Automated patellar height assessment on high-resolution radiographs with a novel deep learning-based approach  

作　　者：Kamil Kwolek Dariusz Grzelecki Konrad Kwolek Dariusz Marczak Jacek Kowalczewski Marcin Tyrakowski 

机构地区：[1]Department of Spine Disorders and Orthopaedics,Centre of Postgraduate Medical Education,Gruca Orthopaedic and Trauma Teaching Hospital,Otwock 05-400,Poland [2]Department of Orthopaedics and Rheumoorthopedics,Centre of Postgraduate Medical Education,Gruca Orthopaedic and Trauma Teaching Hospital,Otwock 05-400,Poland [3]Department of Orthopaedics and Traumatology,University Hospital,Krakow 30-663,Poland

出　　处：《World Journal of Orthopedics》2023年第6期387-398,共12页世界骨科杂志（英文版）

摘　　要：BACKGROUND Artificial intelligence and deep learning have shown promising results in medical imaging and interpreting radiographs.Moreover,medical community shows a gaining interest in automating routine diagnostics issues and orthopedic measurements.AIM To verify the accuracy of automated patellar height assessment using deep learning-based bone segmentation and detection approach on high resolution radiographs.METHODS 218 Lateral knee radiographs were included in the analysis.82 radiographs were utilized for training and 10 other radiographs for validation of a U-Net neural network to achieve required Dice score.92 other radiographs were used for automatic(U-Net)and manual measurements of the patellar height,quantified by Caton-Deschamps(CD)and Blackburne-Peel(BP)indexes.The detection of required bones regions on high-resolution images was done using a You Only Look Once(YOLO)neural network.The agreement between manual and automatic measurements was calculated using the interclass correlation coefficient(ICC)and the standard error for single measurement(SEM).To check U-Net's generalization the segmentation accuracy on the test set was also calculated.RESULTS Proximal tibia and patella was segmented with accuracy 95.9%(Dice score)by U-Net neural network on lateral knee subimages automatically detected by the YOLO network(mean Average Precision mAP greater than 0.96).The mean values of CD and BP indexes calculated by orthopedic surgeons(R#1 and R#2)was 0.93(±0.19)and 0.89(±0.19)for CD and 0.80(±0.17)and 0.78(±0.17)for BP.Automatic measurements performed by our algorithm for CD and BP indexes were 0.92(±0.21)and 0.75(±0.19),respectively.Excellent agreement between the orthopedic surgeons’measurements and results of the algorithm has been achieved(ICC>0.75,SEM<0.014).CONCLUSION Automatic patellar height assessment can be achieved on high-resolution radiographs with the required accuracy.Determining patellar end-points and the joint line-fitting to the proximal tibia joint surface allows for accurate CD and

关 键 词：Medical imaging Artificial intelligence in orthopedics Patellar index Deep learning Bone segmentation Region of interest detection 

分 类 号：R816.8[医药卫生—放射医学]