Machine Learning-Aided Tool Generates High-Quality Chest X-Ray Images to Diagnose COVID-19 More Accurately
By HospiMedica International staff writers Posted on 15 Dec 2020 |
![Illustration Illustration](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2020-12-15/SDD-2331C.jpg)
Illustration
A new method of generating high-quality chest X-ray images can be used to diagnose COVID-19 more accurately than current methods.
The team of researchers at the University of Maryland, Baltimore County (UMBC; Baltimore, MD, USA) has published its findings in the proceedings of the IEEE Big Data 2020 Conference. The need for rapid and accurate COVID-19 testing is high, including testing that can determine if COVID-19 is impacting a patient's respiratory system. Many clinicians use X-ray technology to classify images of possible cases of COVID-19, but the limited data available makes it more challenging to classify those images accurately.
The UMBC researchers developed their tool as an extension of generative adversarial networks (GANs) - machine learning frameworks that can quickly generate new data based on statistics from a training set. The team's more advanced method uses what they call Mean Teacher + Transfer Generative Adversarial Networks (MTT-GAN). The MTT-GANs are superior to GANs because the images they generate are much more similar to authentic images generated by x-ray machines. The MTT-GAN classification system has the potential to help improve the accuracy of COVID-19 classifiers, making it an important diagnostic tool for physicians who are still working to understand the range of ways this complex disease presents in patients.
"The availability of data is one of the most important aspects of machine learning and our research has taken an incremental theoretical step towards generating data using the MTT-GAN," said Sumeet Menon, a Ph.D. student in computer science at UMBC who led the research team. "This paper mainly focuses on generating more COVID-19 X-rays using the MTT-GAN, which could be widely used to train machine learning models and could have many applications, including classification of CT-scans and segmentation."
Related Links:
University of Maryland, Baltimore County
The team of researchers at the University of Maryland, Baltimore County (UMBC; Baltimore, MD, USA) has published its findings in the proceedings of the IEEE Big Data 2020 Conference. The need for rapid and accurate COVID-19 testing is high, including testing that can determine if COVID-19 is impacting a patient's respiratory system. Many clinicians use X-ray technology to classify images of possible cases of COVID-19, but the limited data available makes it more challenging to classify those images accurately.
The UMBC researchers developed their tool as an extension of generative adversarial networks (GANs) - machine learning frameworks that can quickly generate new data based on statistics from a training set. The team's more advanced method uses what they call Mean Teacher + Transfer Generative Adversarial Networks (MTT-GAN). The MTT-GANs are superior to GANs because the images they generate are much more similar to authentic images generated by x-ray machines. The MTT-GAN classification system has the potential to help improve the accuracy of COVID-19 classifiers, making it an important diagnostic tool for physicians who are still working to understand the range of ways this complex disease presents in patients.
"The availability of data is one of the most important aspects of machine learning and our research has taken an incremental theoretical step towards generating data using the MTT-GAN," said Sumeet Menon, a Ph.D. student in computer science at UMBC who led the research team. "This paper mainly focuses on generating more COVID-19 X-rays using the MTT-GAN, which could be widely used to train machine learning models and could have many applications, including classification of CT-scans and segmentation."
Related Links:
University of Maryland, Baltimore County
Latest COVID-19 News
- Low-Cost System Detects SARS-CoV-2 Virus in Hospital Air Using High-Tech Bubbles
- World's First Inhalable COVID-19 Vaccine Approved in China
- COVID-19 Vaccine Patch Fights SARS-CoV-2 Variants Better than Needles
- Blood Viscosity Testing Can Predict Risk of Death in Hospitalized COVID-19 Patients
- ‘Covid Computer’ Uses AI to Detect COVID-19 from Chest CT Scans
- MRI Lung-Imaging Technique Shows Cause of Long-COVID Symptoms
- Chest CT Scans of COVID-19 Patients Could Help Distinguish Between SARS-CoV-2 Variants
- Specialized MRI Detects Lung Abnormalities in Non-Hospitalized Long COVID Patients
- AI Algorithm Identifies Hospitalized Patients at Highest Risk of Dying From COVID-19
- Sweat Sensor Detects Key Biomarkers That Provide Early Warning of COVID-19 and Flu
- Study Assesses Impact of COVID-19 on Ventilation/Perfusion Scintigraphy
- CT Imaging Study Finds Vaccination Reduces Risk of COVID-19 Associated Pulmonary Embolism
- Third Day in Hospital a ‘Tipping Point’ in Severity of COVID-19 Pneumonia
- Longer Interval Between COVID-19 Vaccines Generates Up to Nine Times as Many Antibodies
- AI Model for Monitoring COVID-19 Predicts Mortality Within First 30 Days of Admission
