AUTHOR=Bassani Tito , Cina Andrea , Galbusera Fabio , Sconfienza Luca Maria , Albano Domenico , Barcellona Federica , Colombini Alessandra , Luca Andrea , Brayda-Bruno Marco TITLE=Automatic classification of the vertebral endplate lesions in magnetic resonance imaging by deep learning model JOURNAL=Frontiers in Surgery VOLUME=Volume 10 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/surgery/articles/10.3389/fsurg.2023.1172313 DOI=10.3389/fsurg.2023.1172313 ISSN=2296-875X ABSTRACT=A novel classification scheme for endplate lesions, based on T2-weighted images from MRI scan, has been recently introduced and validated. The scheme categorizes intervertebral spaces as ‘normal’, ‘wavy/irregular’, ‘notched’, and ‘Schmorl’s node’. These lesions have been associated with spinal pathologies, including disc degeneration and low back pain. The exploitation of an automatic tool for the detection of the lesions would facilitate the clinical practice by reducing the workload and the diagnosis time. The present work exploits a deep learning application based on convolutional neural networks to automatically classify the type of lesion. T2-weighted MRI scans of the sagittal lumbosacral spine of consecutive patients were retrospectively collected. The middle slice of each scan was manually processed to identify the intervertebral spaces from L1L2 to L5S1, and the corresponding lesion type was labelled. A total of 1559 gradable discs were obtained, with the following distribution: ‘normal’ (567 discs), ‘wavy/irregular’ (485), ‘notched’ (362), and ‘Schmorl’s node’ (145). The dataset was divided randomly into a training set and a validation set while preserving the original distribution of lesion types in each set. A pre-trained network for image classification was utilized, and fine-tuning was performed using the training set. The retrained net was then applied to the validation set to evaluate the overall accuracy and accuracy for each specific lesion type. The overall accuracy was found equal to 88%. The accuracy for the specific lesion type was found as follows: 91% (normal), 82% (wavy/irregular), 93% (notched), and 83% (Schmorl’s node). The results indicate that the deep learning approach achieved strong accuracy for both overall classification and individual lesion types. In clinical applications, this implementation could be employed as part of an automatic detection tool for pathological conditions characterized by the presence of endplate lesions, such as spinal osteochondrosis.