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

Applications of Artificial Intelligence for Pediatric Cancer Imaging

Artificial intelligence (AI) is transforming medical imaging of adult patients. However, its utilization in pediatric oncology imaging remains constrained, in part due to the inherent data scarcity associated with childhood cancers. Pediatric cancers are rare, and imaging technologies are evolving rapidly, leading to insufficient data of a particular type to effectively train these algorithms. The small market size of pediatrics compared to adults could also contribute to this challenge, as market size is a driver of commercialization. This article provides an overview of the current state of AI applications for pediatric cancer imaging, including applications for medical image acquisition, processing, reconstruction, segmentation, diagnosis, staging, and treatment response monitoring. While current developments are promising, impediments due to diverse anatomies of growing children and nonstandardized imaging protocols have led to limited clinical translation thus far. Opportunities include leveraging reconstruction algorithms to achieve accelerated low-dose imaging and automating the generation of metric-based staging and treatment monitoring scores. Transfer-learning of adult-based AI models to pediatric cancers, multi-institutional data sharing, and ethical data privacy practices for pediatric patients with rare cancers will be keys to unlocking AI's full potential for clinical translation and improved outcomes for these young patients.

Computed Tomography-Based Radiomics Signature for Predicting Segmental Chromosomal Aberrations at 1p36 and 11q23 in Pediatric Neuroblastoma

OBJECTIVE

This study aimed to develop and assess the precision of a radiomics signature based on computed tomography imaging for predicting segmental chromosomal aberrations (SCAs) status at 1p36 and 11q23 in neuroblastoma.

METHODS

Eighty-seven pediatric patients diagnosed with neuroblastoma and with confirmed genetic testing for SCAs status at 1p36 and 11q23 were enrolled and randomly stratified into a training set and a test set. Radiomics features were extracted from 3-phase computed tomography images and analyzed using various statistical methods. An optimal set of radiomics features was selected using a least absolute shrinkage and selection operator regression model to calculate the radiomics score for each patient. The radiomics signature was validated using receiver operating characteristic curves to obtain the area under the curve and 95% confidence interval (CI).

RESULTS

Eight radiomics features were carefully selected and used to compute the radiomics score, which demonstrated a statistically significant distinction between the SCAs and non-SCAs groups in both sets. The radiomics signature achieved an area under the curve of 0.869 (95% CI, 0.788-0.943) and 0.883 (95% CI, 0.753-0.978) in the training and test sets, respectively. The accuracy of the radiomics signature was 0.817 and 0.778 in the training and test sets, respectively. The Hosmer-Lemeshow test confirmed that the radiomics signature was well calibrated.

CONCLUSIONS

Computed tomography-based radiomics signature has the potential to predict SCAs at 1p36 and 11q23 in neuroblastoma.

Prediction of High-Risk Neuroblastoma Among Neuroblastic Tumors Using Radiomics Features Derived from Magnetic Resonance Imaging: A Pilot Study

PURPOSE

This study aimed to predict high-risk neuroblastoma among neuroblastic tumors using radiomics features extracted from MRI.

MATERIALS AND METHODS

Pediatric patients (age≤18 years) diagnosed with neuroblastic tumors who had pre-treatment MR images available were enrolled from institution A from January 2010 to November 2019 (training set) and institution B from January 2016 to January 2022 (test set). Segmentation was performed with regions of interest manually drawn along tumor margins on the slice with the widest tumor area by two radiologists. First-order and texture features were extracted and intraclass correlation coefficients (ICCs) were calculated. Multivariate logistic regression (MLR) and random forest (RF) models from 10-fold cross-validation were built using these features. The trained MLR and RF models were tested in an external test set.

RESULTS

Thirty-two patients (M:F=23:9, 26.0±26.7 months) were in the training set and 14 patients (M:F=10:4, 33.4±20.4 months) were in the test set with radiomics features (n=930) being extracted. For 10 of the most relevant features selected, intra- and inter-observer variability was moderate to excellent (ICCs 0.633-0.911, 0.695-0.985, respectively). The area under the receiver operating characteristic curve (AUC) was 0.94 (sensitivity 67%, specificity 91%, and accuracy 84%) for the MLR model and the average AUC was 0.83 (sensitivity 44%, specificity 87%, and accuracy 75%) for the RF model from 10-fold cross-validation. In the test set, AUCs of the MLR and RF models were 0.94 and 0.91, respectively.

CONCLUSION

An MRI-based radiomics model can help predict high-risk neuroblastoma among neuroblastic tumors.

18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) imaging of pediatric neuroblastoma: a multi-omics parameters method to predict MYCN copy number category

Background

The MYCN copy number category is closely related to the prognosis of neuroblastoma (NB). Therefore, this study aimed to assess the predictive ability of 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) radiomic features for MYCN copy number in NB.

Methods

A retrospective analysis was performed on 104 pediatric patients with NB that had been confirmed by pathology. To develop the Bio-omics model (B-model), which incorporated clinical and biological aspects, PET/CT radiographic features, PET quantitative parameters, and significant features with multivariable stepwise logistic regression were preserved. Important radiomics features were identified through least absolute shrinkage and selection operator (LASSO) and univariable analysis. On the basis of radiomics features obtained from PET and CT scans, the radiomics model (R-model) was developed. The significant bio-omics and radiomics features were combined to establish a Multi-omics model (M-model). The above 3 models were established to differentiate MYCN wild from MYCN gain and MYCN amplification (MNA). The calibration curve and receiver operating characteristic (ROC) curve analyses were performed to verify the prediction performance. Post hoc analysis was conducted to compare whether the constructed M-model can distinguish MYCN gain from MNA.

