Artificial intelligence to now help diagnose breast cancer

Agencies
August 10, 2019

Washington D.C., Aug 10: Researchers discovered an artificial intelligence system that could help pathologists read biopsies more accurately and to better detect and diagnose breast cancer. 

The new system, described in a study published in the journal 'JAMA Network Open,' helped interpret medical images used to diagnose breast cancer that can be difficult for the human eye to classify, and it does so nearly as accurate or better as experienced pathologists.

"It is critical to get a correct diagnosis from the beginning so that we can guide patients to the most effective treatments," said Dr. Joann Elmore, the study's senior author and a professor of medicine at the David Geffen School of Medicine at UCLA.

A 2015 study led by Elmore found that pathologists often disagree on the interpretation of breast biopsies, which are performed on millions of women each year.

That earlier research revealed that diagnostic errors occurred in about one out of every six women who had ductal carcinoma in situ (a noninvasive type of breast cancer), and that incorrect diagnoses were given in about half of the biopsy cases of breast atypia (abnormal cells that are associated with a higher risk for breast cancer).

"Medical images of breast biopsies contain a great deal of complex data and interpreting them can be very subjective. Distinguishing breast atypia from ductal carcinoma in situ is important clinically but very challenging for pathologists. Sometimes, doctors do not even agree with their previous diagnosis when they are shown the same case a year later," said Elmore, who is also a researcher at the UCLA Jonsson Comprehensive Cancer Center.

The scientists reasoned that artificial intelligence could provide more accurate readings consistently because by drawing from a large data set, the system can recognise patterns in the samples that are associated with cancer but are difficult for humans to see.

The team fed 240 breast biopsy images into a computer, training it to recognise patterns associated with several types of breast lesions, ranging from benign (noncancerous) and atypia to ductal carcinoma in situ, or DCIS, and invasive breast cancer. Separately, the correct diagnoses for each image were determined by a consensus among three expert pathologists.

To test the system, the researchers compared its readings to independent diagnoses made by 87 practising U.S. pathologists. While the artificial intelligence program came close to performing as well as human doctors in differentiating cancer from non-cancer cases, the AI program outperformed doctors when differentiating DCIS from atypia, considered the greatest challenge in breast cancer diagnosis.

The system correctly determined whether scans showed DCIS or atypia more often than the doctors; it had sensitivity between 0.88 and 0.89, while the pathologists' average sensitivity was 0.70. (A higher sensitivity score indicates a greater likelihood that diagnosis and classification are correct.)

"These results are very encouraging. There is low accuracy among practising pathologists in the U.S. when it comes to the diagnosis of atypia and ductal carcinoma in situ, and the computer-based automated approach shows great promise," Elmore said.

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
May 18,2020

China, where the novel coronavirus originated, has reported 111 cases since beginning of May, which shows the infection rate has dipped, and 3 deaths since April 27, according to the WHO. A Shanghai-based Noida doctor says China is close to winning the battle against COVID-19, and the combination of zinc, hydroxychloroquine (HCQ) and antibiotic azithromycin has been able to save the lives of coronavirus patients.

Speaking to media persons, Dr Sanjeev Choubey, Medical Director Internal Medicine at St. Michael Hospital said this combination has been adopted as a line of treatment for patients infected with coronavirus, and as a result patients are recovering, decreasing their need for intensive care.

What is the line of treatment for COVID-19 patients, which also include asymptomatic patients?

The combination of zinc, hydroxychloroquine and antibiotic azithromycin has produced positive results, and it helped in the recovery of many COVID-19 patients. The combination -- Ascorbic Acid, B-complex, Zinc, Selenium, L-carnitine, Vitamin B-12 and Glutathione normal saline should be administered on patients twice a week for at least 6 weeks. This is COVID-19 treatment protocol for prophylaxis, and it implies both asymptomatic and symptomatic along with other medicine support.

Based on your experience on COVID-19 in China, after how many tests, is it safe to call a person coronavirus free?

The coronavirus should be performed at least 9 times, before terming a patient COVID-19 free. It is a standard in China. This procedure has worked in China and it will also work in India. Minimum five tests should be mandatory through RT-PCR.

Does coronavirus majorly attack the respiratory system or it could lead to organ failure too?

Line of treatment should not be just looking at the respiratory system, as the problem lies somewhere else. COVID-19 attacks many vital organs in the body. In China, a coronavirus patient died from a stroke. In the autopsy it was found that the innermost layer in the arteries was swollen. It was concluded that coronavirus had inflamed the layer of the arteries leading to clotting, which was a factor in generating a heart attack. Therefore, COVID-19 is not just a respiratory problem.

Amid the coronavirus pandemic, should autopsy be made mandatory in the case of unpredictable death or where reasons for death are not unknown?

Patients below 50 years, who die suddenly and the reasons are not known, then it should be mandatory to conduct the autopsy. After death, coronavirus is active in the body for five days, and it fades away on day 6. Therefore, if an autopsy is done then it will help in understanding this disease. In China, we have seen young COVID-19 patients, aged 22 and 28, succumbed to strokes.

Since the beginning of May, India has recorded more than 2,000 cases everyday in the first week, then it jumped past 3,000 mark in the second week. Finally, the tally is 4,987 on May 17. At 90,927 cases, has India progressed into community transmission or Stage3?

Yes, India has moved into Stage 3. The data suggests that 3,000 to 4,000 active COVID-19 cases, who are asymptomatic, are moving around and spreading the infection. The research has indicated that COVID-19 from an infected person spreads in 30 minutes to non-infected persons. The relaxation on the lockdown will certainly contribute to a high infection rate.

Do you think India has reached its peak in COVID-19 cases, or the sharp rise will continue till July end?

It seems India has already reached its peak and cases will begin to come down from June end or beginning of July first week. If social distancing norms are followed then certainly things can improve, but if not followed then it may get worse. High population density is a major contributor for the increase in cases. The government should continue to focus on finding hotspots, and urge people to follow the rules, eventually it is for people’s own benefit.

Has China won the battle against COVID-19?

It seems China has won the battle by not opening up Wuhan. The Chinese are following a COVID-19 patient’s engagement program, where the authorities continuously interact with people infected with the disease. The Government of India should reward people who follow the guidelines; it will help in setting up a positive trend in the society.

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.
News Network
February 4,2020

Toronto, Feb 4: People who text while walking face a higher risk of an accident than those listening to music or talking on the phone, a study has found.

The study, published in the journal Injury Prevention, found that smartphone texting is linked to compromised pedestrian safety, with higher rates of 'near misses', and failure to look left and right before crossing a road.

Researchers from the University of Calgary in Canada call for a more thorough approach to exploring the impact of distracted pedestrian behaviours on crash risk.

Worldwide, around 270,000 pedestrians die every year, accounting for around a fifth of all road traffic deaths, according to the researchers.

'Pedestrian distraction' has become a recognised safety issue as more and more people use their smartphones or hand held devices while walking on the pavement and crossing roads, they said.

The researchers looked for published evidence to gauge the potential impact on road safety of hand-held or hands-free device activities.

This included talking on the phone, text messaging, browsing and listening to music.

From among 33 relevant studies, they pooled the data from 14 -- involving 872 people -- and systematically reviewed the data from another eight.

The analysis showed that listening to music wasn't associated with any heightened risk of potentially harmful pedestrian behaviours.

Talking on the phone was associated with a small increase in the time taken to start crossing the road, and slightly more missed opportunities to cross the road safely.

The researchers found that text messaging emerged as the potentially most harmful behaviour.

It was associated with significantly lower rates of looking left and right before or while crossing the road, and with moderately increased rates of collisions, and close calls with other pedestrians or vehicles, they said.

Texting also affected the time taken to cross a road, and missed opportunities to cross safely, but to a lesser extent, according to the researchers.

The review of the eight observational studies revealed that the percentage of pedestrians who were distracted ranged from 12 to 45 per cent, they said.

It also found behaviours were influenced by several factors, including gender, time of day, solo or group crossing, and walking speed.

The researchers acknowledge "a variety of study quality issues" which limit the generalisability of the findings.

"Given the ubiquity of smartphones, social media, apps, digital video and streaming music, which has infiltrated most aspects of daily life, distracted walking and street cross will be a road safety issue for the foreseeable future," the researchers noted.

"And as signage and public awareness campaigns don't seem to alter pedestrian behaviour, establishing the relationship between distracted walking behaviour and crash risk is an essential research need," they said.

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
April 14,2020

There is no evidence that the Bacille Calmette-Guerin (BCG) vaccine, which is primarily used against tuberculosis, protects people against infection with the novel coronavirus, the World Health Organization (WHO) said.

The WHO therefore didn't recommend BCG vaccination for the prevention of COVID-19 in the absence of evidence, according to its daily situation report on Monday, Xinhua news agency reported.

"There is experimental evidence from both animal and human studies that the BCG vaccine has non-specific effects on the immune system. These effects have not been well characterized and their clinical relevance remains unknown," WHO stated.

Two clinical trials addressing the question are underway, and WHO will evaluate the evidence when it is available, it noted.

BCG vaccination prevents severe forms of tuberculosis in children and diversion of local supplies may result in an increase of disease and deaths from the tuberculosis, it warned.

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.