1
|
Alan N, Zenkin S, Lavadi RS, Legarreta AD, Hudson JS, Fields DP, Agarwal N, Mamindla P, Ak M, Peddagangireddy V, Puccio L, Buell TJ, Hamilton DK, Kanter AS, Okonkwo DO, Zinn PO, Colen RR. Associating T1-Weighted and T2-Weighted Magnetic Resonance Imaging Radiomic Signatures With Preoperative Symptom Severity in Patients With Cervical Spondylotic Myelopathy. World Neurosurg 2024; 184:e137-e143. [PMID: 38253177 DOI: 10.1016/j.wneu.2024.01.072] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2023] [Accepted: 01/14/2024] [Indexed: 01/24/2024]
Abstract
BACKGROUND Preoperative symptom severity in cervical spondylotic myelopathy (CSM) can be variable. Radiomic signatures could provide an imaging biomarker for symptom severity in CSM. This study utilizes radiomic signatures of T1-weighted and T2-weighted magnetic resonance imaging images to correlate with preoperative symptom severity based on modified Japanese Orthopaedic Association (mJOA) scores for patients with CSM. METHODS Sixty-two patients with CSM were identified. Preoperative T1-weighted and T2-weighted magnetic resonance imaging images for each patient were segmented from C2-C7. A total of 205 texture features were extracted from each volume of interest. After feature normalization, each second-order feature was further subdivided to yield a total of 400 features from each volume of interest for analysis. Supervised machine learning was used to build radiomic models. RESULTS The patient cohort had a median mJOA preoperative score of 13; of which, 30 patients had a score of >13 (low severity) and 32 patients had a score of ≤13 (high severity). Radiomic analysis of T2-weighted imaging resulted in 4 radiomic signatures that correlated with preoperative mJOA with a sensitivity, specificity, and accuracy of 78%, 89%, and 83%, respectively (P < 0.004). The area under the curve value for the ROC curves were 0.69, 0.70, and 0.77 for models generated by independent T1 texture features, T1 and T2 texture features in combination, and independent T2 texture features, respectively. CONCLUSIONS Radiomic models correlate with preoperative mJOA scores using T2 texture features in patients with CSM. This may serve as a surrogate, objective imaging biomarker to measure the preoperative functional status of patients.
Collapse
Affiliation(s)
- Nima Alan
- Department of Neurological Surgery, University of California, San Francisco, San Francisco, California.
| | - Serafettin Zenkin
- Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania
| | - Raj Swaroop Lavadi
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Andrew D Legarreta
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Joseph S Hudson
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Daryl P Fields
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Nitin Agarwal
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania; Department of Neurological Surgery, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania
| | - Priyadarshini Mamindla
- Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania
| | - Murat Ak
- Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania
| | - Vishal Peddagangireddy
- Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania
| | - Lauren Puccio
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Thomas J Buell
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - D Kojo Hamilton
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Adam S Kanter
- Department of Neurosurgery, Hoag Neurosciences Institute, Newport Beach, California
| | - David O Okonkwo
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Pascal O Zinn
- Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Rivka R Colen
- Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania; Hillman Cancer Center, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania
| |
Collapse
|
2
|
Khan AF, Mohammadi E, Haynes G, Hameed S, Rohan M, Anderson DB, Weber KA, Muhammad F, Smith ZA. Evaluating tissue injury in cervical spondylotic myelopathy with spinal cord MRI: a systematic review. EUROPEAN SPINE JOURNAL : OFFICIAL PUBLICATION OF THE EUROPEAN SPINE SOCIETY, THE EUROPEAN SPINAL DEFORMITY SOCIETY, AND THE EUROPEAN SECTION OF THE CERVICAL SPINE RESEARCH SOCIETY 2024; 33:133-154. [PMID: 37926719 DOI: 10.1007/s00586-023-07990-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/02/2023] [Revised: 04/02/2023] [Accepted: 10/03/2023] [Indexed: 11/07/2023]
Abstract
PURPOSE Cervical Spondylotic Myelopathy (CSM) is a degenerative condition that leads to loss of cervical spinal cord (CSC) integrity. Various spinal cord Magnetic Resonance Imaging (MRI) methods can identify and characterize the extent of this damage. This systematic review aimed to evaluate the diagnostic, biomarker, and predictive utilities of different spinal cord MRI methods in clinical research studies of CSM. The aim was to provide a comprehensive understanding of the progress in this direction for future studies and effective diagnosis and management of CSM. METHODS A comprehensive literature search was conducted on PubMed and EMBASE from 2010 to 2022 according to PRISMA guidelines. Studies with non-human subjects, less than 3T magnetic field strength, non-clinical design, or not quantitatively focusing on the structural integrity of CSC were excluded. The extracted data from each study included demographics, disease severity, MRI machine characteristics, quantitative metrics, and key findings in terms of diagnostic, biomarker, and predictive utilities of each MRI method. The risk of bias was performed using the guide from AHRQ. The quality of evidence was assessed separately for each type of utility for different MRI methods using GRADE. RESULTS Forty-seven studies met the inclusion criteria, utilizing diffusion-weighted imaging (DTI) (n = 39), magnetization transfer (MT) (n = 6), MR spectroscopy (n = 3), and myelin water imaging (n = 1), as well as a combination of MRI methods (n = 12). The metric fractional anisotropy (FA) showed the highest potential in all facets of utilities, followed by mean diffusivity. Other promising metrics included MT ratio and intracellular volume fraction, especially in multimodal studies. However, the level of evidence for these promising metrics was low due to a small number of studies. Some studies, mainly DTI, also reported the usefulness of spinal cord MRI in mild CSM. CONCLUSIONS Spinal cord MRI methods can potentially facilitate the diagnosis and management of CSM by quantitatively interrogating the structural integrity of CSC. DTI is the most promising MRI method, and other techniques have also shown promise, especially in multimodal configurations. However, this field is in its early stages, and more studies are needed to establish the usefulness of spinal cord MRI in CSM.