Results

The M-model showed excellent predictive performance in differentiating MYCN wild from MYCN gain and MNA, which was better than that of the B-model and R-model [area under the curve (AUC) 0.83, 95% confidence interval (CI): 0.74-0.92 vs. 0.81, 95% CI: 0.72-0.90 and 0.79, 95% CI: 0.69-0.89]. The calibration curve showed that the M-model had the highest reliability. Post hoc analysis revealed the great potential of the M-model in differentiating MYCN gain from MNA (AUC 0.95, 95% CI: 0.89-1).

Conclusions

The M-model model based on bio-omics and radiomics features is an effective tool to distinguish MYCN copy number category in pediatric patients with NB.

Radiomics in differential diagnosis of Wilms tumor and neuroblastoma with adrenal location in children

OBJECTIVES

Machine learning methods can be applied successfully to various medical imaging tasks. Our aim with this study was to build a robust classifier using radiomics and clinical data for preoperative diagnosis of Wilms tumor (WT) or neuroblastoma (NB) in pediatric abdominal CT.

MATERIAL AND METHODS

This is a single-center retrospective study approved by the Institutional Ethical Board. CT scans of consecutive patients diagnosed with WT or NB admitted to our hospital from January 2005 to December 2021 were evaluated. Three distinct datasets based on clinical centers and CT machines were curated. Robust, non-redundant, high variance, and relevant radiomics features were selected using data science methods. Clinically relevant variables were integrated into the final model. Dice score for similarity of tumor ROI, Cohen's kappa for interobserver agreement among observers, and AUC for model selection were used.

RESULTS

A total of 147 patients, including 90 WT (mean age 34.78 SD: 22.06 months; 43 male) and 57 NB (mean age 23.77 SD:22.56 months; 31 male), were analyzed. After binarization at 24 months cut-off, there was no statistically significant difference between the two groups for age (p = .07) and gender (p = .54). CT clinic radiomics combined model achieved an F1 score of 0.94, 0.93 accuracy, and an AUC 0.96.

CONCLUSION

In conclusion, the CT-based clinic-radiologic-radiomics combined model could noninvasively predict WT or NB preoperatively. Notably, that model correctly predicted two patients, which none of the radiologists could correctly predict. This model may serve as a noninvasive preoperative predictor of NB/WT differentiation in CT, which should be further validated in large prospective models.

CLINICAL RELEVANCE STATEMENT

CT-based clinic-radiologic-radiomics combined model could noninvasively predict Wilms tumor or neuroblastoma preoperatively.

KEY POINTS

• CT radiomics features can predict Wilms tumor or neuroblastoma from abdominal CT preoperatively. • Integrating clinic variables may further improve the performance of the model. • The performance of the combined model is equal to or greater than human readers, depending on the lesion size.

Application of Machine Learning and Deep EfficientNets in Distinguishing Neonatal Adrenal Hematomas From Neuroblastoma in Enhanced Computed Tomography Images

Background

The aim of the study was to employ a combination of radiomic indicators based on computed tomography (CT) imaging and machine learning (ML), along with deep learning (DL), to differentiate between adrenal hematoma and adrenal neuroblastoma in neonates.

Methods

A total of 76 neonates were included in this retrospective study (40 with neuroblastomas and 36 with adrenal hematomas) who underwent CT and divided into a training group (n = 38) and a testing group (n = 38). The regions of interest (ROIs) were segmented by two radiologists to extract radiomics features using Pyradiomics package. ML classifications were done using support vector machine (SVM), AdaBoost, Extra Trees, gradient boosting, multi-layer perceptron (MLP), and random forest (RF). EfficientNets was employed and classified, based on radiometrics. The area under curve (AUC) of the receiver operating characteristic (ROC) was calculated to assess the performance of each model.

Results

Among all features, the least absolute shrinkage and selection operator (LASSO) logistic regression selected nine features. These radiomics features were used to construct radiomics model. In the training cohort, the AUCs of SVM, MLP and Extra Trees models were 0.967, 0.969 and 1.000, respectively. The corresponding AUCs of the test cohort were 0.985, 0.971 and 0.958, respectively. In the classification task, the AUC of the DL framework was 0.987.

Conclusion

ML decision classifiers and DL framework constructed from CT-based radiomics features offered a non-invasive method to differentiate neonatal adrenal hematoma from neuroblastoma and performed better than the clinical experts.

Predicting Neuroblastoma Patient Risk Groups, Outcomes, and Treatment Response Using Machine Learning Methods: A Review

Neuroblastoma, a paediatric malignancy with high rates of cancer-related morbidity and mortality, is of significant interest to the field of paediatric cancers. High-risk NB tumours are usually metastatic and result in survival rates of less than 50%. Machine learning approaches have been applied to various neuroblastoma patient data to retrieve relevant clinical and biological information and develop predictive models. Given this background, this study will catalogue and summarise the literature that has used machine learning and statistical methods to analyse data such as multi-omics, histological sections, and medical images to make clinical predictions. Furthermore, the question will be turned on its head, and the use of machine learning to accurately stratify NB patients by risk groups and to predict outcomes, including survival and treatment response, will be summarised. Overall, this study aims to catalogue and summarise the important work conducted to date on the subject of expression-based predictor models and machine learning in neuroblastoma for risk stratification and patient outcomes including survival, and treatment response which may assist and direct future diagnostic and therapeutic efforts.

