A magnetic resonance imaging based radiomics model to predict mitosis cycles in intracranial meningioma

Krähling, Hermann; Musigmann, Manfred; Akkurt, Burak Han; Sartoretti, Thomas; Sartoretti, Elisabeth; Henssen, Dylan; Stummer, Walter; Heindel, Walter; Brokinkel, Benjamin; Mannil, Manoj

doi:10.1038/s41598-023-28089-y

Cited by 3 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Ari et al showed that radiomic-based machine learning can be used to non-invasively predict pseudoprogression in high-grade gliomas [2]. Krähling et al developed an MRI-based radiomics model to predict mitotic cycles in intracranial meningiomas before surgery [3]. In Musigmann et al, it was shown that ML algorithms can predict possible total and subtotal resections of skull meningiomas using pre-treatment T1 post-contrast MR images [4].…”

Section: Introductionmentioning

confidence: 99%

Use Test of Automated Machine Learning in Cancer Diagnostics

et al. 2023

Self Cite

View full text Add to dashboard Cite

Our aim is to investigate the added value of automated machine learning (AutoML) for potential future applications in cancer diagnostics. Using two important diagnostic questions, the non-invasive determination of IDH mutation status and ATRX status, we analyze whether it is possible to use AutoML to develop models that are comparable in performance to conventional machine learning models (ML) developed by experts. For this purpose, we develop AutoML models using different feature preselection methods and compare the results with previously developed conventional ML models. The cohort used for our study comprises T2-weighted MRI images of 124 patients with histologically confirmed gliomas. Using AutoML, we were able to develop sophisticated models in a very short time with only a few lines of computer code. In predicting IDH mutation status, we obtained a mean AUC of 0.7400 and a mean AUPRC of 0.8582. ATRX mutation status was predicted with very similar discriminatory power, with a mean AUC of 0.7810 and a mean AUPRC of 0.8511. In both cases, AutoML was even able to achieve a discriminatory power slightly above that of the respective conventionally developed models in a very short computing time, thus making such methods accessible to non-experts in the near future.

show abstract

Section: Introductionmentioning

confidence: 99%

Use Test of Automated Machine Learning in Cancer Diagnostics

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

Intracranial meningioma: A review of recent and emerging data on the utility of preoperative imaging for management

Beutler,

Lee,

Edminster

et al. 2024

Journal of Neuroimaging

View full text Add to dashboard Cite

Meningiomas are the most common neoplasms of the central nervous system, accounting for approximately 40% of all brain tumors. Surgical resection represents the mainstay of management for symptomatic lesions. Preoperative planning is largely informed by neuroimaging, which allows for evaluation of anatomy, degree of parenchymal invasion, and extent of peritumoral edema. Recent advances in imaging technology have expanded the purview of neuroradiologists, who play an increasingly important role in meningioma diagnosis and management. Tumor vascularity can now be determined using arterial spin labeling and dynamic susceptibility contrast‐enhanced sequences, allowing the neurosurgeon or neurointerventionalist to assess patient candidacy for preoperative embolization. Meningioma consistency can be inferred based on signal intensity; emerging machine learning technologies may soon allow radiologists to predict consistency long before the patient enters the operating room. Perfusion imaging coupled with magnetic resonance spectroscopy can be used to distinguish meningiomas from malignant meningioma mimics. In this comprehensive review, we describe key features of meningiomas that can be established through neuroimaging, including size, location, vascularity, consistency, and, in some cases, histologic grade. We also summarize the role of advanced imaging techniques, including magnetic resonance perfusion and spectroscopy, for the preoperative evaluation of meningiomas. In addition, we describe the potential impact of emerging technologies, such as artificial intelligence and machine learning, on meningioma diagnosis and management. A strong foundation of knowledge in the latest meningioma imaging techniques will allow the neuroradiologist to help optimize preoperative planning and improve patient outcomes.

show abstract

Machine Learning on MRI Radiomic Features to Assess Recurrence Risk in High-grade Meningiomas

Chen,

Hao,

Zhang

2024

Preprint

View full text Add to dashboard Cite

Purpose We used radiomics-based machine learning (ML) of T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (T1C) for assessing relapse risk in patients with high-grade meningiomas (HGMs). Methods 279 features were extracted from each ROI. The datasets were randomly divided into two groups, the training set (∼70%) and the test set (∼30%). Data of 192 individuals were used for external validation. Combinations of data preprocessing methods, including normalization (Min-Max, Z-score, Mean) and dimensionality reduction (Pearson Correlation Coefficients (PCC)), and feature selector (max-Number, cluster) were analyzed for their prediction performance (totaling to 60 combinations). Kaplan–Meier curve, Cox proportional hazards regression model were used and concordance index (C-index), integrated Brier score (IBS) were selected. Results WHO grade, age, gender, histogram (Mean, Perc.90%, Perc.99%), Gray-level co-occurrence matrix (S(3, -3)DifVarnc, S(5, 5)Correlat, S(1, 0)SumEntrp, S(2, -2)InvDfMom), Teta1, WavEnLL_s-2 and GrVariance were identified as the significant recurrence factors. The pipeline using Mean_PCC_Cluster_10 of T1C yielded the highest efficiency with an IBS of 0.170, 0.188, 0.208 and C-index of 0.709, 0.705, 0.602 in the train, test and validation sets, respectively. The pipeline using MinMax_PCC_Cluster_19 of T2WI yielded the highest efficiency with an IBS of 0.189, 0.175, 0.185 and C-index of 0.783, 0.66, 0.649 in the train, test and validation sets. The pipeline using MinMax_PCC_Cluster_13 of T2WI + T1C yielded the highest efficiency with an IBS of 0.152, 0.164, 0.191 and C-index of 0.701, 0.656, 0.593 in the train, test and validation sets, respectively. Conclusion Machine learning on MRI radiomic features can slightly help predict recurrence risk in HGMs. T2WI or T1C yielded better efficiency than T2WI + T1C. The parameters with the best power were Mean, Perc.99%, WavEnLL_s-2, Teta1 and GrVariance.

show abstract

A magnetic resonance imaging based radiomics model to predict mitosis cycles in intracranial meningioma

Cited by 3 publications

References 28 publications

Use Test of Automated Machine Learning in Cancer Diagnostics

Use Test of Automated Machine Learning in Cancer Diagnostics

Intracranial meningioma: A review of recent and emerging data on the utility of preoperative imaging for management

Machine Learning on MRI Radiomic Features to Assess Recurrence Risk in High-grade Meningiomas

Contact Info

Product

Resources

About