Convection-Enhanced Delivery (CED) in an Animal Model of Malignant Peripheral Nerve Sheath (MPNST) Tumors and Plexiform Neurofibromas (PN)

2012 ◽  
Author(s):  
Kaleb Yohay
Author(s):  
Maria T. Acosta

Neurofibromatosis type 1 (Nf1) is a neurocutaneous disorder with a prevalence of approximately 1 in 2,500–3,500 individuals (Ferner et al. 2007). The physical manifestations of Nf1, such as café au lait spots, axillary freckling, iris hamartomas (Lisch nodules), osseous lesions (sphenoid wing dysplasia, pseudoarthrosis), and benign as well as malignant neural tumors (neurofibromas, optic gliomas), are well recognized (Castle et al. 2003; Ferner et al. 2007). National Institutes of Health (NIH) criteria are currently used for clinical diagnosis (1988) (Table 31.1). The clinical severity of this disorder is quite variable, and approximately 20% of children with Nf1 will later have considerable physical complications (Castle et al. 2003; Ferner et al. 2007; Williams et al. 2009). Other clinical manifestations are abnormalities of the cardiovascular, gastrointestinal, renal, and endocrine systems, facial and body disfigurement, cognitive deficit, and malignancies of the peripheral nerve sheath and central nervous system. The tumors that occur in Nf1 are dermal and plexiform neurofibromas, optic gliomas, malignant peripheral nerve sheath tumors (MPNSTs), pheochromocytomas, and rhabdomyosarcomas (Castle et al. 2003). Children with Nf1 have an increased risk of developing myeloid disease, particularly juvenile chronic myeloid leukemia. Some 30%–40% of Nf1 patients develop plexiform neurofibromas (Szudek, Evans, and Friedman 2003). Malignant peripheral nerve sheath tumors are present in 5%–10% of cases (Evans et al. 2002), often in preexisting plexiform neurofibromas (Castle et al. 2003). Although many see the predisposition to cancer as the major concern regarding Nf1, some of the more prevalent features are not directly related to tumors (Acosta, Gioia, and Silva 2006). Cognitive dysfunction, academic difficulties, and school failure, occur in 40%–80% (Hyman, Arthur, and North 2006; Krab et al. 2008; North et al. 1997). These complications affect the day-to-day life of these children, and are the largest cause of lifetime morbidity in the pediatric Nf1 population (Acosta et al. 2006). These deficits impact on long-term adaptation to society (Acosta et al. 2006; Barton and North 2007; Krab et al. 2008; Krab et al. 2009).


2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi128-vi129
Author(s):  
Ina Ly ◽  
Tianyu Liu ◽  
Wenli Cai ◽  
Daniel Kwon ◽  
Olivia Michaels ◽  
...  

Abstract BACKGROUND Several MRI features are proposed to distinguish between plexiform neurofibromas (PNF) and malignant peripheral nerve sheath tumors (MPNST) in neurofibromatosis type 1 (NF1), including tumor size, margins, and degree of heterogeneity. However, most of these features are descriptive in nature, subject to intra-/interrater variability, and based on small single-institution studies. The goal of this study was to identify radiomic features that can differentiate between NF1-associated PNF and MPNST. METHODS 31 MPNSTs and 24 PNFs from five centers were segmented on short TI inversion recovery sequences using a semi-automated segmentation software (3DQI). Standard pre-processing was performed, including N4 bias field correction, intensity normalization (using a mean of 120 SI and standard deviation of 80 SI), and resampling to 1 mm3 voxel resolution. 1688 radiomic features were extracted from the tumor region of interest using PyRadiomics, an open-source Python radiomics package. To classify tumors as PNF or MPNST, we implemented the Boruta algorithm and correlation removal for selection of important features. A Random Forest model was built using the top ten selected features. Five-fold cross-validation was performed and repeated 100 times. Model performance was evaluated using the area under the ROC curve (AUC), sensitivity, specificity, accuracy, and confidence intervals. RESULTS The top ten features included in the model were five intensity features, two shape features, and three texture features. The model demonstrated an AUC of 0.891 (95% CI 0.882-0.899), sensitivity of 0.744, specificity of 0.847, and accuracy of 0.802 (95% CI 0.792-0.813). CONCLUSIONS Our machine learning model demonstrated high performance in classifying tumors as either PNF or MPNST in NF1 individuals. Inclusion of additional tumors for model training and testing on an independent dataset are underway. Ultimately, our model may enable improved differentiation between PNF and MPNST compared to descriptive MRI features, permit early patient risk stratification, and improve patient outcomes.


2016 ◽  
Vol 77 (S 01) ◽  
Author(s):  
Matthew Carlson ◽  
Jeffrey Jacob ◽  
Elizabeth Habermann ◽  
Amy Wagie ◽  
Aditya Raghunathan ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document