# Neuro-trauma Finding Detection on CQ500 Source: [Neuro-trauma Finding Detection on CQ500]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:46:27.196Z Evaluation of model performance for detecting multiple critical neuro-trauma findings (Hemorrhage, Mass Effect, Midline Shift) using the CQ500 dataset, reporting AUC for each finding. 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 | Neuro-trauma Finding Detection | | Dataset (including any stated split) | CQ500 | | Metric | Hemorrhage AUC | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 1 of 1 | | 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 - [Hemorrhage AUC](): Higher is better; unit: PERCENT. - [Mass Effect AUC](): Higher is better; unit: PERCENT. - [Midline Shift AUC](): Higher is better; unit: PERCENT. ## Recorded results | Method | Hemorrhage AUC | Result date | Report paper | | --- | --- | --- | --- | | DeepCNTD-Net | 92 | Not recorded | 68fa77291e209131cea717a1 | ### DeepCNTD-Net Hemorrhage AUC: 92. Result ID: 69946bd23a6c3148491d212d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"hemSegFeat":"true","brainAnatFeat":"true"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.