PedDx: An End-to-End Deep Learning Framework for Pediatric Posterior Fossa Tumor Diagnosis with Agentic AI–Enabled Independent External Evaluation
Year: 2026
Type: preprint
Abstract: Reliable clinical translation of diagnostic artificial intelligence (AI) requires evaluation beyond classification accuracy. We developed PedDx, a segmentation-free framework for pediatric posterior fossa tumor diagnosis using T2-weighted MRI, pretrained 3DINO representations, calibrated predictions, and confidence-based abstention. Evaluation included 492 discovery, 114 replication, 129 external validation, and 40 independently tested cases, alongside 236 out-of-distribution (OOD) cases and controlled imaging perturbations. Classification accuracy was 79.8% in replication and 81.4% in external validation, increasing to 90.5% and 88.7%, respectively, among non-abstained cases. OOD analyses revealed performance degradation and confidently incorrect predictions, while perturbation analyses identified acquisition and alignment vulnerabilities. An external institution independently executed the complete agentic workflow, successfully generating predictions and structured quality-control reports for all 40 cases, with classification accuracy of 92.5%, increasing to 97.3% among non-abstained cases. PedDx demonstrates how uncertainty assessment, failure-mode characterization, external validation, and independently reproducible, traceable reporting can collectively inform the reliability and limitations of diagnostic AI systems.
Source: medRxiv
Authors: Anahita Fathi Kazerooni, Fadel Batal, Bhavyasri Vunnava, Eswar Damaraju, Amin Tavallaii, Deep Gandhi, Anurag Gottipati, Pengjia Zhu, Dimosthenis Chrysochoou, Sanaz Varshochi, Sahand Adib Moradi, Ariana M. Familiar, Andrew Chiang, Yog Vaghani, Ghasem Azemi, Mikaela Doig, Minh-Son To, Amanda Luck, Meen Chul Kim, Neda Khalili, Nastaran Khalili, Paarth Jain, Celine Lee, Jordan R. Hansford, Antonio Di Ieva, Phillip B. Storm, Adam C. Resnick, Kartik Reddy, Arastoo Vossough, Ali Nabavizadeh
Institutions: Children's Hospital of Philadelphia, University of Pennsylvania, Emory University, Macquarie University, Women's and Children's Hospital, South Australian Health and Medical Research Institute, Flinders University, Flinders Medical Centre, Adelaide University, Nepean Hospital, Children's Healthcare of Atlanta
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7224500629