Automated Segmentation of Vertebrae on Lateral Chest Radiography Using Deep Learning
This addresses the problem of manual segmentation for radiologists, but it is incremental as it applies an existing method to a specific medical imaging task.
The study developed an automated deep learning algorithm for segmenting thoracic vertebrae on lateral chest radiographs, achieving an average dice coefficient of 90.5 and IoU of 81.75 on a test set.
The purpose of this study is to develop an automated algorithm for thoracic vertebral segmentation on chest radiography using deep learning. 124 de-identified lateral chest radiographs on unique patients were obtained. Segmentations of visible vertebrae were manually performed by a medical student and verified by a board-certified radiologist. 74 images were used for training, 10 for validation, and 40 were held out for testing. A U-Net deep convolutional neural network was employed for segmentation, using the sum of dice coefficient and binary cross-entropy as the loss function. On the test set, the algorithm demonstrated an average dice coefficient value of 90.5 and an average intersection-over-union (IoU) of 81.75. Deep learning demonstrates promise in the segmentation of vertebrae on lateral chest radiography.