Characterisation of malignant peripheral nerve sheath tumours in neurofibromatosis-1 using heterogeneity analysis of 18F-FDG PET

Impact of CT and MRI in the diagnostic workup of malignant triton tumour-a monocentric analysis and review of the literature

OBJECTIVES

Malignant triton tumours (MTTs) are rare but aggressive subtypes of malignant peripheral nerve sheath tumours (MPNSTs) with a high recurrence rate and 5-year survival of 14%. Systematic imaging data on MTTs are scarce and mainly based on single case reports. Therefore, we aimed to identify typical CT and MRI features to improve early diagnosis rates of this uncommon entity.

METHODS

A systematic review on literature published until December 2022 on imaging characteristics of MTTs was performed. Based on that, we conducted a retrospective, monocentric analysis of patients with histopathologically proven MTTs from our department. Explorative data analysis was performed.

RESULTS

Initially, 29 studies on 34 patients (31.42 ± 22.6 years, 12 female) were evaluated: Literature described primary MTTs as huge, lobulated tumours (108 ± 99.3 mm) with central necrosis (56% [19/34]), low T1w (81% [17/21]), high T2w signal (90% [19/21]) and inhomogeneous enhancement on MRI (54% [7/13]). Analysis of 16 patients (48.9 ± 13.8 years; 9 female) from our institution revealed comparable results: primary MTTs showed large, lobulated masses (118 mm ± 64.9) with necrotic areas (92% [11/12]). MRI revealed low T1w (100% [7/7]), high T2w signal (100% [7/7]) and inhomogeneous enhancement (86% [6/7]). Local recurrences and soft-tissue metastases mimicked these features, while nonsoft-tissue metastases appeared unspecific.

CONCLUSIONS

MTTs show characteristic features on CT and MRI. However, these do not allow a reliable differentiation between MTTs and other MPNSTs based on imaging alone. Therefore, additional histopathological analysis is required.

ADVANCES IN KNOWLEDGE

This largest published systematic analysis on MTT imaging revealed typical but unspecific imaging features that do not allow a reliable, imaging-based differentiation between MTTs and other MPNSTs. Hence, additional histopathological analysis remains essential.

Image-Based Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors in Neurofibromatosis Type 1

Neurofibromatosis type 1 (NF1) is a dominant hereditary disease characterized by the mutation of the NF1 gene, affecting 1/3000 individuals worldwide. Most NF1 patients are predisposed to benign peripheral nerve sheath tumors (PNSTs), including cutaneous neurofibromas (CNFs) and plexiform neurofibromas (PNFs). However, 5%-10% of PNFs will ultimately develop into malignant peripheral nerve sheath tumors (MPNSTs), which have a poor prognosis. Early and reliable differentiation of benign and malignant tumors in NF1 patients is of great necessity. Pathological evaluation is the “gold standard” for a definite diagnosis, but the invasive nature of the biopsy procedure restricts it from applying as a screening tool during the decades-long follow-up of these patients. Non-invasive image-based diagnostic methods such as CT and MRI are often considered essential screening tools for multiple types of tumors. For NF1 patients’ lifelong regular follow-ups, these radiological methods are currently used for tumor evaluation. However, no consensus was established on screening the malignant transformation of benign PNSTs. Moreover, novel technologies like radiogenomics and PET-MRI have not been well evaluated and fully adopted for NF1 patients. This review summarizes current studies of different imaging methods for differentiating benign and malignant tumors in NF1. Meanwhile, we discussed the prospects of the usage of new tools such as radiogenomics and PET-MRI to distinguish MPNST from benign PNSTs more precisely. Summarizing these findings will help clarify the directions of future studies in this area and ultimately contribute to the radiology images-based clinical screening of MPNST in NF1 patients and finally improve the overall survival rates of these patients.

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.

Diagnostic value of 18F-FDG PET-CT in detecting malignant peripheral nerve sheath tumors among adult and pediatric neurofibromatosis type 1 patients

Purpose

Detecting malignant peripheral nerve sheath tumors (MPNSTs) remains difficult. ¹⁸F-FDG PET-CT has been shown helpful, but ideal threshold values of semi-quantitative markers remain unclear, partially because of variation among scanners. Using EU-certified scanners diagnostic accuracy of ideal and commonly used ¹⁸F-FDG PET-CT thresholds were investigated and differences between adult and pediatric lesions were evaluated.

