Related Experiment Video
Updated: Nov 5, 2025

09:45
Mosaic Zebrafish Transgenesis for Functional Genomic Analysis of Candidate Cooperative Genes in Tumor Pathogenesis
Published on: March 31, 2015
11.4K
Radiogenomics prediction for MYCN amplification in neuroblastoma: A hypothesis generating study
Angela Di Giannatale1, Pier Luigi Di Paolo2, Davide Curione2
1Department of Pediatric Hematology/Oncology and Cell and Gene Therapy, IRCCS Ospedale Pediatrico Bambino Gesù, Rome, Italy.
Pediatric Blood & Cancer
|May 18, 2021
Summary
Computed tomography (CT) radiomics can predict MYCN amplification in neuroblastoma (NB). This imaging biomarker analysis enhances outcome prediction for this aggressive childhood cancer.
Area of Science:
- Radiomics and Medical Imaging
- Oncology and Cancer Research
- Genetics and Genomics
Background:
- MYCN amplification is a key prognostic factor in neuroblastoma (NB), influencing treatment and outcomes.
- Intratumoral heterogeneity can sometimes be linked to MYCN amplification.
- Radiomics offers advanced image analysis for extracting quantitative data from radiological scans.
Purpose of the Study:
- To develop a radiogenomics model correlating CT radiomics features with MYCN amplification status in NB.
- To investigate the potential of imaging biomarkers for predicting NB prognosis.
Main Methods:
- Retrospective analysis of pretherapy CT scans from 78 NB patients.
- Segmentation of NB lesions and extraction of 232 radiomics features.
- Dimensionality reduction, feature selection (Boruta, Pearson correlation), and logistic regression modeling.
Main Results:
- Two radiomics features, mean of voxel intensity histogram and zone size non-uniformity, were selected.
- The logistic regression model achieved an AUC of 0.879 on the training set.
- Validation on an independent cohort yielded an AUC of 0.813 and 0.85 accuracy.
Conclusions:
- CT-based radiomics effectively predicts MYCN amplification status in neuroblastoma.
- This approach supports the development of imaging biomarkers for improved outcome prediction in NB.
- Radiogenomics models show promise for non-invasive assessment of NB tumor biology.

