Dataset Information

CT-Based Radiomics Signature With Machine Learning Predicts MYCN Amplification in Pediatric Abdominal Neuroblastoma.

ABSTRACT:

Purpose

MYCN amplification plays a critical role in defining high-risk subgroup of patients with neuroblastoma. We aimed to develop and validate the CT-based machine learning models for predicting MYCN amplification in pediatric abdominal neuroblastoma.

Methods

A total of 172 patients with MYCN amplified (n = 47) and non-amplified (n = 125) were enrolled. The cohort was randomly stratified sampling into training and testing groups. Clinicopathological parameters and radiographic features were selected to construct the clinical predictive model. The regions of interest (ROIs) were segmented on three-phrase CT images to extract first-, second- and higher-order radiomics features. The ICCs, mRMR and LASSO methods were used for dimensionality reduction. The selected features from the training group were used to establish radiomics models using Logistic regression, Support Vector Machine (SVM), Bayes and Random Forest methods. The performance of four different radiomics models was evaluated according to the area under the receiver operator characteristic (ROC) curve (AUC), and then compared by Delong test. The nomogram incorporated of clinicopathological parameters, radiographic features and radiomics signature was developed through multivariate logistic regression. Finally, the predictive performance of the clinical model, radiomics models, and nomogram was evaluated in both training and testing groups.

Results

In total, 1,218 radiomics features were extracted from the ROIs on three-phrase CT images, and then 14 optimal features, including one original first-order feature and eight wavelet-transformed features and five LoG-transformed features, were identified and selected to construct the radiomics models. In the training group, the AUC of the Logistic, SVM, Bayes and Random Forest model was 0.940, 0.940, 0.780 and 0.927, respectively, and the corresponding AUC in the testing group was 0.909, 0.909, 0.729, 0.851, respectively. There was no significant difference among the Logistic, SVM and Random Forest model, but all better than the Bayes model (p <0.005). The predictive performance of the Logistic radiomics model based on three-phrase is similar to nomogram, but both better than the clinical model and radiomics model based on single venous phase.

Conclusion

The CT-based radiomics signature is able to predict MYCN amplification of pediatric abdominal NB with high accuracy based on SVM, Logistic and Random Forest classifiers, while Bayes classifier yields lower predictive performance. When combined with clinical and radiographic qualitative features, the clinics-radiomics nomogram can improve the performance of predicting MYCN amplification.

SUBMITTER: Chen X

PROVIDER: S-EPMC8181422 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Simple Summary MYCN gene amplification, the strongest prognostic marker of aggressive neuroblastoma, is detected on invasive biopsy tissues. This study aimed to establish a less invasive method to detect MYCN status based on MYCN mRNA contents in large extracellular vesicles or microvesicles. MYCN mRNA-containing microvesicles were detectable in three distinct MYCN-amplified neuroblastoma cell lines but absent in three neuroblastoma cells with MYCN-non-amplification. The feasibility of this EV-based workflow was successfully demonstrated by using the simulated samples (prepared by pulsing neuroblastoma MVs into the normal human serum) and bone marrow plasma specimens obtained from nine patients at various disease stages. Taken together, this study established the novel EV-based method for detecting MYCN status in pediatric neuroblastoma. Abstract MYCN amplification is the strongest predictor of high-risk neuroblastoma (NB). The standard procedure to detect MYCN status requires invasive procedures. Extracellular vesicles (EVs) contain molecular signatures of originated cells, present in biofluids, and serve as an invaluable source for cancer liquid biopsies. This study aimed to establish an EV-based method to detect the MYCN status of NB. Two EV subtypes, i.e., microvesicles (MVs) and exosomes, were sequentially isolated from the culture supernatant by step-wise centrifugation, ultrafiltration, and size-exclusion chromatography. Quantitative RT-PCR was performed to detect MYCN mRNA. As a result, MYCN mRNA was detectable in the MVs, but not exosomes, of MYCN-amplified NB cells. MYCN mRNA-containing MVs (MYCN-MV) were successfully detected in three distinct MYCN-amplified NB cell lines but absent in three MYCN non-amplification cells. The simulated samples were prepared by pulsing MVs into human serum. MYCN–MV detection in the simulated samples showed a less interfering effect from the human blood matrix. Validation using clinical specimens (2 mL bone marrow plasma) obtained from patients at various disease stages showed a promising result. Five out of six specimens of MYCN-amplified patients showed positive results, while there were no false positives in four plasma samples of the MYCN non-amplification group. This study communicated a novel EV-based method for detecting the MYCN status of pediatric NB based on MYCN mRNA contents in MVs. Future studies should be pursued in a prospective cohort to determine its true diagnostic performance.