Prediction of Vestibular Schwannoma Surgical Outcome Using Deep Neural Network

Yu, Yansuo; Song, Gang; Zhao, Yixin; Liang, Jiantao; Liu, Qiang

doi:10.1016/j.wneu.2023.03.090

Cited by 4 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent work on predicting VS recurrence and postoperative outcome using artificial neural networks supported our findings. The degree of resection correlated with the risk of recurrence and larger tumours were associated with poorer postoperative outcome ( 29 , 30 ).…”

Section: Discussionmentioning

confidence: 99%

Recurrences and progression following microsurgery of vestibular schwannoma

et al. 2023

View full text Add to dashboard Cite

BackgroundThe treatment approach of vestibular schwannoma (VS) has seen a change in recent years, with a trend away from radical surgery towards preservation of cranial nerve function. A recent study reported recurrences as long as 20 years after complete removal of VS.ObjectiveTo report the risk of recurrence and progression in our patient population the authors retrospectively reviewed outcomes of patients.MethodsCases with unilateral VS who had undergone primary microsurgery via retrosigmoidal approach between 1995 and 2021 were investigated. Complete tumor removal was defined as gross total resection (GTR), a capsular remnant was categorized as near total resection (NTR) and residual tumor was designated as subtotal resection (STR). The primary endpoint was radiological recurrence-free survival.Results386 patients fulfilled the inclusion criteria of the study and were evaluated. GTR was achieved in 284 patients (73.6%), NTR was achieved in 63 patients (10.1%) and STR was present in 39 patients (16.3%). A total of 28 patients experienced recurrences with significant differences in the three subgroups. The strongest predictor of recurrence was the extent of resection, with patients who underwent STR having an almost 10-fold higher risk of recurrence and patients who had undergone NTR having an almost 3-fold higher risk than those treated with GTR. More than 20% of recurrences (6/28) occured after more than 5 years.ConclusionThe degree of resection is an important guide to the interval of follow-up, but long-term follow-up should be considered also in the case of GTR. The majority of recurrences occurs after 3–5 years. Nevertheless, a follow-up of at least 10 years should be carried out.

show abstract

Section: Discussionmentioning

confidence: 99%

Recurrences and progression following microsurgery of vestibular schwannoma

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Artificial Intelligence (AI) has emerged as a valuable tool in these studies, contributing to various aspects of VS research. Deep learning and machine learning techniques have been utilized for tumour segmentation [12,13,14], growth prediction [15,16], surgical outcome prediction [17,18], and Koos grade prediction [19].…”

Section: Use Of Artificial Intelligence In Vsmentioning

confidence: 99%

Artificial intelligence for personalized management of vestibular schwannoma: A clinical implementation study within a multidisciplinary decision making environment

Wijethilake,

Connor,

Oviedova

et al. 2023

Preprint

View full text Add to dashboard Cite

BackgroundThe management of patients with Vestibular Schwannoma (VS) relies heavily on precise measurements of tumour size and determining growth trends.MethodsIn this study, we introduce a novel computer-assisted approach designed to aid clinical decision-making during Multidisciplinary Meetings (MDM) for patients with VS through the provision of automatically generated tumour volume and standard linear measurements. We conducted two simulated MDMs with the same 50 patients evaluated in both cases to compare our proposed approach against the standard process, focusing on its impact on preparation time and decision-making.FindingsAutomated reports provided acceptable information in 72% of cases, as assessed by an expert neuroradiologist, while the remaining 28% required some revision with manual feature extraction. The segmentation models used in this report generation task achieved Dice scores of 0.9392 (± 0.0351) for contrast-enhanced T1 and 0.9331 (± 0.0354) for T2 MRI in delineating whole tumor regions. The automated computer-assisted reports that included additional tumour information initially extended the neuro-radiologist’s preparation time for the MDM (2m 54s (± 1m and 22s) per case) compared to the standard preparation time (2m 36s (± 1m and 5s) per case). However, the computer-assisted simulated MDM (CAS-MDM) approach significantly improved MDM efficiency, with shorter discussion times per patient (1m 15s (± 0m and 28s) per case) compared to standard simulated MDM (SS-MDM) (1m 21s (± 0m and 44s) per case).InterpretationThis pilot clinical implementation study highlights the potential benefits of integrating automated measurements into clinical decision-making for VS management. An initial learning curve in interpreting new data measurements is quickly mastered and the enhanced communication of growth patterns and more comprehensive assessments ultimately provides clinicians with the tools to offer patients more personalized care.FundingN. Wijethilake was supported by the UK Medical Research Council [MR/N013700/1] and the King’s College London MRC Doctoral Training Partnership in Biomedical Sciences. This work was supported by core funding from the Wellcome Trust (203148/Z/16/Z) and EPSRC (NS/A000049/1) and an MRC project grant (MC/PC/180520). TV is also supported by a Medtronic/Royal Academy of Engineering Research Chair (RCSRF1819/7/34).Graphical AbstractHighlightsThe first study to evaluate the impact of AI assisted reporting in a clinical setting.AI generated segmentations can be used to provide a clinical guideline driven report facilitating personalized patient managementVolumetric tumour measurements provide a more comprehensive assessment of tumour growth.

show abstract

Artificial intelligence in otolaryngology

Farrokhian,

Bur

2024

Big Data in Otolaryngology

View full text Add to dashboard Cite

Prediction of Vestibular Schwannoma Surgical Outcome Using Deep Neural Network

Cited by 4 publications

References 23 publications

Recurrences and progression following microsurgery of vestibular schwannoma

Recurrences and progression following microsurgery of vestibular schwannoma

Artificial intelligence for personalized management of vestibular schwannoma: A clinical implementation study within a multidisciplinary decision making environment

Artificial intelligence in otolaryngology

Contact Info

Product

Resources

About