基于深度学习的腰椎前后位数字X线片定量形态学研究

Deep learning-based quantitative morphological study of anteroposterior digital radiographs of the lumbar spine.

作者信息

Chen Zhizhen, Wang Wenqi, Chen Xiaofei, Dong Fuwen, Cheng Guohua, He Linyang, Ma Chunyu, Yao Hongyan, Zhou Sheng

机构信息

Medical Imaging Center of Gansu Provincial Maternity and Child-care Hospital, Lanzhou, China.

The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, China.

出版信息

Quant Imaging Med Surg. 2024 Aug 1;14(8):5385-5395. doi: 10.21037/qims-22-540. Epub 2023 Feb 22.

DOI:10.21037/qims-22-540

PMID:39144021

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11320550/

Abstract

BACKGROUND

Morphological parameters of the lumbar spine are valuable in assessing lumbar spine diseases. However, manual measurement of lumbar morphological parameters is time-consuming. Deep learning has automatic quantitative and qualitative analysis capabilities. To develop a deep learning-based model for the automatic quantitative measurement of morphological parameters from anteroposterior digital radiographs of the lumbar spine and to evaluate its performance.

METHODS

This study used 1,368 anteroposterior digital radiographs of the lumbar spine to train a deep learning model to measure the quantitative morphological indicators, including L1 to L5 vertebral body height (VBH) and L1-L2 to L4-L5 intervertebral disc height (IDH). The means of the manual measurements by three radiologists were used as the reference standard. The parameters predicted by the model were analyzed against the manual measurements using paired -tests. Percentage of correct key points (PCK), intra-class correlation coefficient (ICC), Pearson correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), and Bland-Altman plots were performed to assess the performance of the model.

RESULTS

Within the 3-mm distance threshold, the model had a PCK range of 99.77-99.46% for the L1 to L4 vertebrae and 77.37% for the L5 vertebrae. Except for VBH-L5 and IDH_L3-L4, IDH_L4-L5 (P<0.05), the estimated values of the model in the remaining parameters were not statistically significant compared with the reference standard (P>0.05). Except for VBH-L5 and IDH_L4-L5, the model showed good correlation and consistency with the reference standard (ICC =0.84-0.96, r=0.85-0.97, MAE =0.5-0.66, RMSE =0.66-0.95). The model outperformed other models (EfficientDet + Unet, EfficientDet + DarkPose, HRNet, and Unet) in predicting landmarks within a distance threshold of 1.5 to 5 mm.

CONCLUSIONS

The model developed in this study can automatically measure the morphological parameters of the L1 to L4 vertebrae from anteroposterior digital radiographs of the lumbar spine. Its performance is close to the level of radiologists.

摘要

背景

腰椎的形态学参数在评估腰椎疾病方面具有重要价值。然而，手动测量腰椎形态学参数耗时较长。深度学习具有自动定量和定性分析能力。旨在开发一种基于深度学习的模型，用于从腰椎前后位数字X线片自动定量测量形态学参数，并评估其性能。

方法

本研究使用1368张腰椎前后位数字X线片训练深度学习模型，以测量定量形态学指标，包括L1至L5椎体高度（VBH）以及L1-L2至L4-L5椎间盘高度（IDH）。三位放射科医生手动测量的平均值用作参考标准。使用配对t检验将模型预测的参数与手动测量结果进行分析。进行正确关键点百分比（PCK）、组内相关系数（ICC）、皮尔逊相关系数（r）、平均绝对误差（MAE）、均方根误差（RMSE）以及Bland-Altman图来评估模型的性能。

结果

在3毫米距离阈值内，该模型对L1至L4椎体的PCK范围为99.77%-99.46%，对L5椎体为77.37%。除VBH-L5、IDH_L3-L4和IDH_L4-L5（P<0.05）外，模型在其余参数的估计值与参考标准相比无统计学意义（P>0.05）。除VBH-L5和IDH_L4-L5外，模型与参考标准显示出良好的相关性和一致性（ICC =0.84-0.96，r=0.85-0.97，MAE =0.5-0.66，RMSE =0.66-0.95）。在1.5至5毫米的距离阈值内预测地标时，该模型优于其他模型（EfficientDet + Unet、EfficientDet + DarkPose、HRNet和Unet）。