Hearing Loss and Volumetric Growth Rate in Observed Vestibular Schwannoma Patients

2021 ◽  
Author(s):  
Zane Schnurman ◽  
Jason Gurewitz ◽  
Aya Nakamura ◽  
John Golfinos ◽  
J. Thomas Roland Jr ◽  
...  
Keyword(s):  
Growth Rate ◽  
Hearing Loss ◽  
Vestibular Schwannoma ◽  
Volumetric Growth

scholarly journals Predicting Growth Trajectory in Vestibular Schwannoma From Radiomic Data Using Supervised Machine Learning Techniques

Neurosurgery ◽  
2019 ◽  
Vol 66 (Supplement_1) ◽  
Author(s):  
Conor Grady ◽  
Hesheng Wang ◽  
Zane Schnurman ◽  
Tanxia Qu ◽  
Douglas Kondziolka
Keyword(s):  
Machine Learning ◽  
Growth Rate ◽  
Vestibular Schwannoma ◽  
High Growth ◽  
High Growth Rate ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Volumetric Growth ◽  
Learning Techniques ◽  
Pre Treatment

Abstract INTRODUCTION Clinicians are not able to predict the growth-rate of a vestibular schwannoma (VS) by reviewing a standard MRI. Recently, the field of radiomics has enabled high-dimensional, quantitative datasets to be created from imaging obtained during routine clinical care. This study investigates whether supervised machine learning techniques can yield accurate predictions of volumetric growth-rate based on radiomic data from MRIs of treatment-naïve VSs. METHODS A total of 212 patients diagnosed with unilateral VS between 2012 and 2018 underwent measurement of tumor volume on all pre-treatment MRIs. The number of MRIs per patient ranged from 2 to 11, totaling 699 individual studies. Annualized volumetric growth-rate was calculated for each patient. Two cohorts were formed from the 30 patients with the lowest (−20% to 10%) and the 40 patients with the highest (55%–165%) annualized growth-rates, respectively. Manual segmentation of tumor volumes on the last pre-treatment MRI for each patient was performed using 3D Slicer. Pyradiomics was used to calculate histogram, shape, and texture parameters from ADC, CISS, T2 weighted, and postcontrast T1 weighted sequences, resulting in a total of 311 radiomic parameters per volume of interest. Two models predicting cohort membership, a random forest classifier (RFC) and a gradient boosted trees (XGBoost) algorithm, were then trained on a training dataset containing the radiomic profiles of 25 patients from the low growth-rate cohort and 35 patients from the high growth-rate cohort. The models were then tested against the radiomic profiles of the 10 patients withheld from the training group. RESULTS Following tuning of hyperparameters, both models were able to predict individual tumor membership in the low-growth-rate or high growth-rate cohorts with 100% accuracy. Area under the receiver operating curve (ROC) curve (AUC) was 1.0 for both models. CONCLUSION Supervised machine learning techniques can predict growth-rate in VS based on radiomic parameters. External validation is warranted.

Hearing loss and volumetric growth rate in untreated vestibular schwannoma

2021 ◽  
pp. 1-8
Author(s):  
Jason Gurewitz ◽  
Zane Schnurman ◽  
Aya Nakamura ◽  
Ralph E. Navarro ◽  
Dev N. Patel ◽  
...  
Keyword(s):  
Growth Rate ◽  
Hearing Loss ◽  
Tumor Growth ◽  
Growth Rates ◽  
Volumetric Growth ◽  
Class A ◽  
Hazard Ratios ◽  
Increased Risk ◽  
Initial Tumor ◽  
Initial Tumor Size

OBJECTIVE In this study, the authors aimed to clarify the relationship between hearing loss and tumor volumetric growth rates in patients with untreated vestibular schwannoma (VS). METHODS Records of 128 treatment-naive patients diagnosed with unilateral VS between 2012 and 2018 with serial audiometric assessment and MRI were reviewed. Tumor growth rates were determined from initial and final tumor volumes, with a median follow-up of 24.3 months (IQR 8.5–48.8 months). Hearing changes were based on pure tone averages, speech discrimination scores, and American Academy of Otolaryngology–Head and Neck Surgery hearing class. Primary outcomes were the loss of class A hearing and loss of serviceable hearing, estimated using the Kaplan-Meier method and with associations estimated from Cox proportional hazards models and reported as hazard ratios. RESULTS Larger initial tumor size was associated with an increased risk of losing class A (HR 1.5 for a 1-cm3 increase; p = 0.047) and serviceable (HR 1.3; p < 0.001) hearing. Additionally, increasing volumetric tumor growth rate was associated with elevated risk of loss of class A hearing (HR 1.2 for increase of 100% per year; p = 0.031) and serviceable hearing (HR 1.2; p = 0.014). Hazard ratios increased linearly with increasing growth rates, without any evident threshold growth rate that resulted in a large, sudden increased risk of hearing loss. CONCLUSIONS Larger initial tumor size and faster tumor growth rates were associated with an elevated risk of loss of class A and serviceable hearing.

scholarly journals Sudden sensorineural hearing loss in patients with vestibular schwannoma

