Spine Explorer: a deep learning based fully automated program for efficient and reliable quantifications of the vertebrae and discs on sagittal lumbar spine MR images

Magnetic resonance imaging (MRI) plays a significant role in the diagnosis of lumbar disc disease. However, the use of MRI is limited because of its high cost and significant operating and processing time. More importantly, MRI is contraindicated for some patients with claustrophobia or cardiac pacemakers due to the possibility of injury. In contrast, computed tomography (CT) scans are much less expensive, are faster, and do not face the same limitations. In this paper, we propose a method for estimating lumbar spine MR images based on CT images using a novel objective function and a dual cycle-consistent adversarial network (DC 2 Anet) with semi-supervised learning. The objective function includes six independent loss terms to balance quantitative and qualitative losses, enabling the generation of a realistic and accurate synthetic MR image. DC 2 Anet is also capable of semi-supervised learning, and the network is general enough for supervised or unsupervised setups. Experimental results prove that the method is accurate, being able to construct MR images that closely approximate reference MR images, while also outperforming four other state-of-the-art methods.

Download Full-text

Automatic Segmentation and Delineation of Intervertebral Discs on Lumbar Spine MR Images

VipIMAGE 2019 - Lecture Notes in Computational Vision and Biomechanics ◽

10.1007/978-3-030-32040-9_13 ◽

2019 ◽

pp. 117-126

Author(s):

Wai Teng Liu ◽

André R. S. Marcal

Keyword(s):

Lumbar Spine ◽

Automatic Segmentation ◽

Intervertebral Discs ◽

Mr Images ◽

Spine Mr

Download Full-text

Variation in the Quality of Lumbar Spine MR Images in Washington State

Radiology ◽

10.1148/radiology.215.2.r00ma35483 ◽

2000 ◽

Vol 215 (2) ◽

pp. 483-490 ◽

Cited By ~ 10

Author(s):

Jeffrey G. Jarvik ◽

William D. Robertson ◽

Frank Wessbecher ◽

Kenneth Reger ◽

Cam Solomon ◽

...

Keyword(s):

Lumbar Spine ◽

Washington State ◽

Mr Images ◽

Spine Mr

Download Full-text

Semi-Automatic Segmentation of Vertebral Bodies in MR Images of Human Lumbar Spines

Applied Sciences ◽

10.3390/app8091586 ◽

2018 ◽

Vol 8 (9) ◽

pp. 1586 ◽

Cited By ~ 5

Author(s):

Sewon Kim ◽

Won Bae ◽

Koichi Masuda ◽

Christine Chung ◽

Dosik Hwang

Keyword(s):

Lumbar Spine ◽

Vertebral Body ◽

Automatic Segmentation ◽

Dice Similarity Coefficient ◽

Mr Images ◽

Segmentation Accuracy ◽

Body Segmentation ◽

Spine Mr ◽

Vertebral Bodies ◽

Automatic Algorithm

We propose a semi-automatic algorithm for the segmentation of vertebral bodies in magnetic resonance (MR) images of the human lumbar spine. Quantitative analysis of spine MR images often necessitate segmentation of the image into specific regions representing anatomic structures of interest. Existing algorithms for vertebral body segmentation require heavy inputs from the user, which is a disadvantage. For example, the user needs to define individual regions of interest (ROIs) for each vertebral body, and specify parameters for the segmentation algorithm. To overcome these drawbacks, we developed a semi-automatic algorithm that considerably reduces the need for user inputs. First, we simplified the ROI placement procedure by reducing the requirement to only one ROI, which includes a vertebral body; subsequently, a correlation algorithm is used to identify the remaining vertebral bodies and to automatically detect the ROIs. Second, the detected ROIs are adjusted to facilitate the subsequent segmentation process. Third, the segmentation is performed via graph-based and line-based segmentation algorithms. We tested our algorithm on sagittal MR images of the lumbar spine and achieved a 90% dice similarity coefficient, when compared with manual segmentation. Our new semi-automatic method significantly reduces the user’s role while achieving good segmentation accuracy.

Download Full-text

Lumbar spine (MR)

e-Anatomy ◽

10.37019/e-anatomy/278222 ◽

2008 ◽

Author(s):

Antoine Micheau ◽

Denis Hoa

Keyword(s):

Lumbar Spine ◽

Spine Mr

Download Full-text

Gravity determines the direction of nerve roots sedimentation in the lumbar spinal canal

BMC Musculoskeletal Disorders ◽

10.1186/s12891-021-04032-y ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Jun Yang ◽

Zhiyun Feng ◽

Nian Chen ◽

Zhenhua Hong ◽

Yongyu Zheng ◽

...