CT radiomics to differentiate between Wilms tumor and clear cell sarcoma of the kidney in children

BACKGROUND

To investigate the role of CT radiomics in distinguishing Wilms tumor (WT) from clear cell sarcoma of the kidney (CCSK) in pediatric patients.

METHODS

We retrospectively enrolled 83 cases of WT and 33 cases of CCSK. These cases were randomly stratified into a training set (n = 81) and a test set (n = 35). Several imaging features from the nephrographic phase were analyzed, including the maximum tumor diameter, the ratio of the maximum CT value of the tumor solid portion to the mean CT value of the contralateral renal vein (CTmax/CT renal vein), and the presence of dilated peritumoral cysts. Radiomics features from corticomedullary phase were extracted, selected, and subsequently integrated into a logistic regression model. We evaluated the model's performance using the area under the curve (AUC), 95% confidence interval (CI), and accuracy.

RESULTS

In the training set, there were statistically significant differences in the maximum tumor diameter (P = 0.021) and the presence of dilated peritumoral cysts (P = 0.005) between WT and CCSK, whereas in the test set, no statistically significant differences were observed (P > 0.05). The radiomics model, constructed using four radiomics features, demonstrated strong performance in the training set with an AUC of 0.889 (95% CI: 0.811-0.967) and an accuracy of 0.864. Upon evaluation using fivefold cross-validation in the training set, the AUC remained high at 0.863 (95% CI: 0.774-0.952), with an accuracy of 0.852. In the test set, the radiomics model achieved an AUC of 0.792 (95% CI: 0.616-0.968) and an accuracy of 0.857.

CONCLUSION

CT radiomics proves to be diagnostically valuable for distinguishing between WT and CCSK in pediatric cases.

A narrative review of radiomics and deep learning advances in neuroblastoma: updates and challenges

Neuroblastoma is an extremely heterogeneous tumor that commonly occurs in children. The diagnosis and treatment of this tumor pose considerable challenges due to its varied clinical presentations and intricate genetic aberrations. Presently, various imaging modalities, including computed tomography, magnetic resonance imaging, and positron emission tomography, are utilized to assess neuroblastoma. Nevertheless, these conventional imaging modalities have limitations in providing quantitative information for accurate diagnosis and prognosis. Radiomics, an emerging technique, can extract intricate medical imaging information that is imperceptible to the human eye and transform it into quantitative data. In conjunction with deep learning algorithms, radiomics holds great promise in complementing existing imaging modalities. The aim of this review is to showcase the potential of radiomics and deep learning advancements to enhance the diagnostic capabilities of current imaging modalities for neuroblastoma.

Predicting MYCN amplification in paediatric neuroblastoma: development and validation of a 18F-FDG PET/CT-based radiomics signature

OBJECTIVES

To develop and validate an 18F-FDG PET/CT-based clinical-radiological-radiomics nomogram and evaluate its value in the diagnosis of MYCN amplification (MNA) in paediatric neuroblastoma (NB) patients.

METHODS

A total of 104 patients with NB were retrospectively included. We constructed a nomogram to predict MNA based on radiomics signatures, clinical and radiological features. The multivariable logistic regression and the least absolute shrinkage and selection operator (LASSO) were used for feature selection. Radiomics models are constructed using decision trees (DT), logistic regression (LR) and support vector machine (SVM) classifiers. A clinical-radiological (C-R) model was developed using clinical and radiological features. A clinical-radiological-radiomics (C-R-R) model was developed using the C-R model of the best radiomics model. The prediction performance was verified by receiver operating characteristic (ROC) curve analysis, calibration curve analysis and decision curve analysis (DCA) in the training and validation cohorts.

RESULTS

The present study showed that four radiomics signatures were significantly correlated with MNA. The SVM classifier was the best model of radiomics signature. The C-R-R model has the best discriminant ability to predict MNA, with AUCs of 0.860 (95% CI, 0.757-0.963) and 0.824 (95% CI, 0.657-0.992) in the training and validation cohorts, respectively. The calibration curve indicated that the C-R-R model has the goodness of fit and DCA confirms its clinical utility.

CONCLUSION

Our research provides a non-invasive C-R-R model, which combines the radiomics signatures and clinical and radiological features based on 18F-FDGPET/CT images, shows excellent diagnostic performance in predicting MNA, and can provide useful biological information with stratified therapy.

CRITICAL RELEVANCE STATEMENT

Radiomic signatures of 18F-FDG-based PET/CT can predict MYCN amplification in neuroblastoma.

KEY POINTS

• Radiomic signatures of 18F-FDG-based PET/CT can predict MYCN amplification in neuroblastoma. • SF, LDH, necrosis and TLG are the independent risk factors of MYCN amplification. • Clinical-radiological-radiomics model improved the predictive performance of MYCN amplification.

