1
|
Wang M, Su Z, Liu Z, Chen T, Cui Z, Li S, Pang S, Lu H. Deep Learning-Based Automated Magnetic Resonance Image Segmentation of the Lumbar Structure and Its Adjacent Structures at the L4/5 Level. Bioengineering (Basel) 2023; 10:963. [PMID: 37627848 PMCID: PMC10451852 DOI: 10.3390/bioengineering10080963] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2023] [Revised: 08/07/2023] [Accepted: 08/11/2023] [Indexed: 08/27/2023] Open
Abstract
(1) Background: This study aims to develop a deep learning model based on a 3D Deeplab V3+ network to automatically segment multiple structures from magnetic resonance (MR) images at the L4/5 level. (2) Methods: After data preprocessing, the modified 3D Deeplab V3+ network of the deep learning model was used for the automatic segmentation of multiple structures from MR images at the L4/5 level. We performed five-fold cross-validation to evaluate the performance of the deep learning model. Subsequently, the Dice Similarity Coefficient (DSC), precision, and recall were also used to assess the deep learning model's performance. Pearson's correlation coefficient analysis and the Wilcoxon signed-rank test were employed to compare the morphometric measurements of 3D reconstruction models generated by manual and automatic segmentation. (3) Results: The deep learning model obtained an overall average DSC of 0.886, an average precision of 0.899, and an average recall of 0.881 on the test sets. Furthermore, all morphometry-related measurements of 3D reconstruction models revealed no significant difference between ground truth and automatic segmentation. Strong linear relationships and correlations were also obtained in the morphometry-related measurements of 3D reconstruction models between ground truth and automated segmentation. (4) Conclusions: We found it feasible to perform automated segmentation of multiple structures from MR images, which would facilitate lumbar surgical evaluation by establishing 3D reconstruction models at the L4/5 level.
Collapse
Affiliation(s)
- Min Wang
- Department of Spinal Surgery, Fifth Affiliated Hospital of Sun Yat-Sen University, 52 Meihua Dong Lu, Xiangzhou District, Zhuhai 519000, China; (M.W.); (Z.S.); (Z.L.); (T.C.); (Z.C.)
| | - Zhihai Su
- Department of Spinal Surgery, Fifth Affiliated Hospital of Sun Yat-Sen University, 52 Meihua Dong Lu, Xiangzhou District, Zhuhai 519000, China; (M.W.); (Z.S.); (Z.L.); (T.C.); (Z.C.)
| | - Zheng Liu
- Department of Spinal Surgery, Fifth Affiliated Hospital of Sun Yat-Sen University, 52 Meihua Dong Lu, Xiangzhou District, Zhuhai 519000, China; (M.W.); (Z.S.); (Z.L.); (T.C.); (Z.C.)
| | - Tao Chen
- Department of Spinal Surgery, Fifth Affiliated Hospital of Sun Yat-Sen University, 52 Meihua Dong Lu, Xiangzhou District, Zhuhai 519000, China; (M.W.); (Z.S.); (Z.L.); (T.C.); (Z.C.)
| | - Zhifei Cui
- Department of Spinal Surgery, Fifth Affiliated Hospital of Sun Yat-Sen University, 52 Meihua Dong Lu, Xiangzhou District, Zhuhai 519000, China; (M.W.); (Z.S.); (Z.L.); (T.C.); (Z.C.)
| | - Shaolin Li
- Department of Radiology, Fifth Affiliated Hospital of Sun Yat-Sen University, 52 Meihua Dong Lu, Xiangzhou District, Zhuhai 519000, China;
| | - Shumao Pang
- School of Biomedical Engineering, Guangzhou Medical University, No. 1, Xinzao Road, Xinzao Town, Panyu, Guangzhou 511436, China
| | - Hai Lu
- Department of Spinal Surgery, Fifth Affiliated Hospital of Sun Yat-Sen University, 52 Meihua Dong Lu, Xiangzhou District, Zhuhai 519000, China; (M.W.); (Z.S.); (Z.L.); (T.C.); (Z.C.)
