Automatic knee meniscus tear detection and orientation classification with Mask-RCNN
Automatic knee meniscus tear detection and orientation classification with Mask-RCNN
复制标题
DOI：
10.1016/j.diii.2019.03.002
复制
发表时间：
2019-04-01
影响因子：
5.5
通讯作者：
Boussel, L.
中科院分区：
文献类型：
--
作者：
Couteaux, V;Si-Mohamed, S.;Boussel, L.
目的：本工作展示了我们对2018年10月法国放射学会在放射学法语之旅期间组织的数据挑战的贡献。这一挑战包括对膝关节半月板撕裂情况、半月板撕裂位置和半月板撕裂方向的MR图像进行分类。材料和方法：我们训练了一个基于掩模区域的卷积神经网络（R-CNN）来明确定位正常和撕裂的半月板，通过集合聚集使其更具鲁棒性，并将其级联到一个浅卷积网络中来分类撕裂的方向。结果：我们的方法准确预测了为挑战提供的数据库中的撕裂。该策略对所有三个任务的加权AUC得分为0.906，在该挑战中排名第一。结论：对非典型的半月板大面积损伤或多发撕裂患者，数据库的扩展或三维数据的应用有助于进一步提高手术效果。(C) 2019法国放射学会。Elsevier Masson SAS出版。版权所有。
Purpose: This work presents our contribution to a data challenge organized by the French Radiology Society during the Journees Francophones de Radiologie in October 2018. This challenge consisted in classifying MR images of the knee with respect to the presence of tears in the knee menisci, on meniscal tear location, and meniscal tear orientation.Materials and methods: We trained a mask region-based convolutional neural network (R-CNN) to explicitly localize normal and torn menisci, made it more robust with ensemble aggregation, and cascaded it into a shallow ConvNet to classify the orientation of the tear.Results: Our approach predicted accurately tears in the database provided for the challenge. This strategy yielded a weighted AUC score of 0.906 for all three tasks, ranking first in this challenge.Conclusion: The extension of the database or the use of 3D data could contribute to further improve the performances especially for non-typical cases of extensively damaged menisci or multiple tears. (C) 2019 Societe francaise de radiologie. Published by Elsevier Masson SAS. All rights reserved.