Computed tomography-based radiomics to assess risk stratification in pediatric malignant peripheral neuroblastic tumors

This study aimed to develop and validate an analysis system based on preoperative computed tomography (CT) to predict the risk stratification in pediatric malignant peripheral neuroblastic tumors (PNTs). A total of 405 patients with malignant PNTs (184 girls and 221 boys; mean age, 33.8 ± 29.1 months) were retrospectively evaluated between January 2010 and June 2018. Radiomic features were extracted from manually segmented tumors on preoperative CT images. Spearman's rank correlation coefficient and the least absolute shrinkage and selection operator (LASSO) were used to eliminate redundancy and select features. A risk model was built to stratify low-, intermediate-, and high-risk groups. An image-defined risk factor (IDRFs) model was developed to classify 266 patients with malignant PNTs and one or more IDRFs into high-risk and non-high-risk groups. The performance of the predictive models was evaluated with respect to accuracy (Acc) and receiver operating characteristic (ROC) curve, including the area under the ROC curve (AUC). The risk model demonstrated good discrimination capability, with an area under the curve (AUC) of 0.903 to distinguish high-risk from non-high-risk groups, and 0.747 to classify intermediate- and low-risk groups. In the IDRF-based risk model with the number of IDRFs, the AUC was 0.876 for classifying the high-risk and non-high-risk groups. Radiomic analysis based on preoperative CT images has the potential to stratify the risk of pediatric malignant PNTs. It had outstanding efficiency in distinguishing patients in the high-risk group, and this predictive model of risk stratification could assist in selecting optimal aggressive treatment options.

Role of MRI radiomics for the prediction of MYCN amplification in neuroblastomas

OBJECTIVES

We evaluate MR radiomics and develop machine learning-based classifiers to predict MYCN amplification in neuroblastomas.

METHODS

A total of 120 patients with neuroblastomas and baseline MR imaging examination available were identified of whom 74 (mean age ± standard deviation [SD] of 6 years and 2 months ± 4 years and 9 months; 43 females and 31 males, 14 MYCN amplified) underwent imaging at our institution. This was therefore used to develop radiomics models. The model was tested in a cohort of children with the same diagnosis but imaged elsewhere (n = 46, mean age ± SD: 5 years 11 months ± 3 years 9 months, 26 females and 14 MYCN amplified). Whole tumour volumes of interest were adopted to extract first-order histogram and second-order radiomics features. Interclass correlation coefficient and maximum relevance and minimum redundancy algorithm were applied for feature selection. Logistic regression, support vector machine, and random forest were employed as the classifiers. Receiver operating characteristic (ROC) analysis was performed to evaluate the diagnostic accuracy of the classifiers on the external test set.

RESULTS

The logistic regression model and the random forest both showed an AUC of 0.75. The support vector machine classifier obtained an AUC of 0.78 on the test set with a sensitivity of 64% and a specificity of 72%.

CONCLUSION

The study provides preliminary retrospective evidence demonstrating the feasibility of MRI radiomics in predicting MYCN amplification in neuroblastomas. Future studies are needed to explore the correlation between other imaging features and genetic markers and to develop multiclass predictive models.

KEY POINTS

• MYCN amplification in neuroblastomas is an important determinant of disease prognosis. • Radiomics analysis of pre-treatment MR examinations can be used to predict MYCN amplification in neuroblastomas. • Radiomics machine learning models showed good generalisability to external test set, demonstrating reproducibility of the computational models.

Prediction of MYCN Gene Amplification in Pediatric Neuroblastomas: Development of a Deep Learning-Based Tool for Automatic Tumor Segmentation and Comparative Analysis of Computed Tomography-Based Radiomics Features Harmonization

OBJECTIVE

MYCN oncogene amplification is closely linked to high-grade neuroblastoma with poor prognosis. Accurate quantification is essential for risk assessment, which guides clinical decision making and disease management. This study proposes an end-to-end deep-learning framework for automatic tumor segmentation of pediatric neuroblastomas and radiomics features-based classification of MYCN gene amplification.

METHODS

Data from pretreatment contrast-enhanced computed tomography scans and MYCN status from 47 cases of pediatric neuroblastomas treated at a tertiary children's hospital from 2009 to 2020 were reviewed. Automated tumor segmentation and grading pipeline includes (1) a modified U-Net for tumor segmentation; (2) extraction of radiomic textural features; (3) feature-based ComBat harmonization for removal of variabilities across scanners; (4) feature selection using 2 approaches, namely, ( a ) an ensemble approach and ( b ) stepwise forward-and-backward selection method using logistic regression classifier; and (5) radiomics features-based classification of MYCN gene amplification using machine learning classifiers.

RESULTS

Median train/test Dice score for modified U-Net was 0.728/0.680. The top 3 features from the ensemble approach were neighborhood gray-tone difference matrix (NGTDM) busyness, NGTDM strength, and gray-level run-length matrix (GLRLM) low gray-level run emphasis, whereas those from the stepwise approach were GLRLM low gray-level run emphasis, GLRLM high gray-level run emphasis, and NGTDM coarseness. The top-performing tumor classification algorithm achieved a weighted F1 score of 97%, an area under the receiver operating characteristic curve of 96.9%, an accuracy of 96.97%, and a negative predictive value of 100%. Harmonization-based tumor classification improved the accuracy by 2% to 3% for all classifiers.

CONCLUSION

The proposed end-to-end framework achieved high accuracy for MYCN gene amplification status classification.

Multi-phase-combined CECT radiomics models for Fuhrman grade prediction of clear cell renal cell carcinoma

Objective

This study aimed to evaluate the effectiveness of multi-phase-combined contrast-enhanced CT (CECT) radiomics methods for noninvasive Fuhrman grade prediction of clear cell renal cell carcinoma (ccRCC).

Methods

A total of 187 patients with four-phase CECT images were retrospectively enrolled and then were categorized into training cohort (n=126) and testing cohort (n=61). All patients were confirmed as ccRCC by histopathological reports. A total of 110 3D classical radiomics features were extracted from each phase of CECT for individual ccRCC lesion, and contrast-enhanced variation features were also calculated as derived radiomics features. These features were concatenated together, and redundant features were removed by Pearson correlation analysis. The discriminative features were selected by minimum redundancy maximum relevance method (mRMR) and then input into a C-support vector classifier to build multi-phase-combined CECT radiomics models. The prediction performance was evaluated by the area under the curve (AUC) of receiver operating characteristic (ROC).

Results

The multi-phase-combined CECT radiomics model showed the best prediction performance (AUC=0.777) than the single-phase CECT radiomics model (AUC=0.711) in the testing cohort (p value=0.039).

Conclusion

The multi-phase-combined CECT radiomics model is a potential effective way to noninvasively predict Fuhrman grade of ccRCC. The concatenation of first-order features and texture features extracted from corticomedullary phase and nephrographic phase are discriminative feature representations.

Radiomics analysis of contrast-enhanced computed tomography in predicting the International Neuroblastoma Pathology Classification in neuroblastoma

PURPOSE

To predict the International Neuroblastoma Pathology Classification (INPC) in neuroblastoma using a computed tomography (CT)-based radiomics approach.

METHODS

We enrolled 297 patients with neuroblastoma retrospectively and divided them into a training group (n = 208) and a testing group (n = 89). To balance the classes in the training group, a Synthetic Minority Over-sampling Technique was applied. A logistic regression radiomics model based on the radiomics features after dimensionality reduction was then constructed and validated in both the training and testing groups. To evaluate the diagnostic performance of the radiomics model, the receiver operating characteristic curve and calibration curve were utilized. Moreover, the decision curve analysis to assess the net benefits of the radiomics model at different high-risk thresholds was employed.

RESULTS

Seventeen radiomics features were used to construct radiomics model. In the training group, radiomics model achieved an area under the curve (AUC), accuracy, sensitivity, and specificity of 0.851 (95% confidence interval (CI) 0.805-0.897), 0.770, 0.694, and 0.847, respectively. In the testing group, radiomics model achieved an AUC, accuracy, sensitivity, and specificity of 0.816 (95% CI 0.725-0.906), 0.787, 0.793, and 0.778, respectively. The calibration curve indicated that the radiomics model was well fitted in both the training and testing groups (p > 0.05). Decision curve analysis further confirmed that the radiomics model performed well at different high-risk thresholds.

CONCLUSION

Radiomics analysis of contrast-enhanced CT demonstrates favorable diagnostic capabilities in distinguishing the INPC subgroups of neuroblastoma.

CRITICAL RELEVANCE STATEMENT

Radiomics features of contrast-enhanced CT images correlate with the International Neuroblastoma Pathology Classification (INPC) of neuroblastoma.

Development and validation of a CT-based radiomics signature for identifying high-risk neuroblastomas under the revised Children's Oncology Group classification system

BACKGROUND

To develop and validate a radiomics signature based on computed tomography (CT) for identifying high-risk neuroblastomas.

PROCEDURE

This retrospective study included 339 patients with neuroblastomas, who were classified into high-risk and non-high-risk groups according to the revised Children's Oncology Group classification system. These patients were then randomly divided into a training set (n = 237) and a testing set (n = 102). Pretherapy CT images of the arterial phase were segmented by two radiologists. Pyradiomics package and FeAture Explorer software were used to extract and process radiomics features. Radiomics models based on linear discriminant analysis (LDA), logistic regression (LR), and support vector machine (SVM) were constructed, and the area under the curve (AUC), 95% confidence interval (CI), and accuracy were calculated.

RESULTS

The optimal LDA, LR, and SVM models had 11, 12, and 14 radiomics features, respectively. The AUC of the LDA model in the training and testing sets were 0.877 (95% CI: 0.833-0.921) and 0.867 (95% CI: 0.797-0.937), with an accuracy of 0.823 and 0.804, respectively. The AUC of the LR model in the training and testing sets were 0.881 (95% CI: 0.839-0.924) and 0.855 (95% CI: 0.781-0.930), with an accuracy of 0.823 and 0.804, respectively. The AUC of the SVM model in the training and testing sets were 0.879 (95% CI: 0.836-0.923) and 0.862 (95% CI: 0.791-0.934), with an accuracy of 0.827 and 0.804, respectively.

CONCLUSIONS

CT-based radiomics is able to identify high-risk neuroblastomas and may provide additional image biomarkers for the identification of high-risk neuroblastomas.

Whole-tumor radiomics analysis of T2-weighted imaging in differentiating neuroblastoma from ganglioneuroblastoma/ganglioneuroma in children: an exploratory study

PURPOSE

To examine the potential of whole-tumor radiomics analysis of T2-weighted imaging (T2WI) in differentiating neuroblastoma (NB) from ganglioneuroblastoma/ganglioneuroma (GNB/GN) in children.

MATERIALS AND METHODS

This study included 102 children with peripheral neuroblastic tumors, comprising 47 NB patients and 55 GNB/GN patients, which were randomly divided into a training group (n = 72) and a test group (n = 30). Radiomics features were extracted from T2WI images, and feature dimensionality reduction was applied. Linear discriminant analysis was used to construct radiomics models, and one-standard error role combined with leave-one-out cross-validation was used to choose the optimal radiomics model with the least predictive error. Subsequently, the patient age at initial diagnosis and the selected radiomics features were incorporated to construct a combined model. The receiver operator characteristic (ROC) curve, decision curve analysis (DCA) and clinical impact curve (CIC) were applied to evaluate the diagnostic performance and clinical utility of the models.

