2-step deep learning model for landmarks localization in spine radiographs

• Published in: Scientific reports Vol. 11; no. 1; p. 9482
• Main Authors: Cina, Andrea, Bassani, Tito, Panico, Matteo, Luca, Andrea, Masharawi, Youssef, Brayda-Bruno, Marco, Galbusera, Fabio
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 04.05.2021; Nature Publishing Group UK; Nature Portfolio
• Subjects: Deep learning; Localization; Neural networks; Radiography; Sacrum; Spine; Vertebrae
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-021-89102-w

In this work we propose to use Deep Learning to automatically calculate the coordinates of the vertebral corners in sagittal x-rays images of the thoracolumbar spine and, from those landmarks, to calculate relevant radiological parameters such as L1-L5 and L1-S1 lordosis and sacral slope. For this purpose, we used 10,193 images annotated with the landmarks coordinates as the ground truth. We realized a model that consists of 2 steps. In step 1, we trained 2 Convolutional Neural Networks to identify each vertebra in the image and calculate the landmarks coordinates respectively. In step 2, we refined the localization using cropped images of a single vertebra as input to another convolutional neural network and we used geometrical transformations to map the corners to the original image. For the localization tasks, we used a differentiable spatial to numerical transform (DSNT) as the top layer. We evaluated the model both qualitatively and quantitatively on a set of 195 test images. The median localization errors relative to the vertebrae dimensions were 1.98% and 1.68% for x and y coordinates respectively. All the predicted angles were highly correlated with the ground truth, despite non-negligible absolute median errors of 1.84°, 2.43° and 1.98° for L1-L5, L1-S1 and SS respectively. Our model is able to calculate with good accuracy the coordinates of the vertebral corners and has a large potential for improving the reliability and repeatability of measurements in clinical tasks.