We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

HospiMedica

Download Mobile App
Recent News AI Critical Care Surgical Techniques Patient Care Health IT Point of Care Business Focus

AI Diagnostic Tool Performs On Par with Radiologists in Detecting Diseases on Chest X-Rays

By HospiMedica International staff writers
Posted on 19 Sep 2022
Print article
Image: New tool overcomes major hurdle in clinical AI design (Photo courtesy of Unsplash)
Image: New tool overcomes major hurdle in clinical AI design (Photo courtesy of Unsplash)

Most artificial intelligence (AI) models require labeled datasets during their “training” so they can learn to correctly identify pathologies. This process is especially burdensome for medical image-interpretation tasks since it involves large-scale annotation by human clinicians, which is often expensive and time-consuming. For instance, to label a chest X-ray dataset, expert radiologists would have to look at hundreds of thousands of X-ray images one by one and explicitly annotate each one with the conditions detected. While more recent AI models have tried to address this labeling bottleneck by learning from unlabeled data in a “pre-training” stage, they eventually require fine-tuning on labeled data to achieve high performance. Now, scientists have developed an AI diagnostic tool that can detect diseases on chest X-rays directly from natural-language descriptions contained in accompanying clinical reports.

The new model named CheXzero that was developed by scientists at Harvard Medical School (Boston, MA, USA) and colleagues at Stanford University (Stanford, CA, USA) is self-supervised, in the sense that it learns more independently, without the need for hand-labeled data before or after training. The step is deemed a major advance in clinical AI design because most current AI models require laborious human annotation of vast reams of data before the labeled data are fed into the model to train it. The model relies solely on chest X-rays and the English-language notes found in accompanying X-ray reports. The model was “trained” on a publicly available dataset containing more than 377,000 chest X-rays and more than 227,000 corresponding clinical notes.

Its performance was then tested on two separate datasets of chest X-rays and corresponding notes collected from two different institutions, one of which was in a different country. This diversity of datasets was meant to ensure that the model performed equally well when exposed to clinical notes that may use different terminology to describe the same finding. Upon testing, the researchers successfully identified pathologies that were not explicitly annotated by human clinicians. It outperformed other self-supervised AI tools and performed with accuracy similar to that of human radiologists. The approach, the researchers said, could eventually be applied to imaging modalities well beyond X-rays, including CT scans, MRIs, and echocardiograms.

“We’re living the early days of the next-generation medical AI models that are able to perform flexible tasks by directly learning from text,” said study lead investigator Pranav Rajpurkar, assistant professor of biomedical informatics in the Blavatnik Institute at HMS. “Up until now, most AI models have relied on manual annotation of huge amounts of data - to the tune of 100,000 images - to achieve a high performance. Our method needs no such disease-specific annotations.”

“With CheXzero, one can simply feed the model a chest X-ray and corresponding radiology report, and it will learn that the image and the text in the report should be considered as similar—in other words, it learns to match chest X-rays with their accompanying report,” Rajpurkar added. “The model is able to eventually learn how concepts in the unstructured text correspond to visual patterns in the image.”

Related Links:
Harvard Medical School 
Stanford University 

New
Gold Member
X-Ray QA Meter
T3 AD Pro
Flocked Fiber Swabs
Puritan® patented HydraFlock®
New
Vertebral Body Replacement System
Hydrolift
New
Pneumatic Stool
Avante 5-Leg Pneumatic Stool

Print article
Radcal

Channels

Critical Care

view channel
mage: The electroceutical epidermal patch is designed to inhibit bacterial growth (Photo courtesy of Saehyun Kim/University of Chicago)

Cutting-Edge Bioelectronic Device Offers Drug-Free Approach to Managing Bacterial Infections

Antibiotic-resistant infections pose an increasing threat to patient safety and healthcare systems worldwide. Recent estimates indicate that drug-resistant infections may rise by 70% by 2050, highlighting... Read more

Surgical Techniques

view channel
Image: Conceptual schematic showing microgrippers (µ-grippers) operating as biopsy tools in the upper urinary tract (Photo courtesy of Wangqu Liu, Yan Wan/Gracias Lab, Johns Hopkins University)

Microgrippers For Miniature Biopsies to Create New Cancer Diagnostic Screening Paradigm

The standard diagnosis of upper urinary tract cancers typically involves the removal of suspicious tissue using forceps, a procedure that is technically challenging and samples only a single region of the organ.... Read more

Patient Care

view channel
Image: The portable biosensor platform uses printed electrochemical sensors for the rapid, selective detection of Staphylococcus aureus (Photo courtesy of AIMPLAS)

Portable Biosensor Platform to Reduce Hospital-Acquired Infections

Approximately 4 million patients in the European Union acquire healthcare-associated infections (HAIs) or nosocomial infections each year, with around 37,000 deaths directly resulting from these infections,... Read more

Health IT

view channel
Image: First ever institution-specific model provides significant performance advantage over current population-derived models (Photo courtesy of Mount Sinai)

Machine Learning Model Improves Mortality Risk Prediction for Cardiac Surgery Patients

Machine learning algorithms have been deployed to create predictive models in various medical fields, with some demonstrating improved outcomes compared to their standard-of-care counterparts.... Read more

Point of Care

view channel
Image: The acoustic pipette uses sound waves to test for biomarkers in blood (Photo courtesy of Patrick Campbell/CU Boulder)

Handheld, Sound-Based Diagnostic System Delivers Bedside Blood Test Results in An Hour

Patients who go to a doctor for a blood test often have to contend with a needle and syringe, followed by a long wait—sometimes hours or even days—for lab results. Scientists have been working hard to... Read more