TY - GEN
T1 - A Composite Dataset of Lumbar Spine Images with Mid-Sagittal View Annotations and Clinically Significant Spinal Measurements
AU - Masood, Rao Farhat
AU - Hassan, Taimur
AU - Raja, Hina
AU - Hassan, Bilal
AU - Dias, Jorge
AU - Werghi, Naoufel
N1 - Funding Information:
We want to thank Dr. Muhammad Asad Qureshi and Dr. Muhammad Babar Khan, who volunteered to annotate this dataset thoroughly. We would also like to express our gratitude to Sud Sudirman [4] for his formal consent to our use and redistribution of his original MRI scans. Also, we want to highlight that this work is supported by a research fund from Khalifa University. Ref: CIRA-2019-047 and CIRA-2021-052,
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - The modern computer-aided screening systems re-quire a large amount of well-annotated training data to produce robust and consistent diagnostic performance. Furthermore, the public datasets designed to evaluate automated spinal disorders screening frameworks lack quantitative labels, which are marked by expert radiologists and clinically validated by spinal surgeons. This paper presents a dataset containing high-resolution (and well-labeled) mid-sagittal views of lumbar spine magnetic resonance imaging (MRI) scans. These scans also contain vertebral body masks along with clinically significant spinal measurements, including lumbar height, intervertebral body distances, vertebral body sidewall dimensions, vertebral body superior and inferior end-plates dimensions, lumbar lordotic angles, and lumbosacral angles. The mid-sagittal view MRI scans within the proposed dataset were first procured, and then they were manually marked by the expert radiologists and validated by the expert spinal surgeons. Afterward, different spinal measurements were recorded, which serves as a benchmark to evaluate the autonomous frameworks for predicting spinal misalignments. In addition to this, the proposed dataset is, to the best of our knowledge, the first composite database that contains lumbar spine mid-sagittal images along with spinal attributes and detailed markings of radiologists duly verified by the spinal surgeons. The proposed dataset, unlike its competitors, also introduces a quantitative vote to the clinicians and researchers in the assessment process of lumbar spine disorders. Apart from this, the dataset is publicly available at https://data.mendeley.com/datasets/k3b363f3vz/2.
AB - The modern computer-aided screening systems re-quire a large amount of well-annotated training data to produce robust and consistent diagnostic performance. Furthermore, the public datasets designed to evaluate automated spinal disorders screening frameworks lack quantitative labels, which are marked by expert radiologists and clinically validated by spinal surgeons. This paper presents a dataset containing high-resolution (and well-labeled) mid-sagittal views of lumbar spine magnetic resonance imaging (MRI) scans. These scans also contain vertebral body masks along with clinically significant spinal measurements, including lumbar height, intervertebral body distances, vertebral body sidewall dimensions, vertebral body superior and inferior end-plates dimensions, lumbar lordotic angles, and lumbosacral angles. The mid-sagittal view MRI scans within the proposed dataset were first procured, and then they were manually marked by the expert radiologists and validated by the expert spinal surgeons. Afterward, different spinal measurements were recorded, which serves as a benchmark to evaluate the autonomous frameworks for predicting spinal misalignments. In addition to this, the proposed dataset is, to the best of our knowledge, the first composite database that contains lumbar spine mid-sagittal images along with spinal attributes and detailed markings of radiologists duly verified by the spinal surgeons. The proposed dataset, unlike its competitors, also introduces a quantitative vote to the clinicians and researchers in the assessment process of lumbar spine disorders. Apart from this, the dataset is publicly available at https://data.mendeley.com/datasets/k3b363f3vz/2.
KW - Lumbar Height
KW - Lumbar Lordotic Angle
KW - Lumbar Spine
KW - Lumbosacral Angle
KW - Spinal Measurements
KW - Vertebral Body Dimensions
UR - http://www.scopus.com/inward/record.url?scp=85133208257&partnerID=8YFLogxK
U2 - 10.1109/ICoDT255437.2022.9787452
DO - 10.1109/ICoDT255437.2022.9787452
M3 - Conference contribution
AN - SCOPUS:85133208257
T3 - 2022 2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022
BT - 2022 2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022
Y2 - 24 May 2022 through 26 May 2022
ER -