{"doi":"10.1093/noajnl/vdae190","title":"Automated pediatric brain tumor imaging assessment tool from CBTN: Enhancing suprasellar region inclusion and managing limited data with deep learning","abstract":"Abstract 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.","journal":"Neuro-Oncology Advances","year":2024,"id":470117,"datarank":0.20794415416798362,"base_score":1.3862943611198906,"endowment":1.3862943611198906,"self_citation_contribution":0.20794415416798362,"citation_network_contribution":0.0,"self_endowment_contribution":0.20794415416798362,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":3,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9585,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1030713,"name":"Nastaran Khalili","orcid":"0000-0001-8078-3591","position":1,"is_corresponding":false},{"id":867842,"name":"Ariana Familiar","orcid":"0000-0002-9315-8653","position":2,"is_corresponding":false},{"id":1072180,"name":"Anurag Gottipati","orcid":null,"position":3,"is_corresponding":false},{"id":1285040,"name":"Neda Khalili","orcid":"0000-0001-8415-8996","position":4,"is_corresponding":false},{"id":873896,"name":"Wenxin Tu","orcid":"0000-0003-3649-2994","position":5,"is_corresponding":false},{"id":1031426,"name":"Shuvanjan Haldar","orcid":null,"position":6,"is_corresponding":false},{"id":867843,"name":"Hannah Anderson","orcid":"0000-0002-9435-1535","position":7,"is_corresponding":false},{"id":459874,"name":"Karthik Viswanathan","orcid":"0000-0002-1288-9965","position":8,"is_corresponding":false},{"id":32657,"name":"Phillip B. Storm","orcid":"0000-0002-7964-2449","position":9,"is_corresponding":false},{"id":473196,"name":"Jeffrey B. Ware","orcid":"0000-0002-3495-9733","position":10,"is_corresponding":false},{"id":32696,"name":"Adam C. Resnick","orcid":"0000-0003-0436-4189","position":11,"is_corresponding":false},{"id":335228,"name":"Arastoo Vossough","orcid":"0000-0003-1346-427X","position":12,"is_corresponding":false},{"id":647730,"name":"Ali Nabavizadeh","orcid":"0000-0002-0380-4552","position":13,"is_corresponding":false},{"id":345391,"name":"Anahita Fathi Kazerooni","orcid":"0000-0001-7131-2261","position":14,"is_corresponding":false},{"id":347632,"name":"Deep Gandhi","orcid":"0000-0002-9479-5427","position":0,"is_corresponding":true}],"reference_count":50,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T02:05:36.656771Z","pmid":"39717438","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}