Collapse
Affiliation(s)
- Ali Fahim Khan
- Department of Neurosurgery, University of Oklahoma Health Sciences Center, 1000 N Lincoln Blvd, Suite 4000, Oklahoma City, OK, 73104, USA
| | - Esmaeil Mohammadi
- Department of Neurosurgery, University of Oklahoma Health Sciences Center, 1000 N Lincoln Blvd, Suite 4000, Oklahoma City, OK, 73104, USA
| | - Grace Haynes
- Stephenson School of Biomedical Engineering, University of Oklahoma, Norman, USA
| | - Sanaa Hameed
- Department of Neurosurgery, University of Oklahoma Health Sciences Center, 1000 N Lincoln Blvd, Suite 4000, Oklahoma City, OK, 73104, USA
| | - Michael Rohan
- Laureate Institute for Brain Research, Tulsa, OK, USA
| | - David B Anderson
- School of Health Sciences, The University of Sydney, Sydney, Australia
| | - Kenneth A Weber
- Systems Neuroscience and Pain Laboratory, Division of Pain Medicine, Stanford University School of Medicine, Stanford University, Palo Alto, CA, USA
| | - Fauziyya Muhammad
- Department of Neurosurgery, University of Oklahoma Health Sciences Center, 1000 N Lincoln Blvd, Suite 4000, Oklahoma City, OK, 73104, USA
| | - Zachary A Smith
- Department of Neurosurgery, University of Oklahoma Health Sciences Center, 1000 N Lincoln Blvd, Suite 4000, Oklahoma City, OK, 73104, USA.
| |
Collapse
|
3
|
Fu H, Shen Z, Lai R, Zhou T, Huang Y, Zhao S, Mo R, Cai M, Jiang S, Wang J, Du B, Qian C, Chen Y, Yan F, Xiang X, Li R, Xie Q. Clinic-radiomics model using liver magnetic resonance imaging helps predict chronicity of drug-induced liver injury. Hepatol Int 2023; 17:1626-1636. [PMID: 37188998 DOI: 10.1007/s12072-023-10539-4] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/14/2023] [Accepted: 04/08/2023] [Indexed: 05/17/2023]
Abstract
BACKGROUND AND AIMS Some drug-induced liver injury (DILI) cases may become chronic, even after drug withdrawal. Radiomics can predict liver disease progression. We established and validated a predictive model incorporating the clinical characteristics and radiomics features for predicting chronic DILI. METHODS One hundred sixty-eight DILI patients who underwent liver gadolinium-diethylenetriamine pentaacetate-enhanced magnetic resonance imaging were recruited. The patients were clinically diagnosed using the Roussel Uclaf causality assessment method. Patients who progressed to chronicity or recovery were randomly divided into the training (70%) and validation (30%) cohorts, respectively. Hepatic T1-weighted images were segmented to extract 1672 radiomics features. Least absolute shrinkage and selection operator regression was used for feature selection, and Rad-score was constructed using support vector machines. Multivariable logistic regression analysis was performed to build a clinic-radiomics model incorporating clinical characteristics and Rad-scores. The clinic-radiomics model was evaluated for its discrimination, calibration, and clinical usefulness in the independent validation set. RESULTS Of 1672 radiomics features, 28 were selected to develop the Rad-score. Cholestatic/mixed patterns and Rad-score were independent risk factors of chronic DILI. The clinic-radiomics model, including the Rad-score and injury patterns, distinguished chronic from recovered DILI patients in the training (area under the receiver operating characteristic curve [AUROC]: 0.89, 95% confidence interval [95% CI]: 0.87-0.92) and validation (AUROC: 0.88, 95% CI: 0.83-0.91) cohorts with good calibration and great clinical utility. CONCLUSION The clinic-radiomics model yielded sufficient accuracy for predicting chronic DILI, providing a practical and non-invasive tool for managing DILI patients.