RESULTS

Fifteen radiomics features were eventually chosen to construct the optimal radiomics model. The area under the curve (AUC) of the radiomics model in the training group and test group was 0.940 [95% confidence interval (CI) 0.886, 0.995] and 0.799 (95%CI 0.632, 0.966), respectively. The combined model, which incorporated patient age and radiomics features, achieved an AUC of 0.963 (95%CI 0.925, 1.000) in the training group and 0.871 (95%CI 0.744, 0.997) in the test group. DCA and CIC demonstrated that the radiomics model and combined model could provide benefits at various thresholds, with the combined model being superior to the radiomics model.

CONCLUSION

Radiomics features derived from T2WI, in combination with the age of the patient at initial diagnosis, may offer a quantitative method for distinguishing NB from GNB/GN, thus aiding in the pathological differentiation of peripheral neuroblastic tumors in children.

Contrast-enhanced computed tomography radiomics in predicting primary site response to neoadjuvant chemotherapy in high-risk neuroblastoma

PURPOSE

To explore the clinical value of contrast-enhanced computed tomography (CECT) radiomics in predicting primary site response to neoadjuvant chemotherapy in high-risk neuroblastoma.

MATERIALS AND METHODS

Seventy patients were retrospectively included and separated into very good partial response (VGPR) group and non-VGPR group according to the changes in primary tumor volume. The clinical features with statistical difference between the two groups were used to construct the clinical models using a logistic regression (LR) algorithm. The radiomics models based on different radiomics features selected by Kruskal-Wallis (KW) test and recursive feature elimination (RFE) were established using support vector machine (SVM) and LR algorithms. The radiomics score (Radscore) and clinical features were integrated into the combined models. Leave-one-out cross-validation (LOOCV) was used to validate the predictive performance of models in the entire dataset.

RESULTS

The optimal clinical model achieved an area under the curve (AUC) of 0.767 [95% confidence interval (CI): 0.638, 0.896] and an accuracy of 0.771 after LOOCV. The AUCs of the best KW + SVM, KW + LR, RFE + SVM, and RFE + LR radiomics models were 0.816, 0.826, 0.853, and 0.850, respectively, and the corresponding AUCs after LOOCV were 0.780, 0.785, 0.755, and 0.772, respectively. The AUC and accuracy after LOOCV of the optimal combined model was 0.804 (95% CI: 0.694, 0.915) and 0.814, respectively. The Delong test showed a statistical difference in predictive performance between the optimal clinical and combined models after LOOCV (Z = 2.003, P = 0.045). The decision curve analysis showed that the combined model performs better than the clinical model.

CONCLUSION

The CECT radiomics models have a favorable predictive performance in predicting VGPR of high-risk neuroblastoma to neoadjuvant chemotherapy. When integrating radiomics features and clinical features, the predictive performance of the combined models can be further improved.

Association of image-defined risk factors with clinical features, tumor biology, and outcomes in neuroblastoma: a single-center retrospective study

Image-defined risk factors (IDRF) in neuroblastoma have been developed to predict tumor resectability and surgical complications; however, the potential prognostic value of IDRF in neuroblastoma has been variably reported. Previous studies did not report the IDRF status separately from the International Neuroblastoma Risk Group (INRG) stage. Moreover, the association between IDRF and clinical and pathological factors has not been discussed further. In this retrospective study, we investigated the clinical and biological features of neuroblastoma at different INRG stages based on IDRF. Event-free survival (EFS) and overall survival (OS) related to the INRG stage were analyzed using log-rank tests, and the prognostic value of the IDRF number and type was also evaluated. Among 72 patients, 182 IDRF at diagnosis were found in 79.2%. The distribution of the INRG stages was 10 L1 (13.9.0%), 25 L2 (34.7%), and 37 M/MS (51.4%). Patients with stage M/Ms had a larger tumor volume, a higher percentage of age ≥ 18 months, elevated lactate dehydrogenase (LDH) level, elevated ferritin level, and a higher percentage of COG high-risk compared with stage L1 and L2 patients. EFS and OS were similar for stage L1 and L2 tumors but were significantly poorer for metastatic disease. However, EFS (P = 0.06) and OS (P = 0.07) were similar for IDRF-negative and positive neuroblastomas. Patients with stage M/Ms with IDRF-positive had poorer EFS (P = 0.001) and OS (P < 0.001) compared with patients in stage L2. An IDRF ≥ 4, vascular IDRF, and infiltrative IDRF of the tumor were significant indicators of poor prognosis.   Conclusion: Our study indicates that increasing the INRG stages based on IDRF is associated with various unfavorable clinical features of neuroblastoma. The principal determinant of survival in neuroblastoma is the presence of metastatic disease more than IDRF alone at diagnosis. Both the number and type of IDRF have important clinical significance in the protocol planning of neuroblastoma, rather than just considering the absence or presence of IDRF. What is Known: • The International Neuroblastoma Risk Group Staging System (INRGSS) now employs image-defined risk factors (IDRFs) to stratify and stage disease. • The presence of IDRF at diagnosis are associated with higher rates of operative complications and incomplete surgical resection. What is New: • The principal determinant of survival from neuroblastoma is the presence of metastatic disease at diagnosis, more than IDRF alone. • IDRF number and type should also be considered during the diagnosis and treatment planning of neuroblastoma, rather than just considering the absence or presence of IDRF.