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Koichiro Wasano ◽  
Naoki Oishi ◽  
Masaru Noguchi ◽  
Ko Hentona ◽  
Seiichi Shinden ◽  
...  
Keyword(s):  
Hearing Loss ◽  
Sensorineural Hearing Loss ◽  
Clinical Features ◽  
Vestibular Schwannoma ◽  
Recovery Rate ◽  
Treatment Plan ◽  
Full Range ◽  
Sudden Sensorineural Hearing Loss ◽  
Sensorineural Hearing ◽  
Recurrence Time

AbstractClinical features of sudden sensorineural hearing loss (SSNHL) associated with vestibular schwannoma (VS) are not fully understood. Determining a treatment plan and explaining it to patients requires clinicians to clearly understand the clinical features related to the tumor, including SSNHL. To identify the full range of clinical features of VS-associated SSNHL, especially recovery of hearing following multiple episodes of SSNHL and what factors predict recovery and recurrence. A multicenter retrospective chart review was conducted in seven tertiary care hospitals between April 1, 2011, and March 31, 2020. We collected and analyzed dose of administered steroid, pure-tone audiometry results, and brain MRIs of patients diagnosed with VS-associated SSNHL. Seventy-seven patients were included. They experienced 109 episodes of audiogram-confirmed SSNHL. The highest proportion of complete recoveries occurred in patients with U-shaped audiograms. The recovery rates for the first, second, and third and subsequent episodes of SSNHL were 53.5%, 28.0%, and 9.1%, respectively. Recovery rate decreased significantly with increasing number of SSNHL episodes (P =0 .0011; Cochran-Armitage test). After the first episode of SSNHL, the recurrence-free rate was 69.9% over 1 year and 57.7% over 2 years; the median recurrence time was 32 months. Logarithmic approximation revealed that there is a 25% probability that SSNHL would recur within a year. SSNHL in patients with VS is likely to recur within one year in 25% of cases. Also, recovery rate decreases as a patient experiences increasing episodes of SSNHL.

Degree of preoperative hearing loss predicts time to early mobilization following vestibular schwannoma microsurgery

2021 ◽  
pp. 103073
Author(s):  
Robert J. Macielak ◽  
Jason H. Barnes ◽  
Jamie J. Van Gompel ◽  
Brian A. Neff ◽  
Michael J. Link ◽  
...  
Keyword(s):  
Hearing Loss ◽  
Vestibular Schwannoma ◽  
Early Mobilization

Hearing loss in vestibular schwannoma: size isn't everything

2016 ◽  
Vol 71 ◽  
pp. S4 ◽  
Author(s):  
Joanna Kate Dixon ◽  
Elizabeth Loney
Keyword(s):  
Hearing Loss ◽  
Vestibular Schwannoma

Preoperative Sudden Hearing Loss May Predict Hearing Preservation After Retrosigmoid Resection of Vestibular Schwannoma

2021 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Kareem O. Tawfik ◽  
Thomas H. Alexander ◽  
Joe Saliba ◽  
Yin Ren ◽  
Bill Mastrodimos ◽  
...  
Keyword(s):  
Hearing Loss ◽  
Vestibular Schwannoma ◽  
Hearing Preservation ◽  
Sudden Hearing Loss

Growth Rate of the Vomer in Normal and Cleft Lip and Palate Human Fetal Specimens

1992 ◽  
Vol 29 (1) ◽  
pp. 38-43 ◽  
Author(s):  
Kyle R. Kimes ◽  
Mark P. Mooney ◽  
Michael I. Siegel ◽  
John S. Todhunter
Keyword(s):  
Growth Rate ◽  
Cleft Lip ◽  
Cleft Lip And Palate ◽  
Three Dimensional ◽  
Growth Curves ◽  
Reconstruction Technique ◽  
Linear Component ◽  
Volumetric Growth ◽  
Significant Difference ◽  
Postmenstrual Age

The present study, part of an ongoing investigation of normal and dysmorphic development of the human fetal oronasal capsule, examined the rate of growth of the vomer. For comparative purposes, 29 human fetal specimens (20 “normal” and 9 cleft lip and palate [CLP]) were celloidin embedded, sectioned, stained with hematoxylin and eosin, and serially digitized. The specimens ranged from 8 to 21 weeks in postmenstrual age. The application of a well-documented three-dimensional reconstruction technique provided quantification of several aspects of the vomer. CLP vomer length and volume were growing at a faster rate In the 8 to 21 week age range. Growth curves were produced by plotting length and volume against postmenstrual age and a significant difference was noted between the slopes (growth rate) of the linear component of the normal and CLP growth curves for vomer length (p < .001) and volume (p < .001). This study tested the hypothesis of a more rapidly growing 8 to 21 week CLP vomer and observed that the growth trends of the CLP vomer are similar to those of the CLP nasal septum, which also was found to possess a significantly larger (p < .001) volumetric growth rate throughout the course of the vomer. Comparative findings suggest that a pathogenetic correlate of CLP is the rapid enlargement of the midline structures of the oral and nasal capsules.

Sign in / Sign up

Export Citation Format

Share Document