1
|
Freeman LM, Ung TH, Thompson JA, Ovard O, Olson M, Hirt L, Hosokawa P, Thaker A, Youssef AS. Refining the predictive value of preoperative apparent diffusion coefficient (ADC) by whole-tumor analysis for facial nerve outcomes in vestibular schwannomas. Acta Neurochir (Wien) 2024; 166:168. [PMID: 38575773 DOI: 10.1007/s00701-024-06059-1] [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: 01/01/2024] [Accepted: 03/24/2024] [Indexed: 04/06/2024]
Abstract
BACKGROUND Apparent diffusion coefficient (ADC) in MRI has been shown to correlate with postoperative House-Brackmann (HB) scores in patients with vestibular schwannoma despite limited methodology. To rectify limitations of single region of interest (ROI) sampling, we hypothesize that whole-tumor ADC histogram analysis will refine the predictive value of this preoperative biomarker related to postoperative facial nerve function. METHODS Of 155 patients who underwent resection of vestibular schwannoma (2014-2020), 125 patients were included with requisite clinical and radiographic data. After volumetric analysis and whole-tumor ADC histogram, regression tree analysis identified ADC cutoff for significant differences in HB grade. Outcomes were extent of resection, facial nerve function, hospital length of stay (LOS), and complications. RESULTS Regression tree analysis defined three quantitative ADC groups (× 10-6 mm2/s) as high (> 2248.77; HB 1.7), mid (1468.44-2248.77; HB 3.1), and low (< 1468.44; HB 2.3) range (p 0.04). The mid-range ADC group had significantly worse postoperative HB scores and longer hospital LOS. Large tumor volume was independently predictive of lower rates of gross total resection (p <0.0001), higher postoperative HB score (p 0.002), higher rate of complications (p 0.04), and longer LOS (p 0.003). CONCLUSIONS Whole-tumor histogram yielded a robust regression tree analysis that defined three ADC groups with significantly different facial nerve outcomes. This likely reflects tumor heterogeneity better than solid-tumor ROI sampling. Whole-tumor ADC warrants further study as a useful radiographic biomarker in patients with vestibular schwannoma who are considering surgical resection.
Collapse
Affiliation(s)
- Lindsey M Freeman
- Department of Neurosurgery, University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Timothy H Ung
- Department of Neurosurgery, University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - John A Thompson
- Department of Neurosurgery, University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Olivia Ovard
- Cancer Center, University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Madeline Olson
- University of Colorado School of Medicine, Aurora, CO, USA
| | - Lisa Hirt
- Department of Neurosurgery, University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Patrick Hosokawa
- Department of Neurosurgery, University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - Ashesh Thaker
- Department of Radiology, University of Colorado Anschutz Medical Campus, Aurora, CO, USA
| | - A Samy Youssef
- Department of Neurosurgery, University of Colorado Anschutz Medical Campus, Aurora, CO, USA.
- Department of Otolaryngology, University of Colorado Anschutz Medical Campus, Aurora, CO, USA.
| |
Collapse
|
2
|
Song D, Zhai Y, Tao X, Zhao C, Wang M, Wei X. Prediction of blood supply in vestibular schwannomas using radiomics machine learning classifiers. Sci Rep 2021; 11:18872. [PMID: 34556732 PMCID: PMC8460834 DOI: 10.1038/s41598-021-97865-5] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2021] [Accepted: 08/26/2021] [Indexed: 01/01/2023] Open
Abstract
This study attempts to explore the radiomics-based features of multi-parametric magnetic resonance imaging (MRI) and construct a machine-learning model to predict the blood supply in vestibular schwannoma preoperatively. By retrospectively collecting the preoperative MRI data of patients with vestibular schwannoma, patients were divided into poor and rich blood supply groups according to the intraoperative recording. Patients were divided into training and test cohorts (2:1), randomly. Stable features were retained by intra-group correlation coefficients (ICCs). Four feature selection methods and four classification methods were evaluated to construct favorable radiomics classifiers. The mean area under the curve (AUC) obtained in the test set for different combinations of feature selecting methods and classifiers was calculated separately to compare the performance of the models. Obtain and compare the best combination results with the performance of differentiation through visual observation in clinical diagnosis. 191 patients were included in this study. 3918 stable features were extracted from each patient. Least absolute shrinkage and selection operator (LASSO) and logistic regression model was selected as the optimal combinations after comparing the AUC calculated by models, which predicted the blood supply of vestibular schwannoma by K-Fold cross-validation method with a mean AUC = 0.88 and F1-score = 0.83. Radiomics machine-learning classifiers can accurately predict the blood supply of vestibular schwannoma by preoperative MRI data.
