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

06/24/2021
by   Hieu T. Nguyen, et al.
17

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 90.02 (mAP@0.5) of 33.56 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.

READ FULL TEXT
research
08/06/2022

An Accurate and Explainable Deep Learning System Improves Interobserver Agreement in the Interpretation of Chest Radiograph

Recent artificial intelligence (AI) algorithms have achieved radiologist...
research
11/30/2021

Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

Early detection improves prognosis in pancreatic ductal adenocarcinoma (...
research
01/22/2023

Applied Deep Learning to Identify and Localize Polyps from Endoscopic Images

Deep learning based neural networks have gained popularity for a variety...
research
08/14/2021

DICOM Imaging Router: An Open Deep Learning Framework for Classification of Body Parts from DICOM X-ray Scans

X-ray imaging in DICOM format is the most commonly used imaging modality...
research
12/11/2017

MURA Dataset: Towards Radiologist-Level Abnormality Detection in Musculoskeletal Radiographs

We introduce MURA, a large dataset of musculoskeletal radiographs contai...
research
01/23/2023

Deep Learning-Based Assessment of Cerebral Microbleeds in COVID-19

Cerebral Microbleeds (CMBs), typically captured as hypointensities from ...
research
10/14/2016

Deep Learning Ensembles for Melanoma Recognition in Dermoscopy Images

Melanoma is the deadliest form of skin cancer. While curable with early ...

Please sign up or login with your details

Forgot password? Click here to reset