MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports
PulseAugur coverage of MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports — every cluster mentioning MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
Radiology AI report evaluation metrics sensitive to reporting variations
A new research paper highlights how variations in radiologist reporting practices can significantly impact the evaluation of AI-based radiology report generation (RRG) models. The study introduces a method called ReRef …
-
New CNN-BiLSTM framework offers factually grounded biomedical text summarization
Researchers have developed a new hybrid framework combining 1D-CNN and BiLSTM models for extractive summarization of biomedical and clinical texts. This approach aims to prevent factual inaccuracies common in abstractiv…
-
ModaLens audit reveals medical VLMs rely more on text than images
Researchers have developed ModaLens, a new audit method to measure the sensitivity of vision-language models (VLMs) in medical contexts. Using the MedGemma-27B model on MIMIC-CXR data, the study found that when radiolog…
-
New AI Model NeoRed Enhances Neonatal Respiratory Disease Diagnosis
Researchers have developed NeoRed, a novel multimodal large language model specifically designed for diagnosing neonatal respiratory diseases. This model addresses limitations in existing systems, such as the domain gap…
-
LLMs evaluated for radiology report accuracy and longitudinal data extraction · 2 sources tracked
Researchers are exploring the use of large language models (LLMs) for improving radiology report quality and extracting longitudinal information. One study compared domain-specific BERT models with open-weight LLMs like…
-
New discrete diffusion model enhances radiology report generation
Researchers have developed DRRG, a novel discrete diffusion framework for radiology report generation that moves beyond traditional autoregressive models. This new approach allows for iterative refinement of reports, mi…
-
New Causal Model Enhances Chest X-Ray Interpretation and Interpretability
Researchers have developed XpertCausal, a novel causal concept bottleneck model designed to enhance the interpretability of chest X-ray interpretation. This model explicitly models the generative process from disease to…
-
New benchmark CRS-Bench evaluates medical image encoder reliability
Researchers have developed CRS-Bench, a new benchmark designed to evaluate the reliability of medical image encoders. Unlike previous methods that focused solely on discrimination, CRS-Bench assesses encoders across fou…
-
New LLM frameworks automate radiology report generation and template creation · 2 sources tracked
Researchers have developed new methods for improving radiology report generation using large language models (LLMs). One approach, ASTAR, automates the creation of standardized radiology reporting templates from clinica…
-
New MLLMs enhance radiology AI with 3D context and uncertainty reasoning · 3 sources tracked
Researchers are advancing multimodal large language models (MLLMs) for radiology, moving beyond simple image analysis to complex reasoning. One paper introduces a framework that addresses the representational mismatch b…
-
Foundation models for chest X-rays show complex fairness trade-offs
A new research paper explores how different adaptation strategies impact the fairness of foundation models used in medical imaging. The study focused on chest X-ray analysis, evaluating three parameter-efficient adaptat…
-
New AI Model Mr.Dec Predicts Hospital Readmissions Using Daily EHR and X-ray Data
Researchers have developed Mr.Dec, a novel multimodal model designed to predict 30-day hospital readmissions by analyzing longitudinal patient data. Unlike previous methods that condense patient history, Mr.Dec processe…
-
New DPO-Clin framework boosts AI medical report accuracy
Researchers have developed DPO-Clin, a new framework to improve the accuracy of medical report generation models. This method addresses factual errors in AI-generated reports by focusing on clinical findings and cross-m…
-
Medical AI training data unreliable, new research finds · 2 sources tracked
Two new research papers highlight critical issues with using public datasets for training medical AI models, particularly for chest radiograph analysis. The first paper, focusing on vision-language models, found that ag…
-
New frameworks and leaderboards aim to standardize AI radiology report generation
Researchers have introduced ReXrank, a public leaderboard and challenge designed to standardize the evaluation of AI models for radiology report generation. This framework utilizes a large test dataset, ReXGradient, and…
-
HarMoE framework enhances chest X-ray VLMs using multi-source pretraining
Researchers have developed HarMoE, a novel framework for pretraining vision-language models (VLMs) on chest radiographs. Unlike previous methods that primarily rely on image-report alignment from MIMIC-CXR, HarMoE lever…
-
AI advances radiology report generation with new reasoning and alignment frameworks · 4 sources tracked
Researchers have developed several new frameworks to improve radiology report generation using AI. HERO optimizes multimodal large language models by factorizing policy optimization into reasoning, diagnosis, and eviden…
-
Chest X-ray ML performance heavily influenced by evaluation references, study finds
A new research paper published on arXiv explores the critical impact of evaluation references on the performance metrics of machine learning models used for chest X-ray analysis. The study highlights that commonly used …
-
New framework detects demographic bias in medical imaging AI
Researchers have developed a new statistical framework to identify and quantify biases in machine learning models used for medical imaging. This method utilizes counterfactual invariance, assessing how model predictions…
-
New KANEx framework enhances medical AI explainability using Kolmogorov-Arnold Networks
Researchers have developed KANEx, a new framework that utilizes Kolmogorov-Arnold Networks (KANs) to improve the interpretability of vision-language models (VLMs) in medical applications. By leveraging the inherent tran…