| |
Collapse
|
2
|
Kawakami M, Takeshita K, Inoue G, Sekiguchi M, Fujiwara Y, Hoshino M, Kaito T, Kawaguchi Y, Minetama M, Orita S, Takahata M, Tsuchiya K, Tsuji T, Yamada H, Watanabe K. Japanese Orthopaedic Association (JOA) clinical practice guidelines on the management of lumbar spinal stenosis, 2021 - Secondary publication. J Orthop Sci 2023; 28:46-91. [PMID: 35597732 DOI: 10.1016/j.jos.2022.03.013] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/14/2022] [Revised: 03/17/2022] [Accepted: 03/29/2022] [Indexed: 01/12/2023]
Abstract
BACKGROUND The Japanese Orthopaedic Association (JOA) guideline for the management of lumbar spinal stenosis (LSS) was first published in 2011. Since then, the medical care system for LSS has changed and many new articles regarding the epidemiology and diagnostics of LSS, conservative treatments such as new pharmacotherapy and physical therapy, and surgical treatments including minimally invasive surgery have been published. In addition, various issues need to be examined, such as verification of patient-reported outcome measures, and the economic effect of revised medical management of patients with lumbar spinal disorders. Accordingly, in 2019 the JOA clinical guidelines committee decided to update the guideline and consequently established a formulation committee. The purpose of this study was to describe the formulation we implemented for the revision of the guideline, incorporating the recent advances of evidence-based medicine. METHODS The JOA LSS guideline formulation committee revised the previous guideline based on the method for preparing clinical guidelines in Japan proposed by the Medical Information Network Distribution Service in 2017. Background and clinical questions were determined followed by a literature search related to each question. Appropriate articles based on keywords were selected from all the searched literature. Using prepared structured abstracts, systematic reviews and meta-analyses were performed. The strength of evidence and recommendations for each clinical question was decided by the committee members. RESULTS Eight background and 15 clinical questions were determined. Answers and explanations were described for the background questions. For each clinical question, the strength of evidence and the recommendation were both decided, and an explanation was provided. CONCLUSIONS The 2021 clinical practice guideline for the management of LSS was completed according to the latest evidence-based medicine. We expect that this guideline will be useful for all medical providers as an index in daily medical care, as well as for patients with LSS.
Collapse
Affiliation(s)
| | | | - Gen Inoue
- Department of Orthopaedic Surgery, Kitasato University, Japan
| | - Miho Sekiguchi
- Department of Orthopaedic Surgery, Fukushima Medical University, Japan
| | - Yasushi Fujiwara
- Department of Orthopaedic Surgery, Hiroshima City Asa Citizens Hospital, Japan
| | - Masatoshi Hoshino
- Department of Orthopaedic Surgery, Osaka City General Hospital, Japan
| | - Takashi Kaito
- Department of Orthopaedic Surgery, Osaka University, Japan
| | | | - Masakazu Minetama
- Spine Care Center, Wakayama Medical University Kihoku Hospital, Japan
| | - Sumihisa Orita
- Center for Frontier Medical Engineering (CFME), Department of Orthopaedic Surgery, Chiba University, Japan
| | - Masahiko Takahata
- Department of Orthopaedic Surgery, Hokkaido University Graduate School of Medicine, Japan
| | | | - Takashi Tsuji
- Department of Orthopaedic Surgery, National Hospital Organization Tokyo Medical Center, Japan
| | - Hiroshi Yamada
- Department of Orthopaedic Surgery, Wakayama Medical University, Japan
| | - Kota Watanabe
- Department of Orthopaedic Surgery, Keio University, Japan
| | | |
Collapse
|
3
|
Lacroix M, Nguyen C, Burns R, Laporte A, Rannou F, Feydy A. Degenerative Lumbar Spine Disease: Imaging and Biomechanics. Semin Musculoskelet Radiol 2022; 26:424-438. [PMID: 36103885 DOI: 10.1055/s-0042-1748912] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2022]
Abstract
Chronic low back pain (CLBP) is one of the most common diagnoses encountered when considering years lived with disability. The degenerative changes of the lumbar spine include a wide spectrum of morphological modifications visible on imaging, some of them often asymptomatic or not consistent with symptoms. Phenotyping by considering both clinical and imaging biomarkers can improve the management of CLBP. Depending on the clinical presentation, imaging helps determine the most likely anatomical nociceptive source, thereby enhancing the therapeutic approach by targeting a specific lesion. Three pathologic conditions with an approach based on our experience can be described: (1) pure painful syndromes related to single nociceptive sources (e.g., disk pain, active disk pain, and facet joint osteoarthritis pain), (2) multifactorial painful syndromes, representing a combination of several nociceptive sources (such as lumbar spinal stenosis pain, foraminal stenosis pain, and instability pain), and (3) nonspecific CLBP, often explained by postural (muscular) syndromes.