Collapse
Affiliation(s)
- Dixiang Song
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, People's Republic of China
| | - Yixuan Zhai
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, People's Republic of China
| | - Xiaogang Tao
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, People's Republic of China
| | - Chao Zhao
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, People's Republic of China
| | - Minkai Wang
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, People's Republic of China
| | - Xinting Wei
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, People's Republic of China.
| |
Collapse
|
3
|
Zhang J, Zhao Z, Dong L, Han T, Zhang G, Cao Y, Zhou J. Differentiating between non-functioning pituitary macroadenomas and sellar meningiomas using ADC. Endocr Connect 2020; 9:1233-1239. [PMID: 33112805 PMCID: PMC7774768 DOI: 10.1530/ec-20-0434] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/14/2020] [Accepted: 10/19/2020] [Indexed: 11/23/2022]
Abstract
INTRODUCTION AND AIM It is difficult to distinguish between non-functioning pituitary macroadenomas (NFPMAs) and sellar meningiomas because of their overlapping imaging manifestations on routine MRI, especially in cases of meningiomas growing into the saddle. Here, we aimed to differentiate between these two tumors using apparent diffusion coefficient (ADC) values and MRI characteristics. METHODS A total of 60 NFPMA and 52 sellar meningioma cases confirmed by the pathological analysis were retrospectively reviewed. All patients were examined via routine MRI and diffusion-weighted imaging (DWI) before undergoing surgery. The clinical characteristics, MRI characteristics, and max ADC (ADCmax), average ADC (ADCmean), and minimum ADC (ADCmin) values were compared between the two tumors via Chi-square test and two sample t-tests. Receiver operating characteristic (ROC) curve and binary logistic regression analyses were conducted to determine the discrimination ability. RESULTS The ADCmax, ADCmean, and ADCmin values were significantly higher in NFPMAs compared to sellar meningiomas (P < 0.001 for all). Among ADC values, ADCmax demonstrated good performance with an AUC of 0.896 (95% CI, 0.823-0.969) and accuracy of 88.7%. A cut-off value of 0.97 × 10-3 mm2/s was used for ADCmax for differentiation between tumors. A combination of ADCmax values and clinicoradiological features showed the best discrimination ability for differential diagnosis between the two tumors, with an AUC of 0.981 (95% CI, 0.958-1.000) and accuracy of 96.9%. CONCLUSION A combination of ADCmax and clinicoradiological features demonstrates good discrimination ability and high accuracy for differentiation between NFPMAs and sellar meningiomas, and is a potential quantitative tool to aid in the selection of surgical techniques.
Collapse
Affiliation(s)
- Jing Zhang
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China
- Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China
- Second Clinical School, Lanzhou University, Lanzhou, China
| | - Zhiyong Zhao
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China
- Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China
- Second Clinical School, Lanzhou University, Lanzhou, China
| | - Li Dong
- Department of Pathology, Lanzhou University Second Hospital, Lanzhou, China
| | - Tao Han
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China
- Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China
- Second Clinical School, Lanzhou University, Lanzhou, China
| | - Guojin Zhang
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China
- Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China
- Second Clinical School, Lanzhou University, Lanzhou, China
| | - Yuntai Cao
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China
- Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China
- Second Clinical School, Lanzhou University, Lanzhou, China
| | - Junlin Zhou
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China
- Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China
- Second Clinical School, Lanzhou University, Lanzhou, China
- Correspondence should be addressed to J Zhou:
| |
Collapse
|
4
|
Tao YY, Zhou Y, Wang R, Gong XQ, Zheng J, Yang C, Yang L, Zhang XM. Progress of intravoxel incoherent motion diffusion-weighted imaging in liver diseases. World J Clin Cases 2020; 8:3164-3176. [PMID: 32874971 PMCID: PMC7441263 DOI: 10.12998/wjcc.v8.i15.3164] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/26/2020] [Revised: 06/11/2020] [Accepted: 07/14/2020] [Indexed: 02/05/2023] Open
Abstract
Traditional magnetic resonance (MR) diffusion-weighted imaging (DWI) uses a single exponential model to obtain the apparent diffusion coefficient to quantitatively reflect the diffusion motion of water molecules in living tissues, but it is affected by blood perfusion. Intravoxel incoherent motion (IVIM)-DWI utilizes a double-exponential model to obtain information on pure water molecule diffusion and microcirculatory perfusion-related diffusion, which compensates for the insufficiency of traditional DWI. In recent years, research on the application of IVIM-DWI in the diagnosis and treatment of hepatic diseases has gradually increased and has achieved considerable progress. This study mainly reviews the basic principles of IVIM-DWI and related research progress in the diagnosis and treatment of hepatic diseases.