Improved risk stratification by PET-based intratumor heterogeneity in children with high-risk neuroblastoma

PURPOSE

The substratification of high-risk neuroblastoma is challenging, and new predictive imaging biomarkers are warranted for better patient selection. The aim of the study was to evaluate the prognostic role of PET-based intratumor heterogeneity and its potential ability to improve risk stratification in neuroblastoma.

METHODS

Pretreatment 18F-FDG PET/CT scans from 112 consecutive children with newly diagnosed neuroblastoma were retrospectively analyzed. The primary tumor was segmented in the PET images. SUVs, volumetric parameters including metabolic tumor volume (MTV) and total lesion glycolysis (TLG), and texture features were extracted. After the exclusion of imaging features with poor and moderate reproducibility, the relationships between the imaging indices and clinicopathological factors, as well as event-free survival (EFS), were assessed.

RESULTS

The median follow-up duration was 33 months. Multivariate analysis showed that PET-based intratumor heterogeneity outperformed clinicopathological features, including age, stage, and MYCN, and remained the most robust independent predictor for EFS [training set, hazard ratio (HR): 6.4, 95% CI: 3.1-13.2, p < 0.001; test set, HR: 5.0, 95% CI: 1.8-13.6, p = 0.002]. Within the clinical high-risk group, patients with a high metabolic heterogeneity showed significantly poorer outcomes (HR: 3.3, 95% CI: 1.6-6.8, p = 0.002 in the training set; HR: 4.4, 95% CI: 1.5-12.9, p = 0.008 in the test set) compared to those with relatively homogeneous tumors. Furthermore, intratumor heterogeneity outran the volumetric indices (MTVs and TLGs) and yielded the best performance of distinguishing high-risk patients with different outcomes with a 3-year EFS of 6% vs. 47% (p = 0.001) in the training set and 9% vs. 51% (p = 0.004) in the test set.

CONCLUSION

PET-based intratumor heterogeneity was a strong independent prognostic factor in neuroblastoma. In the clinical high-risk group, intratumor heterogeneity further stratified patients with distinct outcomes.

Changes in image-defined risk factors with neoadjuvant chemotherapy in pediatric abdominal neuroblastoma

PURPOSE

To observe the changes in image-defined risk factors (IDRFs) with neoadjuvant chemotherapy in pediatric abdominal neuroblastoma and to investigate the correlations between IDRF changes and histopathological features. In addition, this study also investigated the correlations between residual IDRFs after neoadjuvant chemotherapy and intraoperative complications.

METHODS

Forty-three patients with abdominal neuroblastoma who received neoadjuvant chemotherapy in our hospital from January 2015 to September 2021 were enrolled. Intraoperative records, histopathological features, and CT images at initial diagnosis and after neoadjuvant chemotherapy of all patients were retrospectively collected and analyzed.

RESULTS

A total of 245 IDRFs were found at initial diagnosis, with a median of 6 [5, 7] IDRFs per patient. After neoadjuvant chemotherapy, IDRFs significantly decreased to 156 (p < 0.001), with a median of 4 [3, 5] IDRFs remaining per patient. The majority of IDRFs (6/8, 75.00%) were significantly improved after neoadjuvant chemotherapy (p < 0.05), while tumor invasion of renal pedicles (p > 0.05) and adjacent structures (p > 0.05) was the least responsive IDRF. IDRFs in different types of neuroblastoma decreased significantly after neoadjuvant chemotherapy (p < 0.05), while they were not significant in neuroblastoma with low and intermediate mitosis-karyorrhexis indices (p > 0.05). The number of residual IDRFs correlated positively with the volumes of intraoperative blood loss (r = 0.399, p = 0.008), but not with the presence of intraoperative complications (r = 0.111, p = 0.478).

CONCLUSIONS

IDRFs in different types of neuroblastoma can be significantly improved after neoadjuvant chemotherapy, while IDRFs in neuroblastoma with low and intermediate mitosis-karyorrhexis indices might not be easily improved. At the same time, the number of residual IDRFs after neoadjuvant chemotherapy might not correlate with the occurrence of intraoperative complications in abdominal neuroblastoma.

18F-FDG PET/CT-based radiomics nomogram could predict bone marrow involvement in pediatric neuroblastoma

Objective

To develop and validate an ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT)-based radiomics nomogram for non-invasively prediction of bone marrow involvement (BMI) in pediatric neuroblastoma.

Methods

A total of 133 patients with neuroblastoma were retrospectively included and randomized into the training set (n = 93) and test set (n = 40). Radiomics features were extracted from both CT and PET images. The radiomics signature was developed. Independent clinical risk factors were identified using the univariate and multivariate logistic regression analyses to construct the clinical model. The clinical-radiomics model, which integrated the radiomics signature and the independent clinical risk factors, was constructed using multivariate logistic regression analysis and finally presented as a radiomics nomogram. The predictive performance of the clinical-radiomics model was evaluated by receiver operating characteristic curves, calibration curves and decision curve analysis (DCA).

Results

Twenty-five radiomics features were selected to construct the radiomics signature. Age at diagnosis, neuron-specific enolase and vanillylmandelic acid were identified as independent predictors to establish the clinical model. In the training set, the clinical-radiomics model outperformed the radiomics model or clinical model (AUC: 0.924 vs. 0.900, 0.875) in predicting the BMI, which was then confirmed in the test set (AUC: 0.925 vs. 0.893, 0.910). The calibration curve and DCA demonstrated that the radiomics nomogram had a good consistency and clinical utility.

Conclusion

The ¹⁸F-FDG PET/CT-based radiomics nomogram which incorporates radiomics signature and independent clinical risk factors could non-invasively predict BMI in pediatric neuroblastoma.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-022-01283-8.