Methods

A retrospective cohort study was performed including patients from two hospitals with a clinical or radiological suspicion of MPNST between 2013 and 2019. Several markers were studied for ideal threshold values and differences among adults and children. A diagnostic algorithm was subsequently developed.

Results

Sixty patients were included (10 MPNSTs). Ideal threshold values were 5.8 for SUVmax (sensitivity 0.70, specificity 0.92), 5.0 for SUVpeak (sensitivity 0.70, specificity 0.97), 1.7 for TLmax (sensitivity 0.90, specificity 0.86), and 2.3 for TLmean (sensitivity 0.90, specificity 0.79). The standard TLmean threshold value of 2.0 yielded a sensitivity of 0.90 and specificity of 0.74, while the standard SUVmax threshold value of 3.5 yielded a sensitivity of 0.80 and specificity of 0.63. SUVmax and adjusted SUV for lean body mass (SUL) were lower in children, but tumor-to-liver ratios were similar in adult and pediatric lesions. Using TLmean > 2.0 or TLmean < 2.0 and SUVmax > 3.5, a sensitivity and specificity of 1.00 and 0.63 can be achieved.

Conclusion

¹⁸F-FDG PET-CT offers adequate accuracy to detect MPNSTs. SUV values in pediatric MPNSTs may be lower, but tumor-to-liver ratios are not. By combining TLmean and SUVmax values, a 100% sensitivity can be achieved with acceptable specificity.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11060-021-03936-y.

18F-FDG texture analysis predicts the pathological Fuhrman nuclear grade of clear cell renal cell carcinoma

PURPOSE

This article analyzes the image heterogeneity of clear cell renal cell carcinoma (ccRCC) based on positron emission tomography (PET) and positron emission tomography-computed tomography (PET/CT) texture parameters, and provides a new objective quantitative parameter for predicting pathological Fuhrman nuclear grading before surgery.

METHODS

A retrospective analysis was performed on preoperative PET/CT images of 49 patients whose surgical pathology was ccRCC, 27 of whom were low grade (Fuhrman I/II) and 22 of whom were high grade (Fuhrman III/IV). Radiological parameters and standard uptake value (SUV) indicators on PET and computed tomography (CT) images were extracted by using the LIFEx software package. The discriminative ability of each texture parameter was evaluated through receiver operating curve (ROC). Binary logistic regression analysis was used to screen the texture parameters with distinguishing and diagnostic capabilities and whose area under curve (AUC) > 0.5. DeLong's test was used to compare the AUCs of PET texture parameter model and PET/CT texture parameter model with traditional maximum standardized uptake value (SUVmax) model and the ratio of tumor SUVmax to liver SUVmean (SUL)model. In addition, the models with the larger AUCs among the SUV models and texture models were prospectively internally verified.

RESULTS

In the ROC curve analysis, the AUCs of SUVmax model, SUL model, PET texture parameter model, and PET/CT texture parameter model were 0.803, 0.819, 0.873, and 0.926, respectively. The prediction ability of PET texture parameter model or PET/CT texture parameter model was significantly better than SUVmax model (P = 0.017, P = 0.02), but it was not better than SUL model (P = 0.269, P = 0.053). In the prospective validation cohort, both the SUL model and the PET/CT texture parameter model had good predictive ability, and the AUCs of them were 0.727 and 0.792, respectively.

CONCLUSION

PET and PET/CT texture parameter models can improve the prediction ability of ccRCC Fuhrman nuclear grade; SUL model may be the more accurate and easiest way to predict ccRCC Fuhrman nuclear grade.

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.

A Bayesian approach for diagnostic accuracy of malignant peripheral nerve sheath tumors: a systematic review and meta-analysis

Background

Malignant peripheral nerve sheath tumors (MPNST) carry a dismal prognosis and require early detection and complete resection. However, MPNSTs are prone to sampling errors and biopsies or resections are cumbersome and possibly damaging in benign peripheral nerve sheath tumor (BPNST). This study aimed to systematically review and quantify the diagnostic accuracy of noninvasive tests for distinguishing MPNST from BPNST.

