Advanced searches left 3/3

Vestibular Schwannoma - Europe PMC

Summarized by Plex Scholar
Last Updated: 09 August 2022

* If you want to update the article please login/register

Deep Learning for Automatic Segmentation of Vestibular Schwannoma: A Retrospective Study from Multi-Centre Routine MRI

Objectivist goal Achievable vestibular schwannoma obtained from routine clinical imaging can improve clinical workflow, facilitate diagnosis, and support patient management. On datasets of standardised MRI images obtained for stereotactic surgery planning, good automatic segmentation results were achieved. Automatic segmentation of VS on such datasets is also possible with high certainty, as shown here. Methods We obtained a large multi-centre clinical database of 168 patients with a single sporadic VS who were referred from ten medical centers and then seen at a single center in a single center. To automatically pick contrast-enhanced T1-weighted images and T2-weighted images, a selection procedure based on image modality, resolution orientation, and acquisition timeframe was set. Manual ground truth segmentations were established in an iterative process in which segmentations were: 1 developed or modified by a specialist firm; 2 reviewed by one of three experienced radiologists; and 3 validated by an expert team; and 3 validated by an expert team. Within the nnU-Net framework, we used deep learning to develop our VS segmentation model, which was based on convolutional neural networks CNN. Tests and findings Our model's results When based on the MC-RC testing program as well as the public testing set, our model produced high Dice scores. Dice scores were 90. 8 percent for T2w and 82. 3 percent for a combined ceT1w+T2w input on a combined ceT1w+T2w test, a total of 85. 3 percent for T2w and 82. 3 percent for a combined ceT1w+T2w data set on the MC-RC testing set, with 86. 6 percent for T2w and 82. 3 percent for a combined ceT1w+T2w and 82. 3u00b111. Conclusions We developed a system for automatic VS segmentation in large multi-centre clinical datasets. On the MC-RC testing set, a model based on a publicly available dataset obtained for Gamma Knife stereotactic radiosurgery did not do well on the MC-RC testing set.

Source link: https://europepmc.org/article/PPR/PPR527996


Stereotactic radiosurgery for Koos grade IV vestibular schwannoma in young patients: a multi-institutional study

However, the safety and effectiveness of SRS in Koos grade IV patients aged 216445 years old have yet to be investigated. The aim of this report is to report the clinical and radiological outcomes of Koos grade IV in young patients treated with a single-session SRS. Methods This retrospective, multicenter review included SRS-treated patients, u226445 years old, who presented with non-life threatening or incapacitating signs as a result of a Kooos Grade IV VS and a follow-up u2265 12 months. Early tumor enlargement occurred in 10. 9% of patients and was attributed to tumor progression at the last follow-up. At 5 and 10-years, the likelihood of improvement or preservation of facial nerve function was 97%. Conclusion One-session SRS is a safe and efficient alternative to surgical resection in selected patients ranging from medical co-morbidities to those who have declining resection.

Source link: https://europepmc.org/article/PPR/PPR526174


Postoperative magnetic resonance imaging signal changes in middle cerebral peduncle after vestibular schwannoma surgery.

Preoperative compression of middle cerebellar peduncle is common in vestibular schwannomas. Similarly, an elevated MCP FLAIR signal is often present and is thought to be correlated with intraoperative MCP injury. This research explores the dynamics of MCP FLAIR signal shifts over time and their implications on long-term MCP atrophy. In 24 patients, an immediate postoperative re-expansion of middle cerebellar peduncle was discovered. No relationship was found between tumor size and preoperative FLAIR, however tumor thickness was negatively related to MCP thickness. And when controlling for tumour size, both tumor size, and preoperative MCP thickness, a striking negative correlation between a postoperative FLAIR and follow-up thickness was found between a postoperative FLAIR and follow-up thickness was found. Conclusion The middle cerebellar peduncle FLAIR signal appears to be associated with long-term thickness of MCP in patients with vestibular schwannomas undergoing surgical resection, regardless of its initial size, but does not seem to correlate with clinical findings.

Source link: https://europepmc.org/article/MED/35913025


Long-term natural history and patterns of sporadic vestibular schwannoma growth: A multi-institutional volumetric analysis of 952 patients.

Methods Volumetric tumor measurements from 3505 serial MRI studies were analyzed from unselected consecutive patients undergoing wait-and-scan care at three tertiary referral centers between 1998 and 2018. Following initial growth of 77%, 37%, and 24%, among 405 patients who continued to be observable despite initial growth, 210 patients who remained unchanged, with subsequent growth-free survival rates at 1, 3, and 5 years following subsequent growth of 77%, 38 percent, and 24%. A longer time between diagnosis and detection of initial growth was helpful, with an elevated risk of subsequent expansion and increasing tumor growth. While most vestibular schwannomas show an overall tendency for volumetric growth following diagnosis, prior tumor growth does not accurately predict future growth. A larger tumor size and rising tumor growth rate portend a greater chance of continued growth.

Source link: https://europepmc.org/article/MED/34964894


Whole Tumor Radiomics Analysis for Risk Factors Associated with Rapid Growth of Vestibular Schwannoma in Contrast-Enhanced T1-Weighted Images.

Aims: Using radiomics analysis on magnetic resonance imaging along with clinical causes, we'll find out the reasons behind rapid growth of vestibular schwannoma. Methods 93 patients with vestibular schwannoma underwent contrast-enhanced T1-weighted MRI at least twice as part of their medical diagnosis from August 2005 to February 2019. Using 3D Slicer software, ninety-three texture features were extracted from the tumor image data. Using Random Forest and Bounty, we determined the texture features that greatly affected maximal tumor diameter growth of more than 2 mm/year. The best AUC was found in the mixed model of texture characteristics and clinical factors, followed by the pure texture-based and pure clinical models. Conclusions In contrast-enhanced T1-weighted photographs, we discovered that texture features were strongly associated with rapid rise of vestibular schwannoma. The mixed model had a higher diagnostic success than either the pure texture or clinical models.

Source link: https://europepmc.org/article/MED/35863640


Preoperative vestibular evoked myogenic potentials (VEMPs), caloric test, and pure tone audiometry to identify the vestibular nerve branch of schwannoma origin: preliminary results in a series of 26 cases.

Vestibular schwannoma is a benign tumor that arises in the internal auditory canal and the cerebellopontine angle, potentially decreasing hearing or balance. Most VS tumors develop from one of two vestibular branches, the superior or inferior vestibular nerve. The nerve of source was predicted on the basis of preoperative vestibular stimulation test, caloric stimulation test, and pure tone audiometry on 26 recipients. The possibility of predicting the branch of origination was shown by receiver operating characteristic curves analysis of preoperative testing results. Surgical stimulation, nystagmus detectable at caloric stimulation, and PTA 75 dB HL were all used to obtain good accuracy for inferior vestibular nerve implant of the tumor. Preoperatively predicted tumor origins in 24 of 26 cases, but not in 24 of 26 cases, as the origin determined during surgery. With high certainty, preoperative audiological and vestibular testing can determine the vestibular tumor branch of origin with high certainty.

Source link: https://europepmc.org/article/MED/35819734

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions