Anahita Fathi Kazerooni

Assistant Professor

University of Pennsylvania
Country flagUnited States
ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (4)

Background Cancers show heterogeneity at various levels, from genome to radiological imaging. This study aimed to explore the interplay between genomic, transcriptomic, and radiophenotypic data in pediatric low-grade glioma (pLGG), the most common group of brain tumors in children. Methods We analyzed data from 201 pLGG patients in the Children’s Brain Tumor Network (CBTN), using principal component analysis and K-Means clustering on 881 radiomic features, along with clinical variables (age, sex, tumor location), to identify imaging clusters and examine their association with 2021 WHO pLGG classifications. To determine the transcriptome pathways linked to imaging clusters, we employed a supervised machine learning model with elastic net logistic regression based on the pathways identified through gene set enrichment and gene co-expression network analyses. Results Three imaging clusters with distinct radiomic characteristics were identified. BRAF V600E mutations were primarily found in imaging cluster 3, while KIAA1549::BRAF fusion occurred in subtype 1. The model’s predictive accuracy (AUC) was 0.77 for subtype 1, 0.78 for subtype 2, and 0.70 for subtype 3. Each imaging cluster exhibited unique molecular mechanisms: subtype 1 was linked to oxidative phosphorylation, PDGFRB , and interleukin signaling, whereas subtype 3 was associated with histone acetylation and DNA methylation pathways, related to BRAF V600E pLGGs. Conclusions Our radiogenomics study indicates that the intrinsic molecular characteristics of tumors correlate with distinct imaging subgroups in pLGG, paving the way for future multi-modal investigations that may enhance understanding of disease progression and targetability.

Year:

2024

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 2-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 < .05 for all). Whole tumor 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. Enhancing tumor 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 ET regions, adapting to MRI sessions with missing sequences in limited data context.

Year:

2024

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. Brief key points: Deep learning models for skull-stripping, including the sellar/suprasellar regions, demonstrate robustness across various pediatric brain tumor histologies. The automated brain tumor segmentation models perform reliably even in limited data scenarios. Importance of the Study We present robust skull-stripping models that work with single- and multi-parametric MR images and include the sellar-suprasellar regions in the extracted brain tissue. Since ∼10% of the pediatric brain tumors originate in the sellar/suprasellar region, including the deep-seated regions within the extracted brain tissue makes these models generalizable for a wider range of tumor histologies. We also present two tumor segmentation models, one for segmenting whole tumor using T2/FLAIR images, and another for segmenting enhancing tumor region using T1-Gd and T2/FLAIR images. These models demonstrate excellent performance with limited input. Both the skull-stripping and tumor segmentation models work with one- or two-input MRI sequences, making them useful in cases where multi-parametric images are not available – especially in real-world clinical scenarios. These models help to address the issue of missing data, making it possible to include subjects for longitudinal assessment and monitoring treatment response, which would have otherwise been excluded.

Year:

2024

In this study, we present a comprehensive radiogenomic analysis of pediatric low-grade gliomas (pLGGs), combining treatment-naïve multiparametric MRI and RNA sequencing. We identified three immunological clusters using XCell enrichment scores, highlighting an ‘immune-hot’ group correlating with poorer prognosis, suggesting potential benefits from immunotherapies. A radiomic signature predicting immunological profiles showed balanced accuracies of 81.5% and 84.4% across discovery and replication cohorts, respectively. Our clinicoradiomic model predicted progression-free survival with concordance indices of 0.71 and 0.77 in these cohorts, and the clinicoradiomic scores correlated with treatment response (p = 0.001). We also explored germline variants and transcriptomic pathways related to clinicoradiomic risk, identifying those involved in tumor growth and immune responses. This is the first radiogenomic analysis in pLGGs that enhances prognostication by prediction of immunological profiles, assessment of patients’ risk of progression, prediction of treatment response to standard-of-care therapies, and early stratification of patients to identify potential candidates for novel therapies targeting specific pathways.

Year:

2024

Collaborators (1)

Ali Nabavizadeh

University of Pennsylvania

UNITED STATES
View details