Methods

Studies on accuracy of MRI, FDG-PET (fluorodeoxyglucose positron emission tomography), and liquid biopsies were identified in PubMed and Embase from 2000 to 2019. Pooled accuracies were calculated using Bayesian bivariate meta-analyses. Individual level-patient data were analyzed for ideal maximum standardized uptake value (SUV_max) threshold on FDG-PET.

Results

Forty-three studies were selected for qualitative synthesis including data on 1875 patients and 2939 lesions. Thirty-five studies were included for meta-analyses. For MRI, the absence of target sign showed highest sensitivity (0.99, 95% CI: 0.94-1.00); ill-defined margins (0.94, 95% CI: 0.88-0.98); and perilesional edema (0.95, 95% CI: 0.83-1.00) showed highest specificity. For FDG-PET, SUV_max and tumor-to-liver ratio show similar accuracy; sensitivity 0.94, 95% CI: 0.91-0.97 and 0.93, 95% CI: 0.87-0.97, respectively, specificity 0.81, 95% CI: 0.76-0.87 and 0.79, 95% CI: 0.70-0.86, respectively. SUV_max ≥3.5 yielded the best accuracy with a sensitivity of 0.99 (95% CI: 0.93-1.00) and specificity of 0.75 (95% CI: 0.56-0.90).

Conclusions

Biopsies may be omitted in the presence of a target sign and the absence of ill-defined margins or perilesional edema. Because of diverse radiological characteristics of MPNST, biopsies may still commonly be required. In neurofibromatosis type 1, FDG-PET scans may further reduce biopsies. Ideal SUV_max threshold is ≥3.5.

Preoperative prediction of regional lymph node metastasis of colorectal cancer based on 18F-FDG PET/CT and machine learning

PURPOSE

To establish and validate a regional lymph node (LN) metastasis prediction model of colorectal cancer (CRC) based on 18F-FDG PET/CT and radiomic features using machine-learning methods.

METHODS

A total of 199 colorectal cancer patients underwent pre-therapy diagnostic 18F-FDG PET/CT scans and CRC radical surgery. The Chang-Gung Image Texture Analysis toolbox (CGITA) was used to extract 70 PET radiomic features reflecting 18F-FDG uptake heterogeneity of tumors. The least absolute shrinkage and selection operator (LASSO) algorithm was used to select radiomic features and develop a radiomic signature score (Rad-score). The training set was used to establish five machine-learning prediction models and the test set was used to test the efficacy of the models. The effectiveness of the models was compared by ROC analysis.

RESULTS

The CRC patients were divided into a training set (n = 144) and a test set (n = 55). Two radiomic features were selected to build the Rad-score. Five machine-learning algorithms including logistic regression, support vector machine (SVM), random forest, neural network and eXtreme gradient boosting (XGBoost) were used to established models. Among the five machine-learning models, logistic regression (AUC 0.866, 95% CI 0.808-0.925) and XGBoost (AUC 0.903, 95% CI 0.855-0.951) models performed the best. In the training set, the AUC of these two models were significantly higher than that of the LN metastasis status reported by 18F-FDG PET/CT for differentiating positive and negative regional LN metastases in CRC (all p < 0.05). Good efficacy of the above two models was also achieved in the test set. We created a nomogram based on the logistic regression model that visualized the results and provided an easy-to-use method for predicting regional LN metastasis in patients with CRC.

CONCLUSION

In this study, five machine-learning models for preoperative prediction of regional LN metastasis of CRC based on 18F-FDG PET/CT and PET-based radiomic features were successfully developed and validated. Among them, the logistic regression and XGBoost models performed the best, with higher efficacy than 18F-FDG PET/CT in both the training and test sets.

