Artificial Intelligence system can identify cancer tumours better than humans

Agencies
August 26, 2018

Washington, Aug 26: Scientists have developed an artificial intelligence system that can accurately detect tiny specks of lung cancer in CT scans, which radiologists often have a difficult time identifying. The AI system is about 95 per cent accurate, compared to 65 per cent when done by human eyes, researchers said.

“We used the brain as a model to create our system,” said Rodney LaLonde, a doctoral candidate at University of Central Florida in the US. The approach is similar to the algorithms that facial-recognition software uses. It scans thousands of faces looking for a particular pattern to find its match.

The group fed more than 1,000 CT scans into the software they developed to help the computer learn to look for the tumours. They had to teach the computer different things to help it learn properly. The system was taught to ignore other tissue, nerves and other masses it encountered in the CT scans and analyse lung tissues.

Researchers are fine-tuning the AI’s ability to identify cancerous versus benign tumours.

Comments

Add new comment

  • Coastaldigest.com reserves the right to delete or block any comments.
  • Coastaldigset.com is not responsible for its readers’ comments.
  • Comments that are abusive, incendiary or irrelevant are strictly prohibited.
  • Please use a genuine email ID and provide your name to avoid reject.
Agencies
February 23,2020

Los Angeles, Feb 23: According to researchers, if administered quickly, a common medication that reduces bleeding could be a treatment for bleeding stroke.

The Spot Sign and Tranexamic Acid on Preventing ICH Growth - Australasia Trial (STOP-AUST) was a multicenter, prospective, randomized, double-blind, placebo-controlled, phase 2 clinical trial using the antifibrinolytic agent tranexamic acid in people with intracerebral hemorrhage (ICH).

ICH is a severe form of acute stroke with few treatment options.

Tranexamic acid is currently used to treat or prevent excessive blood loss from trauma, surgery, tooth removal, nosebleeds and heavy menstruation. For this study, one hundred patients with active brain bleeding were given either intravenous tranexamic acid or placebo within 4.5 hours of symptom onset.

Researchers analyzed brain CT scans taken during the 24-hour period after treatment with tranexamic acid or placebo.

Researchers found a trend towards reduced hemorrhage expansion in the group treated with tranexamic acid, especially in those treated within 3 hours of the brain bleed. However, this trend was not statistically significant. The finding was consistent with previous research using the medication.

"Further trials using tranexamic acid are ongoing and focusing on ultra-early treatment - within 2 hours. 

This is where the greatest opportunity for intervention appears to be. Tranexamic acid is inexpensive, safe and widely available. Our results and others provide great impetus for further, focused research using this treatment," Nawaf Yassi said.

Larger trials focused on patient outcomes are required for this therapy to enter routine clinical practice.

Comments

Add new comment

  • Coastaldigest.com reserves the right to delete or block any comments.
  • Coastaldigset.com is not responsible for its readers’ comments.
  • Comments that are abusive, incendiary or irrelevant are strictly prohibited.
  • Please use a genuine email ID and provide your name to avoid reject.
Agencies
June 10,2020

Early treatment with the antiviral drug remdesivir has been found to reduce viral load and prevent lung disease in macaques infected with SARS-CoV-2 that causes COVID-19, according to a study.

The findings, published in the journal Nature on Tuesday, support the early use of remdesivir treatment in patients with COVID-19 to prevent progression to pneumonia.

Researchers from the National Institutes of Health in the US noted that remdesivir has broad antiviral activity and has been shown to be effective against infections with SARS-CoV and MERS-CoV in animal models.

The drug is being tested in human clinical trials for the treatment of COVID-19, they said.

Researcher Emmie de Wit and colleagues investigated the effects of remdesivir treatment in rhesus macaques, a recently established model of SARS-CoV-2 infection.

Two sets of six macaques were inoculated with SARS-CoV-2.

One group was treated with remdesivir 12 hours later -- close to the peak of virus reproduction in the lungs -- and these macaques received treatment every 24 hours until six days after inoculation.

In contrast to the control group, the researchers found that macaques that received remdesivir did not show signs of respiratory disease, and had reduced damage to the lungs.

Viral loads in the lower respiratory tract were also reduced in the treated animals; viral levels were around 100 times lower in the lower-respiratory tract of remdesivir-treated macaques 12 hours after the first dose, they said.

The researchers said that infectious virus could no longer be detected in the treatment group three days after initial infection, but was still detectable in four out of six control animals.

Despite this virus reduction in the lower respiratory tract, no reduction in virus shedding was observed, which indicates that clinical improvement may not equate to a lack of infectiousness, they said.

Dosing of remdesivir in the rhesus macaques is equivalent to that used in humans, the researchers noted.

They cautioned that it is difficult to directly translate the timing of treatment used in corresponding disease stages in humans, because rhesus macaques normally develop only mild disease.

However, researchers said the results indicate that remdesivir treatment of COVID-19 should be initiated as early as possible to achieve the maximum treatment effect.

Comments

Add new comment

  • Coastaldigest.com reserves the right to delete or block any comments.
  • Coastaldigset.com is not responsible for its readers’ comments.
  • Comments that are abusive, incendiary or irrelevant are strictly prohibited.
  • Please use a genuine email ID and provide your name to avoid reject.