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
February 4,2020

Despite tremendous advances in treatment of congenital heart disease (CHD), a new global study shows that the chances for a child to survive a CHD diagnosis is significantly less in low-income countries.

The research revealed that nearly 12 million people are currently living with CHD globally, 18.7 per cent more than in 1990.

The findings, published in The Lancet, is drawn from the first comprehensive study of congenital heart disease across 195 countries, prepared using data from the Global Burden of Diseases, Injuries and Risk Factors Study 2017 (GBD).

"Previous congenital heart estimates came from few data sources, were geographically narrow and did not evaluate CHD throughout the life course," said the study authors from Children's National Hospital in the US.

This is the first time the GBD study data was used along with all available data sources and previous publications - making it the most comprehensive study on the congenital heart disease burden to date.

The study found a 34.5 per cent decline in deaths from congenital disease between 1990 to 2017. Nearly 70 per cent of deaths caused by CHD in 2017 (180,624) were in infants less than one year old.

Most CHD deaths occurred in countries within the low and low-middle socio-demographic index (SDI) quintiles.

Mortality rates get lower as a country's Socio-demographic Index (SDI) rises, the study said.

According to the researchers, birth prevalence of CHD was not related to a country's socio-demographic status, but overall prevalence was much lower in the poorest countries of the world.

This is because children in these countries do not have access to life saving surgical services, they added.

"In high income countries like the United States, we diagnose some heart conditions prenatally during the 20-week ultrasound," said Gerard Martin from Children's National Hospital who contributed to the study.

"For children born in middle- and low-income countries, these data draw stark attention to what we as cardiologists already knew from our own work in these countries -- the lack of diagnostic and treatment tools leads to lower survival rates for children born with CHD," said researcher Craig Sable.

"The UN has prioritised reduction of premature deaths from heart disease, but to meet the target of 'ending preventable deaths of newborns and children under 5 years of age,' health policy makers will need to develop specific accountability measures that address barriers and improve access to care and treatment," the authors wrote.

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
March 11,2020

With the sales of chicken and mutton going down due to the coronavirus scare, it is the humble 'Kathal' (jackfruit) is emerging as an acceptable alternative.

'Kathal' is now selling at ₹120 per kilogram -- an increase of more than 120 per cent over the normal ₹50 per kilogram.

The jackfruit, in fact, is now priced higher than chicken which is selling at ₹80 per kilogram due to poor demand.

"It is better having a 'Kathal' biryani instead of a mutton biryani. It tastes reasonably good. The only problem is that 'Kathal' has been sold out in the vegetable market and is difficult to find," said Purnima Srivastava whose family savours non-vegetarian food on a regular basis.

The corona scare has hit poultry business so hard and the Poultry Farm Association recently organized a Chicken Mela in Gorakhpur to dispel the misconception that birds are carriers of the deadly virus.

"In fact, we gave away plateful of chicken dishes for Rs 30 to encourage people to savour the delicacies. We cooked one thousand kilograms of chicken for the Mela and the entire stock was sold out," said Vineet Singh, head of the Poultry Farm Association.

However, the Mela did not do much to dispel the fears about chicken, mutton or fish consumption amid the virus outbreak.

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 19,2020

While coughing, fever and difficulty in breathing are common symptoms of COVID-19, a new case study has found that pink eye is also a reason to be tested for the disease.

The study, published in the Canadian Journal of Ophthalmology, determined that conjunctivitis and keratoconjunctivitis can also be primary symptoms of COVID-19.

The researchers noted that in March, a 29-year-old woman arrived at the Royal Alexandra Hospital's Eye Institute of Alberta with a severe case of conjunctivitis and minimal respiratory symptoms.

After the patient had undergone several days of treatment with little improvement -- and after it had been determined that the woman had recently returned home from Asia -- a resident ordered a COVID-19 test.

The test came back positive, according to the researchers.

"What is interesting in this case, and perhaps very different to how it had been recognised at that specific time, was that the main presentation of the illness was not a respiratory symptom. It was the eye," said Carlos Solarte, an assistant professor at the University of Alberta in Canada.

"There was no fever and no cough, so we weren't led to suspect COVID-19 at the beginning. We didn't know it could present primarily with the eye and not with the lungs," Solarte said.

Academic studies at the outset of the pandemic identified conjunctivitis as a secondary symptoms in about 10 to 15 per cent of COVID-19 cases, he said.

Since then, scientists have gained greater knowledge of how the virus can transmit through and affect the body's mucous membrane system, of which the conjunctiva -- the clear, thin membrane that covers the front surface of the eye -- is an extension.

While the finding provides important new health information for the public, it also makes eye exams more complicated for ophthalmologists and staff, the researchers noted.

"The patient in this case eventually recovered well without any issues. But several of the residents and staff who were in close contact with the patient had to be under quarantine," said Solarte.

"Fortunately, none who were involved in her care also tested positive," he said.

Patients coming into an eye clinic with conjunctivitis and keratoconjunctivitis are now treated as potential cases of COVID-19 and extra precautions are taken by staff, according to the researchers.

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.