CT-based morphologic and radiomics features for the classification of MYCN gene amplification status in pediatric neuroblastoma

PURPOSE

MYCN onco-gene amplification in neuroblastoma confers patients to the high-risk disease category for which prognosis is poor and more aggressive multimodal treatment is indicated. This retrospective study leverages machine learning techniques to develop a computed tomography (CT)-based model incorporating semantic and non-semantic features for non-invasive prediction of MYCN amplification status in pediatric neuroblastoma.

METHODS

From 2009 to 2020, 54 pediatric patients treated for neuroblastoma at a specialized children's hospital with pre-treatment contrast-enhanced CT and MYCN status were identified (training cohort, n = 44; testing cohort, n = 10). Six morphologic features and 107 quantitative gray-level texture radiomics features extracted from manually drawn volume-of-interest were analyzed. Following feature selection and class balancing, the final predictive model was developed with eXtreme Gradient Boosting (XGBoost) algorithm. Accumulated local effects (ALE) plots were used to explore main effects of the predictive features. Tumor texture maps were also generated for visualization of radiomics features.

RESULTS

One morphologic and 2 radiomics features were selected for model building. The XGBoost model from the training cohort yielded an area under the receiver operating characteristics curve (AUC-ROC) of 0.930 (95% CI, 0.85-1.00), optimized F1-score of 0.878, and Matthews correlation coefficient (MCC) of 0.773. Evaluation on the testing cohort returned AUC-ROC of 0.880 (95% CI, 0.64-1.00), optimized F1-score of 0.933, and MCC of 0.764. ALE plots and texture maps showed higher "GreyLevelNonUniformity" values, lower "Strength" values, and higher number of image-defined risk factors contribute to higher predicted probability of MYCN amplification.

CONCLUSION

The machine learning model reliably classified MYCN amplification in pediatric neuroblastoma and shows potential as a surrogate imaging biomarker.

Whole-tumour apparent diffusion coefficient (ADC) histogram analysis to identify MYCN-amplification in neuroblastomas: preliminary results

OBJECTIVES

To determine the role of apparent diffusion coefficient (ADC) histogram analysis in the identification of MYCN-amplification status in neuroblastomas.

METHODS

We retrospectively evaluated imaging records from 62 patients with neuroblastomas (median age: 15 months (interquartile range (IQR): 7-24 months); 38 females) who underwent magnetic resonance imaging at our institution before the initiation of any therapy or biopsy. Fourteen patients had MYCN-amplified (MYCNA) neuroblastoma. Histogram parameters of ADC maps from the entire tumour was obtained from the baseline images and the normalised images. The Mann-Whitney U test was used to compare the absolute and normalised histogram parameters amongst neuroblastomas with and without MYCN-amplification. Receiver operating characteristic (ROC) curves and area under the curves (AUC) were generated for the statistically significant histogram parameters. Cut-offs obtained from the ROC curves were evaluated on an external validation set (n-15, MYCNA-6, F-7, age 24 months (10-60)). A logistic regression model was trained to predict MYCNA by combining statistically significant histogram parameters and was evaluated on the validation set.

RESULTS

MYCN-amplified neuroblastomas had statistically significant higher maximum ADC and lower minimum ADC than non-amplified neuroblastomas. They also demonstrated higher entropy, variance, energy, and lower uniformity than non-amplified neoplasms (p > 0.05). Energy, entropy, and maximum ADC had AUC of 0.85, 0.79, and 0.82, respectively.

CONCLUSIONS

Whole tumour ADC histogram analysis of neuroblastomas can differentiate between tumours with and without MYCN-amplification. These parameters can help identify areas for targeted biopsies or can be used to predict subtypes of these high-risk tumours before biopsy results are available.

KEY POINTS

• MYCN-amplification significantly affects treatment decisions in neuroblastomas. • MYCN-amplified neuroblastomas had significantly different ADC histogram metrics as compared to tumours without amplification. • ADC histogram metrics can be used to predict MYCN-amplification status based on imaging.

Prediction for Mitosis-Karyorrhexis Index Status of Pediatric Neuroblastoma via Machine Learning Based 18F-FDG PET/CT Radiomics

Accurate differentiation of intermediate/high mitosis-karyorrhexis index (MKI) from low MKI is vital for the further management of neuroblastoma. The purpose of this research was to investigate the efficacy of ¹⁸F-FDG PET/CT–based radiomics features for the prediction of MKI status of pediatric neuroblastoma via machine learning. A total of 102 pediatric neuroblastoma patients were retrospectively enrolled and divided into training (68 patients) and validation sets (34 patients) in a 2:1 ratio. Clinical characteristics and radiomics features were extracted by XGBoost algorithm and were used to establish radiomics and clinical models for MKI status prediction. A combined model was developed, encompassing clinical characteristics and radiomics features and presented as a radiomics nomogram. The predictive performance of the models was evaluated by AUC and decision curve analysis. The radiomics model yielded AUC of 0.982 (95% CI: 0.916, 0.999) and 0.955 (95% CI: 0.823, 0.997) in the training and validation sets, respectively. The clinical model yielded AUC of 0.746 and 0.670 in the training and validation sets, respectively. The combined model demonstrated AUC of 0.988 (95% CI: 0.924, 1.000) and 0.951 (95% CI: 0.818, 0.996) in the training and validation sets, respectively. The radiomics features could non-invasively predict MKI status of pediatric neuroblastoma with high accuracy.