Limitations and benefits of FDG-PET/CT in NF1 patients with nerve sheath tumors: A cross-sectional/longitudinal study

The purposes of this study were to re-confirm the usefulness of PET/CT in the differentiation of benignity/malignancy of neurogenic tumors in NF1 patients, and to analyze the natural course of plexiform neurofibroma (pNF) and clarify whether PET/CT is also useful for detecting tumors other than neurogenic tumors. PET/CT was prospectively imaged in 36 NF1 patients. There were 14 malignant peripheral nerve sheath tumors (MPNSTs) in 14 patients, and 54 pNFs in 30 patients. Nine patients had both MPNST and pNF. Maximal standardized uptake value (SUVmax) was significantly higher in MPNST (median 7.6: range 4.1-10.4) (P < .001) compared with that of pNF (median 3.7: range 1.6-9.3). The cut-off value of 5.8 resulted in a sensitivity of 78.6% and specificity of 88.9%. Median age was 29 y, and median maximum tumor diameter was 82 mm in 14 MPNST patients. The 5-y overall survival rate was 46.8%. Three patients with low-grade MPNST were alive without disease at the time of this report. In 9 patients in which pNF and MPNST co-existed, 2 showed a higher SUVmax of pNF than that of MPNST. Natural history analysis of pNF (n = 43) revealed that no factors significantly correlated with increased tumor size. Nine lesions other than neurogenic tumors were detected by PET/CT including 5 thyroid lesions and 3 malignant neoplasms. This study revealed the usefulness and limitation of PET/CT for NF1 patients. In the future, it will be necessary to study how to detect over time the malignant transformation of pNF to MPNST, via an intermediate tumor.

A rare case of plexiform neurofibroma of the liver in a patient without neurofibromatosis type 1

Plexiform neurofibroma is mainly associated with neurofibromatosis type 1 and is seldom observed in the liver. Its occurrence in the liver without neurofibromatosis type 1 is even rarer. We report an extremely rare case of plexiform neurofibroma of the liver diagnosed by laparoscopic biopsy in a patient without neurofibromatosis type 1. The patient was a 35-year-old man who had neither clinical signs nor any family history of neurofibromatosis type 1. Abdominal ultrasonography, as part of a health screening, had detected a hepatic tumor. Subsequent contrast ultrasonography, computed tomography, and magnetic resonance imaging showed the tumor extending from the retroperitoneal space around the aorta to the hepatic hilum and distal portal branches in the right hepatic lobe, gallbladder, and left hepatic lobe. ¹⁸F-fluorodeoxyglucose positron emission tomography showed no abnormal accumulation. Histopathological examination of the tumor obtained laparoscopically led to a diagnosis of plexiform neurofibroma. Because the patient was asymptomatic with no features of malignancy, he was only monitored and managed. At follow-up 10 years later, computed tomography showed a decrease in tumor size. It is important to recognize that, while rare, plexiform neurofibroma can occur without neurofibromatosis type 1. We recommend follow-up instead of unreasonable surgery in such cases.

Role of 18F-FDG PET/computed tomography in prognostication and management of malignant peripheral nerve sheath tumors

AIM

Malignant peripheral nerve sheath tumors (MPNSTs) are rare tumors arising from a peripheral nerve or in extraneural soft tissue which shows high metastatic potential and poor prognosis. They can arise de-novo or through malignant transformation in neurofibromatosis (NF-1). The purpose of our study is to evaluate potential role of fluorodeoxyglucose (FDG) PET/computed tomography (CT) in prognostication and management of MPNSTs.

MATERIALS AND METHODS

We have performed a retrospective analysis in patients of MPNSTs who underwent F-FDG PET/CT imaging for staging and restaging. Standardized uptake values (SUVmax and SUVmean) and texture parameters (calculated using radiomics package version 0.1.3) were measured for primary/recurrent lesions and were compared between two groups based on presence of event (recurrence/progression). Student t-test was applied for comparative analyses using the SPSS software package (version 23.0; IBM), with a significance level of 0.05.

RESULTS

Thirty patients (17 male, 13 female; mean age 42.7 ± 15.66 years) were included, who underwent F-FDG PET/CT for staging (n = 10) and restaging (n = 20). Change in management was observed in four patients at baseline and in three patients in follow-up imaging for response assessment, who had progressive disease which prompted treatment intensification. SUVmax of primary/recurrent lesion showed correlation with histopathologic grade (r = 0.712, P = 0.034). Textural analysis showed more heterogeneity in lesions in the high-risk group with recurrence and progression.

