Comparing Linear and Volumetric Vestibular Schwannoma Measurements Between T1 and T2 Magnetic Resonance Imaging Sequences

Accuracy of vestibular schwannoma segmentation using deep learning models - a systematic review & meta-analysis

Vestibular Schwannoma (VS) is a rare tumor with varied incidence rates, predominantly affecting the 60-69 age group. In the era of artificial intelligence (AI), deep learning (DL) algorithms show promise in automating diagnosis. However, a knowledge gap exists in the automated segmentation of VS using DL. To address this gap, this meta-analysis aims to provide insights into the current state of DL algorithms applied to MR images of VS.

METHODOLOGY

Following 2020 PRISMA guidelines, a search across four databases was conducted. Inclusion criteria focused on articles using DL for VS MR image segmentation. The primary metric was the Dice score, supplemented by relative volume error (RVE) and average symmetric surface distance (ASSD).

RESULTS

The search process identified 752 articles, leading to 11 studies for meta-analysis. A QUADAS- 2 analysis revealed varying biases. The overall Dice score for 56 models was 0.89 (CI: 0.88-0.90), with high heterogeneity (I2 = 95.9%). Subgroup analyses based on DL architecture, MRI inputs, and testing set sizes revealed performance variations. 2.5D DL networks demonstrated comparable efficacy to 3D networks. Imaging input analyses highlighted the superiority of contrast-enhanced T1-weighted imaging and mixed MRI inputs.

DISCUSSION

This study fills a gap in systematic review in the automated segmentation of VS using DL techniques. Despite promising results, limitations include publication bias and high heterogeneity. Future research should focus on standardized designs, larger testing sets, and addressing biases for more reliable results. DL have promising efficacy in VS diagnosis, however further validation and standardization is needed.

CONCLUSION

In conclusion, this meta-analysis provides comprehensive review into the current landscape of automated VS segmentation using DL. The high Dice score indicates promising agreement in segmentation, yet challenges like bias and heterogeneity must be addressed in the future research.

Defining tumor growth in vestibular schwannomas: a volumetric inter-observer variability study in contrast-enhanced T1-weighted MRI

PURPOSE

For patients with vestibular schwannomas (VS), a conservative observational approach is increasingly used. Therefore, the need for accurate and reliable volumetric tumor monitoring is important. Currently, a volumetric cutoff of 20% increase in tumor volume is widely used to define tumor growth in VS. The study investigates the tumor volume dependency on the limits of agreement (LoA) for volumetric measurements of VS by means of an inter-observer study.

METHODS

This retrospective study included 100 VS patients who underwent contrast-enhanced T1-weighted MRI. Five observers volumetrically annotated the images. Observer agreement and reliability was measured using the LoA, estimated using the limits of agreement with the mean (LOAM) method, and the intraclass correlation coefficient (ICC).

RESULTS

The 100 patients had a median average tumor volume of 903 mm3 (IQR: 193-3101). Patients were divided into four volumetric size categories based on tumor volume quartile. The smallest tumor volume quartile showed a LOAM relative to the mean of 26.8% (95% CI: 23.7-33.6), whereas for the largest tumor volume quartile this figure was found to be 7.3% (95% CI: 6.5-9.7) and when excluding peritumoral cysts: 4.8% (95% CI: 4.2-6.2).

CONCLUSION

Agreement limits within volumetric annotation of VS are affected by tumor volume, since the LoA improves with increasing tumor volume. As a result, for tumors larger than 200 mm3, growth can reliably be detected at an earlier stage, compared to the currently widely used cutoff of 20%. However, for very small tumors, growth should be assessed with higher agreement limits than previously thought.

Wait-and-scan management in sporadic Koos grade 4 vestibular schwannomas: A longitudinal volumetric study

Background

Volumetric natural history studies specifically on large vestibular schwannomas (VSs), commonly classified as Koos grade 4, are lacking. The aim of the current study is to present the volumetric tumor evolution in sporadic Koos grade 4 VSs and possible predictors for tumor growth.

