{"id":159,"identifier":"LOR-00159","url":"https://lifeofresearch.com/articles/159","title":"Two-Stage Transfer Learning for Slice-Level Pancreatic CT Classification: Performance Benchmarking, Confidence-Interval Reporting, Saliency Audit and a Data-Leakage Risk Analysis","abstract":"Transfer learning with partial fine-tuning separates the two classes almost perfectly on a\r\nslice-level split, and fine-tuning EfficientNet-B0 removes the baseline's specificity failure. However, the\r\nreported figures should be read as an upper bound on clinical performance until they are reproduced with\r\npatient-level partitioning and external data. We provide a reproducible leakage-aware protocol and a\r\nreporting checklist for slice-based pancreatic CT classifiers.","authors":[{"name":"vemulawada Navyasri","affiliation":"","orcid":""}],"type":"article","license":"CC-BY-4.0","keywords":["pancreatic cancer; computed tomography; deep learning; transfer learning; EfficientNet;  Grad-CAM; data leakage; medical image classification"],"publication_date":"2026-10-30","version":1,"views":3,"downloads":2,"created_at":"2026-10-30 06:48:35","doi":"","source":"","source_url":"","files":[{"id":168,"name":"Pancreatic_CT_Research_Paper.pdf","size":1039880,"mime":"application/pdf","downloads":2,"download_url":"https://lifeofresearch.com/articles/159/files/168/Pancreatic_CT_Research_Paper.pdf"}]}