Radiomics-based machine learning models for prediction of medulloblastoma subgroups: a systematic review and meta-analysis of the diagnostic test performance

The intersections between neuroscience and medulloblastoma

Medulloblastoma (MB) represents the most common malignant central nervous system tumor in childhood. The nervous system plays a critical role in the progression of MB, with interactions between the nervous system and cancer significantly influencing oncogenesis, tumor growth, invasion, stemness, and metabolism. These interactions also regulate angiogenesis, metastatic dissemination, the tumor immune microenvironment, and drug resistance. Investigating the nervous system-MB axis holds promise for identifying diagnostic markers, prognostic biomarkers, and therapeutic targets. It also provides insights into the molecular mechanisms underlying MB and informs the development of novel therapeutic strategies. This review summarizes the latest advancements in understanding the interplay between the nervous system and MB, including the role of glial cells in MB and the potential of drug repurposing targeting nervous system components for MB treatment. These findings underscore promising diagnostic and therapeutic opportunities for MB management. Additionally, we outline future research directions in neurosciences that may pave the way for innovative therapeutic approaches and deepen our understanding of this complex disease.

A Machine Learning Model for Predicting Prognosis in HCC Patients With Diabetes After TACE

Purpose

Type II diabetes mellitus (T2DM) has been found to increase the mortality of patients with hepatocellular carcinoma (HCC). Therefore, this study aimed to establish and validate a machine learning-based explainable prediction model of prognosis in patients with HCC and T2DM undergoing transarterial chemoembolization (TACE).

Patients and Methods

The prediction model was developed using data from the derivation cohort comprising patients from three medical centers, followed by external validation utilizing patient data extracted from another center. Further, five predictive models were employed to establish prognosis models for 1-, 2-, and 3-year survival, respectively. Prediction performance was assessed by the receiver operating characteristic (ROC), calibration, and decision curve analysis curves. Lastly, the SHapley Additive exPlanations (SHAP) method was used to interpret the final ML model.

Results

A total of 636 patients were included. Thirteen variables were selected for the model development. The final random survival forest (RSF) model exhibited excellent performance in the internal validation cohort, with areas under the ROC curve (AUCs) of 0.824, 0.853, and 0.810 in the 1-, 2-, and 3-year survival groups, respectively. This model also demonstrated remarkable discrimination in the external validation cohort, achieving AUCs of 0.862, 0.815, and 0.798 in the 1-, 2-, and 3-year survival groups, respectively. SHAP summary plots were also created to interpret the RSF model.

Conclusion

An RSF model with good predictive performance was developed by incorporating simple parameters. This prognostic prediction model may assist physicians in early clinical intervention and improve prognosis outcomes in patients with HCC and comorbid T2DM after TACE.

Advanced imaging techniques and non-invasive biomarkers in pediatric brain tumors: state of the art

In the pediatric age group, brain neoplasms are the second most common tumor category after leukemia, with an annual incidence of 6.13 per 100,000. Conventional MRI sequences, complemented by CT whenever necessary, are fundamental for the initial diagnosis and surgical planning as well as for post-operative evaluations, assessment of response to treatment, and surveillance; however, they have limitations, especially concerning histopathologic or biomolecular phenotyping and grading. In recent years, several advanced MRI sequences, including diffusion-weighted imaging, diffusion tensor imaging, arterial spin labelling (ASL) perfusion, and MR spectroscopy, have emerged as a powerful aid to diagnosis as well as prognostication; furthermore, other techniques such as diffusion kurtosis, amide proton transfer imaging, and MR elastography are being translated from the research environment to clinical practice. Molecular imaging, especially PET with amino-acid tracers, complement MRI in several aspects, including biopsy targeting and outcome prediction. Finally, radiomics with radiogenomics are opening entirely new perspectives for a quantitative approach aiming at identifying biomarkers that can be used for personalized, precision management strategies.

A Pilot Project to Promote Research Competency in Medical Students Through Journal Clubs: Mixed Methods Study

Background

Undergraduate medical students often lack hands-on research experience and fundamental scientific research skills, limiting their exposure to the practical aspects of scientific investigation. The Cerrahpasa Neuroscience Society introduced a program to address this deficiency and facilitate student-led research.

