[
  {
    "id": "10.3390/info17111175",
    "type": "article-journal",
    "title": "Validation Is Not Enough: A Duplicate-Aware, Reproducible Frozen-Feature Benchmark for Brain Tumour MRI Classification on BRISC 2025",
    "author": [
      {
        "family": "Vajjhala",
        "given": "Narasimha Rao"
      },
      {
        "family": "Ramollari",
        "given": "Ervin"
      },
      {
        "family": "Kumar",
        "given": "Rajesh"
      }
    ],
    "container-title": "Information",
    "issued": {
      "date-parts": [
        [
          2026,
          11,
          19
        ]
      ]
    },
    "volume": "17",
    "issue": "11",
    "number": "1175",
    "publisher": "MDPI",
    "ISSN": "2078-2489",
    "DOI": "10.3390/info17111175",
    "URL": "https://www.narasimharao.net/research/duplicate-aware-frozen-feature-benchmark-brain-tumour-mri-brisc-2025/",
    "abstract": "Public brain tumour MRI collections are routinely reported with near-perfect classification accuracy, yet they carry no patient identifiers and their train/test overlap is rarely quantified. We present a duplicate-aware, reproducible frozen-feature benchmark on BRISC 2025 (6000 contrast-enhanced T1-weighted slices; glioma, meningioma, pituitary tumour, no tumour). A perceptual-hash audit found 1352 candidate near-duplicate pairs, with 439 of them crossing the official train/test split, and 104 training images that are pixel-identical to test images; a visual review of sampled pairs showed that most candidates were other slices of the same scan, with an estimated 5–10% false matches. Removing redundant copies and every training image connected to the test set left 5477 images, a split that is duplicate-aware but not patient-independent. Under an identical linear probe, ImageNet-supervised ResNet-18/50 and self-supervised DINOv2 ViT-S/14 were competitive: DINOv2 was numerically ahead (macro-F1 77.3 ± 0.1%, macro-AUROC 93.2%), but no pairwise difference survived Holm correction. In-pool validation overstated official test macro-F1 by 9.7–13.5 points; control experiments showed that this gap is not an artefact of the filtering but mainly reflects a distribution difference between the official partitions. Meningioma recall stayed at 50–53%, and all linear heads were under-confident. We release the splits, audit tables and per-image predictions.",
    "keyword": "brain tumour MRI classification, benchmarking, reproducibility, data leakage, near-duplicate detection, foundation models, DINOv2, linear probing, calibration, selective prediction, medical image analysis, deep learning, perceptual hashing, train/test contamination, ResNet, frozen features, BRISC 2025 dataset",
    "language": "en"
  }
]