{"ID":5438737,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T08:38:05.6384997Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31348","arxiv_id":"2606.31348","title":"Patient-Level Elbow Abnormality Detection: Leakage-Aware Evaluation of Learned Preprocessing, Calibration, and Triage-Oriented Operating Points","abstract":"In this study, we examine learned preprocessing pipelines in the context of triage-oriented orthopedic abnormality detection task using elbow radiographs from MURA dataset. The evaluation focuses on patient-level detection of musculoskeletal abnormalities under a leakage-aware protocol. We compare multiple preprocessing pipelines, with and without a lightweight DnCNN module as a learned preprocessing component, to assess their impact on discrimination and calibration. Performance is assessed using discrimination metrics (AUROC, PR-AUC), calibration measures (ECE, Brier score), and validation-selected operating point analysis targeting high specificity. Results show that differences across preprocessing strategies are modest and configuration-dependent, with no consistent discrimination advantage over the raw-input DenseNet121 baseline. The raw and diverse inputs combined with the DnCNN front-end showed reduced ECE and Brier score, while CLAHE combined with DnCNN did not improve calibration. Overall, the results suggest that under patient-level evaluation, preprocessing gains are modest and configuration-dependent; the raw-input DenseNet121 baseline remains competitive throughout, and no tested preprocessing strategy produced a consistent discrimination advantage across all metrics.","short_abstract":"In this study, we examine learned preprocessing pipelines in the context of triage-oriented orthopedic abnormality detection task using elbow radiographs from MURA dataset. The evaluation focuses on patient-level detection of musculoskeletal abnormalities under a leakage-aware protocol. We compare multiple preprocessin...","url_abs":"https://arxiv.org/abs/2606.31348","url_pdf":"https://arxiv.org/pdf/2606.31348v1","authors":"[\"Ahmed Sallam\",\"Ahmet Kaplan\"]","published":"2026-06-30T08:45:39Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}