Methods

Volumetric tumor measurements and tumor evolution patterns from serial MRI studies were analyzed from selected consecutive patients with Koos grade 4 VS undergoing initial wait-and-scan management between January 2001 and July 2020. The significant volumetric threshold was defined as a change in volume of ≥10%.

Results

Among 215 tumors with a median size (IQR) of 2.7 cm3 (1.8-4.2), 147 tumors (68%) demonstrated growth and 75 tumors (35%) demonstrated shrinkage during follow-up. Growth-free survival rates (95% CI) at 1, 2, 5, and 10 years were 55% (48-61), 36% (29-42), 29% (23-36), and 28% (21-34), respectively and did not significantly differ in tumors> 20 mm (Chi-square = .40; P-value = .53). Four tumor evolution patterns (% of total) were observed: continued growth (60); initial growth then shrinkage (7); continued shrinkage (27); and stability (5). Good hearing (adjusted HR 2.21, 95% CI 1.48-3.30; P < .001) and peritumoral edema (adjusted HR 2.22, 95% CI 1.18-4.13; P = .01) at diagnosis were significantly associated with an increased likelihood of growth.

Conclusions

Koos grade 4 VSs show a wide variety in size and growth. Due to variable growth patterns, an initial wait-and-scan strategy with short scan intervals may be an acceptable option in selected tumors, if no significant clinical symptoms of mass effect that warrant treatment are present.

Automated 2-Dimensional Measurement of Vestibular Schwannoma: Validity and Accuracy of an Artificial Intelligence Algorithm

OBJECTIVE

Validation of automated 2-dimensional (2D) diameter measurements of vestibular schwannomas on magnetic resonance imaging (MRI).

STUDY DESIGN

Retrospective validation study using 2 data sets containing MRIs of vestibular schwannoma patients.

SETTING

University Hospital in The Netherlands.

METHODS

Two data sets were used, 1 containing 1 scan per patient (n = 134) and the other containing at least 3 consecutive MRIs of 51 patients, all with contrast-enhanced T1 or high-resolution T2 sequences. 2D measurements of the maximal extrameatal diameters in the axial plane were automatically derived from a 3D-convolutional neural network compared to manual measurements by 2 human observers. Intra- and interobserver variabilities were calculated using the intraclass correlation coefficient (ICC), agreement on tumor progression using Cohen's kappa.

RESULTS

The human intra- and interobserver variability showed a high correlation (ICC: 0.98-0.99) and limits of agreement of 1.7 to 2.1 mm. Comparing the automated to human measurements resulted in ICC of 0.98 (95% confidence interval [CI]: 0.974; 0.987) and 0.97 (95% CI: 0.968; 0.984), with limits of agreement of 2.2 and 2.1 mm for diameters parallel and perpendicular to the posterior side of the temporal bone, respectively. There was satisfactory agreement on tumor progression between automated measurements and human observers (Cohen's κ = 0.77), better than the agreement between the human observers (Cohen's κ = 0.74).

CONCLUSION

Automated 2D diameter measurements and growth detection of vestibular schwannomas are at least as accurate as human 2D measurements. In clinical practice, measurements of the maximal extrameatal tumor (2D) diameters of vestibular schwannomas provide important complementary information to total tumor volume (3D) measurements. Combining both in an automated measurement algorithm facilitates clinical adoption.

Assessing Tumor Volume for Sporadic Vestibular Schwannomas: A Comparison of Methods of Volumetry

INTRODUCTION

The size of vestibular schwannomas (VS) is a major factor guiding the initial decision of treatment and the definition of tumor control or failure. Accurate measurement and standardized definition are mandatory; yet no standard exist. Various approximation methods using linear measures or segmental volumetry have been reported. We reviewed different methods of volumetry and evaluated their correlation and agreement using our own historical cohort.

