MIMIC-CXR
The largest publicly available chest X-ray report dataset, sourced from Beth Israel Deaconess Medical Center. It contains approximately 220,000 examination records and is widely used for training and evaluating radiology report generation systems.
Timeline (last 90 days)
The research team conducted experiments on three datasets—IU X-ray, MIMIC-CXR, and CheXpert Plus—to validate the effectiveness of MambaXray-PRB.
TALON was validated on the MIMIC-CXR dataset and outperformed current state-of-the-art methods on multiple clinical efficacy metrics and graph-based evaluation metrics.
MIMIC-CXR is currently the largest publicly available chest X-ray report dataset, containing approximately 220,000 examinations from Beth Israel Deaconess Medical Center, with most patients having multiple follow-up records.
On MIMIC-CXR and MIMIC-IV BHC, the model performs well on unstructured narrative text but degrades to near position-baseline levels when faced with highly templated reports.
All Facts (4)
The research team conducted experiments on three datasets—IU X-ray, MIMIC-CXR, and CheXpert Plus—to validate the effectiveness of MambaXray-PRB.
50%UnverifiedTALON was validated on the MIMIC-CXR dataset and outperformed current state-of-the-art methods on multiple clinical efficacy metrics and graph-based evaluation metrics.
50%UnverifiedMIMIC-CXR is currently the largest publicly available chest X-ray report dataset, containing approximately 220,000 examinations from Beth Israel Deaconess Medical Center, with most patients having multiple follow-up records.
50%UnverifiedOn MIMIC-CXR and MIMIC-IV BHC, the model performs well on unstructured narrative text but degrades to near position-baseline levels when faced with highly templated reports.
50%