Three‐dimensional reconstruction of Kambin's triangle based on automated magnetic resonance image segmentation

Su, Zhihai; Liu, Zheng; Wang, Min; Li, Shaolin; Lin, Liyan; Yuan, Zhen; Pang, Shumao; Feng, Qianjin; Chen, Tao; Lü, Hai

doi:10.1002/jor.25303

Cited by 11 publications

(17 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, many other segmentation studies aiming at recreating lumbar structures focused on bones [20][21][22], discs [23], and spinal muscles [19]. To the authors' knowledge, only one study succeeded in recreating a comprehensive 3D model of the Kambin's triangle including bones, dura mater, discs, and nerve roots [16]. In their study, Su et…”

Section: Review Kambin's Triangle Reconstructionmentioning

confidence: 99%

“…Although it is well agreed that a thorough understanding of foraminal anatomy (including Kambin's triangle) is important for the success of t-MISS, fewer studies have been successful at reconstructing a three-dimensional (3D) image of the Kambin's triangle [12,14,15]. This 3D reconstruction is important for surgical planning and real-time navigation in the t-MISS operating field [16]. Here, we present the most up-to-date review on the 3D reconstruction of Kambin's triangle, and a preview of the current and next era of spinal surgical management through the triangle.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Current and Future Applications of the Kambin’s Triangle in Lumbar Spine Surgery

Waguia¹,

Gupta²,

Gamel³

et al. 2022

Cureus

View full text Add to dashboard Cite

Kambin's triangle has become the anatomical location of choice when accessing the lumbar spine to treat degenerative spinal disorders. Currently, lumbar interbody fusion is the most common procedure utilizing this space; however, with the advent of the Kambin's prism definition, advanced imaging modalities, and robotic-assisted techniques, lumbar spine surgery has become increasingly precise and less invasive. These technological and procedural advances have drastically reduced the rate of complications, improved patient outcomes, and expanded the use of the Kambin's triangle to treat different pathologies utilizing cuttingedge techniques. In this review, the authors present the current uses of the Kambin's triangle and the future application of this anatomical corridor in lumbar spine surgery.

show abstract

Section: Review Kambin's Triangle Reconstructionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Current and Future Applications of the Kambin’s Triangle in Lumbar Spine Surgery

Waguia¹,

Gupta²,

Gamel³

et al. 2022

Cureus

View full text Add to dashboard Cite

show abstract

“…Few studies 19,20 have focused on the automatic segmentation of the vertebral notch and articular processes, essential to lumbar structures. Su et al 20 . have developed a method for 3D reconstruction of Kambin's triangle, not for rapid 3D LIVF reconstruction.…”

Section: Introductionmentioning

confidence: 99%

“…[13][14][15][16] Previous studies have demonstrated the success of deep learning in the automatic MRI segmentation, but these studies have mainly focused on segmenting vertebra bodies and intervertebral discs without segmenting the vertebral notch and articular processes. 17,18 Few studies 19,20 have focused on the automatic segmentation of the vertebral notch and articular processes, essential to lumbar structures. Su et al 20 have developed a method for 3D reconstruction of Kambin's triangle, not for rapid 3D LIVF reconstruction.…”

Section: Introductionmentioning

confidence: 99%

“…17,18 Few studies 19,20 have focused on the automatic segmentation of the vertebral notch and articular processes, essential to lumbar structures. Su et al 20 have developed a method for 3D reconstruction of Kambin's triangle, not for rapid 3D LIVF reconstruction. Liu et al 19 have developed a deep learning model for automatic MRI of vertebra bone structures (vertebra body, vertebral notch and articular processes) and intervertebral discs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Magnetic Resonance Image Segmentation of Spinal Structures at the L4‐5 Level with Deep Learning: 3D Reconstruction of Lumbar Intervertebral Foramen