Objective

The primary goal of this initiative was to enhance medical students' research output by enabling them to generate and publish peer-reviewed papers within the framework of this pilot project. The project aimed to provide an accessible, global model for research training through structured journal clubs, mentorship from experienced peers, and resource access.

Methods

In January 2022, a total of 30 volunteer students from various Turkish medical schools participated in this course-based undergraduate research experience program. Students self-organized into 2 groups according to their preferred study type: original research or systematic review. Two final-year students with prior research experience led the project, developing training modules using selected materials. The project was implemented entirely online, with participants completing training modules before using their newly acquired theoretical knowledge to perform assigned tasks.

Results

Based on student feedback, the project timeline was adjusted to allow for greater flexibility in meeting deadlines. Despite these adjustments, participants successfully completed their tasks, applying the theoretical knowledge they had gained to their respective assignments. As of April 2024, the initiative has culminated in 3 published papers and 3 more under peer review. The project has also seen an increase in student interest in further involvement and self-paced learning.

Conclusions

This initiative leverages globally accessible resources for research training, effectively fostering research competency among participants. It has successfully demonstrated the potential for undergraduates to contribute to medical research output and paved the way for a self-sustaining, student-led research program. Despite some logistical challenges, the project provided valuable insights for future implementations, showcasing the potential for students to engage in meaningful, publishable research.

Artificial intelligence in predicting recurrence after first-line treatment of liver cancer: a systematic review and meta-analysis

BACKGROUND

The aim of this study was to conduct a systematic review and meta-analysis to comprehensively evaluate the performance and methodological quality of artificial intelligence (AI) in predicting recurrence after single first-line treatment for liver cancer.

METHODS

A rigorous and systematic evaluation was conducted on the AI studies related to recurrence after single first-line treatment for liver cancer, retrieved from the PubMed, Embase, Web of Science, Cochrane Library, and CNKI databases. The area under the curve (AUC), sensitivity (SENC), and specificity (SPEC) of each study were extracted for meta-analysis.

RESULTS

Six percutaneous ablation (PA) studies, 16 surgical resection (SR) studies, and 5 transarterial chemoembolization (TACE) studies were included in the meta-analysis for predicting recurrence after hepatocellular carcinoma (HCC) treatment, respectively. Four SR studies and 2 PA studies were included in the meta-analysis for recurrence after intrahepatic cholangiocarcinoma (ICC) and colorectal cancer liver metastasis (CRLM) treatment. The pooled SENC, SEPC, and AUC of AI in predicting recurrence after primary HCC treatment via PA, SR, and TACE were 0.78, 0.90, and 0.92; 0.81, 0.77, and 0.86; and 0.73, 0.79, and 0.79, respectively. The values for ICC treated with SR and CRLM treated with PA were 0.85, 0.71, 0.86 and 0.69, 0.63,0.74, respectively.

CONCLUSION

This systematic review and meta-analysis demonstrates the comprehensive application value of AI in predicting recurrence after a single first-line treatment of liver cancer, with satisfactory results, indicating the clinical translation potential of AI in predicting recurrence after liver cancer treatment.

Application of Machine Learning for Classification of Brain Tumors: A Systematic Review and Meta-Analysis

BACKGROUND

Classifying brain tumors accurately is crucial for treatment and prognosis. Machine learning (ML) shows great promise in improving tumor classification accuracy. This study evaluates ML algorithms for differentiating various brain tumor types.

METHODS

A systematic review and meta-analysis were conducted, searching PubMed, Embase, and Web of Science up to March 14, 2023. Studies that only investigated image segmentation accuracy or brain tumor detection instead of classification were excluded. We extracted binary diagnostic accuracy data, constructing contingency tables to derive sensitivity and specificity.

