Promising future for AI in breast cancer detection

Breast cancer is the most frequent cancer among women. Each year it impacts around 2.1 million women. Also it is the leading cause of cancer-related deaths among women. According to WHO in 2018, 627,000 women died from breast cancer. 

To improve breast cancer outcomes and survival, early detection is critical. Mammogram is a great option which doctors suggest women to undergo, especially once they cross 40 years. But Mammogram is not error free. Research says, about 20% of mammograms gives out  false-negative results, meaning the doctor or technician fails to detect the cancer. False-positive mammograms are also possible, wherein doctor or technician reports of cancer, but is proven wrong upon further testing, which makes it not so reliable. Also mammogram poses radiation risk.

So like in any other field, hope lies in Artificial Intelligence. Let’s look at following solutions which can surely give some hope when it comes to detecting Breast cancer, with nearly hundred percent accuracy.

  1. Google’s LYNA

Google’s LYNA powered by Artificial Intelligence can detect the spread of breast cancer accurately. LYNA, which stands for “LYmph Node Assistant,” uses Deep Learning. Researchers have “trained” LYNA using  pathology slides from patients with metastatic breast cancer, or the stage of breast cancer where the disease has spread from the primary tumor site to nearby lymph nodes. Pathologists  who used LYNA reported that diagnosing micrometastases was much “easier” with it. It could distinguish a slide with metastatic cancer from a slide without, with an accuracy of 99%. Though it will take some time before we see pathologists around the world using LYNA, but it does gives hope.

  1. NIRAMAI

Niramai Health Analytix cofounded by Dr Geetha Manjunath and Nidhi Mathur are behind NIRAMAI. NIRAMAI stands for Non Invasive Risk Assessment with Machine Learning. Niramai has created non-intrusive breast cancer screening solution using heat maps and artificial intelligence. They have already screened around 4500 women using this tool and have been successful in detecting Breast cancer early on. This technology is so strong that they have 10 patents granted for this with six in US. They already got approvals from the Drug Controller General of India for NIRAMAI as a class A medical device. The best part is this solution is low cost, accurate, automated and portable can be operated by a simple clinician. https://niramai.com/

  1. Tetris like Program to Detect Breast Cancer

A fully-automated medical image analysis program driven by AI is getting ready to detect breast tumours at University of Adelaide’s Australian Institute for Machine Learning. It brings together MRI scan and Artificial Intelligence and employs the traversal movement and style of a retro video game, Tetris, to examine the breast area. This program uses a green square to navigate and search over the breast image to locate lesions. The square changes to red in colour if a lesion is detected. This approach is 1.78 times faster in finding a lesion.

Many more AI powered diagnostic tools are getting ready. Its matter of time we get to read about them. Employing these new generation tools for sure will speed up the diagnosis and will make the disease diagnosis more accurate and easy.

Leave a Reply