- AI Predicts COVID Prognosis at Near-Expert Level Based Off CT Scans
Channels
Critical Care
view channel![Image: An ingestible smart sensor could detect cancers (Photo courtesy of The Khan lab) Image: An ingestible smart sensor could detect cancers (Photo courtesy of The Khan lab)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-06-13/Untitled-design-4 (1).jpg)
GPS-Like Smart Pills with AI Provide Real-Time 3D Monitoring Of Gastrointestinal Health
Gas produced in the intestines when bacteria digest food can provide valuable information about a person's health. Currently, to measure gastrointestinal (GI) tract gases, physicians use methods such as... Read more![Image: An image of skin-inspired sensory robot (Photo courtesy of University of North Carolina at Chapel Hill) Image: An image of skin-inspired sensory robot (Photo courtesy of University of North Carolina at Chapel Hill)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-06-12/IMG_2406_1.jpg)
Soft Robots with Electronic Skins and Artificial Muscles to Provide Medical Treatment
Researchers have developed advanced soft robots that are equipped with electronic skins and artificial muscles, enabling them to detect their environment and modify their actions in real time.... Read moreSurgical Techniques
view channel![Image: New studies suggest benefit of total robotic metabolic and bariatric surgery over conventional laparoscopy (Photo courtesy of 123RF) Image: New studies suggest benefit of total robotic metabolic and bariatric surgery over conventional laparoscopy (Photo courtesy of 123RF)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-06-13/143615440_m_normal_none.jpg)
Total Robotic Metabolic and Bariatric Surgery Proves More Beneficial than Conventional Laparoscopy
According to the U.S. Centers for Disease Control and Prevention (CDC), 42.4% of Americans are affected by obesity. Research indicates that obesity can compromise the immune system, trigger chronic inflammation,... Read more![Image: Concept of the wirelessly actuated undulating pump and its integration into an esophageal stent (Photo courtesy of Advanced Functional Materials/ doi.org/10.1002/adfm.202405865) Image: Concept of the wirelessly actuated undulating pump and its integration into an esophageal stent (Photo courtesy of Advanced Functional Materials/ doi.org/10.1002/adfm.202405865)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-06-11/adfm202405865-fig-0001-m.jpg)
Wirelessly Activated Robotic Device Aids Digestion in Patients with Compromised Organs
The transport of fluids and solids is essential in the human body, driven by a wave-like movement in the lumen known as peristalsis. However, peristalsis can be disrupted in patients who have obstructions... Read morePatient Care
view channel![Image: The portable, handheld BeamClean technology inactivates pathogens on commonly touched surfaces in seconds (Photo courtesy of Freestyle Partners) Image: The portable, handheld BeamClean technology inactivates pathogens on commonly touched surfaces in seconds (Photo courtesy of Freestyle Partners)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-05-01/Freestyle_1.jpg)
First-Of-Its-Kind Portable Germicidal Light Technology Disinfects High-Touch Clinical Surfaces in Seconds
Reducing healthcare-acquired infections (HAIs) remains a pressing issue within global healthcare systems. In the United States alone, 1.7 million patients contract HAIs annually, leading to approximately... Read more![Image: The newly-launched solution can transform operating room scheduling and boost utilization rates (Photo courtesy of Fujitsu) Image: The newly-launched solution can transform operating room scheduling and boost utilization rates (Photo courtesy of Fujitsu)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2023-09-26/SDD-294798729.jpg)
Surgical Capacity Optimization Solution Helps Hospitals Boost OR Utilization
An innovative solution has the capability to transform surgical capacity utilization by targeting the root cause of surgical block time inefficiencies. Fujitsu Limited’s (Tokyo, Japan) Surgical Capacity... Read more![Image: The Instrument Pod is clinically proven to make the OR and sterile processing more efficient (Photo courtesy of Turbett Surgical) Image: The Instrument Pod is clinically proven to make the OR and sterile processing more efficient (Photo courtesy of Turbett Surgical)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2023-07-13/SDD-294797885.jpg)
Game-Changing Innovation in Surgical Instrument Sterilization Significantly Improves OR Throughput
A groundbreaking innovation enables hospitals to significantly improve instrument processing time and throughput in operating rooms (ORs) and sterile processing departments. Turbett Surgical, Inc.... Read moreHealth IT
view channel![Image: First ever institution-specific model provides significant performance advantage over current population-derived models (Photo courtesy of Mount Sinai) Image: First ever institution-specific model provides significant performance advantage over current population-derived models (Photo courtesy of Mount Sinai)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2023-05-26/SDD-294797344.jpg)