CONCLUSION

F-FDG PET/CT can be used for staging and restaging in MPNSTs leading to change in management. Texture analysis and quantitative F-FDG PET/CT parameters can help in prognostication at both baseline and relapse.

Spatial heterogeneity of oxygenation and haemodynamics in breast cancer resolved in vivo by conical multispectral optoacoustic mesoscopy

The characteristics of tumour development and metastasis relate not only to genomic heterogeneity but also to spatial heterogeneity, associated with variations in the intratumoural arrangement of cell populations, vascular morphology and oxygen and nutrient supply. While optical (photonic) microscopy is commonly employed to visualize the tumour microenvironment, it assesses only a few hundred cubic microns of tissue. Therefore, it is not suitable for investigating biological processes at the level of the entire tumour, which can be at least four orders of magnitude larger. In this study, we aimed to extend optical visualization and resolve spatial heterogeneity throughout the entire tumour volume. We developed an optoacoustic (photoacoustic) mesoscope adapted to solid tumour imaging and, in a pilot study, offer the first insights into cancer optical contrast heterogeneity in vivo at an unprecedented resolution of <50 μm throughout the entire tumour mass. Using spectral methods, we resolve unknown patterns of oxygenation, vasculature and perfusion in three types of breast cancer and showcase different levels of structural and functional organization. To our knowledge, these results are the most detailed insights of optical signatures reported throughout entire tumours in vivo, and they position optoacoustic mesoscopy as a unique investigational tool linking microscopic and macroscopic observations.

Treatment of malignant peripheral nerve sheath tumors in pediatric NF1 disease

BACKGROUND

Malignant peripheral nerve sheath tumors (MPNSTs) are rare yet highly aggressive soft tissue sarcomas. Children with neurofibromatosis type 1 (NF1) have a 10% lifetime risk for development of MPNST. Prognosis remains poor and survival seems worse for NF1 patients.

METHODS

This narrative review highlights current practices and pitfalls in the management of MPNST in pediatric NF1 patients.

RESULTS

Preoperative diagnostics can be challenging, but PET scans have shown to be useful tools. More recently, functional MRI holds promise as well. Surgery remains the mainstay treatment for these patients, but careful planning is needed to minimize postoperative morbidity. Functional reconstructions can play a role in improving functional status. Radiotherapy can be administered to enhance local control in selected cases, but care should be taken to minimize radiation effects as well as reduce the risk of secondary malignancies. The exact role of chemotherapy has yet to be determined. Reports on the efficacy of chemotherapy vary as some report lower effects in NF1 populations. Promisingly, survival seems to ameliorate in the last few decades and response rates of chemotherapy may increase in NF1 populations when administering it as part of standard of care. However, in metastasized disease, response rates remain poor. New systemic therapies are therefore desperately warranted and multiple trials are currently investigating the role of drugs. Targeted drugs are nevertheless not yet included in first line treatment.

CONCLUSION

Both research and clinical efforts benefit from multidisciplinary approaches with international collaborations in this rare malignancy.

What can artificial intelligence teach us about the molecular mechanisms underlying disease?

While molecular imaging with positron emission tomography or single-photon emission computed tomography already reports on tumour molecular mechanisms on a macroscopic scale, there is increasing evidence that there are multiple additional features within medical images that can further improve tumour characterization, treatment prediction and prognostication. Early reports have already revealed the power of radiomics to personalize and improve patient management and outcomes. What remains unclear is how these additional metrics relate to underlying molecular mechanisms of disease. Furthermore, the ability to deal with increasingly large amounts of data from medical images and beyond in a rapid, reproducible and transparent manner is essential for future clinical practice. Here, artificial intelligence (AI) may have an impact. AI encompasses a broad range of 'intelligent' functions performed by computers, including language processing, knowledge representation, problem solving and planning. While rule-based algorithms, e.g. computer-aided diagnosis, have been in use for medical imaging since the 1990s, the resurgent interest in AI is related to improvements in computing power and advances in machine learning (ML). In this review we consider why molecular and cellular processes are of interest and which processes have already been exposed to AI and ML methods as reported in the literature. Non-small-cell lung cancer is used as an exemplar and the focus of this review as the most common tumour type in which AI and ML approaches have been tested and to illustrate some of the concepts.