METHODS

We selected patients treated for sporadic VS by Gammaknife radiosurgery (GKRS) in our department. Using the stereotactic 3D T1 enhancing MRI on the day of GKRS, 4 methods of volumetry using linear measurements (5-axis, 3-axis, 3-axis-averaged, and 1-axis) and segmental volumetry were compared to each other. The degree of correlation was evaluated using an intraclass correlation test (ICC 3,1). The agreement between the different methods was evaluated using Bland-Altman diagrams.

RESULTS

A total of 2,188 patients were included. We observed an excellent ICC between 5-axis volumetry (0.98), 3-axis volumetry (0.96), and 3-axis-averaged volumetry (0.96) and segmental volumetry, respectively, irrespective of the Koos grade or Ohata classification. The ICC for 1-axis volumetry was lower (0.72) and varied depending on the Koos and Ohata subgroups. None of these methods were substitutable.

CONCLUSION

Although segmental volumetry is deemed the most accurate method, it takes more effort and requires sophisticated computation systems compared to methods of volumetry using linear measurements. 5-axis volumetry affords the best adequacy with segmental volumetry among all methods under assessment, irrespective of the shape of the tumor. 1-axis volumetry should not be used.

The study of predictive factors for the evolution of vestibular schwannomas

PURPOSE

The primary objective was to determine whether the analysis of textural heterogeneity of vestibular schwannomas on MRI at diagnosis was predictive of their radiological evolutivity. The secondary objective was to determine whether some clinical or radiological factors could also be predictive of growth.

METHODS

We conducted a pilot, observational and retrospective study of patients with a vestibular schwannoma, initially monitored, between April 2001 and November 2019 within the Oto-Neurosurgical Institute of Champagne Ardenne, Texture analysis was performed on gadolinium injected T1 and CISS T2 MRI sequences and six parameters were extracted: mean greyscale intensity, standard deviation of the greyscale histogram distribution, entropy, mean positive pixels, skewness and kurtosis, which were analysed by the Lasso method, using statistically penalised Cox models. Extrameatal location, tumour necrosis, perceived hearing loss < 2 years with objectified tone audiometry asymmetry, tinnitus at diagnosis, were investigated by the Log-Rank test to obtain univariate survival analyses.

RESULTS

78 patients were included and divided into 2 groups: group A comprising 39 "stable patients", and B comprising the remaining 39 "progressive patients". Independent analysis of the texture factors did not predict the growth potential of vestibular schwannomas. Among the clinical or radiological signs of interest, hearing loss < 2 years was identified as a prognostic factor for tumour progression with a significant trend (p = 0.05).

CONCLUSIONS

This study did not identify an association between texture analysis and vestibular schwannomas growth. Decreased hearing in the 2 years prior to diagnosis appears to predict potential radiological progression.

Machine Learning for Automated Calculation of Vestibular Schwannoma Volumes

HYPOTHESIS

Machine learning-derived algorithms are capable of automated calculation of vestibular schwannoma tumor volumes without operator input.

BACKGROUND

Volumetric measurements are most sensitive for detection of vestibular schwannoma growth and important for patient counseling and management decisions. Yet, manually measuring volume is logistically challenging and time-consuming.

METHODS

We developed a deep learning framework fusing transformers and convolutional neural networks to calculate vestibular schwannoma volumes without operator input. The algorithm was trained, validated, and tested on an external, publicly available data set consisting of magnetic resonance imaging images of medium and large tumors (178-9,598 mm 3 ) with uniform acquisition protocols. The algorithm was then trained, validated, and tested on an internal data set of variable size tumors (5-6,126 mm 3 ) with variable acquisition protocols.

RESULTS

The externally trained algorithm yielded 87% voxel overlap (Dice score) with manually segmented tumors on the external data set. The same algorithm failed to translate to accurate tumor detection when tested on the internal data set, with Dice score of 36%. Retraining on the internal data set yielded Dice score of 82% when compared with manually segmented images, and 85% when only considering tumors of similar size as the external data set (>178 mm 3 ). Manual segmentation by two experts demonstrated high intraclass correlation coefficient (0.999).

