and refill the deducted

关 键 词：兴趣区域(ROI) 目标检测 位置匹配 大数据 滑动窗口 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]