VinDr-SpineXR: A deep learning framework for spinal lesions detection and classification from radiographs

TL;DR

This paper introduces VinDr-SpineXR, a deep learning framework for detecting and classifying spinal lesions in X-ray images, supported by a large annotated dataset, achieving promising accuracy and localization performance.

Contribution

The work presents a new large-scale annotated spine X-ray dataset and a deep learning framework for lesion detection and classification, establishing a baseline for future research.

Findings

Achieved 88.61% AUROC for abnormality classification.

Obtained 33.56% mAP for lesion localization.

Provided publicly available dataset and models.

Abstract

Radiographs are used as the most important imaging tool for identifying spine anomalies in clinical practice. The evaluation of spinal bone lesions, however, is a challenging task for radiologists. This work aims at developing and evaluating a deep learning-based framework, named VinDr-SpineXR, for the classification and localization of abnormalities from spine X-rays. First, we build a large dataset, comprising 10,468 spine X-ray images from 5,000 studies, each of which is manually annotated by an experienced radiologist with bounding boxes around abnormal findings in 13 categories. Using this dataset, we then train a deep learning classifier to determine whether a spine scan is abnormal and a detector to localize 7 crucial findings amongst the total 13. The VinDr-SpineXR is evaluated on a test set of 2,078 images from 1,000 studies, which is kept separate from the training set. It demonstrates an area under the receiver operating characteristic curve (AUROC) of 88.61% (95% CI 87.19%, 90.02%) for the image-level classification task and a mean average precision (mAP@0.5) of 33.56% for the lesion-level localization task. These results serve as a proof of concept and set a baseline for future research in this direction. To encourage advances, the dataset, codes, and trained deep learning models are made publicly available.