Radiomic biomarkers informative of cancerous transformation in neurofibromatosis-1 plexiform tumors

Evaluation of magnetic resonance imaging-based radiomics characteristics for differentiation of benign and malignant peripheral nerve sheath tumors in neurofibromatosis type 1

BACKGROUND

Patients with neurofibromatosis type 1 (NF1) develop benign (BPNST), premalignant atypical (ANF), and malignant (MPNST) peripheral nerve sheath tumors. Radiological differentiation of these entities is challenging. Therefore, we aimed to evaluate the value of a magnetic resonance imaging (MRI)-based radiomics machine-learning (ML) classifier for differentiation of these three entities of internal peripheral nerve sheath tumors in NF1 patients.

METHODS

MRI was performed at 3T in 36 NF1 patients (20 male; age: 31 ± 11 years). Segmentation of 117 BPNSTs, 17 MPNSTs, and 8 ANFs was manually performed using T2w spectral attenuated inversion recovery sequences. One hundred seven features per lesion were extracted using PyRadiomics and applied for BPNST versus MPNST differentiation. A 5-feature radiomics signature was defined based on the most important features and tested for signature-based BPNST versus MPNST classification (random forest [RF] classification, leave-one-patient-out evaluation). In a second step, signature feature expressions for BPNSTs, ANFs, and MPNSTs were evaluated for radiomics-based classification for these three entities.

RESULTS

The mean area under the receiver operator characteristic curve (AUC) for the radiomics-based BPNST versus MPNST differentiation was 0.94, corresponding to correct classification of on average 16/17 MPNSTs and 114/117 BPNSTs (sensitivity: 94%, specificity: 97%). Exploratory analysis with the eight ANFs revealed intermediate radiomic feature characteristics in-between BPNST and MPNST tumor feature expression.

CONCLUSION

In this proof-of-principle study, ML using MRI-based radiomics characteristics allows sensitive and specific differentiation of BPNSTs and MPNSTs in NF1 patients. Feature expression of premalignant atypical tumors was distributed in-between benign and malignant tumor feature expressions, which illustrates biological plausibility of the considered radiomics characteristics.

PET/MRI Improves Management of Children with Cancer

Integrated PET/MRI has shown significant clinical value for staging and restaging of children with cancer by providing functional and anatomic tumor evaluation with a 1-stop imaging test and with up to 80% reduced radiation exposure compared with 18F-FDG PET/CT. This article reviews clinical applications of 18F-FDG PET/MRI that are relevant for pediatric oncology, with particular attention to the value of PET/MRI for patient management. Early adopters from 4 different institutions share their insights about specific advantages of PET/MRI technology for the assessment of young children with cancer. We discuss how whole-body PET/MRI can be of value in the evaluation of certain anatomic regions, such as soft tissues and bone marrow, as well as specific PET/MRI interpretation hallmarks in pediatric patients. We highlight how whole-body PET/MRI can improve the clinical management of children with lymphoma, sarcoma, and neurofibromatosis, by reducing the number of radiologic examinations needed (and consequently the radiation exposure), without losing diagnostic accuracy. We examine how PET/MRI can help in differentiating malignant tumors versus infectious or inflammatory diseases. Future research directions toward the use of PET/MRI for treatment evaluation of patients undergoing immunotherapy and assessment of different theranostic agents are also briefly explored. Lessons learned from applications in children might also be extended to evaluations of adult patients.

Machine Learning Approach to Differentiation of Peripheral Schwannomas and Neurofibromas: A Multi-Center Study

BACKGROUND

Non-invasive differentiation between schwannomas and neurofibromas is important for appropriate management, preoperative counseling, and surgical planning, but has proven difficult using conventional imaging. The objective of this study was to develop and evaluate machine learning approaches for differentiating peripheral schwannomas from neurofibromas.

METHODS

We assembled a cohort of schwannomas and neurofibromas from 3 independent institutions and extracted high-dimensional radiomic features from gadolinium-enhanced, T1-weighted MRI using the PyRadiomics package on Quantitative Imaging Feature Pipeline. Age, sex, neurogenetic syndrome, spontaneous pain, and motor deficit were recorded. We evaluated the performance of 6 radiomics-based classifier models with and without clinical features and compared model performance against human expert evaluators.

RESULTS

107 schwannomas and 59 neurofibroma were included. The primary models included both clinical and imaging data. The accuracy of the human evaluators (0.765) did not significantly exceed the no-information rate (NIR), whereas the Support Vector Machine (0.929), Logistic Regression (0.929), and Random Forest (0.905) classifiers exceeded the NIR. Using the method of DeLong, the AUC for the Logistic Regression (AUC=0.923) and K Nearest Neighbor (AUC=0.923) classifiers was significantly greater than the human evaluators (AUC=0.766; p = 0.041).

CONCLUSIONS

The radiomics-based classifiers developed here proved to be more accurate and had a higher AUC on the ROC curve than expert human evaluators. This demonstrates that radiomics using routine MRI sequences and clinical features can aid in differentiation of peripheral schwannomas and neurofibromas.

Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study

BACKGROUND

Clinicoradiologic differentiation between benign and malignant peripheral nerve sheath tumors (PNSTs) has important management implications.

OBJECTIVE

To develop and evaluate machine-learning approaches to differentiate benign from malignant PNSTs.

