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.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us
Detecto

Download Mobile App




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
Platinum Supplier
STI Test
Vivalytic Sexually Transmitted Infection (STI) Array
New
Surgical Table
ARCUS 601
New
Analgesic Gas Delivery System
O-Two Equinox Advantage
New
Digital Video Colposcope
CS6/CS6 Pro

Print article

Channels

AI

view channel
Image: A novel research study moves the needle on predicting coronary artery disease (Photo courtesy of Pexels)

AI-Enabled ECG Analysis Predicts Heart Attack Risk Nearly as well as CT Scans

Increased coronary artery calcium is a marker of coronary artery disease that can lead to a heart attack. Traditionally, CT scans are used to diagnose buildup of coronary artery calcium, although CT scanners... Read more

Critical Care

view channel
Image: New spray fights infections and antibiotic resistance (Photo courtesy of Chalmers University of Technology)

Hydrogel-Based Spray Kills Antibiotic-Resistant Bacteria in Wounds and Biomedical Implants

Antibiotic resistance has been ranked among the top ten threats to global health by the World Health Organization (WHO). Antibiotic-resistant bacteria is estimated to cause almost 1.3 million deaths annually... Read more

Health IT

view channel
Image: Using digital data can improve health outcomes (Photo courtesy of Unsplash)

Electronic Health Records May Be Key to Improving Patient Care, Study Finds

When a patient gets transferred from a hospital to a nearby specialist or rehabilitation facility, it is often difficult for personnel at the new facility to access the patient’s electronic health records... Read more

Point of Care

view channel
Image: Steripath improves the diagnostic accuracy and timeliness of sepsis test results (Photo courtesy of Magnolia)

All-in-One Device Reduces False-Positive Diagnostic Test Results for Bloodstream Infections

Blood cultures are considered the gold standard diagnostic test for the detection of blood stream infections, such as sepsis. However, positive blood culture results can be frequently wrong, and about... Read more

Business

view channel
Image: The global endoscopy equipment market is projected to surpass USD 40 billion by 2027 (Photo courtesy of Pexels)

Global Endoscopy Equipment Market Driven by Growing Hospital Investment in Advanced Instruments

The global endoscopy equipment market is projected to register a CAGR of 7% from USD 28.9 billion in 2022 to USD 40.6 billion by 2027, driven by increasing demand for endoscopy to diagnose and treat target... Read more
Copyright © 2000-2023 Globetech Media. All rights reserved.