北京大学学报（自然科学版）2019，Vol.55Issue(5)：858-863,6.DOI:10.13209/j.0479-8023.2019.039
基于步行时足底压力信息的前交叉韧带断裂辅助诊断方法
Anterior Cruciate Ligament Deficiency Auxiliary Diagnosis Based on Plantar Pressure Information during Walking
摘要
Abstract
To study the identification of dynamic anterior cruciate ligament deficiency based on plantar pressure information, using convolutional neural network, raw plantar pressure data during walking were converted into images to establish the connection between plantar pressure and anterior cruciate ligament deficiency. Given plenty of input images and classification results, convolutional neural network could update its parameters for iterations to fit the connection. Plantar pressure data collected by acquisition system (FootScan?) were divided into two parts, training set and test set. The training set was used for training the deep learning model tune the parameters, which helped the model analyze the data better, while the test set was used to generate diagnosis, compare the results to the ground-truth to evaluate the model’s accuracy, and judge its performance as an auxiliary tool for clinical diagnosis. The results show that trained deep learning model can correctly diagnose over 90% cases in the test set, and only takes about 3 seconds to make a diagnosis. The proposed dynamic plantar pressure information based deep learning model can provide auxiliary diagnosis in very short time, which provides references for the auxiliary diagnosis and rehabilitation in clinical medicine.关键词
前交叉韧带断裂/ 足底压力/ 辅助诊断/ 深度学习Key words
anterior cruciate ligament deficiency/ plantar pressure/ auxiliary diagnosis/ deep learning引用本文复制引用
黄红拾,王政飞,许国雄,李文新,张思,张东霞,敖英芳..基于步行时足底压力信息的前交叉韧带断裂辅助诊断方法[J].北京大学学报（自然科学版）,2019,55(5):858-863,6.基金项目
国家自然科学基金(91646202)、北京大学医学-信息科学联合研究种子基金(BMU20160590)、北京大学第三医院院临床重点项目(BYSY 2017012)和广州市产学研协同创新重大专项(201604020095)资助 （91646202）
