Towards consistency in pediatric brain tumor measurements: Challenges, solutions, and the role of artificial intelligence-based segmentation

Familiar, Ariana M; Fathi Kazerooni, Anahita; Vossough, Arastoo; Ware, Jeffrey B; Bagheri, Sina; Khalili, Nastaran; Anderson, Hannah; Haldar, Debanjan; Storm, Phillip B; Resnick, Adam C; Kann, Benjamin H; Aboian, Mariam; Kline, Cassie; Weller, Michael; Huang, Raymond Y; Chang, Susan M; Fangusaro, Jason R; Hoffman, Lindsey M; Mueller, Sabine; Prados, Michael; Nabavizadeh, Ali

doi:10.1093/neuonc/noae093

Cited by 4 publications

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

CAR T cell therapy for pediatric central nervous system tumors: a review of the literature and current North American trials

Ronsley,

Bertrand,

Song

et al. 2024

Cancer Metastasis Rev

View full text Add to dashboard Cite

Central nervous system (CNS) tumors are the leading cause of cancer-related death in children. Typical therapy for CNS tumors in children involves a combination of surgery, radiation, and chemotherapy. While upfront therapy is effective for many high-grade tumors, therapy at the time of relapse remains limited. Furthermore, for diffuse intrinsic pontine glioma (DIPG) and diffuse midline glioma (DMG), there are currently no curative therapies. Chimeric antigen receptor T (CAR T) cell therapy is a promising novel treatment avenue for these tumors. Here, we review the preclinical evidence for CAR T cell use in pediatric brain tumors, the preliminary clinical experience of CNS CAR T cell trials, toxicity associated with systemic and locoregional CAR T cell therapy for CNS tumors, challenges in disease response evaluation with CAR T cell therapy, and the knowledge gained from correlative biologic studies from these trials in the pediatric and young adult population.

show abstract

CAR T cell therapy for pediatric central nervous system tumors: a review of the literature and current North American trials

Ronsley,

Bertrand,

Song

et al. 2024

Cancer Metastasis Rev

View full text Add to dashboard Cite

show abstract

Automated pediatric brain tumor imaging assessment tool from CBTN: Enhancing suprasellar region inclusion and managing limited data with deep learning

Gandhi,

Khalili,

Familiar

et al. 2024

Neuro-Oncology Advances

View full text Add to dashboard Cite

Background Fully-automatic skull-stripping and tumor segmentation are crucial for monitoring pediatric brain tumors (PBT). Current methods, however, often lack generalizability, particularly for rare tumors in the sellar/suprasellar regions and when applied to real-world clinical data in limited data scenarios. To address these challenges, we propose AI-driven techniques for skull-stripping and tumor segmentation . Methods Multi-institutional, multi-parametric MRI scans from 527 pediatric patients (n=336 for skull-stripping, n=489 for tumor segmentation) with various PBT histologies were processed to train separate nnU-Net-based deep learning models for skull-stripping, whole tumor (WT), and enhancing tumor (ET) segmentation. These models utilized single (T2/FLAIR) or multiple (T1-Gd and T2/FLAIR) input imaging sequences. Performance was evaluated using Dice scores, sensitivity, and 95% Hausdorff distances. Statistical comparisons included paired or unpaired two-sample t-tests and Pearson’s correlation coefficient based on Dice scores from different models and PBT histologies. Results Dice scores for the skull-stripping models for whole brain and sellar/suprasellar region segmentation were 0.98±0.01 (median 0.98) for both multi- and single-parametric models, with significant Pearson’s correlation coefficient between single- and multi-parametric Dice scores (r > 0.80; p<0.05 for all). WT Dice scores for single-input tumor segmentation models were 0.84±0.17 (median=0.90) for T2 and 0.82±0.19 (median=0.89) for FLAIR inputs. ET Dice scores were 0.65±0.35 (median=0.79) for T1-Gd+FLAIR and 0.64±0.36 (median=0.79) for T1-Gd+T2 inputs. Conclusion Our skull-stripping models demonstrate excellent performance and include sellar/suprasellar regions, using single- or multi-parametric inputs. Additionally, our automated tumor segmentation models can reliably delineate whole lesions and enhancing tumor regions, adapting to MRI sessions with missing sequences in limited data context.

show abstract

Automated Pediatric Brain Tumor Imaging Assessment Tool from CBTN: Enhancing Suprasellar Region Inclusion and Managing Limited Data with Deep Learning

Gandhi,

Khalili,

Familiar

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Fully-automatic skull-stripping and tumor segmentation are crucial for monitoring pediatric brain tumors (PBT). Current methods, however, often lack generalizability, particularly for rare tumors in the sellar/suprasellar regions and when applied to real-world clinical data in limited data scenarios. To address these challenges, we propose AI-driven techniques for skull-stripping and tumor segmentation. Methods: Multi-institutional, multi-parametric MRI scans from 527 pediatric patients (n=336 for skull-stripping, n=489 for tumor segmentation) with various PBT histologies were processed to train separate nnU-Net-based deep learning models for skull-stripping, whole tumor (WT), and enhancing tumor (ET) segmentation. These models utilized single (T2/FLAIR) or multiple (T1-Gd and T2/FLAIR) input imaging sequences. Performance was evaluated using Dice scores, sensitivity, and 95% Hausdorff distances. Statistical comparisons included paired or unpaired two-sample t-tests and Pearsons correlation coefficient based on Dice scores from different models and PBT histologies. Results: Dice scores for the skull-stripping models for whole brain and sellar/suprasellar region segmentation were 0.98±0.01 (median 0.98) for both multi- and single-parametric models, with significant Pearsons correlation coefficient between single- and multi-parametric Dice scores (r > 0.80; p<0.05 for all). WT Dice scores for single-input tumor segmentation models were 0.84±0.17 (median=0.90) for T2 and 0.82±0.19 (median=0.89) for FLAIR inputs. ET Dice scores were 0.65±0.35 (median=0.79) for T1-Gd+FLAIR and 0.64±0.36 (median=0.79) for T1-Gd+T2 inputs. Conclusion: Our skull-stripping models demonstrate excellent performance and include sellar/suprasellar regions, using single- or multi-parametric inputs. Additionally, our automated tumor segmentation models can reliably delineate whole lesions and enhancing tumor regions, adapting to MRI sessions with missing sequences in limited data context.

show abstract

Towards consistency in pediatric brain tumor measurements: Challenges, solutions, and the role of artificial intelligence-based segmentation

Cited by 4 publications

References 83 publications

CAR T cell therapy for pediatric central nervous system tumors: a review of the literature and current North American trials

CAR T cell therapy for pediatric central nervous system tumors: a review of the literature and current North American trials

Automated pediatric brain tumor imaging assessment tool from CBTN: Enhancing suprasellar region inclusion and managing limited data with deep learning

Automated Pediatric Brain Tumor Imaging Assessment Tool from CBTN: Enhancing Suprasellar Region Inclusion and Managing Limited Data with Deep Learning

Contact Info

Product

Resources

About