Search Results for author:
Found 69 papers, 30 papers with code
Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT
The extraction of labels from radiology text reports enables large-scale training of medical imaging models.
FreeTumor: Large-Scale Generative Tumor Synthesis in Computed Tomography Images for Improving Tumor Recognition
To tackle this challenge, we introduce FreeTumor, an innovative Generative AI (GAI) framework to enable large-scale tumor synthesis for mitigating data scarcity.
A Data-Efficient Pan-Tumor Foundation Model for Oncology CT Interpretation
Artificial intelligence-assisted imaging analysis has made substantial strides in tumor diagnosis and management.
ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports
The increasing adoption of AI-generated radiology reports necessitates robust methods for detecting hallucinations--false or unfounded statements that could impact patient care.
a2z-1 for Multi-Disease Detection in Abdomen-Pelvis CT: External Validation and Performance Analysis Across 21 Conditions
We present a comprehensive evaluation of a2z-1, an artificial intelligence (AI) model designed to analyze abdomen-pelvis CT scans for 21 time-sensitive and actionable findings.
The Impact of AI Assistance on Radiology Reporting: A Pilot Study Using Simulated AI Draft Reports
Radiologists face increasing workload pressures amid growing imaging volumes, creating risks of burnout and delayed reporting times.
MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting
In medical reporting, the accuracy of radiological reports, whether generated by humans or machine learning algorithms, is critical.
FactCheXcker: Mitigating Measurement Hallucinations in Chest X-ray Report Generation Models
Medical vision-language model models often struggle with generating accurate quantitative measurements in radiology reports, leading to hallucinations that undermine clinical reliability.
ReXrank: A Public Leaderboard for AI-Powered Radiology Report Generation
AI-driven models have demonstrated significant potential in automating radiology report generation for chest X-rays.
RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models
Generating accurate radiology reports from medical images is a clinically important but challenging task.
A Perspective for Adapting Generalist AI to Specialized Medical AI Applications and Their Challenges
The integration of Large Language Models (LLMs) into medical applications has sparked widespread interest across the healthcare industry, from drug discovery and development to clinical decision support, assisting telemedicine, medical devices, and healthcare insurance applications.
ReXplain: Translating Radiology into Patient-Friendly Video Reports
This work demonstrates a new paradigm in AI-assisted medical communication, potentially improving patient engagement and satisfaction in radiology care, and opens new avenues for research in multimodal medical communication.
ReXErr: Synthesizing Clinically Meaningful Errors in Diagnostic Radiology Reports
Working with board-certified radiologists, we developed error categories that capture common mistakes in both human and AI-generated reports.
ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metrics
Given the rapidly expanding capabilities of generative AI models for radiology, there is a need for robust metrics that can accurately measure the quality of AI-generated radiology reports across diverse hospitals.
Uncovering Knowledge Gaps in Radiology Report Generation Models through Knowledge Graphs
Recent advancements in artificial intelligence have significantly improved the automatic generation of radiology reports.
Towards Non-invasive and Personalized Management of Breast Cancer Patients from Multiparametric MRI via A Large Mixture-of-Modality-Experts Model
MOME exemplifies a discriminative, robust, scalable, and interpretable multimodal model, paving the way for noninvasive, personalized management of breast cancer patients based on multiparametric breast imaging data.
Direct Preference Optimization for Suppressing Hallucinated Prior Exams in Radiology Report Generation
Our work is, to the best of our knowledge, the first work to apply DPO to medical VLMs, providing a data- and compute- efficient way to suppress problem behaviors while maintaining overall clinical accuracy.
FineRadScore: A Radiology Report Line-by-Line Evaluation Technique Generating Corrections with Severity Scores
In this work, we present FineRadScore, a Large Language Model (LLM)-based automated evaluation metric for generated CXR reports.
Learning Generalized Medical Image Representations through Image-Graph Contrastive Pretraining
Medical image interpretation using deep learning has shown promise but often requires extensive expert-annotated datasets.
A Generalist Learner for Multifaceted Medical Image Interpretation
MedVersa is the first to showcase the viability of multimodal generative medical AI in implementing multimodal outputs, inputs, and dynamic task specification, highlighting its potential as a multifunctional system for comprehensive medical image analysis.
GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration
Specifically, we propose a cooperative framework, Generalist-Specialist Collaboration (GSCo), which consists of two stages, namely the construction of GFM and specialists, and collaborative inference on downstream tasks.
LymphoML: An interpretable artificial intelligence-based method identifies morphologic features that correlate with lymphoma subtype
The accurate classification of lymphoma subtypes using hematoxylin and eosin (H&E)-stained tissue is complicated by the wide range of morphological features these cancers can exhibit.
Multimodal Foundation Models Exploit Text to Make Medical Image Predictions
Finally, we conducted a physician evaluation of model performance on long-form medical cases, finding that the provision of images either reduced or had no effect on model performance when text is already highly informative.
