1
|
Deng R, Wang R, Yao M, Ma L. Percutaneous Stylomastoid Foramen Pulsed Radiofrequency Combined with Steroid Injection for Treatment of Intractable Facial Paralysis After Herpes Zoster. Pain Ther 2024; 13:161-172. [PMID: 38175491 PMCID: PMC10796885 DOI: 10.1007/s40122-023-00571-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2023] [Accepted: 12/11/2023] [Indexed: 01/05/2024] Open
Abstract
INTRODUCTION We investigated the safety and efficacy of percutaneous facial nerve pulsed radiofrequency combined with drug injection for treatment of intractable facial paralysis of herpes zoster. The authors provide a detailed description of percutaneous facial nerve pulsed radiofrequency combined with steroid injection for treatment of intractable facial paralysis after herpes zoster, and they examine its clinical efficacy. This is the first time in the literature to our knowledge that this procedure has been applied in facial paralysis after herpes zoster. METHODS A total of 43 patients with a history of facial paralysis after herpes zoster for > 1 month were enrolled in this retrospective study. The patients were subjected to percutaneous stylomastoid foramen pulsed radiofrequency of the facial nerve under computed tomography (CT) guidance combined with drug injection. The House-Brackmann grades and NRS (Numerical Rating Scale) data collection were performed at different time points (preoperatively, 1 day post-procedure, and 2, 4, and 12 weeks postoperatively). The occurrence of complications was also assessed. RESULTS The 43 participants successfully completed the CT-guided percutaneous stylomastoid foramen pulsed radiofrequency of the facial nerve combined with drug injection. Both approaches [posterior approach of the ear (7 cases) and anterior approach of the ear (36 cases)] were efficacious and safe. The House-Brackmann grades (I, II, III, IV, V, VI) were 4 (3-4), 2 (2-3), 1 (1-2), and 1 (0-2) at different operation times (T0, T1, T2, T3, T4); patients felt significant recovery at T1 after operation and had gradually recovered at each time point but had no significant recovery after T3. The NRS scores at different operation times were 2.690 ± 2.213, 0.700 ± 0.939, 0.580 ± 1.006, 0.440 ± 0.908, and 0.260 ± 0.759, respectively. Differences in NRS scores between T0 and T1/2/3/4 were significant while differences between T1 and T2/3/4 were not significant. Six patients developed mild numbness, nine patients exhibited muscle tension, while one patient exhibited facial stiffness. During surgery, there was no intravascular injection of drugs, no nerve injury was reported, and there was no local anesthetic poisoning or spinal anesthesia. CONCLUSIONS Percutaneous stylomastoid foramen pulsed radiofrequency combined with drug injection of the facial nerve for treatment of intractable facial paralysis after herpes zoster is a minimally invasive technique with high rates of success, safety, and effective outcomes. It is a potential therapeutic option for cases of facial paralysis of herpes zoster with a > 1 month history even for those with severe facial paralysis and whose treatment has failed after oral medication and physiotherapy.
Collapse
Affiliation(s)
- Ruyun Deng
- Department of Anesthesiology, Daqing Oilfeld General Hospital, No. 9 Zhongkang Road, Sartu District, Daqing, 163001, China
| | - Ruxiang Wang
- Department of Anesthesiology and Pain Medicine, The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Ming Yao
- Department of Anesthesiology and Pain Medicine, The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Ling Ma
- Department of Anesthesiology and Pain Medicine, The Affiliated Hospital of Jiaxing University, Jiaxing, China.
| |
Collapse
|
2
|
Application of artificial intelligence to stereotactic radiosurgery for intracranial lesions: detection, segmentation, and outcome prediction. J Neurooncol 2023; 161:441-450. [PMID: 36635582 DOI: 10.1007/s11060-022-04234-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2022] [Accepted: 12/30/2022] [Indexed: 01/14/2023]
Abstract
BACKGROUND Rapid evolution of artificial intelligence (AI) prompted its wide application in healthcare systems. Stereotactic radiosurgery served as a good candidate for AI model development and achieved encouraging result in recent years. This article aimed at demonstrating current AI application in radiosurgery. METHODS Literatures published in PubMed during 2010-2022, discussing AI application in stereotactic radiosurgery were reviewed. RESULTS AI algorithms, especially machine learning/deep learning models, have been administered to different aspect of stereotactic radiosurgery. Spontaneous tumor detection and automated lesion delineation or segmentation were two of the promising application, which could be further extended to longitudinal treatment follow-up. Outcome prediction utilized machine learning algorithms with radiomic-based analysis was another well-established application. CONCLUSIONS Stereotactic radiosurgery has taken a lead role in AI development. Current achievement, limitation, and further investigation was summarized in this article.