Collapse
Affiliation(s)
- Yun-Yun Tao
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology and Medical Research Center of Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, Sichuan Province, China
| | - Yi Zhou
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology and Medical Research Center of Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, Sichuan Province, China
| | - Ran Wang
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology and Medical Research Center of Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, Sichuan Province, China
| | - Xue-Qin Gong
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology and Medical Research Center of Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, Sichuan Province, China
| | - Jing Zheng
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology and Medical Research Center of Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, Sichuan Province, China
| | - Cui Yang
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology and Medical Research Center of Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, Sichuan Province, China
| | - Lin Yang
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology and Medical Research Center of Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, Sichuan Province, China
| | - Xiao-Ming Zhang
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology and Medical Research Center of Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, Sichuan Province, China
| |
Collapse
|
5
|
Kunigelis KE, Hosokawa P, Arnone G, Raban D, Starr A, Gurau A, Sunshine A, Bunn J, Thaker AA, Youssef AS. The predictive value of preoperative apparent diffusion coefficient (ADC) for facial nerve outcomes after vestibular schwannoma resection: clinical study. Acta Neurochir (Wien) 2020; 162:1995-2005. [PMID: 32440924 DOI: 10.1007/s00701-020-04338-1] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2019] [Accepted: 04/07/2020] [Indexed: 02/07/2023]
Abstract
OBJECT Diffusion MRI has been used to predict intraoperative consistency of tumors. Apparent diffusion coefficient (ADC) has shown predictive value as an imaging biomarker in many CNS tumors but has not been studied in a large cohort of patients with vestibular schwannoma. In this study, we examine the utility of ADC as a predictive biomarker for intraoperative tumor characteristics and postoperative facial nerve outcome. METHODS A retrospective review of patients who underwent vestibular schwannoma resection at our institution from 2008 to 2018 yielded 87 patients, of which 72 met inclusion criteria. Operative reports and clinical records were reviewed for clinical data; MRI data were interpreted in a blinded fashion for qualitative and quantitative biomarkers, including tumor ADC. RESULTS Mean tumor ADC values did not predict intraoperative consistency or adherence (p = 0.63). Adherent tumors were associated with worse facial nerve outcomes (p = 0.003). Regression tree analysis identified 3 ADC categories with statistically different facial nerve outcomes. The categories identified were ADC < 1006.04 × 10-6 mm2/s; ADC 1006.04-1563.93 × 10-6 mm2/s and ADC ≥ 1563.94 × 10-6 mm2/s. Postoperative and final House-Brackmann (HB) scores were significantly higher in the intermediate ADC group (2.3, p = 0.0038). HB outcomes were similar between the group with ADC < 1006.04 × 10-6 mm2/s and ≥ 1563.94 × 10-6 mm2/s (1.3 vs 1.3). CONCLUSIONS Middle-range preoperative ADC in vestibular schwannoma suggests a less favorable postoperative HB score. Preoperative measurement of ADC in vestibular schwannoma may provide additional information regarding prognostication of facial nerve outcomes.
Collapse
Affiliation(s)
- Katherine E Kunigelis
- Department of Neurosurgery, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Patrick Hosokawa
- Adult and Child Center for Health Outcomes Research and Delivery Science (ACCORDS), University of Colorado, Aurora, CO, USA
| | - Gregory Arnone
- Department of Neurosurgery, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - David Raban
- Department of Radiology, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Adam Starr
- Department of Radiology, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Andrei Gurau
- University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Alexis Sunshine
- University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Jason Bunn
- University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - Ashesh A Thaker
- Department of Radiology, University of Colorado School of Medicine, Aurora, CO, 80045, USA
| | - A Samy Youssef
- Department of Neurosurgery, University of Colorado School of Medicine, Aurora, CO, 80045, USA.
- Department of Otolaryngology, University of Colorado School of Medicine, Aurora, CO, 80045, USA.
| |
Collapse
|