AI-Powered Software Helps Doctors Detect Breast Cancer

Detect cancer in early stages

This process helps detect cancer in their earliest stages. By detecting cancer early patients have a much likelihood of successful treatment as well as reducing the incidence of ‘interval cancers’ arising between breast screenings. The software leverages the power of Microsoft's suite of AI tools, Power BI.

The algorithm analyses the mammograms for breast density and then it can flag images that need follow up. The system was trained on a large number of mammogram X-ray images.

Software used around the world

Dr. Ralph Highnam founded Volpara to use AI to help overcome some of the difficulties in breast cancer detection. Founded just over ten years ago, the company is now used around the world, from the US to Japan, Australia, and New Zealand.

The company is continually developing its product and hopes that as AI technology also advances they can develop tools to spot cancer growth at the time of screening.

Digital mammograms were introduced in the early 90s. To have a mammogram, the patient stands in front of an X-ray machine and their breast is placed in between clear plastic plates. The X-ray is completed and then repeated for the other breast.

Regular assessments recommended

The X-rays are immediately assessed by the X-ray technician for clarity, but the image must be examined by a doctor or radiologist before the results can be given to the patient. Mammograms are very uncomfortable procedures with many patients experiencing pain during the short procedure.

Most health organizations recommend that women aged 50 to 70 get a mammogram every other year. Having previous mammograms is an important tool for doctors to compare changes in breast tissue.

IVF embraces AI

Artificial intelligence is being used more and more in the health industry to help doctors and professional assess scans. New research is applying AI to help improve the success rates of IVF treatment.

In Vitro Fertilization or IVF has been helping people improve their reproductive odds since its first successful case in 1977. While many improvements in technology have improved the process there are still aspects of the IVF treatment that are time-consuming and relatively inaccurate.

One of these is a process known as “grading.” The task requires an embryologist to examine embryos under a microscope checking their morphological features and assigning a quality score.

Round, even numbers of cells will score highly while fractured and fragmented cells score poorly. Now an algorithm has been trained to grade embryos better than its human counterparts.

Researchers trained a Google deep learning algorithm to identify IVF embryos as either good, fair, or poor based on the likelihood each one would successfully implant.

No doubt more Artificial intelligence systems will be applied to healthcare as the technology continues to improve.