AUTHOR=Chen Xiao , Deng Qingshan , Wang Qiang , Liu Xinmiao , Chen Lei , Liu Jinjin , Li Shuangquan , Wang Meihao , Cao Guoquan 

TITLE=Image Quality Control in Lumbar Spine Radiography Using Enhanced U-Net Neural Networks

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.891766

DOI=10.3389/fpubh.2022.891766

ISSN=2296-2565

ABSTRACT=Purpose:
To standardize the radiography imaging procedure, an image quality control framework using the deep learning technique was developed to segment and evaluate lumbar spine x-ray images according to a defined quality control standard.
Materials and Methods:
A dataset comprising frontal, lateral, and oblique position lumbar spine x-ray images from 1389 patients was analysed in this study. The training set consisted of digital radiography (DR) images of 1070 patients (800, 798, and 623 images of the frontal, lateral, and oblique position, respectively) and the validation set included 319 patients (200, 205, and 156 images of the frontal, lateral, and oblique position, respectively). The quality control standard for lumbar spine x-ray radiography in this study was defined using guidelines of textbooks as a reference. An enhanced encoder-decoder fully convolutional network with U-Net as the backbone was implemented to segment the anatomical structures in the x-ray images. The segmentations were used to build an automatic assessment method to detect unqualified DR images. The dice similarity coefficient (DSC) was used to evaluate segmentation performance.
Results:
The DSC of the frontal position images ranged from 0.82 to 0.96 (mean 0.91 ± 0.06); the DSC of the lateral position images ranged from 0.71 to 0.95 (mean 0.87 ± 0.10); the DSC of the oblique position images ranged from 0.66 to 0.93 (mean 0.80 ± 0.14). The accuracy, sensitivity, and specificity of the assessment method on the validation set were 0.971-0.990 (mean 0.98 ± 0.10), 0.714-0.933 (mean 0.86 ± 0.13), and 0.995-1.000 (mean 0.99 ± 0.12) for the three positions, respectively.
Conclusion:
This deep learning-based algorithm achieves accurate segmentation of lumbar spine x-ray images. It provides a reliable and efficient method to identify the shape of the lumbar spine while automatically determining the radiographic image quality.