Collapse
Affiliation(s)
- Maxime Lacroix
- Department of Musculoskeletal Radiology, Hôpital Cochin, Université de Paris, Paris, France.,Department of Radiology, Hôpital Européen Georges-Pompidou, Université de Paris, Paris, France
| | - Christelle Nguyen
- Department of Physical and Rehabilitation Medicine, Hôpital Cochin, Université de Paris, Paris, France
| | - Robert Burns
- Department of Musculoskeletal Radiology, Hôpital Cochin, Université de Paris, Paris, France
| | - Amandine Laporte
- Department of Musculoskeletal Radiology, Hôpital Cochin, Université de Paris, Paris, France
| | - François Rannou
- Department of Physical and Rehabilitation Medicine, Hôpital Cochin, Université de Paris, Paris, France
| | - Antoine Feydy
- Department of Musculoskeletal Radiology, Hôpital Cochin, Université de Paris, Paris, France
| |
Collapse
|
4
|
ÇANKAL F, PATAT D, ŞİRİNOĞLU T. Radiological evaluation of spinal canal, dural sac, epidural fat and superior articular process in diagnosis of lumbar spinal stenosis. JOURNAL OF HEALTH SCIENCES AND MEDICINE 2021. [DOI: 10.32322/jhsm.973905] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
|
5
|
Wang WB, Sun AJ, Yu HP, Dong JC, Xu H. Dural sac cross-sectional area is a highly effective parameter for spinal anesthesia in geriatric patients undergoing transurethral resection of the prostate: a prospective, double blinded, randomized study. BMC Anesthesiol 2020; 20:139. [PMID: 32493211 PMCID: PMC7268766 DOI: 10.1186/s12871-020-01059-x] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2020] [Accepted: 05/27/2020] [Indexed: 12/01/2022] Open
Abstract
Background Spinal anesthesia is optimal choice for transurethral resection of the prostate (TURP), but the sensory block should not cross the T10 level. With advancing age, the sensory blockade level increases after spinal injection in some patients with spinal canal stenosis. We optimize the dose of spinal anesthesia according to the decreased ratio of the dural sac cross-sectional area (DSCSA), the purpose of this study is to hypothesis that if DSCSA is an effective parameter to modify the dosage of spinal anesthetics to achieve a T10 blockade in geriatric patients undergoing TURP. Methods Sixty geriatric patients schedule for TURP surgery were enrolled in this study. All subjects were randomized divided into two groups, the ultrasound (group U) and the control (group C) groups, patient receive either a dose of 2 ml of 0.5% isobaric bupivacaine in group C, or a modified dose of 0.5% isobaric bupivacaine in group U. We measured the sagittal anteroposterior diameter (D) of the dural sac at the L3–4 level with ultrasound, and calculated the approximate DSCSA (A) according to the following formula: A = π(D/2)2, ( π = 3.14). The modified dosage of bupivacaine was adjusted according to the decreased ratio of the DSCSA. Results The cephalad spread of the sensory blockade level was significantly lower (P < 0.001) in group U (T10, range T7–T12) compared with group C (T3, range T2–T9). The dosage of bupivacaine was significantly decreased in group U compared with group C (P < 0.001). The regression times of the two segments were delay in group U compared with group C (P < 0.001). The maximal decrease in MAP was significantly higher in the group C than in group U after spinal injection (P < 0.001), without any modifications HR in either group. Eight patients in group C and two patients in group U required ephedrine (P = 0.038). Conclusions The DSCSA is a highly effective parameter for spinal anesthesia in geriatric patients undergoing TURP, a modified dose of local anesthetic is a critical factor for controlling the sensory level. Trial registration This study was registered in the Chinese Clinical Trial Registry (Registration number: ChiCTR1800015566).on 8, April, 2018.