Keyword(s):

Lumbar Spine ◽

Mr Imaging ◽

Spinal Canal ◽

Ventral Side ◽

Lateral Position ◽

Dorsal Side ◽

Mr Images ◽

Nerve Roots ◽

Cross Sectional ◽

Dural Sac

Abstract Objectives To investigate the role of gravity in the sedimentation of lumbar spine nerve roots using magnetic resonance (MR) imaging of various body positions. Methods A total of 56 patients, who suffered from back pain and underwent conventional supine lumbar spine MR imaging, were selected from sanmen hospital database. All the patients were called back to our hospital to perform MR imaging in prone position or lateral position. Furthermore, the sedimentation sign (SedSign) was determined based on the suspension of the nerve roots in the dural sac on cross-sectional MR images, and 31 cases were rated as positive and another 25 cases were negative. Results The mean age of negative SedSign group was significantly younger than that of positive SedSign group (51.7 ± 8.7 vs 68.4 ± 10.5, P < 0.05). The constitutions of clinical diagnosis were significantly different between patients with a positive SedSign and those with a negative SedSign (P < 0.001). Overall, nerve roots of the vast majority of patients (48/56, 85.7%) subsided to the ventral side of the dural sac on the prone MR images, although that of 8 (14.3%) patients remain stay in the dorsal side of dural sac. Nerve roots of only one patient with negative SedSign did not settle to the ventral dural sac, while this phenomenon occurred in 7 patients in positive SedSign group (4% vs 22.6%, P < 0.001). In addition, the nerve roots of all the five patients subsided to the left side of dural sac on lateral position MR images. Conclusions The nerve roots sedimentation followed the direction of gravity. Positive SedSign may be a MR sign of lumbar pathology involved the spinal canal.

Download Full-text

An automatic deep learning-based workflow for glioblastoma survival prediction using pre-operative multimodal MR images: a feasibility study

Advances in Radiation Oncology ◽

10.1016/j.adro.2021.100746 ◽

2021 ◽

pp. 100746

Author(s):

Jie Fu ◽

Kamal Singhrao ◽

Xinran Zhong ◽

Yu Gao ◽

Sharon X. Qi ◽

...

Keyword(s):

Deep Learning ◽

Feasibility Study ◽

Survival Prediction ◽

Mr Images

Download Full-text

Method for Diagnosing the Bone Marrow Edema of Sacroiliac Joint in Patients with Axial Spondyloarthritis Using Magnetic Resonance Image Analysis Based on Deep Learning

Diagnostics ◽

10.3390/diagnostics11071156 ◽

2021 ◽

Vol 11 (7) ◽

pp. 1156

Author(s):

Kang Hee Lee ◽

Sang Tae Choi ◽

Guen Young Lee ◽

You Jung Ha ◽

Sang-Il Choi

Keyword(s):

Bone Marrow ◽

Deep Learning ◽

Bone Marrow Edema ◽

Axial Spondyloarthritis ◽

Mr Images ◽

Sacroiliac Joints ◽

Learning Network ◽

Active Sacroiliitis ◽

Deep Learning Network ◽

Marrow Edema

Axial spondyloarthritis (axSpA) is a chronic inflammatory disease of the sacroiliac joints. In this study, we develop a method for detecting bone marrow edema by magnetic resonance (MR) imaging of the sacroiliac joints and a deep-learning network. A total of 815 MR images of the sacroiliac joints were obtained from 60 patients diagnosed with axSpA and 19 healthy subjects. Gadolinium-enhanced fat-suppressed T1-weighted oblique coronal images were used for deep learning. Active sacroiliitis was defined as bone marrow edema, and the following processes were performed: setting the region of interest (ROI) and normalizing it to a size suitable for input to a deep-learning network, determining bone marrow edema using a convolutional-neural-network-based deep-learning network for individual MR images, and determining sacroiliac arthritis in subject examinations based on the classification results of individual MR images. About 70% of the patients and normal subjects were randomly selected for the training dataset, and the remaining 30% formed the test dataset. This process was repeated five times to calculate the average classification rate of the five-fold sets. The gradient-weighted class activation mapping method was used to validate the classification results. In the performance analysis of the ResNet18-based classification network for individual MR images, use of the ROI showed excellent detection performance of bone marrow edema with 93.55 ± 2.19% accuracy, 92.87 ± 1.27% recall, and 94.69 ± 3.03% precision. The overall performance was additionally improved using a median filter to reflect the context information. Finally, active sacroiliitis was diagnosed in individual subjects with 96.06 ± 2.83% accuracy, 100% recall, and 94.84 ± 3.73% precision. This is a pilot study to diagnose bone marrow edema by deep learning based on MR images, and the results suggest that MR analysis using deep learning can be a useful complementary means for clinicians to diagnose bone marrow edema.

Download Full-text