METHODS

We identified PNSTs treated at 3 institutions and extracted high-dimensional radiomics features from gadolinium-enhanced, T1-weighted magnetic resonance imaging (MRI) sequences. Training and test sets were selected randomly in a 70:30 ratio. A total of 900 image features were automatically extracted using the PyRadiomics package from Quantitative Imaging Feature Pipeline. Clinical data including age, sex, neurogenetic syndrome presence, spontaneous pain, and motor deficit were also incorporated. Features were selected using sparse regression analysis and retained features were further refined by gradient boost modeling to optimize the area under the curve (AUC) for diagnosis. We evaluated the performance of radiomics-based classifiers with and without clinical features and compared performance against human readers.

RESULTS

A total of 95 malignant and 171 benign PNSTs were included. The final classifier model included 21 imaging and clinical features. Sensitivity, specificity, and AUC of 0.676, 0.882, and 0.845, respectively, were achieved on the test set. Using imaging and clinical features, human experts collectively achieved sensitivity, specificity, and AUC of 0.786, 0.431, and 0.624, respectively. The AUC of the classifier was statistically better than expert humans (P = .002). Expert humans were not statistically better than the no-information rate, whereas the classifier was (P = .001).

CONCLUSION

Radiomics-based machine learning using routine MRI sequences and clinical features can aid in evaluation of PNSTs. Further improvement may be achieved by incorporating additional imaging sequences and clinical variables into future models.

Imaging Evaluation of Plexiform Neurofibromas in Neurofibromatosis Type 1: A Survey-Based Assessment

OBJECTIVE

To assess imaging utilization practices across clinical specialists in neurofibromatosis type 1 (NF1) for the evaluation of symptomatic and asymptomatic children and adults with or without plexiform neurofibromas (PN).

METHODS

An institutional review board-exempt survey was administered to medical practitioners caring for individuals with NF1 at the Response Evaluation in Neurofibromatosis and Schwannomatosis (REiNS) meeting in September 2019. The survey included questions on respondent demographic data (9 questions), type of imaging obtained for asymptomatic (4 questions) and symptomatic (4 questions) people with and without PN, and utilization of diffusion-weighted imaging (2 questions).

RESULTS

Thirty practitioners participated in the survey. Most were academic neuro-oncologists at high-volume (>10 patients/week) NF1 centers. Of 30 respondents, 26 had access to whole-body MRI (WB-MRI). The most common approach to an asymptomatic person without PN was no imaging (adults: 57% [17/30]; children: 50% [15/30]), followed by a screening WB-MRI (adults: 20% [6/30]; children: 26.7% [8/30]). The most common approach to a person with symptoms or known PN was regional MRI (adults: 90% [27/30]; children: 93% [28/30]), followed by WB-MRI (adults: 20% [6/30]; children: 36.7% [11/30]). WB-MRI was most often obtained to evaluate a symptomatic child with PN (37% [11/30]).

CONCLUSIONS

More than 90% of practitioners indicated they would obtain a regional MRI in a symptomatic patient without known or visible PN. Otherwise, there was little consensus on imaging practices. Given the high prevalence of PN and risk of malignant conversion in this patient population, there is a need to define imaging-based guidelines for optimal clinical care and the design of future clinical trials.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

Background: Although many works have supported the utility of PET radiomics, several authors have raised concerns over the robustness and replicability of the results. This study aimed to perform a systematic review on the topic of PET radiomics and the used methodologies. Methods: PubMed was searched up to 15 October 2020. Original research articles based on human data specifying at least one tumor type and PET image were included, excluding those that apply only first-order statistics and those including fewer than 20 patients. Each publication, cancer type, objective and several methodological parameters (number of patients and features, validation approach, among other things) were extracted. Results: A total of 290 studies were included. Lung (28%) and head and neck (24%) were the most studied cancers. The most common objective was prognosis/treatment response (46%), followed by diagnosis/staging (21%), tumor characterization (18%) and technical evaluations (15%). The average number of patients included was 114 (median = 71; range 20–1419), and the average number of high-order features calculated per study was 31 (median = 26, range 1–286). Conclusions: PET radiomics is a promising field, but the number of patients in most publications is insufficient, and very few papers perform in-depth validations. The role of standardization initiatives will be crucial in the upcoming years.

Longitudinal phenotype development in a minipig model of neurofibromatosis type 1

Neurofibromatosis type 1 (NF1) is a rare, autosomal dominant disease with variable clinical presentations. Large animal models are useful to help dissect molecular mechanisms, determine relevant biomarkers, and develop effective therapeutics. Here, we studied a NF1 minipig model (NF1+/ex42del) for the first 12 months of life to evaluate phenotype development, track disease progression, and provide a comparison to human subjects. Through systematic evaluation, we have shown that compared to littermate controls, the NF1 model develops phenotypic characteristics of human NF1: [1] café-au-lait macules, [2] axillary/inguinal freckling, [3] shortened stature, [4] tibial bone curvature, and [5] neurofibroma. At 4 months, full body computed tomography imaging detected significantly smaller long bones in NF1+/ex42del minipigs compared to controls, indicative of shorter stature. We found quantitative evidence of tibial bowing in a subpopulation of NF1 minipigs. By 8 months, an NF1+/ex42del boar developed a large diffuse shoulder neurofibroma, visualized on magnetic resonance imaging, which subsequently grew in size and depth as the animal aged up to 20 months. The NF1+/ex42del minipig model progressively demonstrates signature attributes that parallel clinical manifestations seen in humans and provides a viable tool for future translational NF1 research.