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![Image: Integration of generative AI into healthcare can increase productivity and enhance patient care (Photo courtesy of Microsoft) Image: Integration of generative AI into healthcare can increase productivity and enhance patient care (Photo courtesy of Microsoft)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2023-05-16/SDD-294797200.jpg)
Strategic Collaboration to Develop and Integrate Generative AI into Healthcare
Top industry experts have underscored the immediate requirement for healthcare systems and hospitals to respond to severe cost and margin pressures. Close to half of U.S. hospitals ended 2022 in the red... Read more![Image: iQueue for Operating Rooms maximizes OR access by optimizing block and open time (Photo courtesy of Freepik) Image: iQueue for Operating Rooms maximizes OR access by optimizing block and open time (Photo courtesy of Freepik)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2023-05-10/SDD-294797132.jpg)
AI-Enabled Operating Rooms Solution Helps Hospitals Maximize Utilization and Unlock Capacity
For healthcare organizations, optimizing operating room (OR) utilization during prime time hours is a complex challenge. Surgeons and clinics face difficulties in finding available slots for booking cases,... Read more![Image: AI model spots those at highest risk for up to three years before diagnosis (Photo courtesy of Freepik) Image: AI model spots those at highest risk for up to three years before diagnosis (Photo courtesy of Freepik)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2023-05-10/SDD-294797117.jpg)
AI Predicts Pancreatic Cancer Three Years before Diagnosis from Patients’ Medical Records
Screening for common cancers like breast, cervix, and prostate cancer relies on relatively simple and highly effective techniques, such as mammograms, Pap smears, and blood tests. These methods have revolutionized... Read morePoint of Care
view channel![Image: POCT offers cost-effective, accessible, and immediate diagnostic solutions (Photo courtesy of Flinders University) Image: POCT offers cost-effective, accessible, and immediate diagnostic solutions (Photo courtesy of Flinders University)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-05-30/28897_about_up_woman_operating_poct_machine.jpg)
POCT for Infectious Diseases Delivers Laboratory Equivalent Pathology Results
On-site pathology tests for infectious diseases in rural and remote locations can achieve the same level of reliability and accuracy as those conducted in hospital laboratories, a recent study suggests.... Read more![Image: The cartridge-based TEG 6s system provides clinicians a complete picture about a patient\'s coagulation profile (Photo courtesy of Haemonetics Corporation) Image: The cartridge-based TEG 6s system provides clinicians a complete picture about a patient\'s coagulation profile (Photo courtesy of Haemonetics Corporation)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-05-28/TEG6s-5-Hospital-Single-Product-Image-429x429-Recovered.jpg)
Cartridge-Based Hemostasis Analyzer System Enables Faster Coagulation Testing
Quickly assessing a patient's total hemostasis status can be critical to influencing clinical outcomes and using blood products. Haemonetics Corporation (Boston, MA, USA) has now obtained 510(k) clearance... Read more![Image: The Quantra Hemostasis System has received US FDA special 510(k) clearance for use with its Quantra QStat Cartridge (Photo courtesy of HemoSonics) Image: The Quantra Hemostasis System has received US FDA special 510(k) clearance for use with its Quantra QStat Cartridge (Photo courtesy of HemoSonics)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-04-05/Quantra_Instrument_QStat_Dials_2022.jpg)
Critical Bleeding Management System to Help Hospitals Further Standardize Viscoelastic Testing
Surgical procedures are often accompanied by significant blood loss and the subsequent high likelihood of the need for allogeneic blood transfusions. These transfusions, while critical, are linked to various... Read moreBusiness
view channel![Image: The Critical Care acquisition will enhance BD’s portfolio of smart connected care solutions (Photo courtesy of BD) Image: The Critical Care acquisition will enhance BD’s portfolio of smart connected care solutions (Photo courtesy of BD)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-06-04/Hemodynamic_Monitoring_1.jpg)
BD Acquires Edwards Lifesciences' Critical Care Product Group for USD 4.2 Billion
BD (Becton, Dickinson and Company, Franklin Lakes, NJ, USA) and Edwards Lifesciences (Irvine, CA, USA) have entered into a definitive agreement under which BD will acquire Edwards' Critical Care product... Read more![Image: The MEDICA START-UP PARK is the meeting place for networking for and with the creative start-up scene (Photo courtesy of Constanze Tillmann/Messe Düsseldorf) Image: The MEDICA START-UP PARK is the meeting place for networking for and with the creative start-up scene (Photo courtesy of Constanze Tillmann/Messe Düsseldorf)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2024-05-30/MEDICA23_STARTUP_PARK.jpg)