Collapse
Affiliation(s)
- Haoshuang Fu
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Zhehan Shen
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
- College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Rongtao Lai
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Tianhui Zhou
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Yan Huang
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Shuang Zhao
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Ruidong Mo
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Minghao Cai
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Shaowen Jiang
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Jiexiao Wang
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Bingying Du
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Cong Qian
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Yaoxing Chen
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Fuhua Yan
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
- College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Xiaogang Xiang
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China.
| | - Ruokun Li
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China.
- College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| | - Qing Xie
- Department of Infectious Diseases, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China.
| |
Collapse
|
4
|
Shan ZM, Ren XS, Shi H, Zheng SJ, Zhang C, Zhuang SY, Wu XT, Xie XH. Machine Learning Prediction Model and Risk Factor Analysis of Reoperation in Recurrent Lumbar Disc Herniation Patients After Percutaneous Endoscopic Lumbar Discectomy. Global Spine J 2023:21925682231173353. [PMID: 37161730 DOI: 10.1177/21925682231173353] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 05/11/2023] Open
Abstract
OBJECTIVE To investigate the risk factors of reoperation after percutaneous endoscopic lumbar discectomy (PELD) due to recurrent lumbar disc herniation (rLDH) and to establish a set of individualized prediction models. METHODS Patients who underwent PELD successfully from January 2016 to February 2022 in a single institution were enrolled in this study. Six methods of machine learning (ML) were used to establish an individualized prediction model for reoperation in rLDH patients after PELD, and these models were compared with logistics regression model to select optimal model. RESULTS A total of 2603 patients were enrolled in this study. 57 patients had repeated operation due to rLDH and 114 patients were selected from the remaining 2546 nonrecurrent patients as matched controls. Multivariate logistic regression analysis showed that disc herniation type (P < .001), Modic changes (type II) (P = .003), sagittal range of motion (sROM) (P = .022), facet orientation (FO) (P = .028) and fat infiltration (FI) (P = .001) were independent risk factors for reoperation in rLDH patients after PELD. The XGBoost AUC was of 90.71%, accuracy was approximately 88.87%, sensitivity was 70.81%, specificity was 97.19%. The traditional logistic regression AUC was 77.4%, accuracy was about 77.73%, sensitivity was 47.15%, specificity was 92.12%. CONCLUSION This study showed that disc herniation type (extrusion, sequestration), Modic changes (type II), a large sROM, a large FO and high FI were independent risk factors for reoperation in LDH patients after PELD. The prediction efficiency of XGBoost model was higher than traditional Logistic regression analysis model.
Collapse
Affiliation(s)
- Zheng-Ming Shan
- Department of Spine Surgery, ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Xue-Song Ren
- School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Hang Shi
- Department of Spine Surgery, ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Shi-Jie Zheng
- Department of Spine Surgery, ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Cong Zhang
- Department of Spine Surgery, ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Su-Yang Zhuang
- Department of Spine Surgery, ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Xiao-Tao Wu
- Department of Spine Surgery, ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Xin-Hui Xie
- Department of Spine Surgery, ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| |
Collapse
|
5
|
Efficient Prediction of Ki-67 Proliferation Index in Meningiomas on MRI: From Traditional Radiological Findings to a Machine Learning Approach. Cancers (Basel) 2022; 14:cancers14153637. [PMID: 35892896 PMCID: PMC9330288 DOI: 10.3390/cancers14153637] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2022] [Revised: 07/22/2022] [Accepted: 07/25/2022] [Indexed: 02/05/2023] Open
Abstract
Background/aim This study aimed to explore the value of radiological and radiomic features retrieved from magnetic resonance imaging in the prediction of a Ki-67 proliferative index in meningioma patients using a machine learning model. Methods This multicenter, retrospective study included 371 patients collected from two centers. The Ki-67 expression was classified into low-expressed and high-expressed groups with a threshold of 5%. Clinical features and radiological features were collected and analyzed by using univariate and multivariate statistical analyses. Radiomic features were extracted from contrast-enhanced images, followed by three independent feature selections. Six predictive models were constructed with different combinations of features by using linear discriminant analysis (LDA) classifier. Results The multivariate analysis suggested that the presence of intratumoral necrosis (p = 0.032) and maximum diameter (p < 0.001) were independently correlated with a high Ki-67 status. The predictive models showed good performance with AUC of 0.837, accuracy of 0.810, sensitivity of 0.857, and specificity of 0.771 in the internal test and with AUC of 0.700, accuracy of 0.557, sensitivity of 0.314, and specificity of 0.885 in the external test. Conclusion The results of this study suggest that the predictive model can efficiently predict the Ki-67 index of meningioma patients to facilitate the therapeutic management.
Collapse
|