Screening populations at high risk for soft tissue sarcoma and surveillance following soft tissue sarcoma resection

Soft tissue sarcomas (STS) are a rare and diverse group of tumors that affect both adult and pediatric populations. This review discusses current screening recommendations for populations at increased risk for STS, including those with genetic predispositions. We also review surveillance guidelines for those at risk for recurrence following curative-intent surgery.

How Effective Are Noninvasive Tests for Diagnosing Malignant Peripheral Nerve Sheath Tumors in Patients with Neurofibromatosis Type 1? Diagnosing MPNST in NF1 Patients

Background

Distinguishing between benign and malignant peripheral nerve sheath tumors (MPNSTs) in neurofibromatosis 1 (NF1) patients prior to excision can be challenging. How can MPNST be most accurately diagnosed using clinical symptoms, magnetic resonance imaging (MRI) findings (tumor size, depth, and necrosis), positron emission tomography (PET) measures (SUV_peak, SUV_max, SUV_{max tumor}/SUV_{mean liver}, and qualitative scale), and combinations of the above? Methods. All NF1 patients who underwent PET imaging at our institution (January 1, 2007–December 31, 2016) were included. Medical records were reviewed for clinical findings; MR images and PET images were interpreted by two fellowship-trained musculoskeletal and nuclear medicine radiologists, respectively. Receiver operating characteristic (ROC) curves were created for each PET measurement; the area under the curve (AUC) and thresholds for diagnosing malignancy were calculated. Logistic regression determined significant predictors of malignancy.

Results

Our population of 41 patients contained 34 benign and 36 malignant tumors. Clinical findings did not reliably predict MPNST. Tumor depth below fascia was highly sensitive; larger tumors were more likely to be malignant but without a useful cutoff for diagnosis. Necrosis on MRI was highly accurate and was the only significant variable in the regression model. PET measures were highly accurate, with AUCs comparable and cutoff points consistent with prior studies. A diagnostic algorithm was created using MRI and PET findings.

Conclusions

MRI and PET were more effective at diagnosing MPNST than clinical features. We created an algorithm for preoperative evaluation of peripheral nerve sheath tumors in NF1 patients, for which additional validation will be indicated.

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

BACKGROUND

This study explores whether objective, quantitative radiomic biomarkers derived from magnetic resonance (MR), positron emission tomography (PET), and computed tomography (CT) may be useful in reliably distinguishing malignant peripheral nerve sheath tumors (MPNST) from benign plexiform neurofibromas (PN).

METHODS

A registration and segmentation pipeline was established using a cohort of NF1 patients with histopathological diagnosis of PN or MPNST, and medical imaging of the PN including MR and PET-CT. The corrected MR datasets were registered to the corresponding PET-CT via landmark-based registration. PET standard-uptake value (SUV) thresholds were used to guide segmentation of volumes of interest: MPNST-associated PET-hot regions (SUV≥3.5) and PN-associated PET-elevated regions (2.0<SUV<3.5). Quantitative imaging features were extracted from the MR, PET, and CT data and compared for statistical differences. Intensity histogram features included (mean, media, maximum, variance, full width at half maximum, entropy, kurtosis, and skewness), while image texture was quantified using Law's texture energy measures, grey-level co-occurrence matrices, and neighborhood grey-tone difference matrices.

RESULTS

For each of the 20 NF1 subjects, a total of 320 features were extracted from the image data. Feature reduction and statistical testing identified 9 independent radiomic biomarkers from the MR data (4 intensity and 5 texture) and 4 PET (2 intensity and 2 texture) were different between the PET-hot versus PET-elevated volumes of interest.

CONCLUSIONS

Our data suggests imaging features can be used to distinguish malignancy in NF1-realted tumors, which could improve MPNST risk assessment and positively impact clinical management of NF1 patients.