CONCLUSION

Sophisticated machine learning algorithms delineate vestibular schwannomas with an accuracy exceeding established norms of up to 20% error for repeated manual volumetric measurements-87% accuracy on a homogeneous data set, and 82% to 85% accuracy on a more varied data set mirroring real world neurotology practice. This technology has promise for clinical applicability and time savings.

Fully Automated 3D Vestibular Schwannoma Segmentation with and without Gadolinium-based Contrast Material: A Multicenter, Multivendor Study

PURPOSE

To develop automated vestibular schwannoma measurements on contrast-enhanced T1- and T2-weighted MRI scans.

MATERIALS AND METHODS

MRI data from 214 patients in 37 different centers were retrospectively analyzed between 2020 and 2021. Patients with hearing loss (134 positive for vestibular schwannoma [mean age ± SD, 54 years ± 12;64 men] and 80 negative for vestibular schwannoma) were randomly assigned to a training and validation set and to an independent test set. A convolutional neural network (CNN) was trained using fivefold cross-validation for two models (T1 and T2). Quantitative analysis, including Dice index, Hausdorff distance, surface-to-surface distance (S2S), and relative volume error, was used to compare the computer and the human delineations. An observer study was performed in which two experienced physicians evaluated both delineations.

RESULTS

The T1-weighted model showed state-of-the-art performance, with a mean S2S distance of less than 0.6 mm for the whole tumor and the intrameatal and extrameatal tumor parts. The whole tumor Dice index and Hausdorff distance were 0.92 and 2.1 mm in the independent test set, respectively. T2-weighted images had a mean S2S distance less than 0.6 mm for the whole tumor and the intrameatal and extrameatal tumor parts. The whole tumor Dice index and Hausdorff distance were 0.87 and 1.5 mm in the independent test set. The observer study indicated that the tool was similar to human delineations in 85%-92% of cases.

CONCLUSION

The CNN model detected and delineated vestibular schwannomas accurately on contrast-enhanced T1- and T2-weighted MRI scans and distinguished the clinically relevant difference between intrameatal and extrameatal tumor parts.Keywords: MRI, Ear, Nose, and Throat, Skull Base, Segmentation, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2022.

Outcomes of Carotid Body Tumor Management with Active Surveillance

OBJECTIVES

To assess outcomes of carotid body tumors (CBTs) managed with active surveillance.

METHODS

Retrospective chart review of CBTs managed with active surveillance from 2001 to 2019.

RESULTS

A total of 115 cases were identified during chart review. Sixty-five of these patients were managed with active surveillance, and 11 patients had bilateral tumors for a total of 76 tumors. Follow-up records with symptomatic outcomes were available for 51 patients, and 47 tumors had follow-up imaging. Thirty-one (66%) actively surveilled CBTs remained stable or decreased in size while 16 (34%) increased in size. Patients undergoing active surveillance developed symptoms in 12 cases, 6 of these patients underwent surgical intervention. Nine CBTs managed with active surveillance (18%) were ultimately resected. The majority of patients who did not undergo surgical intervention never developed symptoms (36/42, 86%).

CONCLUSIONS

Active surveillance may be a reasonable approach for a subset of CBTs.

Sporadic Vestibular Schwannoma Size and Location Do not Correlate With the Severity of Hearing Loss at Initial Presentation

Vestibular schwannoma (VS) is a non-malignant intracranial neoplasm arising from the vestibular branch of the 8th cranial nerve; sensorineural hearing loss (SNHL) is the most common associated symptom. Understanding whether VS imaging characteristics at the time of VS diagnosis can be associated with severity of VS-induced SNHL can impact patient counseling and define promising areas for future research. Patients diagnosed with VS at Massachusetts Eye and Ear (MEE) from 1994 through 2018 were analyzed if magnetic resonance imaging at VS presentation and sequential audiometry were available. Results were compared with original studies available in PubMed, written in English, on VS imaging characteristics and their impact on hearing in patients. A total of 477 patients with unilateral VS from the MEE database demonstrated no significant correlation between any features of tumor imaging at the time of VS diagnosis, such as VS size, impaction or location, and any hearing loss metric. Twenty-three published studies on the impact of VS imaging characteristics on patient hearing met inclusion criteria, with six solely involving NF2 patients and three including both sporadic and NF2-related VS patients. Fifteen studies reported a significant relationship between SNHL and at least one VS imaging characteristic; however, these trends were universally limited to NF2 patients or involved small patient populations, and were not reproduced in larger studies. Taken together, SNHL in sporadic VS patients is not readily associated solely with any tumor imaging characteristics. This finding motivates future studies to define how VS microenvironment and secreted molecules influence VS-induced SNHL.