Collapse
Affiliation(s)
- Wei Bing Wang
- Department of Anesthesiology, The Affiliated AnQing Hospitals of Anhui Medical University, 352th, Renming Road, AnQing, 246003, AnHui province, China.
| | - Ai Jiao Sun
- Department of Anesthesiology, The Affiliated AnQing Hospitals of Anhui Medical University, 352th, Renming Road, AnQing, 246003, AnHui province, China
| | - Hong Ping Yu
- Department of Anesthesiology, The Affiliated AnQing Hospitals of Anhui Medical University, 352th, Renming Road, AnQing, 246003, AnHui province, China
| | - Jing Chun Dong
- Department of Anesthesiology, The Affiliated AnQing Hospitals of Anhui Medical University, 352th, Renming Road, AnQing, 246003, AnHui province, China
| | - Huang Xu
- Department of Anesthesiology, The Affiliated AnQing Hospitals of Anhui Medical University, 352th, Renming Road, AnQing, 246003, AnHui province, China
| |
Collapse
|
6
|
Lim YS, Mun JU, Seo MS, Sang BH, Bang YS, Kang KN, Koh JW, Kim YU. Dural sac area is a more sensitive parameter for evaluating lumbar spinal stenosis than spinal canal area: A retrospective study. Medicine (Baltimore) 2017; 96:e9087. [PMID: 29245329 PMCID: PMC5728944 DOI: 10.1097/md.0000000000009087] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/14/2022] Open
Abstract
Narrowing of the dural sac cross-sectional area (DSCSA) and spinal canal cross-sectional area (SCCSA) have been considered major causes of lumbar central canal spinal stenosis (LCCSS). DSCSA and SCCSA were previously correlated with subjective walking distance before claudication occurs, aging, and disc degeneration. DSCSA and SCCSA have been ideal morphological parameters for evaluating LCCSS. However, the comparative value of these parameters is unknown and no studies have evaluated the clinical optimal cut-off values of DSCSA and SCCSA. This study assessed which parameter is more sensitive.Both DSCSA and SCCSA samples were collected from 135 patients with LCCSS, and from 130 control subjects who underwent lumbar magnetic resonance imaging (MRI) as part of a medical examination. Axial T2-weighted MRI scans were acquired at the level of facet joint from each subject. DSCSA and SCCSA were measured at the L4-L5 intervertebral level on MRI using a picture archiving and communications system.The average DSCSA value was 151.67 ± 53.59 mm in the control group and 80.04 ± 35.36 mm in the LCCSS group. The corresponding average SCCSA values were 199.95 ± 60.96 and 119.17 ± 49.41 mm. LCCSS patients had significantly lower DSCSA and SCCSA (both P < .001). Regarding the validity of both DSCSA and SCCSA as predictors of LCCSS, Receiver operating characteristic curve analysis revealed an optimal cut-off value for DSCSA of 111.09 mm, with 80.0% sensitivity, 80.8% specificity, and an area under the curve (AUC) of 0.87 (95% confidence interval, 0.83-0.92). The best cut off-point of SCCSA was 147.12 mm, with 74.8% sensitivity, 78.5% specificity, and AUC of 0.85 (95% confidence interval, 0.81-0.89).DSCSA and SCCSA were both significantly associated with LCCSS, with DSCSA being a more sensitive measurement parameter. Thus, to evaluate LCCSS patients, pain specialists should more carefully investigate the DSCSA than SCCSA.
Collapse
Affiliation(s)
- Young Su Lim
- Department of Anesthesiology and Pain Medicine, Institute for Integrative Medicine, Catholic Kwandong University of Korea College of Medicine, International St. Mary's Hospital, Incheon
| | - Jong-Uk Mun
- Department of Orthopaedic Surgery, Changwon Gyeongsang National University Hospital, Republic of Korea
| | - Mi Sook Seo
- Department of Anesthesiology and Pain Medicine, Institute for Integrative Medicine, Catholic Kwandong University of Korea College of Medicine, International St. Mary's Hospital, Incheon
| | - Bo-Hyun Sang
- Department of Anesthesiology and Pain Medicine, Institute for Integrative Medicine, Catholic Kwandong University of Korea College of Medicine, International St. Mary's Hospital, Incheon
| | - Yun-Sic Bang
- Department of Anesthesiology and Pain Medicine, Institute for Integrative Medicine, Catholic Kwandong University of Korea College of Medicine, International St. Mary's Hospital, Incheon
| | - Keum Nae Kang
- Department of Anesthesiology and Pain Medicine, National Police Hospital, Seoul, Korea
| | - Jin Woo Koh
- Department of Anesthesiology and Pain Medicine, National Police Hospital, Seoul, Korea
| | - Young Uk Kim
- Department of Anesthesiology and Pain Medicine, Institute for Integrative Medicine, Catholic Kwandong University of Korea College of Medicine, International St. Mary's Hospital, Incheon
| |
Collapse
|