Surveillance After Resection of Vestibular Schwannoma

Tang, Si; Griffin, Andrew; Waksal, Julian A.; Phillips, C. Douglas; Johnson, Carl E.; Comunale, Joseph; Karimi, Sasan; Powell, Tiffany L.; Stieg, Philip E.; Gutin, Philip H.; Brown, Kevin D.; Sheehan, Maura; Selesnick, Samuel H.

doi:10.1097/mao.0000000000000459

Cited by 18 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Volume measures can be derived by summation of the segmented areas on each slice and multiplying by slice thickness. Providing an accurate segmentation from which 2-D and 3-D tumor metrics can be calculated is especially important given growing research that area and volume metrics may be more reliable and accurate measures of tumor size and growth than linear metrics (2,5,6).…”

Section: Discussionmentioning

confidence: 99%

Segmentation of Vestibular Schwannomas on Postoperative Gadolinium-Enhanced T1-Weighted and Noncontrast T2-Weighted Magnetic Resonance Imaging Using Deep Learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

Surveillance of postoperative vestibular schwannomas currently relies on manual segmentation and measurement of the tumor by content experts, which is both labor intensive and time consuming. We aimed to develop and validate deep learning models for automatic segmentation of postoperative vestibular schwannomas on gadolinium-enhanced T1-weighted magnetic resonance imaging (GdT1WI) and noncontrast high-resolution T2-weighted magnetic resonance imaging (HRT2WI). Study Design: A supervised machine learning approach using a U-Net model was applied to segment magnetic resonance imaging images into pixels representing vestibular schwannoma and background pixels. Setting: Tertiary care hospital. Patients: Our retrospective data set consisted of 122 GdT1WI and 122 HRT2WI studies in 82 postoperative adult patients with a vestibular schwannoma treated with subtotal surgical resection between September 1, 2007, and April 17, 2018. Forty-nine percent of our cohort was female, the mean age at the time of surgery was 49.8 years, and the median time from surgery to follow-up scan was 2.26 years. Intervention(s): N/A.Main Outcome Measure(s): Tumor areas were manually segmented in axial images and used as ground truth for training and evaluation of the model. We measured the Dice score of the predicted segmentation results in comparison to manual segmentations from experts to assess the model's accuracy.Results: The GdT1WI model achieved a Dice score of 0.89, and the HRT2WI model achieved a Dice score of 0.85. Conclusion:We demonstrated that postoperative vestibular schwannomas can be accurately segmented on GdT1WI and HRT2WI without human intervention using deep learning. This artificial intelligence technology has the potential to improve the postoperative surveillance and management of patients with vestibular schwannomas.

show abstract

Section: Discussionmentioning

confidence: 99%

Segmentation of Vestibular Schwannomas on Postoperative Gadolinium-Enhanced T1-Weighted and Noncontrast T2-Weighted Magnetic Resonance Imaging Using Deep Learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The literature is also supportive of using linear dimension rather than volumetric calculations. [17][18][19][20] Furthermore, the method utilized to measure vs in this study (using the inbuilt calliper software in PACS) offers reproducibility to other healthcare centres.…”

Section: Discussionmentioning

confidence: 99%

Should we be moving to a national standardized non-gadolinium MR imaging protocol for the surveillance of vestibular schwannomas?

Currie

Saunders

Macmullen-Price

et al. 2019

The British Journal of Radiology

View full text Add to dashboard Cite

Getting It Right First Time (GIRFT) is a UK national programme designed to improve the quality of care within the NHS by reducing unwarranted variations. By tackling variations in the way services are delivered across the NHS, and by sharing best practice between trusts, GIRFT identifies changes that will help improve care and patient outcomes, as well as delivering efficiencies such as the reduction of unnecessary procedures and cost savings. 1 Imaging performed for the surveillance of patients with non-operated brain tumours such as vestibular schwannomas is a practice that may benefit from the GIRFT model. Vestibular schwannomas (vs), also known as acoustic neuromas, are benign tumours that originate from the Schwann cells of the vestibular nerve sheath and typically occur in the cerebellopontine angle and internal auditory canal. 2 They account for 10% of all brain neoplasms and studies have approximated their incidence to 10-20 cases per million people per year, although this is likely an

show abstract

“…Many of the previously reported studies use a manual segmentation volume measurement technique which is impractical for use in daily clinical practice [ 14 , 16 , 21 , 30 ]. Some studies have used a semi-automated volume segmentation tool which uses an ‘active contouring’ algorithm to outline the tumour on each slice; each slice area is then automatically summated and multiplied by slice thickness to provide a volume [ 13 , 18 ].…”

Section: Discussionmentioning

confidence: 99%

“…The majority of previous studies showing the benefits of volumetric over linear measurements of VS have used the manual segmentation or Cavilieri method where the tumour is manually outlined on each MRI slice and the area multiplied by slice thickness [ 10 , 14 , 16 , 21 ]. This is a time-consuming technique taking 15–25 min per tumour measurement [ 10 , 14 ], making it impractical for routine clinical practice.…”

Section: Introductionmentioning

confidence: 99%

A comparison of semi-automated volumetric vs linear measurement of small vestibular schwannomas

MacKeith

Das

Graves

et al. 2018

Eur Arch Otorhinolaryngol

View full text Add to dashboard Cite

ObjectiveAccurate and precise measurement of vestibular schwannoma (VS) size is key to clinical management decisions. Linear measurements are used in routine clinical practice but are prone to measurement error. This study aims to compare a semi-automated volume segmentation tool against standard linear method for measuring small VS. This study also examines whether oblique tumour orientation can contribute to linear measurement error.Study designExperimental comparison of observer agreement using two measurement techniques.SettingTertiary skull base unit.ParticipantsTwenty-four patients with unilateral sporadic small (< 15 mm maximum intracranial dimension) VS imaged with 1 mm-thickness T1-weighted Gadolinium enhanced MRI.Main outcome measures(1) Intra and inter-observer intraclass correlation coefficients (ICC), repeatability coefficients (RC), and relative smallest detectable difference (%SDD). (2) Mean change in maximum linear dimension following reformatting to correct for oblique orientation of VS.ResultsIntra-observer ICC was higher for semi-automated volumetric when compared with linear measurements, 0.998 (95% CI 0.994–0.999) vs 0.936 (95% CI 0.856–0.972), p < 0.0001. Inter-observer ICC was also higher for volumetric vs linear measurements, 0.989 (95% CI 0.975–0.995) vs 0.946 (95% CI 0.880–0.976), p = 0.0045. The intra-observer %SDD was similar for volumetric and linear measurements, 9.9% vs 11.8%. However, the inter-observer %SDD was greater for volumetric than linear measurements, 20.1% vs 10.6%. Following oblique reformatting to correct tumour angulation, the mean increase in size was 1.14 mm (p = 0.04).ConclusionSemi-automated volumetric measurements are more repeatable than linear measurements when measuring small VS and should be considered for use in clinical practice. Oblique orientation of VS may contribute to linear measurement error.

show abstract

Surveillance After Resection of Vestibular Schwannoma

Cited by 18 publications

References 17 publications

Segmentation of Vestibular Schwannomas on Postoperative Gadolinium-Enhanced T1-Weighted and Noncontrast T2-Weighted Magnetic Resonance Imaging Using Deep Learning

Segmentation of Vestibular Schwannomas on Postoperative Gadolinium-Enhanced T1-Weighted and Noncontrast T2-Weighted Magnetic Resonance Imaging Using Deep Learning

Should we be moving to a national standardized non-gadolinium MR imaging protocol for the surveillance of vestibular schwannomas?

A comparison of semi-automated volumetric vs linear measurement of small vestibular schwannomas

Contact Info

Product

Resources

About