Clinical trial · Observational
Development and Validation of an AI Foundation Model for CNS Tumor Classification
Development and Validation of an Artificial Intelligence Foundation Model for Hierarchical Classification of Central Nervous System Tumors Using Hematoxylin and Eosin Whole-Slide Images
- Source
- ClinicalTrials.gov
- Retrieved
- Sep 8, 2026
- Layer
- normalized (units and labels harmonized; values unchanged)
- Run
- ING-CLINICALTRIALS-20260908-000001
Summary
Brief summary (as posted)
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.
Conditions
Conditions (2)
Free-text conditions as registered, with the CancerIndex entity they were reconciled to and the match type.
| Condition (as posted) | Mapped entity | Match | Confidence |
|---|---|---|---|
| Brain Tumors | Brain Neoplasm | ALIAS | 0.90 |
| Central Nervous System Neoplasms | Central Nervous System Neoplasm | ONTOLOGY_EXACT | 0.90 |
Interventions
Interventions (0)
Data not yet available
Design
Arms and outcomes
Arms (1)
- label
- CNS Tumor Retrospective Cohort
- description
- Retrospective cohort of approximately 20,000 patients with primary or secondary CNS tumors treated surgically at Huashan Hospital, Fudan University, with archived H\&E slides and linked de-identified clinical, pathological, and molecular diagnostic data used for AI model development and internal validation.
Primary outcomes (1)
- measure
- Hierarchical CNS tumor classification performance on the internal hold-out test set
- timeFrame
- Assessed at model evaluation after completion of training, up to Jul 2029
- description
- 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).
Secondary outcomes (4)
- measure
- Comparative performance of alternative feature extractors and MIL aggregation methods
Eligibility
Eligibility (as posted)
- Sex
- All
- Minimum age
- 9 Years
Show eligibility criteria text
Inclusion Criteria: 1. Patients who underwent brain or spinal tumor resection or biopsy at Huashan Hospital Fudan University and Shandong Provincial Hospital. 2. Postoperative pathology diagnosis consistent with a primary or secondary central nervous system tumor. 3. Availability of archived routine H\&E-stained glass slides or existing digital whole-slide image files of adequate quality for analysis. 4. Availability of essential de-identified clinical and pathological information, including age, sex, tumor location, and key surgical/pathology records. 5. Use of archived data and samples permitted under institutional ethics approval, including waiver of informed consent where applicable. Exclusion Criteria: 1. 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. 2. Insufficient viable tumor tissue or insufficient analyzable tumor area for patch extraction. 3. Missing or uncertain pathological diagnosis that cannot be reliably reassigned according to the WHO 2021 CNS tumor classification using available records. 4. Cases lacking sufficient clinical, pathological, or molecular information required for core study analyses. 5. Other cases determined by the investigators to be unsuitable for algorithm training or evaluation after quality control review.
References
Publications (0)
Data not yet available