Vestibular Schwannoma Measurements-Is Volumetric Analysis Clinically Necessary?

OBJECTIVE

1) To compare vestibular schwannoma maximum linear dimensions and calculated volume with measured volume in accurately determining tumor volume and growth. 2) To determine natural growth history of vestibular schwannomas utilizing volumetric measurements in an observed patient population.

STUDY DESIGN

Retrospective chart review.

SETTING

Tertiary academic referral.

PATIENTS

One hundred fifty two adults with a vestibular schwannoma who underwent observational management with sequential magnetic resonance imaging (MRI) scans (496 scans).

INTERVENTION

MRI scans.

MAIN OUTCOME MEASURES

Tumor volume calculated from linear dimensions compared with measured volume. The percentage change in tumor size (linear or volume) between consecutive MRI scans.

RESULTS

The percentage change in tumor size between consecutive MRIs is significantly different between maximum linear dimension (MLD) and measured tumor volume (p = 0.03), but no difference exists in the percentage change between measured and calculated tumor volume (p = 0.882 for three linear measurements, p = 0.637 for two linear measurements). The overall number of growing tumors is 57.2% (n = 87) with an average growth rate of 62.6%. If a criterion for growth of 20% change is used, 32.2% of tumors monitored by linear volume would have demonstrated growth while 57.2% of tumors with measured volume demonstrated growth.

CONCLUSION

Maximum linear dimensions are a significantly less sensitive measure of tumor growth compared with measured volumes. Calculated tumor volume utilizing three linear measurements is an accurate predictor of both measured tumor volume and tumor growth.

Automated Detection of Vestibular Schwannoma Growth Using a Two-Dimensional U-Net Convolutional Neural Network

OBJECTIVES/HYPOTHESIS

To determine if an automated vestibular schwannoma (VS) segmentation model has comparable performance to using the greatest linear dimension to detect growth.

STUDY DESIGN

Case-control Study.

METHODS

Patients were selected from an internal database who had an initial gadolinium-enhanced T1-weighted magnetic resonance imaging scan and a follow-up scan captured at least 5 months later. Two observers manually segmented the VS to compute volumes, and one observer's segmentations were used to train a convolutional neural network model to automatically segment the VS and determine the volume. The results of automatic segmentation were compared to the observer whose measurements were not used in model development to measure agreement. We then examined the sensitivity, specificity, and area under the receiver-operating characteristic curve (AUC) to compare automated volumetric growth detection versus using the greatest linear dimension. Growth detection determined by the external observer's measurements served as the gold standard.

RESULTS

A total of 65 patients and 130 scans were studied. The automated method of segmentation demonstrated excellent agreement with the observer whose measurements were not used for model development for the initial scan (interclass correlational coefficient [ICC] = 0.995; 95% confidence interval [CI]: 0.991-0.997) and follow-up scan (ICC = 0.960; 95% CI: 0.935-0.975). The automated method of segmentation demonstrated increased sensitivity (72.2% vs. 63.9%), specificity (79.3% vs. 69.0%), and AUC (0.822 vs. 0.701) compared to using the greatest linear dimension for growth detection.

CONCLUSIONS

In detecting VS growth, a convolutional neural network model outperformed using the greatest linear dimension, demonstrating a potential application of artificial intelligence methods to VS surveillance.

LEVEL OF EVIDENCE

4 Laryngoscope, 131:E619-E624, 2021.