Collapse
|
3
|
Lee WK, Yang HC, Lee CC, Lu CF, Wu CC, Chung WY, Wu HM, Guo WY, Wu YT. Lesion delineation framework for vestibular schwannoma, meningioma and brain metastasis for gamma knife radiosurgery using stereotactic magnetic resonance images. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 229:107311. [PMID: 36577161 DOI: 10.1016/j.cmpb.2022.107311] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/11/2022] [Revised: 12/06/2022] [Accepted: 12/13/2022] [Indexed: 06/17/2023]
Abstract
BACKGROUND AND OBJECTIVE GKRS is an effective treatment for smaller intracranial tumors with a high control rate and low risk of complications. Target delineation in medical MR images is essential in the planning of GKRS and follow-up. A deep learning-based algorithm can effectively segment the targets from medical images and has been widely explored. However, state-of-the-art deep learning-based target delineation uses fixed sizes, and the isotropic voxel size may not be suitable for stereotactic MR images which use different anisotropic voxel sizes and numbers of slices according to the lesion size and location for clinical GKRS planning. This study developed an automatic deep learning-based segmentation scheme for stereotactic MR images. METHODS We retrospectively collected stereotactic MR images from 506 patients with VS, 1,069 patients with meningioma and 574 patients with BM who had been treated using GKRS; the lesion contours and individual T1W+C and T2W MR images were extracted from the GammaPlan system. The three-dimensional patching-based training strategy and dual-pathway architecture were used to manage inconsistent FOVs and anisotropic voxel size. Furthermore, we used two-parametric MR image as training input to segment the regions with different image characteristics (e.g., cystic lesions) effectively. RESULTS Our results for VS and BM demonstrated that the model trained using two-parametric MR images significantly outperformed the model trained using single-parametric images with median Dice coefficients (0.91, 0.05 versus 0.90, 0.06, and 0.82, 0.23 versus 0.78, 0.34, respectively), whereas predicted delineations in meningiomas using the dual-pathway model were dominated by single-parametric images (median Dice coefficients 0.83, 0.17 versus 0.84, 0.22). Finally, we combined three data sets to train the models, achieving the comparable or even higher testing median Dice (VS: 0.91, 0.07; meningioma: 0.83, 0.22; BM: 0.84, 0.23) in three diseases while using two-parametric as input. CONCLUSIONS Our proposed deep learning-based tumor segmentation scheme was successfully applied to multiple types of intracranial tumor (VS, meningioma and BM) undergoing GKRS and for segmenting the tumor effectively from stereotactic MR image volumes for use in GKRS planning.
Collapse
Affiliation(s)
- Wei-Kai Lee
- Institute of Biophotonics, National Yang Ming Chiao Tung University, 155, Sec. 2, Li-Nong St. Beitou Dist., Taipei 112304, Taiwan
| | - Huai-Che Yang
- School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan; Department of Neurosurgery, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Cheng-Chia Lee
- School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan; Department of Neurosurgery, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Chia-Feng Lu
- Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Chih-Chun Wu
- Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan; School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Wen-Yuh Chung
- School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan; Department of Neurosurgery, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Hsiu-Mei Wu
- Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan; School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Wan-Yuo Guo
- Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan; School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Yu-Te Wu
- Institute of Biophotonics, National Yang Ming Chiao Tung University, 155, Sec. 2, Li-Nong St. Beitou Dist., Taipei 112304, Taiwan; Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan; Brain Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan.
| |
Collapse
|
4
|
Peker S, Samanci Y, Ozdemir IE, Kunst HPM, Eekers DBP, Temel Y. Long-term results of upfront, single-session Gamma Knife radiosurgery for large cystic vestibular schwannomas. Neurosurg Rev 2022; 46:2. [PMID: 36471101 DOI: 10.1007/s10143-022-01911-3] [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] [Accepted: 11/29/2022] [Indexed: 12/12/2022]
Abstract
Anecdotally, cystic vestibular schwannomas (cVSs) are regarded to have unpredictable biologic activity with poorer clinical results, and most studies showed a less favorable prognosis following surgery. While stereotactic radiosurgery (SRS) is a well-established therapeutic option for small- to medium-sized VSs, cVSs are often larger, thus making upfront SRS more complicated. The purpose of this retrospective study was to assess the efficacy and safety of upfront SRS for large cVSs. The authors reviewed the data of 54 patients who received upfront, single-session Gamma Knife radiosurgery (GKRS) with a diagnosis of large cVS (> 4 cm3). Patients with neurofibromatosis type 2, multiple VSs, or recurrent VSs and < 24 months of clinical and neuroimaging follow-up were excluded. Hearing loss (48.1%) was the primary presenting symptom. The majority of cVSs were Koos grade IV (66.7%), and the most prevalent cyst pattern was "mixed pattern of small and big cysts" (46.3%). The median time between diagnosis and GKRS was 12 months (range, 1-147 months). At GKRS, the median cVS volume was 6.95 cm3 (range, 4.1-22 cm3). The median marginal dose was 12 Gy (range, 10-12 Gy). The mean radiological and clinical follow-up periods were 62.2 ± 34.04 months (range, 24-169 months) and 94.9 ± 45.41 months (range, 24-175 months), respectively. At 2, 6, and 12 years, the tumor control rates were 100%, 95.7%, and 85.0%, respectively. Tumor shrinkage occurred in 92.6% of patients (n = 50), tumor volume remained stable in 5.6% of patients (n = 3), and tumor growth occurred in 1.9% of patients (n = 1). At a median follow-up of 53.5 months, the pre-GKRS tumor volume significantly decreased to 2.35 cm3 (p < 0.001). While Koos grade 3 patients had a greater possibility of attaining higher volume reduction, "multiple small thick-walled cyst pattern" and smaller tumor volumes decreased the likelihood of achieving higher volume reduction. Serviceable hearing (Gardner-Robertson Scale I-II) was present in 16.7% of patients prior to GKRS and it was preserved in all of these patients following GKRS. After GKRS, 1.9% of patients (n = 1) had new-onset trigeminal neuralgia. There was no new-onset facial palsy, hemifacial spasm, or hydrocephalus. Contrary to what was believed, our findings suggest that upfront GKRS seems to be a safe and effective treatment option for large cVSs.
Collapse
Affiliation(s)
- Selcuk Peker
- Department of Neurosurgery, School of Medicine, Koç University, Davutpasa Caddesi No. 4, 34010, Zeytinburnu, Istanbul, Turkey.
- Gamma Knife Center, Department of Neurosurgery, Koç University Hospital, Istanbul, Turkey.
- School for Mental Health and Neuroscience (MHeNS), Maastricht University Medical Center, Maastricht, The Netherlands.
| | - Yavuz Samanci
- Gamma Knife Center, Department of Neurosurgery, Koç University Hospital, Istanbul, Turkey
- Department of Neurosurgery, Koç University Hospital, Istanbul, Turkey
| | - Inan Erdem Ozdemir
- Gamma Knife Center, Department of Neurosurgery, Koç University Hospital, Istanbul, Turkey
| | - Henricus P M Kunst
- Department of Otorhinolaryngology, Maastricht University Medical Center, Maastricht, The Netherlands
- Department of Otorhinolaryngology, Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands
- Dutch Academic Alliance Skull Base Pathology, Maastricht University Medical Center, Radboud University Medical Center, Maastricht/Nijmegen, The Netherlands
| | - Daniëlle B P Eekers
- Dutch Academic Alliance Skull Base Pathology, Maastricht University Medical Center, Radboud University Medical Center, Maastricht/Nijmegen, The Netherlands
- Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Center, Maastricht, The Netherlands
| | - Yasin Temel
- School for Mental Health and Neuroscience (MHeNS), Maastricht University Medical Center, Maastricht, The Netherlands
- Dutch Academic Alliance Skull Base Pathology, Maastricht University Medical Center, Radboud University Medical Center, Maastricht/Nijmegen, The Netherlands
- Department of Neurosurgery, Maastricht University Medical Center, Maastricht, The Netherlands
| |
Collapse
|
5
|
Convolutional Neural Networks to Detect Vestibular Schwannomas on Single MRI Slices: A Feasibility Study. Cancers (Basel) 2022; 14:cancers14092069. [PMID: 35565199 PMCID: PMC9104481 DOI: 10.3390/cancers14092069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/10/2022] [Revised: 03/30/2022] [Accepted: 04/19/2022] [Indexed: 02/04/2023] Open
Abstract
Simple Summary Due to the fact that they take inter-slice information into account, 3D- and 2.5D-convolutional neural networks (CNNs) potentially perform better in tumor detection tasks than 2D-CNNs. However, this potential benefit is at the expense of increased computational power and the need for segmentations as an input. Therefore, in this study we aimed to detect vestibular schwannomas (VSs) in individual magnetic resonance imaging (MRI) slices by using a 2D-CNN. We retrained (539 patients) and internally validated (94 patients) a pretrained CNN using contrast-enhanced MRI slices from one institution. Furthermore, we externally validated the CNN using contrast-enhanced MRI slices from another institution. This resulted in an accuracy of 0.949 (95% CI 0.935–0.963) and 0.912 (95% CI 0.866–0.958) for the internal and external validation, respectively. Our findings indicate that 2D-CNNs might be a promising alternative to 2.5-/3D-CNNs for certain tasks thanks to the decreased requirement for computational power and the fact that there is no need for segmentations. Abstract In this study. we aimed to detect vestibular schwannomas (VSs) in individual magnetic resonance imaging (MRI) slices by using a 2D-CNN. A pretrained CNN (ResNet-34) was retrained and internally validated using contrast-enhanced T1-weighted (T1c) MRI slices from one institution. In a second step, the model was externally validated using T1c- and T1-weighted (T1) slices from a different institution. As a substitute, bisected slices were used with and without tumors originating from whole transversal slices that contained part of the unilateral VS. The model predictions were assessed based on the categorical accuracy and confusion matrices. A total of 539, 94, and 74 patients were included for training, internal validation, and external T1c validation, respectively. This resulted in an accuracy of 0.949 (95% CI 0.935–0.963) for the internal validation and 0.912 (95% CI 0.866–0.958) for the external T1c validation. We suggest that 2D-CNNs might be a promising alternative to 2.5-/3D-CNNs for certain tasks thanks to the decreased demand for computational power and the fact that there is no need for segmentations. However, further research is needed on the difference between 2D-CNNs and more complex architectures.
Collapse
|