LUMINOUS Database: Lumbar Multifidus Muscle Segmentation From Ultrasound

@article{,
title= {LUMINOUS Database: Lumbar Multifidus Muscle Segmentation From Ultrasound},
keywords= {},
author= {},
abstract= {This database provides the US ground truth of the left and right LM muscles at the L5 level (in prone and standing positions) of 109 US datasets of young athletic adult volunteers (64 males, 45 females, age: 21.1 ± 1.7). The LUMINOUS database contains the US images with their corresponding manually segmented binary masks, serving as the ground truth. The purpose of the database is to enable development and validation of deep learning algorithms used for automatic segmentation tasks related to the assessment of the LM cross-sectional area (CSA) and echo intensity (EI).

The 109 athletes underwent a US procedure to obtain LM images at the L5 level in both the prone and standing positions. The LOGIQ e ultrasound machine (GE Healthcare, Milwaukee, WI) was used with a curvilinear probe with its imaging parameters maintained at the following values for all image acquisitions: frequency: 5 MHz, gain: 60, depth: 8.0 cm. To assess LM CSA, transverse US images were obtained bilaterally. For subjects with larger muscles, the right and left sides were imaged unilaterally.


(a) B-mode image of subject 50 (acquired unilaterally) with corresponding segmentation of the left MF in the prone position shown in (b). (c) B-mode image of subject 50 (acquired unilaterally) with corresponding segmentation of the left MF in the standing position shown in (d)

(a) B-mode image of subject 46 (acquired bilaterally) with corresponding segmentations of the left and right MF in the prone position shown in (b)
The ground truth segmentations of LM CSA and LM EI measurements in prone and standing positions were performed on the acquired data using Fiji, a distribution of the ImageJ image processing software. The B-mode images and binary segmentation masks for each subject are deposited as *.tif files.


https://users.encs.concordia.ca/~impact/wp-content/uploads/2020/07/1-550x400.png},
terms= {},
license= {https://creativecommons.org/licenses/by/4.0/},
superseded= {},
url= {https://users.encs.concordia.ca/~impact/luminous-database/}
}