[
    {
        "id": "osp-15360",
        "type": "article-journal",
        "title": "SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models",
        "author": [
            {
                "family": "Mahbub",
                "given": "Md Kawsher"
            },
            {
                "family": "Biswas",
                "given": "Milon"
            },
            {
                "family": "Morshed",
                "given": "Mirza Niaz"
            },
            {
                "family": "Yu",
                "given": "Wei"
            }
        ],
        "URL": "https://omanscience.com/en/articles/spatialuq-post-hoc-uncertainty-quantification-from-spatial-consistency-in-black-box-vision-models",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Clinical vision models are often deployed as frozen black boxes with no access to internals, retraining, or ground truth at inference time. We introduce \\textbf{SpatialUQ}, a post-hoc uncertainty method using only output probabilities. It measures the Jensen-Shannon divergence between the global prediction and the mean of five fixed spatial crops in six deterministic forward passes. The premise is simple, trustworthy predictions are spatially consistent. On NIH ChestX-ray14 (DenseNet-121, $N{=}25{,}596$), our Multicrop Uncertainty Score (MUS) reaches $0.784$ failure-detection AUC versus $0.664$ for MC-Dropout ($p{"
    }
]