Automated 2-Dimensional Measurement of Vestibular Schwannoma: Validity and Accuracy of an Artificial Intelligence Algorithm.
artificial intelligence
automated measurement
vestibular schwannoma
volume
Journal
Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery
ISSN: 1097-6817
Titre abrégé: Otolaryngol Head Neck Surg
Pays: England
ID NLM: 8508176
Informations de publication
Date de publication:
Dec 2023
Dec 2023
Historique:
revised:
12
06
2023
received:
20
03
2023
accepted:
11
07
2023
medline:
22
11
2023
pubmed:
9
8
2023
entrez:
9
8
2023
Statut:
ppublish
Résumé
Validation of automated 2-dimensional (2D) diameter measurements of vestibular schwannomas on magnetic resonance imaging (MRI). Retrospective validation study using 2 data sets containing MRIs of vestibular schwannoma patients. University Hospital in The Netherlands. 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. 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). 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.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1582-1589Informations de copyright
© 2023 The Authors. Otolaryngology-Head and Neck Surgery published by Wiley Periodicals LLC on behalf of American Academy of Otolaryngology-Head and Neck Surgery Foundation.
Références
Arthurs BJ, Fairbanks RK, Demakas JJ, et al. A review of treatment modalities for vestibular schwannoma. Neurosurg Rev. 2011;34:265-279. doi:10.1007/s10143-011-0307-8
Management of sporadic vestibular schwannoma. Otolaryngol Clin North Am. 2015;48:407-422.
Matthies C, Samii M. Management of 1000 vestibular schwannomas (acoustic neuromas): clinical presentation. Neurosurgery. 1997;40:1-9.
Møller MN, Hansen S, Miyazaki H, Stangerup SE, Caye-Thomasen P. Active treatment is not indicated in the majority of patients diagnosed with a vestibular schwannoma: a review on the natural history of hearing and tumor growth. Curr Otorhinolaryngol Rep. 2014;2:242-247. doi:10.1007/s40136-014-0064-7
Kanzaki J, Tos M, Sanna M, Moffat DA. New and modified reporting systems from the consensus meeting on systems for reporting results in vestibular schwannoma. Otol Neurotol. 2003;24(4):642-649. doi:10.1097/00129492-200307000-00019
Varughese JK, Wentzel-Larsen T, Vassbotn F, Moen G, Lund-Johansen M. Analysis of vestibular schwannoma size in multiple dimensions: a comparative cohort study of different measurement techniques. Clin Otolaryngol. 2010;35(2):97-103. doi:10.1111/j.1749-4486.2010.02099.x
Mackeith S, Das T, Graves M, et al. A comparison of semi-automated volumetric vs linear measurement of small vestibular schwannomas. Eur Arch Otrhinolaryngol. 2018;275(4):867-874. doi:10.1007/s00405-018-4865-z
van de Langenberg R, de Bondt BJ, Nelemans PJ, Baumert BG, Stokroos RJ. Follow-up assessment of vestibular schwannomas: volume quantification versus two-dimensional measurements. Neuroradiology. 2009;51(8):517-524. doi:10.1007/s00234-009-0529-4
Cross JJ, Baguley DM, Antoun NM, Moffat DA, Prevost AT. Reproducibility of volume measurements of vestibular schwannomas-a preliminary study. Clin Otolaryngol. 2006;31(2):123-129. doi:10.1111/j.1749-4486.2006.01161.x
Shapey J, Wang G, Dorent R, et al. An artificial intelligence framework for automatic segmentation and volumetry of vestibular schwannomas from contrast-enhanced T1-weighted and high-resolution T2-weighted MRI. J Neurosurg. 2021;134:171-179. doi:10.3171/2019.9.JNS191949
Lee C, Lee W-K, Wu C-C, et al. Applying artificial intelligence to longitudinal imaging analysis of vestibular schwannoma following radiosurgery. Sci Rep. 2021;11(1):3106. doi:10.1038/s41598-021-82665-8
George-Jones NA, Wang K, Wang J, Hunter JB. Automated detection of vestibular schwannoma growth using a two-dimensional U-Net convolutional neural network. Laryngoscope. 2021;131(2):131. doi:10.1002/lary.28695
Neve OM, Chen Y, Tao Q, et al. Fully automated 3D vestibular schwannoma segmentation with and without gadolinium-based contrast material: a multicenter, multivendor study. Radiol Artif Intell. 2022;4(4):e210300. doi:10.1148/ryai.210300
Koos WT, Day JD, Matula C, Levy DI. Neurotopographic considerations in the microsurgical treatment of small acoustic neurinomas. J Neurosurg. 1998;88(3):506-512. doi:10.3171/jns.1998.88.3.0506
Carlson M, Van Gompel J, Wiet R, et al. A cross-sectional survey of the north american skull base society: current practice patterns of vestibular schwannoma evaluation and management in North America. J Neurol Surg B Skull Base. 2018;79(3):289-296. doi:10.1055/s-0037-1607319
Macielak RJ, Wallerius KP, Lawlor SK, et al. Defining clinically significant tumor size in vestibular schwannoma to inform timing of microsurgery during wait-and-scan management: moving beyond minimum detectable growth. J Neurosurg. Published online October 15, 2021. doi:10.3171/2021.4.jns21465
Marinelli JP, Lohse CM, Carlson ML. Introducing an evidence-based approach to wait-and-scan management of sporadic vestibular schwannoma. Otolaryngol Clin North Am. 2023;56(3):445-457. doi:10.1016/j.otc.2023.02.006
Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18(2):203-211. doi:10.1038/s41592-020-01008-z
Shapey J, Kujawa A, Dorent R, et al. Data From: Segmentation of Vestibular Schwannoma From Magnetic Resonance Imaging: An Open Annotated Dataset and Baseline Algorithm [Dataset]. The Cancer Imaging Archive; 2021. doi:10.7937/TCIA.9YTJ-5Q73
Martin Bland J, Altman D. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet. 1986;327(8476):307-310.
Coelho DH, Tang Y, Suddarth B, Mamdani M. MRI surveillance of vestibular schwannomas without contrast enhancement: clinical and economic evaluation. Laryngoscope. 2018;128(1):202-209. doi:10.1002/lary.26589
Hougaard D, Norgaard A, Pedersen T, Bibby BM, Ovesen T. Is a redefinition of the growth criteria of vestibular schwannomas needed. Am J Otolaryngol. 2014;35(2):192-197. doi:10.1016/j.amjoto.2013.08.002
Tolisano AM, Wick CC, Hunter JB. Comparing linear and volumetric vestibular schwannoma measurements between T1 and T2 magnetic resonance imaging sequences. Otol Neurotol. 2019;40:67. doi:10.1097/mao.0000000000002208