Role of diffusion-weighted imaging in differentiation between posterior fossa brain tumors

Mustafa, Wessam; Abbas, Mohammed; Elsorougy, Lamiaa

doi:10.1186/s41983-019-0145-0

Cited by 9 publications

(20 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By measuring the microscopic displacement of water molecules, diffusion imaging can provide information regarding tumor cellularity and organization, with inversely known correlation between tumor cellularity and diffusion values [3,10]. PFTs differ by their cellularity and diffusion values, with Medulloblastoma having the highest cellularity and thus the lowest diffusivity values, compared to Pilocytic astrocytoma which is usually a cystic tumor that even in the solid component is less cellular [9][10][11][12]. Regarding patients' age, the statistical analysis of our cohort reveals significant age differences between the Ependymoma and other tumor groups, consistent with literature results [1][2][3][4], which justifies age integration to improve the performance of a CNN based classification model.…”

Section: Discussionmentioning

confidence: 99%

“…MRI is the method of choice for the assessment of children with PFT, with diffusion imaging shown to provide important information in predicting histology and tumor grade. However currently it remains quite difficult to predict all PFT pathologies based on radiological visual assessment of MRI alone [3,[7][8][9][10][11][12]. The main challenges in the assessment of PFT tumors are the small number of pediatric patients with PFT and the imbalance of the dataset.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Pediatric Posterior Fossa Tumors Using Convolutional Neural Network and Tabular Data

et al. 2021

View full text Add to dashboard Cite

Posterior fossa tumors (PFT) are the most common tumors in children. Differentiation between the various PFT types is critical, as different tumors have diverse treatment approaches. This study proposes the use of fused architecture comprising two neural networks, a pre-trained ResNet-50 Convolutional Neural Network (CNN) and a tabular based network for the classification of PFT. The study included data for 158 MRI scans of 22 healthy controls and 136 pediatric patients with newly diagnosed PFT (63 Pilocytic Astrocytoma, 57 Medulloblastoma and 16 Ependymoma). The input data for classification were from magnetic resonance imaging: post contrast T1-weighted, fluid attenuated inversion recovery and diffusion Trace images, and tabular data: subject's age. Evaluation of the model was performed in a stratified 5-fold cross-validation manner, based on accuracy, precision, recall and F1 score metrics. Model explanation was performed in terms of visual explanation of the CNN by Gradient-weighted Class Activation Mapping (Grad-CAM) and by testing the contribution to the classification results of the different imaging input data sets and the proposed fused architectures relative to CNN only and tabular only architectures. The best classification results were obtained with the fused CNN + tabular data architecture, and based on diffusion Trace images, achieving mean cross-validation accuracy of 0.88±0.04 for the validation and 0.87±0.02 for the test dataset. Overall, the proposed architecture achieved improvement in accuracy and F1 score compared to CNN method for this dataset.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classification of Pediatric Posterior Fossa Tumors Using Convolutional Neural Network and Tabular Data

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The moderately cellular ependymoma, a known WHO Grade 2 tumour, has variable restricted diffusion according to imaging literature. 24,26 It was only between pilocytic astrocytoma and ependymoma where Mustafa et al 24 did not find a significant difference on ADC map values. Further contrasts of other densely cellular tumours with restricted diffusion such as CPC and pineoblastoma are known grades 3 and 4 WHO classifications, respectively.…”

Section: World Health Organization Classification Of Central Nervous System Tumoursmentioning

confidence: 93%

“…It is worth noting that DWI offers a potential volatile tool as a practical imaging guide to the WHO tumour grade. Mustafa et al 24 and several other authors noted significant differences of paediatric CNS tumour water diffusion properties utilising apparent diffusion coefficient (ADC) map values, which somewhat correlate with the WHO tumour grade. Significant differences regarding fluid diffusion restriction were noted in pilocytic astrocytoma, ependymoma, medulloblastoma and brainstem glioma.…”

Section: World Health Organization Classification Of Central Nervous System Tumoursmentioning

confidence: 98%

See 1 more Smart Citation

MRI characteristics of intracranial masses in the paediatric population of KwaZulu-Natal: A neuroimaging-based study

Gumede

Langa²,

Enicker

2021

South African Journal of Radiology

View full text Add to dashboard Cite

Background: MRI is the imaging modality of choice for the assessment of intracranial masses in children. Imaging is vital in planning further management.Objectives: The purpose of this study was to describe the common intracranial masses and their imaging characteristics in the paediatric population referred to Inkosi Albert Luthuli Central Hospital for MRI of the brain.Method: We retrospectively reviewed the medical records of paediatric patients (aged from birth to 18 years) who underwent MRI investigations for intracranial masses between January 2010 and December 2016.Results: A total of 931 MRI brain scans were performed. One hundred and seven scans met the inclusion criteria, of which 92 were primary brain tumours and 15 were inflammatory masses. The majority were females (56%). The mean age was 12 ± 4.52 (range of 3–18 years). The most common presenting symptom was seizures (70/107, 65.4%). We categorised the masses according to supra- and infratentorial compartments. The most common site for masses was the supratentorial compartment (n = 56, 52%). The most common masses in the supratentorial compartment were craniopharyngiomas (14/45, 31.1%), whilst in the infratentorial compartment, the most common masses were medulloblastomas (24/47, 51.1%).Conclusion: In our series, the supratentorial compartment was the commonest site for intracranial masses. The most common tumour in the infratentorial compartment was medulloblastoma. This information is vital in formulating differential diagnoses of intracranial masses.

show abstract

Clinical applications of diffusion-weighted sequence in brain imaging: beyond stroke

et al. 2021

View full text Add to dashboard Cite

Diffusion-weighted imaging (DWI) is a well-established MRI sequence for diagnosing early stroke and provides therapeutic implications. However, DWI yields pertinent information in various other brain pathologies and helps establish a specific diagnosis and management of other central nervous system disorders. Some of these conditions can present with acute changes in neurological status and mimic stroke. This review will focus briefly on diffusion imaging techniques, followed by a more comprehensive description of the utility of DWI in common neurological entities beyond stroke.

show abstract

Role of diffusion-weighted imaging in differentiation between posterior fossa brain tumors

Cited by 9 publications

References 22 publications

Classification of Pediatric Posterior Fossa Tumors Using Convolutional Neural Network and Tabular Data

Classification of Pediatric Posterior Fossa Tumors Using Convolutional Neural Network and Tabular Data

MRI characteristics of intracranial masses in the paediatric population of KwaZulu-Natal: A neuroimaging-based study

Clinical applications of diffusion-weighted sequence in brain imaging: beyond stroke

Contact Info

Product

Resources

About