# Vertebra Fracture Recognition on RSNA dataset (test) Source: [Vertebra Fracture Recognition on RSNA dataset (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:32.513Z Evaluation of model performance for recognizing vertebra fractures using the test split of the RSNA dataset, reporting classification and diagnostic metrics like Accuracy, F1-Score, Sensitivity, Specificity, and ROC-AUC. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Vertebra Fracture Recognition | | Dataset (including any stated split) | RSNA dataset (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Sensitivity](): Higher is better; unit: PERCENT. - [Specificity](): Higher is better; unit: PERCENT. - [F1-Score](): Higher is better; unit: PERCENT. - [ROC-AUC](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | CNN-Transformer | 94.51 | Not recorded | 6971af3ae25ad2fa9d1edc13 | | CNN-Transformer | 93.69 | Not recorded | 6971af3ae25ad2fa9d1edc13 | | CNN-Transformer | 93.55 | Not recorded | 6971af3ae25ad2fa9d1edc13 | | EfficientNetB0 | 89.72 | Not recorded | 6971af3ae25ad2fa9d1edc13 | | DenseNet121 | 87.52 | Not recorded | 6971af3ae25ad2fa9d1edc13 | | DenseNet121 | 87.2 | Not recorded | 6971af3ae25ad2fa9d1edc13 | | ResNet18 | 60.63 | Not recorded | 6971af3ae25ad2fa9d1edc13 | | DenseNet121 | 50.05 | Not recorded | 6971af3ae25ad2fa9d1edc13 | | DenseNet121 | 13.82 | Not recorded | 6971af3ae25ad2fa9d1edc13 | ### CNN-Transformer Accuracy: 94.51. Result ID: 69979d2f5698665ec4f31694. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"-","View":"-","Mode":"Score Fusion"}. This record does not assert independent reproduction. ### CNN-Transformer Accuracy: 93.69. Result ID: 69979d2f5698665ec4f31693. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"2.5D (Max Projection Stacks)","View":"Axial"}. This record does not assert independent reproduction. ### CNN-Transformer Accuracy: 93.55. Result ID: 69979d2f5698665ec4f31692. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"2.5D (Slice Stacks)","View":"Axial"}. This record does not assert independent reproduction. ### EfficientNetB0 Accuracy: 89.72. Result ID: 69979d2f5698665ec4f31691. [Reporting paper]() Recorded evaluation configuration: {"Input":"3D","View":"-"}. This record does not assert independent reproduction. ### DenseNet121 Accuracy: 87.52. Result ID: 69979d2f5698665ec4f3168c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"2D","View":"Axial"}. This record does not assert independent reproduction. ### DenseNet121 Accuracy: 87.2. Result ID: 69979d2f5698665ec4f3168f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"2D","View":"Fused"}. This record does not assert independent reproduction. ### ResNet18 Accuracy: 60.63. Result ID: 69979d2f5698665ec4f31690. [Reporting paper]() Recorded evaluation configuration: {"Input":"2D","View":"Fused"}. This record does not assert independent reproduction. ### DenseNet121 Accuracy: 50.05. Result ID: 69979d2f5698665ec4f3168e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"2D","View":"Sagittal"}. This record does not assert independent reproduction. ### DenseNet121 Accuracy: 13.82. Result ID: 69979d2f5698665ec4f3168d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"2D","View":"Coronal"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.