RESULTS

Fifty-one studies were included. The pooled area under the curve for glioblastoma versus lymphoma and low-grade versus high-grade gliomas were 0.99 (95% confidence interval [CI]: 0.98-1.00) and 0.89, respectively. The pooled sensitivity and specificity for benign versus malignant tumors were 0.90 (95% CI: 0.85-0.93) and 0.93 (95% CI: 0.90-0.95), respectively. The pooled sensitivity and specificity for low-grade versus high-grade gliomas were 0.99 (95% CI: 0.97-1.00) and 0.94, (95% CI: 0.79-0.99), respectively. Primary versus metastatic tumor identification yields sensitivity and specificity of 0.89, (95% CI: 0.83-0.93) and 0.87 (95% CI: 0.82-0.91), correspondingly. The differentiation of gliomas from pituitary tumors yielded the highest results among primary brain tumor classifications: sensitivity of 0.99 (95% CI: 0.99-1.00) and specificity of 0.99 (95% CI: 0.98-1.00).

CONCLUSIONS

ML demonstrated excellent performance in classifying brain tumor images, with near-maximum area under the curves, sensitivity, and specificity.

Exploring the Methodological Approaches of Studies on Radiographic Databases Used in Cariology to Feed Artificial Intelligence: A Systematic Review

INTRODUCTION

A growing number of studies on diagnostic imaging show superior efficiency and accuracy of computer-aided diagnostic systems compared to those of certified dentists. This methodological systematic review aimed to evaluate the different methodological approaches used by studies focusing on machine learning and deep learning that have used radiographic databases to classify, detect, and segment dental caries.

METHODS

The protocol was registered in PROSPERO before data collection (CRD42022348097). Literature research was performed in MEDLINE, Embase, IEEE Xplore, and Web of Science until December 2022, without language restrictions. Studies and surveys using a dental radiographic database for the classification, detection, or segmentation of carious lesions were sought. Records deemed eligible were retrieved and further assessed for inclusion by two reviewers who resolved any discrepancies through consensus. A third reviewer was consulted when any disagreements or discrepancies persisted between the two reviewers. After data extraction, the same reviewers assessed the methodological quality using the CLAIM and QUADAS-AI checklists.

RESULTS

After screening 325 articles, 35 studies were eligible and included. The bitewing was the most commonly used radiograph (n = 17) at the time when detection (n = 15) was the most explored computer vision task. The sample sizes used ranged from 95 to 38,437, while the augmented training set ranged from 300 to 315,786. Convolutional neural network was the most commonly used model. The mean completeness of CLAIM items was 49% (SD ± 34%). The applicability of the CLAIM checklist items revealed several weaknesses in the methodology of the selected studies: most of the studies were monocentric, and only 9% of them used an external test set when evaluating the model's performance. The QUADAS-AI tool revealed that only 43% of the studies included in this systematic review were at low risk of bias concerning the standard reference domain.

CONCLUSION

This review demonstrates that the overall scientific quality of studies conducted to feed artificial intelligence algorithms is low. Some improvement in the design and validation of studies can be made with the development of a standardized guideline for the reproducibility and generalizability of results and, thus, their clinical applications.

Newly Recognized Genetic Tumor Syndromes of the CNS in the 5th WHO Classification: Imaging Overview with Genetic Updates

The nervous system is commonly involved in a wide range of genetic tumor-predisposition syndromes. The classification of genetic tumor syndromes has evolved during the past years; however, it has now become clear that these syndromes can be categorized into a relatively small number of major mechanisms, which form the basis of the new 5th edition of the World Health Organization book (beta online version) on genetic tumor syndromes. For the first time, the World Health Organization has also included a separate chapter on genetic tumor syndromes in the latest edition of all the multisystem tumor series, including the 5th edition of CNS tumors. Our understanding of these syndromes has evolved rapidly since the previous edition (4th edition, 2016) with recognition of 8 new syndromes, including the following: Elongator protein complex-medulloblastoma syndrome, BRCA1-associated protein 1 tumor-predisposition syndrome, DICER1 syndrome, familial paraganglioma syndrome, melanoma-astrocytoma syndrome, Carney complex, Fanconi anemia, and familial retinoblastoma. This review provides a description of these new CNS tumor syndromes with a focus on imaging and genetic characteristics.

Clinico-Radiological Outcomes in WNT-Subgroup Medulloblastoma

Medulloblastoma (MB) comprises four broad molecular subgroups, namely wingless (WNT), sonic hedgehog (SHH), Group 3, and Group 4, respectively, with subgroup-specific developmental origins, unique genetic profiles, distinct clinico-demographic characteristics, and diverse clinical outcomes. This is a retrospective audit of clinical outcomes in molecularly confirmed WNT-MB patients treated with maximal safe resection followed by postoperative standard-of-care risk-stratified adjuvant radio(chemo)therapy at a tertiary-care comprehensive cancer centre. Of the 74 WNT-MB patients registered in a neuro-oncology unit between 2004 to 2020, 7 patients accrued on a prospective clinical trial of treatment deintensification were excluded, leaving 67 patients that constitute the present study cohort. The median age at presentation was 12 years, with a male preponderance (2:1). The survival analysis was restricted to 61 patients and excluded 6 patients (1 postoperative mortality plus 5 without adequate details of treatment or outcomes). At a median follow-up of 72 months, Kaplan-Meier estimates of 5-year progression-free survival and overall survival were 87.7% and 91.2%, respectively. Traditional high-risk features, large residual tumour (≥1.5 cm2), and leptomeningeal metastases (M+) did not significantly impact upon survival in this molecularly characterized WNT-MB cohort treated with risk-stratified contemporary multimodality therapy. The lack of a prognostic impact of conventional high-risk features suggests the need for refined risk stratification and potential deintensification of therapy.

Prognosis Individualized: Survival predictions for WHO grade II and III gliomas with a machine learning-based web application

WHO grade II and III gliomas demonstrate diverse biological behaviors resulting in variable survival outcomes. In the context of glioma prognosis, machine learning (ML) approaches could facilitate the navigation through the maze of factors influencing survival, aiding clinicians in generating more precise and personalized survival predictions. Here we report the utilization of ML models in predicting survival at 12, 24, 36, and 60 months following grade II and III glioma diagnosis. From the National Cancer Database, we analyze 10,001 WHO grade II and 11,456 grade III cranial gliomas. Using the area under the receiver operating characteristic (AUROC) values, we deploy the top-performing models in a web application for individualized predictions. SHapley Additive exPlanations (SHAP) enhance the interpretability of the models. Top-performing predictive models are the ones built with LightGBM and Random Forest algorithms. For grade II gliomas, the models yield AUROC values ranging from 0.813 to 0.896 for predicting mortality across different timeframes, and for grade III gliomas, the models yield AUROCs ranging from 0.855 to 0.878. ML models provide individualized survival forecasts for grade II and III glioma patients across multiple clinically relevant time points. The user-friendly web application represents a pioneering digital tool to potentially integrate predictive analytics into neuro-oncology clinical practice, to empower prognostication and personalize clinical decision-making.

MBMethPred: a computational framework for the accurate classification of childhood medulloblastoma subgroups using data integration and AI-based approaches

Childhood medulloblastoma is a malignant form of brain tumor that is widely classified into four subgroups based on molecular and genetic characteristics. Accurate classification of these subgroups is crucial for appropriate treatment, monitoring plans, and targeted therapies. However, misclassification between groups 3 and 4 is common. To address this issue, an AI-based R package called MBMethPred was developed based on DNA methylation and gene expression profiles of 763 medulloblastoma samples to classify subgroups using machine learning and neural network models. The developed prediction models achieved a classification accuracy of over 96% for subgroup classification by using 399 CpGs as prediction biomarkers. We also assessed the prognostic relevance of prediction biomarkers using survival analysis. Furthermore, we identified subgroup-specific drivers of medulloblastoma using functional enrichment analysis, Shapley values, and gene network analysis. In particular, the genes involved in the nervous system development process have the potential to separate medulloblastoma subgroups with 99% accuracy. Notably, our analysis identified 16 genes that were specifically significant for subgroup classification, including EP300, CXCR4, WNT4, ZIC4, MEIS1, SLC8A1, NFASC, ASCL2, KIF5C, SYNGAP1, SEMA4F, ROR1, DPYSL4, ARTN, RTN4RL1, and TLX2. Our findings contribute to enhanced survival outcomes for patients with medulloblastoma. Continued research and validation efforts are needed to further refine and expand the utility of our approach in other cancer types, advancing personalized medicine in pediatric oncology.

Advancing personalized prognosis in atypical and anaplastic meningiomas through interpretable machine learning models

PURPOSE

The primary purpose of this study was to utilize machine learning (ML) models to create a web application that can predict survival outcomes for patients diagnosed with atypical and anaplastic meningiomas.

METHODS

In this retrospective cohort study, patients diagnosed with WHO grade II and III meningiomas were selected from the National Cancer Database (NCDB) to analyze survival outcomes at 12, 36, and 60 months. Five machine learning algorithms - TabPFN, TabNet, XGBoost, LightGBM, and Random Forest were employed and optimized using the Optuna library for hyperparameter tuning. The top-performing models were then deployed into our web-based application.

RESULTS

From the NCDB, 12,197 adult patients diagnosed with histologically confirmed WHO grade II and III meningiomas were retrieved. The mean age was 61 (± 20), and 6,847 (56.1%) of these were females. Performance evaluation indicated that the top-performing models for each outcome were the models built with the TabPFN algorithm. The TabPFN models yielded area under the receiver operating characteristic (AUROC) values of 0.805, 0.781, and 0.815 in predicting 12-, 36-, and 60-month mortality, respectively.

CONCLUSION

With the continuous growth of neuro-oncology data, ML algorithms act as key tools in predicting survival outcomes for WHO grade II and III meningioma patients. By incorporating these interpretable models into a web application, we can practically utilize them to improve risk evaluation and prognosis for meningioma patients.

Preoperative prediction of sonic hedgehog and group 4 molecular subtypes of pediatric medulloblastoma based on radiomics of multiparametric MRI combined with clinical parameters

Purpose

To construct a machine learning model based on radiomics of multiparametric magnetic resonance imaging (MRI) combined with clinical parameters for predicting Sonic Hedgehog (SHH) and Group 4 (G4) molecular subtypes of pediatric medulloblastoma (MB).

Methods

The preoperative MRI images and clinical data of 95 patients with MB were retrospectively analyzed, including 47 cases of SHH subtype and 48 cases of G4 subtype. Radiomic features were extracted from T1-weighted imaging (T1), contrast-enhanced T1 weighted imaging (T1c), T2-weighted imaging (T2), T2 fluid-attenuated inversion recovery imaging (T2FLAIR), and apparent diffusion coefficient (ADC) maps, using variance thresholding, SelectKBest, and Least Absolute Shrinkage and Selection Operator (LASSO) regression algorithms. The optimal features were filtered using LASSO regression, and a logistic regression (LR) algorithm was used to build a machine learning model. The receiver operator characteristic (ROC) curve was plotted to evaluate the prediction accuracy, and verified by its calibration, decision and nomogram. The Delong test was used to compare the differences between different models.

Results

A total of 17 optimal features, with non-redundancy and high correlation, were selected from 7,045 radiomics features, and used to build an LR model. The model showed a classification accuracy with an under the curve (AUC) of 0.960 (95% CI: 0.871-1.000) in the training cohort and 0.751 (95% CI: 0.587-0.915) in the testing cohort, respectively. The location of the tumor, pathological type, and hydrocephalus status of the two subtypes of patients differed significantly (p < 0.05). When combining radiomics features and clinical parameters to construct the combined prediction model, the AUC improved to 0.965 (95% CI: 0.898-1.000) in the training cohort and 0.849 (95% CI: 0.695-1.000) in the testing cohort, respectively. There was a significant difference in the prediction accuracy, as measured by AUC, between the testing cohorts of the two prediction models, which was confirmed by Delong's test (p = 0.0144). Decision curves and nomogram further validate that the combined model can achieve net benefits in clinical work.

Conclusion

The combined prediction model, constructed based on radiomics of multiparametric MRI and clinical parameters can potentially provide a non-invasive clinical approach to predict SHH and G4 molecular subtypes of MB preoperatively.