Style-Aware Radiology Report Generation with RadGraph and Few-Shot Prompting
First, we extract the content from an image; then, we verbalize the extracted content into a report that matches the style of a specific radiologist.
Exploring the Boundaries of GPT-4 in Radiology
In this paper, we focus on assessing the performance of GPT-4, the most capable LLM so far, on the text-based applications for radiology reports, comparing against state-of-the-art (SOTA) radiology-specific models.
Augmenting medical image classifiers with synthetic data from latent diffusion models
While hundreds of artificial intelligence (AI) algorithms are now approved or cleared by the US Food and Drugs Administration (FDA), many studies have shown inconsistent generalization or latent bias, particularly for underrepresented populations.
RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extraction
We present RadGraph2, a novel dataset for extracting information from radiology reports that focuses on capturing changes in disease state and device placement over time.
Med-Flamingo: a Multimodal Medical Few-shot Learner
However, existing models typically have to be fine-tuned on sizeable down-stream datasets, which poses a significant limitation as in many medical applications data is scarce, necessitating models that are capable of learning from few examples in real-time.
Improving Zero-Shot Detection of Low Prevalence Chest Pathologies using Domain Pre-trained Language Models
We hypothesize that domain pre-trained models such as CXR-BERT, BlueBERT, and ClinicalBERT offer the potential to improve the performance of CLIP-like models with specific domain knowledge by replacing BERT weights at the cost of breaking the original model's alignment.
BenchMD: A Benchmark for Unified Learning on Medical Images and Sensors
Finally, we evaluate performance on out-of-distribution data collected at different hospitals than the training data, representing naturally-occurring distribution shifts that frequently degrade the performance of medical AI models.
Video Pretraining Advances 3D Deep Learning on Chest CT Tasks
We demonstrate video pretraining improves the average performance of seven 3D models on two chest CT datasets, regardless of finetuning dataset size, and that video pretraining allows 3D models to outperform 2D baselines.
Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generation
In this work, we propose Contrastive X-Ray REport Match (X-REM), a novel retrieval-based radiology report generation module that uses an image-text matching score to measure the similarity of a chest X-ray image and radiology report for report retrieval.
Improving dermatology classifiers across populations using images generated by large diffusion models
Dermatological classification algorithms developed without sufficiently diverse training data may generalize poorly across populations.
Benchmarking saliency methods for chest X-ray interpretation
Saliency methods, which produce heat maps that highlight the areas of the medical image that influence model prediction, are often presented to clinicians as an aid in diagnostic decision-making.
Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors
Current deep learning models trained to generate radiology reports from chest radiographs are capable of producing clinically accurate, clear, and actionable text that can advance patient care.
Deep Learning-Based Sparse Whole-Slide Image Analysis for the Diagnosis of Gastric Intestinal Metaplasia
We develop an evaluation framework inspired by the early classification literature, in order to quantify the tradeoff between diagnostic performance and inference time for sparse analytic approaches.
Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management
Recent advances in Natural Language Processing (NLP), and specifically automated Question Answering (QA) systems, have demonstrated both impressive linguistic fluency and a pernicious tendency to reflect social biases.
RadGraph: Extracting Clinical Entities and Relations from Radiology Reports
We release a development dataset, which contains board-certified radiologist annotations for 500 radiology reports from the MIMIC-CXR dataset (14, 579 entities and 10, 889 relations), and a test dataset, which contains two independent sets of board-certified radiologist annotations for 100 radiology reports split equally across the MIMIC-CXR and CheXpert datasets.
Structured dataset documentation: a datasheet for CheXpert
Following the structured format of Datasheets for Datasets, this paper expands on the original CheXpert paper and other sources to show the critical role played by radiologists in the creation of reliable labels and to describe the different aspects of the dataset composition in detail.
3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations
We propose 3KG, a physiologically-inspired contrastive learning approach that generates views using 3D augmentations of the 12-lead electrocardiogram.
Effect of Radiology Report Labeler Quality on Deep Learning Models for Chest X-Ray Interpretation
Next, after training image classification models using labels generated from the different radiology report labelers on one of the largest datasets of chest X-rays, we show that an image classification model trained on labels from the VisualCheXbert labeler outperforms image classification models trained on labels from the CheXpert and CheXbert labelers.
MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning
We propose a selective learning method using meta-learning and deep reinforcement learning for medical image interpretation in the setting of limited labeling resources.
CheXbreak: Misclassification Identification for Deep Learning Models Interpreting Chest X-rays
A major obstacle to the integration of deep learning models for chest x-ray interpretation into clinical settings is the lack of understanding of their failure modes.
CheXseen: Unseen Disease Detection for Deep Learning Interpretation of Chest X-rays
Second, we evaluate whether models trained on seen diseases can detect seen diseases when co-occurring with diseases outside the subset (unseen diseases).
VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels
We also find that VisualCheXbert better agrees with radiologists labeling chest X-ray images than do radiologists labeling the corresponding radiology reports by an average F1 score across several medical conditions of between 0. 12 (95% CI 0. 09, 0. 15) and 0. 21 (95% CI 0. 18, 0. 24).
CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray Segmentation
Medical image segmentation models are typically supervised by expert annotations at the pixel-level, which can be expensive to acquire.
MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation
Our controlled experiments show that the keys to improving downstream performance on disease classification are (1) using patient metadata to appropriately create positive pairs from different images with the same underlying pathologies, and (2) maximizing the number of different images used in query pairing.
CheXternal: Generalization of Deep Learning Models for Chest X-ray Interpretation to Photos of Chest X-rays and External Clinical Settings
Recent advances in training deep learning models have demonstrated the potential to provide accurate chest X-ray interpretation and increase access to radiology expertise.
CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretation
First, we find no relationship between ImageNet performance and CheXpert performance for both models without pretraining and models with pretraining.
MoCo-Pretraining Improves Representations and Transferability of Chest X-ray Models
Using 0. 1% of labeled training data, we find that a linear model trained on MoCo-pretrained representations outperforms one trained on representations without MoCo-pretraining by an AUC of 0. 096 (95% CI 0. 061, 0. 130), indicating that MoCo-pretrained representations are of higher quality.
CheXphotogenic: Generalization of Deep Learning Models for Chest X-ray Interpretation to Photos of Chest X-rays
In this study, we measured the diagnostic performance for 8 different chest x-ray models when applied to photos of chest x-rays.
GloFlow: Global Image Alignment for Creation of Whole Slide Images for Pathology from Video
The application of deep learning to pathology assumes the existence of digital whole slide images of pathology slides.
MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models
In this work, we propose MoCo-CXR, which is an adaptation of the contrastive learning method Momentum Contrast (MoCo), to produce models with better representations and initializations for the detection of pathologies in chest X-rays.
DLBCL-Morph: Morphological features computed using deep learning for an annotated digital DLBCL image set
We used a deep learning model to segment all tumor nuclei in the ROIs, and computed several geometric features for each segmented nucleus.
CheXphoto: 10,000+ Photos and Transformations of Chest X-rays for Benchmarking Deep Learning Robustness
We introduce CheXphoto, a dataset of smartphone photos and synthetic photographic transformations of chest x-rays sampled from the CheXpert dataset.
CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT
The extraction of labels from radiology text reports enables large-scale training of medical imaging models.
CheXpedition: Investigating Generalization Challenges for Translation of Chest X-Ray Algorithms to the Clinical Setting
First, we find that the top 10 chest x-ray models on the CheXpert competition achieve an average AUC of 0. 851 on the task of detecting TB on two public TB datasets without fine-tuning or including the TB labels in training data.
CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison
On a validation set of 200 chest radiographic studies which were manually annotated by 3 board-certified radiologists, we find that different uncertainty approaches are useful for different pathologies.
Ranked #96 on
Multi-Label Classification
on CheXpert
Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network
With specificity fixed at the average specificity achieved by cardiologists, the sensitivity of the DNN exceeded the average cardiologist sensitivity for all rhythm classes.
Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet
Magnetic resonance imaging (MRI) of the knee is the preferred method for diagnosing knee injuries.
Ranked #1 on
Multi-Label Classification
on MRNet
Know What You Don't Know: Unanswerable Questions for SQuAD
Extractive reading comprehension systems can often locate the correct answer to a question in a context document, but they also tend to make unreliable guesses on questions for which the correct answer is not stated in the context.
MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs
To evaluate models robustly and to get an estimate of radiologist performance, we collect additional labels from six board-certified Stanford radiologists on the test set, consisting of 207 musculoskeletal studies.
Malaria Likelihood Prediction By Effectively Surveying Households Using Deep Reinforcement Learning
We build a deep reinforcement learning (RL) agent that can predict the likelihood of an individual testing positive for malaria by asking questions about their household.
CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
We develop an algorithm that can detect pneumonia from chest X-rays at a level exceeding practicing radiologists.
Ranked #3 on
Pneumonia Detection
on ChestX-ray14
Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
We develop an algorithm which exceeds the performance of board certified cardiologists in detecting a wide range of heart arrhythmias from electrocardiograms recorded with a single-lead wearable monitor.
SQuAD: 100,000+ Questions for Machine Comprehension of Text
We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100, 000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage.
Augur: Mining Human Behaviors from Fiction to Power Interactive Systems
From smart homes that prepare coffee when we wake, to phones that know not to interrupt us during important conversations, our collective visions of HCI imagine a future in which computers understand a broad range of human behaviors.
Driverseat: Crowdstrapping Learning Tasks for Autonomous Driving
While emerging deep-learning systems have outclassed knowledge-based approaches in many tasks, their application to detection tasks for autonomous technologies remains an open field for scientific exploration.
An Empirical Evaluation of Deep Learning on Highway Driving
We collect a large data set of highway data and apply deep learning and computer vision algorithms to problems such as car and lane detection.
Ranked #2 on
Lane Detection
on Caltech Lanes Cordova