Chen

Liu

et al. 2022

Orthopaedic Surgery

Self Cite

View full text Add to dashboard Cite

Objective: 3D reconstruction of lumbar intervertebral foramen (LIVF) has been beneficial in evaluating surgical trajectory. Still, the current methods of reconstructing the 3D LIVF model are mainly based on manual segmentation, which is laborious and time-consuming. This study aims to explore the feasibility of automatically segmenting lumbar spinal structures and increasing the speed and accuracy of 3D lumbar intervertebral foramen (LIVF) reconstruction on magnetic resonance image (MRI) at the L4-5 level.Methods: A total of 100 participants (mean age: 42.2 AE 14.0 years; 52 males and 48 females; mean body mass index, 22.7 AE 3.2 kg/m 2 ), were enrolled in this prospective study between March and July 2020. All participants were scanned on L4-5 level with a 3T MR unit using 3D T2-weighted sampling perfection with applicationoptimized contrast with various flip-angle evolutions (SPACE) sequences. The lumbar spine's vertebra bone structures (VBS) and intervertebral discs (IVD) were manually segmented by skilled surgeons according to their anatomical outlines from MRI. Then all manual segmentation were saved and used for training. An automated segmentation method based on a 3D U-shaped architecture network (3D-UNet) was introduced for the automated segmentation of lumbar spinal structures. A number of quantitative metrics, including dice similarity coefficient (DSC), precision, and recall, were used to evaluate the performance of the automated segmentation method on MRI. Wilcoxon signed-rank test was applied to compare morphometric parameters, including foraminal area, height and width of 3D LIVF models between automatic and manual segmentation. The intra-class correlation coefficient was used to assess the test-retest reliability and inter-observer reliability of multiple measurements for these morphometric parameters of 3D LIVF models. Results:The automatic segmentation performance of all spinal structures (VBS and IVD) was found to be 0.918 (healthy levels: 0.922; unhealthy levels: 0.916) for the mean DSC, 0.922 (healthy levels: 0.927; unhealthy levels: 0.920) for the mean precision, and 0.917 (healthy levels: 0.918; unhealthy levels: 0.917) for the mean recall in the test dataset. It took approximately 2.5 s to achieve each automated segmentation, far less than the 240 min for manual segmentation. Furthermore, no significant differences were observed in the foraminal area, height and width of the 3D LIVF models between manual and automatic segmentation images (P > 0.05).

show abstract

Automatic segmentation of dura for quantitative analysis of lumbar stenosis: A deep learning study with 518 CT myelograms

Fan,

Li,

Wang

et al. 2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

BackgroundThe diagnosis of lumbar spinal stenosis (LSS) can be challenging because radicular pain is not often present in the culprit‐level localization. Accurate segmentation and quantitative analysis of the lumbar dura on radiographic images are key to the accurate differential diagnosis of LSS. The aim of this study is to develop an automatic dura‐contouring tool for radiographic quantification on computed tomography myelogram (CTM) for patients with LSS.MethodsA total of 518 CTM cases with or without lumbar stenosis were included in this study. A deep learning (DL) segmentation algorithm 3‐dimensional (3D) U‐Net was deployed. A total of 210 labeled cases were used to develop the dura‐contouring tool, with the ratio of the training, independent testing, and external validation datasets being 150:30:30. The Dice score (DCS) was the primary measure to evaluate the segmentation performance of the 3D U‐Net, which was subsequently developed as the dura‐contouring tool to segment another unlabeled 308 CTM cases with LSS. Automatic masks of 446 slices on the stenotic levels were then meticulously reviewed and revised by human experts, and the cross‐sectional area (CSA) of the dura was compared.ResultsThe mean DCS of the 3D U‐Net were 0.905 ± 0.080, 0.933 ± 0.018, and 0.928 ± 0.034 in the five‐fold cross‐validation, the independent testing, and the external validation datasets, respectively. The segmentation performance of the dura‐contouring tool was also comparable to that of the second observer (the human expert). With the dura‐contouring tool, only 59.0% (263/446) of the automatic masks of the stenotic slices needed to be revised. In the revised cases, there were no significant differences in the dura CSA between automatic masks and corresponding revised masks (p = 0.652). Additionally, a strong correlation of dura CSA was found between the automatic masks and corresponding revised masks (r = 0.805).ConclusionsA dura‐contouring tool was developed that could automatically segment the dural sac on CTM, and it demonstrated high accuracy and generalization ability. Additionally, the dura‐contouring tool has the potential to be applied in patients with LSS because it facilitates the quantification of the dural CSA on stenotic slices.

show abstract

Three‐dimensional reconstruction of Kambin's triangle based on automated magnetic resonance image segmentation

Cited by 11 publications

References 36 publications

Current and Future Applications of the Kambin’s Triangle in Lumbar Spine Surgery

Current and Future Applications of the Kambin’s Triangle in Lumbar Spine Surgery

Automated Magnetic Resonance Image Segmentation of Spinal Structures at the L4‐5 Level with Deep Learning: 3D Reconstruction of Lumbar Intervertebral Foramen

Automatic segmentation of dura for quantitative analysis of lumbar stenosis: A deep learning study with 518 CT myelograms

Contact Info

Product

Resources

About