Volumetric analysis of IDH-mutant lower-grade glioma: a natural history study of tumor growth rates before and after treatment

Huang, Raymond Y.; Young, Robert J.; Ellingson, Benjamin M.; Veeraraghavan, Harini; Wang, Wei; Tixier, Florent; Um, Hyemin; Nawaz, Rasheed; Luks, Tracy; Kim, John; Gerstner, Elizabeth R.; Schiff, David; Peters, Katherine B.; Mellinghoff, Ingo K.; Chang, Susan M.; Cloughesy, Timothy F.; Wen, Patrick Y.

doi:10.1093/neuonc/noaa105

Cited by 27 publications

(15 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to determining changes in tumor size, other measures of clinical benefit such as changes in neurocognitive function, quality of life and seizures may be useful in assessing the utility of novel therapies. In particular, seizure control has recently been proposed as an additional metric in disease response and as an endpoint in trials for LGGs [25].…”

Section: Rano-low Grade Gliomamentioning

confidence: 99%

Use of the Response Assessment in Neuro-Oncology (RANO) criteria in clinical trials and clinical practice

2019

Self Cite

View full text Add to dashboard Cite

Section: Rano-low Grade Gliomamentioning

confidence: 99%

Use of the Response Assessment in Neuro-Oncology (RANO) criteria in clinical trials and clinical practice

2019

Self Cite

View full text Add to dashboard Cite

“…A recent meta-analysis revealed that Pyradiomics was used in eight human studies and one phantom study, and was the most frequently used software, with others using open-source software (CGITA, MaZda, LifeX, IBEX) and others using Matlab [ 33 ]. In imaging analysis of central nervous system tumors, analyses that employ traditional radiomic analysis have been applied to combine imaging and molecular markers notably O6-methylguanine-DNA methyltransferase (MGMT) [ 74 – 77 ], IDH [ 74 , 78 – 80 ], 1p19q [ 81 , 82 ], H3K27M [ 83 ]. The diagnostic performance of radiomics using ML algorithms to predict MGMT status in glioma patients was the subject of a comprehensive literature search of PubMed, EMBASE, and Web of Science until 27 July 2021 [ 75 ] which identified 15 studies with 1663 patients and documented a pooled sensitivity and specificity of ML for predicting MGMT promoter methylation in gliomas of 85% and 84% in the training cohort (n=15) and 84% and 78% in the validation cohort (n=5) with an AUC of 0.91 in the training cohort and 0.88 in the validation cohort concluding that ML can predict MGMT promoter methylation status in glioma with a higher performance than non-machine learning methods [ 75 ].…”

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

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

“…Novel advanced MRI techniques have been studied receive ongoing attention, but their accuracy is not well known. Recent evidence suggests that tumor volume may be superior for determining response assessment in LGGs due to more stable measures of tumor growth rates allowing for assessment of tumor growth over time with less variability, highest and possibly superior inter-reader agreement, and lowest reader discordance rates [44].The extent and alteration overtime of the T2 FLAIR signal remains a significant challenge in LGG since these tumors are non-enhancing upfront but is also pivotal in HGG since the T2 FLAIR signal is altered by radiation therapy as well other factors [18,22]. Recent evidence when analyzing longitudinal normalized FLAIR images using voxel-wise Parametric Response Mapping (PRM) to monitor volume fractions of increased, decreased, or unchanged altered FLAIR intensity, showed that PRMrFLAIR+ exceeding 10%, stratified patients for at risk of failure after 5.6 months (p<0.0001), while RANO criteria did not stratify these patients until 15.4 months (p <0.0001) [45].…”

Section: Is the Mri The Best Imaging Modality To Examine Progression ...mentioning

confidence: 99%

Using Artificial Intelligence and Magnetic Resonance Imaging to Address Limitations in Response Assessment in Glioma

Krauze

2022

Oncol Insights

View full text Add to dashboard Cite

Gliomas are rapidly progressive, neurologically devastating, nearly uniformly fatal brain tumors. In WHO grade IV tumors like glioblastoma, the standard of care involves maximal surgical resection followed by concurrent radiation therapy (RT) and temozolomide (TMZ) chemotherapy followed by adjuvant TMZ. This results in overall survival (OS) of less than 30% at two years. Currently, tumor progression assessment is based on clinician assessment and MRI interpretation using Response Assessment in Neuro-Oncology (RANO) criteria. These criteria classify response as complete, partial, stable, or progression. This approach, however, suffers from significant limitations due to the difficulty in interpreting MRI findings on T1 gad and T2 FLAIR sequences, lack of concurrent correlation with radiation therapy fields, inconsistent follow-up imaging, concurrent administration of steroids, and systemic management, including immunotherapy. The neuro-oncology field struggles with classifying true progression vs. pseudoprogression vs. pseudoresponse with progression guidelines actively evolving. The lack of consensus on the definition of progression impairs the ability to initiate earlier management upon progression, judge the impact of therapies, and optimize and personalize management. Due to the pivotal role of imaging, radiology is at the center of the question of optimizing and advancing response criteria [1-5]. The hypothesis is that MRI images of patients with glioma, when subjected to change over time analysis (at diagnosis, prior to and post-radiation therapy), can identify features predictive of treatment failure helping guide patient management in the clinic. Likely a combination of imaging and biospecimen-driven biomarkers is needed. Given the large amount of data generated by both approaches, success in this space hinges on leveraging computational approaches and artificial intelligence algorithms validated using large-scale publicly available data sets to disentangle the complexity and heterogeneity inherent in glioma progression.

show abstract

Volumetric analysis of IDH-mutant lower-grade glioma: a natural history study of tumor growth rates before and after treatment

Cited by 27 publications

References 22 publications

Use of the Response Assessment in Neuro-Oncology (RANO) criteria in clinical trials and clinical practice

Use of the Response Assessment in Neuro-Oncology (RANO) criteria in clinical trials and clinical practice

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

Using Artificial Intelligence and Magnetic Resonance Imaging to Address Limitations in Response Assessment in Glioma

Contact Info

Product

Resources

About