Development and Validation of an AI Foundation Model for CNS Tumor Classification
Trial statusNot yet recruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age9+
SponsorHuashan Hospital
About this trial
This is a multi-center, retrospective, observational study to develop and internally validate an artificial intelligence (AI) foundation model for hierarchical classification of central nervous system (CNS) tumors using approximately 20,000 hematoxylin and eosin (H\&E) whole-slide images (WSIs) collected at Huashan Hospital Fudan University and Shandong Provincial Hospital. Archived pathology slides and linked de-identified clinical, histopathological, and molecular diagnostic data from patients who underwent neurosurgical tumor resection or biopsy between January 1, 2010 and December 31, 2025 will be retrospectively analyzed.
The study aims to train and evaluate weakly supervised multiple-instance learning models using pathology foundation models and conventional convolutional neural network feature extractors to predict tumor category, tumor family, terminal WHO 2021 CNS tumor diagnosis, and selected molecular alterations directly from routine H\&E slides. Internal model validation will be performed using patient-level training, validation, and hold-out test datasets. Secondary analyses include comparison of model architectures, virtual molecular profiling, interpretability analyses using attention heatmaps, and comparison of AI-assisted versus pathologist-only diagnostic performance on selected internal test cases.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Patients who underwent brain or spinal tumor resection or biopsy at Huashan Hospital Fudan University and Shandong Provincial Hospital.
Postoperative pathology diagnosis consistent with a primary or secondary central nervous system tumor.
Availability of archived routine H&E-stained glass slides or existing digital whole-slide image files of adequate quality for analysis.
Availability of essential de-identified clinical and pathological information, including age, sex, tumor location, and key surgical/pathology records.
Disqualifiers
Severe slide preparation or scanning artifacts that preclude meaningful computational analysis, including extensive tissue folding, severe bubbles, severe detachment, markedly uneven staining/fading, or severe out-of-focus scanning.
Insufficient viable tumor tissue or insufficient analyzable tumor area for patch extraction.
Missing or uncertain pathological diagnosis that cannot be reliably reassigned according to the WHO 2021 CNS tumor classification using available records.
Cases lacking sufficient clinical, pathological, or molecular information required for core study analyses.
Trial population
The study population consists of pediatric (≥9) and adult patients of any sex who underwent neurosurgical resection or biopsy for a suspected central nervous system (CNS) tumor at Huashan Hospital, Fudan University, between January 1, 2010 and December 31, 2025, and who have an available postoperative pathological diagnosis, archived hematoxylin and eosin (H\&E) stained slides and/or digital whole-slide images, and sufficient linked de-identified clinical, pathological, and molecular data for retrospective analysis. The cohort includes patients with primary or secondary CNS tumors for whom routine clinical care generated pathology materials suitable for computational pathology analysis.
Trial design
Design model
Cohort
Time perspective
Retrospective
Treatments tested in this trial
Not listed
Trial groups
20,000 Participants
are grouped into 1 trial groupGroup A: CNS Tumor Retrospective Cohort
Trial outcomes
Primary outcomes
1
Hierarchical CNS tumor classification performance on the internal hold-out test set
Diagnostic performance of the final AI model for hierarchical classification of CNS tumors at the tumor category, tumor family, and terminal WHO 2021 diagnosis levels using de-identified H\&E whole-slide images. Performance metrics will include macro- and/or micro-area under the receiver operating characteristic curve (AUC), balanced accuracy, weighted F1 score, and Matthews correlation coefficient (MCC).
Time frame
Assessed at model evaluation after completion of training, up to Jul 2029Secondary outcomes
1
Comparative performance of alternative feature extractors and MIL aggregation methods
Comparison of model performance across feature extractors (ResNet50, UNI, CONCH) and aggregation methods (ABMIL, CLAM) on the internal validation and hold-out test datasets using AUC, balanced accuracy, sensitivity, specificity, weighted F1 score, and MCC.
Time frame
Up to Jul 20292
Prediction performance for selected molecular biomarkers
Performance of the AI model in predicting selected molecular alterations from H\&E whole-slide images, including but not limited to IDH1/2 mutation, 1p/19q codeletion, H3 K27M/G34 alteration, TERT promoter mutation, and BRAF V600E, measured by AUC, sensitivity, specificity, and MCC.
Time frame
Up to Jul 20293
Agreement between AI attention maps and neuropathologist-identified diagnostic regions
Qualitative and semi-quantitative interpretability assessment of overlap between model attention heatmaps and diagnostically relevant regions identified independently by expert neuropathologists.
Time frame
Up to Jul 20294
Human versus AI versus AI-assisted diagnostic performance
Comparison of diagnostic accuracy, inter-rater agreement, and slide review time among AI-only diagnosis, pathologist-only diagnosis, and AI-assisted pathologist diagnosis on a selected internal test subset. Inter-rater agreement will be evaluated using Cohen's kappa where appropriate.
Time frame
Up to Jul 2029Locations
Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Huashan Hospital
Lead sponsor
Shandong Provincial Hospital
Collaborator
Source ClinicalTrials.gov
This trial is not recruiting at the moment. You can still explore other options: