Comparison of Radiomics-Based Machine-Learning Classifiers in Diagnosis of Glioblastoma From Primary Central Nervous System Lymphoma

Chen, Chaoyue; Zheng, Aiping; Ou, Xuejin; Wang, Jian; Ma, Xuelei

doi:10.3389/fonc.2020.01151

Cited by 30 publications

(32 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Increasingly data is evolving showing that ML-based imaging analysis is vulnerable to feature selection [ 61 , 63 ]. In a recent study where radiomics-based ML algorithms in Differentiating Glioblastoma (GBM) from primary central nervous system lymphoma (PCNSL) were evaluated, 5 selection methods (distance correlation, random forest, Least Absolute Shrinkage and Selection Operator (LASSO), eXtreme gradient boosting (Xgboost), and Gradient Boosting Decision Tree) and 3 radiomics-based ML classifiers Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and Logistic Regression (LR)) were compared [ 63 ]. The authors noted that the most optimal discriminative performance was observed among all classifiers when combined with the suitable selection method.…”

Section: Segmentationmentioning

confidence: 99%

“…For LDA-based models, the optimal one was Distance Correlation + LDA with AUC of 0.978. For SVM-based models, Distance Correlation + SVM was the one with highest AUC of 0.959, while for LR-based models, the highest AUC was 0.966 established with LASSO + LR [ 63 ]. In a literature review spanning 2013 to 2018, LR and LASSO were the two most used techniques for feature selection [ 64 ].…”

Section: Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models

AV¹,

Zhuge²,

Zhao³

et al. 2022

J Biotechnol Biomed

View full text Add to dashboard Cite

The interpretation of imaging in medicine in general and in oncology specifically remains problematic due to several limitations which include the need to incorporate detailed clinical history, patient and disease-specific history, clinical exam features, previous and ongoing treatment, and account for the dependency on reproducible human interpretation of multiple factors with incomplete data linkage. To standardize reporting, minimize bias, expedite management, and improve outcomes, the use of Artificial Intelligence (AI) has gained significant prominence in imaging analysis. In oncology, AI methods have as a result been explored in most cancer types with ongoing progress in employing AI towards imaging for oncology treatment, assessing treatment response, and understanding and communicating prognosis. Challenges remain with limited available data sets, variability in imaging changes over time augmented by a growing heterogeneity in analysis approaches. We review the imaging analysis workflow and examine how hand-crafted features also referred to as traditional Machine Learning (ML), Deep Learning (DL) approaches, and hybrid analyses, are being employed in AI-driven imaging analysis in central nervous system tumors. ML, DL, and hybrid approaches coexist, and their combination may produce superior results although data in this space is as yet novel, and conclusions and pitfalls have yet to be fully explored. We note the growing technical complexities that may become increasingly separated from the clinic and enforce the acute need for clinician engagement to guide progress and ensure that conclusions derived from AI-driven imaging analysis reflect that same level of scrutiny lent to other avenues of clinical research.

show abstract

Section: Segmentationmentioning

confidence: 99%

Section: Segmentationmentioning

confidence: 99%

AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models

AV¹,

Zhuge²,

Zhao³

et al. 2022

J Biotechnol Biomed

View full text Add to dashboard Cite

show abstract

“…The feature selection and model-building methods vary significantly among studies (see Table S1), and in some cases, the models include clinical or semantic variables. MRI sequences used for tumor differentiation vary as well and have, for example, CE T1 sequences only [46,52,54] as well as combinations of ADC and T1CE [55]; ADC, FLAIR, and CE T1 [47]; DWI, CE T1, and FLAIR [48]; CE T1, T2 and DWI [50]; T1, T2, and FLAIR [51,56]; or ADC and gradientecho [15]. A study involving 141 patients reported over 90% accuracy in differentiation between various tumor entities, including GBM, lymphoma, BM, and meningioma, using five MRI sequences in total [15].…”

Section: Primary Cns Lymphomamentioning

confidence: 99%

Beyond Glioma: The Utility of Radiomic Analysis for Non-Glial Intracranial Tumors

Kalasauskas

Kosterhon

Keric

et al. 2022

Cancers

View full text Add to dashboard Cite

The field of radiomics is rapidly expanding and gaining a valuable role in neuro-oncology. The possibilities related to the use of radiomic analysis, such as distinguishing types of malignancies, predicting tumor grade, determining the presence of particular molecular markers, consistency, therapy response, and prognosis, can considerably influence decision-making in medicine in the near future. Even though the main focus of radiomic analyses has been on glial CNS tumors, studies on other intracranial tumors have shown encouraging results. Therefore, as the main focus of this review, we performed an analysis of publications on PubMed and Web of Science databases, focusing on radiomics in CNS metastases, lymphoma, meningioma, medulloblastoma, and pituitary tumors.

show abstract

“…A recent meta-analysis assessing the utility of ML models for PCNSL diagnosis reports 0.878 as the lowest AUC across eight studies [61]. Another prospectively validated model reported an AUC of 0.978 using only T1 weighted images [62]. ML-based algorithms have advantages of being open access, easily accessible, and minimal reliance on novel machines or software.…”

Section: Machine Learning: Better Analysis Of Conventional Mri Meta-datamentioning

confidence: 99%

Primary Central Nervous System Lymphoma: Focus on Indian Perspective

Pandey¹,

Biswas²,

Baghmar³

et al. 2022

Lymphoma

View full text Add to dashboard Cite

Early suspicion, withholding steroids, stereotactic biopsy, and high-dose methotrexate (HD-MTX) are essential for the treatment of primary CNS lymphoma (PCNSL) making its management in lower-middle-income countries (LMIC) challenging. Novel radiological methods, clinician awareness about the disease, and utilization of drugs like thiotepa and ibrutinib which can be given on an outpatient basis may allow better management of these patients in resource-poor settings. Combined with a late presenting demographic, this results in poorer outcomes in the Indian subcontinent as compared to its western counterparts. In this review, we summarize the currently available data on PCNSL in the Indian subcontinent. We also review the current standard of care for PCNSL and present potential modifications or research areas that may potentially improve outcomes in LMIC.

show abstract

Comparison of Radiomics-Based Machine-Learning Classifiers in Diagnosis of Glioblastoma From Primary Central Nervous System Lymphoma

Cited by 30 publications

References 26 publications

AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models

AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models

Beyond Glioma: The Utility of Radiomic Analysis for Non-Glial Intracranial Tumors

Primary Central Nervous System Lymphoma: Focus on Indian Perspective

Contact Info

Product

Resources

About