Non-contrast magnetic resonance imaging for monitoring patients with acoustic neuroma

Forgues, Mathieu; Mehta, Rahul; Anderson, Dwayne; Morel, C.; Miller, Laura Stephanie; Sevy, Alexander; Son, Leslie; Arriaga, Moisés A.

doi:10.1017/s0022215118001342

Cited by 10 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sometimes this can result in false-positive findings mainly with small lesion-like abnormalities [49,50]. T2-weighted MRI can help to show peritumoral oedema and the presence of cysts [51,52]. There are no major differences in MRI characteristics with routine imaging between NF2 VS and sporadic VS (Figures 1 and 2).…”

Section: Imaging Of Vsmentioning

confidence: 99%

Therapy of Sporadic and NF2-Related Vestibular Schwannoma

Yao

Alahmari

Temel

et al. 2020

Cancers

View full text Add to dashboard Cite

Vestibular schwannoma (VS) is a benign primary brain tumor that occurs sporadic or as part of a genetic syndrome. The most common cause is the mutation of the NF2 tumor suppressor gene that is involved in the production of the protein merlin. Merlin plays a role in cell growth and cell adhesion. In patients with NF2, the VSs arise bilaterally and coincide with other brain tumors. In sporadic VS, the tumor is typically unilateral and does not coincide in combination with other tumors. MRI is the standard imaging technique and can be used to assess the size and aspect of the tumor as well as the progression of disease. The preferred management of large VS in both VS types is surgery with or without adjuvant radiation. The management for the medium- or small-sized VS includes wait and scan, radiotherapy and/or surgery. This choice depends on the preference of the patient and institutional protocols. The outcomes of surgical and radiotherapy treatments are improving due to progress in surgical equipment/approaches, advances in radiation delivery techniques and dose optimizations protocols. The main purpose of the management of VS is preserving function as long as possible in combination with tumor control.

show abstract

Section: Imaging Of Vsmentioning

confidence: 99%

Therapy of Sporadic and NF2-Related Vestibular Schwannoma

Yao

Alahmari

Temel

et al. 2020

Cancers

View full text Add to dashboard Cite

show abstract

“…Patients with small tumors are usually monitored through scheduled magnetic resonance imaging (MRI) investigations. In this way, should the tumor grow or become symptomatic, it can be treated with surgery or SRS [ 3 , 4 ]. The latter can also be considered in cases where traditional surgery is not indicated, for example, in patients with neurofibromatosis, comorbidities, or elderly patients [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Development of Predictive Models for the Response of Vestibular Schwannoma Treated with Cyberknife®: A Feasibility Study Based on Radiomics and Machine Learning

Zanetti

Martin

Pascuzzo

et al. 2023

JPM

View full text Add to dashboard Cite

Purpose: to predict vestibular schwannoma (VS) response to radiosurgery by applying machine learning (ML) algorithms on radiomic features extracted from pre-treatment magnetic resonance (MR) images. Methods: patients with VS treated with radiosurgery in two Centers from 2004 to 2016 were retrospectively evaluated. Brain T1-weighted contrast-enhanced MR images were acquired before and at 24 and 36 months after treatment. Clinical and treatment data were collected contextually. Treatment responses were assessed considering the VS volume variation based on pre- and post-radiosurgery MR images at both time points. Tumors were semi-automatically segmented and radiomic features were extracted. Four ML algorithms (Random Forest, Support Vector Machine, Neural Network, and extreme Gradient Boosting) were trained and tested for treatment response (i.e., increased or non-increased tumor volume) using nested cross-validation. For training, feature selection was performed using the Least Absolute Shrinkage and Selection Operator, and the selected features were used as input to separately build the four ML classification algorithms. To overcome class imbalance during training, Synthetic Minority Oversampling Technique was used. Finally, trained models were tested on the corresponding held out set of patients to evaluate balanced accuracy, sensitivity, and specificity. Results: 108 patients treated with Cyberknife® were retrieved; an increased tumor volume was observed at 24 months in 12 patients, and at 36 months in another group of 12 patients. The Neural Network was the best predictive algorithm for response at 24 (balanced accuracy 73% ± 18%, specificity 85% ± 12%, sensitivity 60% ± 42%) and 36 months (balanced accuracy 65% ± 12%, specificity 83% ± 9%, sensitivity 47% ± 27%). Conclusions: radiomics may predict VS response to radiosurgery avoiding long-term follow-up as well as unnecessary treatment.

show abstract

“…Cranial magnetic resonance imaging (cMRI) is frequently used in the diagnostic work-up of neurological 5 , 6 and otologic diseases 7 , 8 . The increasing indications for cMRI, better availability, and lower examination cost have led to an increased implementation of cMRI worldwide 9 .…”

Section: Introductionmentioning

confidence: 99%

Dimensions and forms of artefacts in 1.5 T and 3 T MRI caused by cochlear implants

Gottfried

Dejaco

Fischer

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Cochlear implantation is a standard treatment option due to expanding indications. Cranial magnetic resonance imaging (cMRI) has become a widespread diagnostic tool. Therefore, an increased number of cochlear implant (CI) users are undergoing cMRI scans. This study aimed to investigate the issue of the CI magnet impacting MRI quality and artifacts. 1.5 T and 3 T MRI scans with 4 defined sequences (T2-TSE, T2-TIRM, T1-3D-MPRAGE, and TDI) were performed on a phantom with a CI (SYNCHRONY System by MED-EL Austria) in place. The resulting MRI artifacts were retrospectively compared to MRI artifacts observed in patients with a CI. All images were transferred to AMIRA and visualized by manual segmentation. Usable image quality was achieved in three sequences (T2-TSE, T2-TIRM and T1-mprage). Observed artifacts differed in shape and size depending on the sequence. Maximum diameters of signal void areas ranged from 58 × 108 × 98 mm to 127 × 123 × 153 mm. Image distortions were larger. MRI artifacts caused by the SYNCHRONY system are asymmetric with varying shape, depending on the sequence. The phantom artefacts are similar to those in CI users. Considering the observed asymmetry, the hypothesis of varying implantation locations resulting in varying positions of the signal void area needs to be further investigated.

show abstract

Non-contrast magnetic resonance imaging for monitoring patients with acoustic neuroma

Abstract: The T2-weighted sequences are fairly accurate in measuring acoustic neuroma size and identifying growth if one keeps in mind the caveats associated with the tumour characteristics or location.

Cited by 10 publications

References 21 publications

Therapy of Sporadic and NF2-Related Vestibular Schwannoma

Therapy of Sporadic and NF2-Related Vestibular Schwannoma

Development of Predictive Models for the Response of Vestibular Schwannoma Treated with Cyberknife®: A Feasibility Study Based on Radiomics and Machine Learning

Dimensions and forms of artefacts in 1.5 T and 3 T MRI caused by cochlear implants

Contact Info

Product

Resources

About