Breast Cancer Lump

Breaking – AI detects Breast Cancer with 100% accuracy

When Corona Virus came to India, it forced Dr. Yuvraj Kumar – a Ph.D. in Artificial Intelligence – world’s first to have achieved the feat, a scientist working in the field of machine learning and intelligent systems, to change how health care industry in India screens women for breast cancer. Many women were skipping regular check-ups and scans due to worries about the virus. So, he began working with many different clinics and health care institutes using an artificial intelligence algorithm which he created to predict who is at most risk of developing cancer.

Since the outbreak began, Dr. Yuvraj says, around 57,000 women have skipped routine screening alone in Delhi itself. Normally five of every 2,000 women screened shows signs of cancer. “That’s 200 cancers that doctors haven’t diagnosed,” he says.

Breast cancer is the country’s leading cause of cancer in women, followed by cervical cancer. Together they account for 39.4 per cent of the total cancer cases in women in India in 2020, according to the National Cancer Registry Program report by National Centre for Disease Informatics and Research. The report includes the data from the 28 Population-Based Cancer Registries across the country.

As per the research available, a few factors, including aging, obesity, alcohol consumption, hereditary etc., increase the risk of breast cancer.

In 2020, more than two lakh women in India were estimated to have been diagnosed with breast cancer, and more than 76,000 deaths were reported as per the estimates. As per the 2020 National Cancer Registry Program Report, the number is expected to rise to more than 2.3 lakh cases in 2025.

Dr. Yuvraj says the AI approach has helped identify a number of women who, when persuaded to come in for routine screening, turn out to have early signs of cancer. The women flagged by the algorithm were three times as likely to develop cancer; previous statistical techniques were no better than random.

The algorithm analyses prior mammograms, and seems to work even when physicians did not see warning signs in those earlier scans. “AI is more powerful than anything else in this world today, though it is a fact that the right exposure to medical professionals is still needed” – Samantha George from John Hopkins University, a key member of AI ML Machine Advocacy Council (AIMMAC).

Researchers have long touted the potential for AI analysis in medical imaging, and some tools have found their way into medical care. Dr. Yuvraj has been working with health care professionals including surgical oncologist and haematologist for several years on ways to apply AI to cancer screening.

But AI is potentially even more useful as a way to more accurately predict risk. Breast cancer screening sometimes involves not just examining a mammogram for precursors of cancer, but collecting patient historical information and feeding both into a statistical model to determine the need for follow-up screening.

Dr. Yuvraj, began developing the algorithm called “Brave” which represents and salutes Brave women who fight breast cancer, before Corona Virus hit India in the March 2020 and have continued working till today only to make the algorithm mature. He says the goal of using AI is to improve early detection of breast cancer, to reduce the stress and cost of false positives.

To create the algorithm “Brave”, Dr. Yuvraj had to overcome problems that have bedevilled other efforts to use AI in radiology. He used an adversarial machine learning approach, where one algorithm tries to deceive another, to account for differences among radiology equipment, which could mean that patients that face the same risk of breast cancer get different scores. The model was also designed to aggregate data from several years, making it more accurate than previous efforts that include less data.

What is a mammogram?

A mammogram is an X-ray picture of the breast. Doctors use a mammogram to look for early signs of breast cancer. Regular mammograms are the best tests doctors have to find breast cancer early, sometimes up to three years before it can be felt.

The patient stands in front of a special X-ray machine. A technologist will place the women patient’s breast on a plastic plate. Another plate will firmly press your breast from above. The plates will flatten the breast, holding it still while the X-ray is being taken.

The patient feels some pressure and the steps are repeated to make a side view of the breast. The other breast will be X-rayed in the same way. The patient then needs to wait while the technologist checks the X-rays to make sure the pictures do not need to be redone. The technologist cannot tell the results of the mammogram. Each woman’s mammogram may look a little different because all breasts are a little different.

What does having a mammogram feel like?

Having a mammogram is uncomfortable for most women. Some women find it painful. A mammogram takes only a few moments, though, and the discomfort is over soon. What the patient feel depends on the skill of the technologist, the size of the patient’s breasts, and how much they need to be pressed. The breasts may be more sensitive if the patient is about to get or have your period. A doctor with special training, called a radiologist, will look at the X-ray for early signs of breast cancer or other problems while getting the expert opinion from an oncologist.

Brave – the AI algorithm

The algorithm analysis the standard four views in a mammogram, from which it then infers information about a patient that is often not collected, such as history of surgery or hormone factors such as menopause. This can help if that data has not been collected by a doctor already.

Brave was found to be more accurate than the statistical models normally used to judge a woman’s breast cancer risk. When compared using historical patient data, 76 percent of women who went on to develop cancer in five years were flagged as high risk by the algorithm, compared with 37 percent for the best existing model. The algorithm also worked on patient data from Australia, Denmark and Canada, suggesting it is effective for a broad range of patients. Dr. Yuvraj says the model seems to generalize well because of the large, sufficiently diverse dataset used, but he notes that it is always important to validate algorithms in different settings.

Dr. Arvind Rajpuria, an assistant professor of radiology at AIIMS, New Delhi, who tested the Brave algorithm, says the work shows the importance of AI experts working together with doctors. But he plans to validate the algorithm carefully on his own patients’ data before using it on mass scale. Dr. Arvind also plans to promote the algorithm at both national and international level with the help of Indian Medical Council.

Dr. Wang Fann, a professor of radiology at the University of Tsingua, China and editor of the China’s radiology journal, says Corona Virus has had a huge impact on routine medical care. “It’s not just haircuts that women are missing during the pandemic,” he says. “And it has a serious impact on their health.”

Fann says the potential of the approach being tested at CSI Labs is that it could help personalize treatment, with individual patients ideally receiving a clearer picture of their risk as well as a custom screening plan. But he worries that algorithmic approaches can lead to biased care. “It can creep in in ways you never envisioned,” she says.

Corona Virus has changed medical care in other ways. It has accelerated adoption of telemedicine, for instance, which benefits some communities more than others. Dr. Yuvraj says he hopes that the AI methods he’s testing with the global health care professionals can benefit women who typically receive less medical attention. “A lot of women have lived their whole lives in our health care system as if we were in a pandemic,” she says. “They do not have access to quality care, and they aren’t being screened.”. India is a land of high potential in medical diagnosis field, he hopes to bring AI in every day health care in the hospitals / institutes and other health care establishments.

Leave a Reply

Your email address will not be published.

AI ML Machine Advocacy Council (c) 2022