Hungary has emerged as a testing ground for artificial intelligence technology that can help detect breast cancer in patients that doctors miss. AI systems are being rolled out across five clinics and hospitals that carry out over 35,000 screenings annually. AI is proving an impressive way of detecting cancer, at least as well as human radiologists. It is one of the most concrete examples to date of how AI is improving public health, particularly in Hungary where there is already a robust breast cancer screening program in place.
However, doctors and AI developers have called for additional clinical trials to ensure the system is more widely adopted as an automated second or third reader of breast cancer screens. Widespread adoption of the technology would also require the technology to prove it can produce accurate results on women of all ages, ethnicities and body types. The technology must also show it can recognise more complex forms of breast cancer and reduce false-positives. Moreover, concerns have been raised that AI technology may replace human radiologists, but experts insist that the technology is only effective when used in partnership with trained doctors.
At Bács-Kiskun County Hospital outside Budapest, radiologist Dr Éva Ambrózay, who has over two decades of experience, was looking at a patient’s mammogram when AI software flagged several areas of the scan as potentially cancerous. This was despite two radiologists having said that the X-ray did not show any signs of breast cancer. Dr Ambrózay ordered the patient to return for a biopsy.
AI usage is growing, and its impact is significant. However, A.I. still faces regulatory scrutiny and resistance from some doctors and health institutions. The technology’s ultimate goal is to provide better medical diagnoses and outcomes, and Dr László Tabár, a leading mammography educator in Europe, believes AI technology will eventually be lifesaving. Dr Tabár said he looks forward to the day when women will ask whether a breast cancer centre has AI or not.
AI is having a remarkable effect on detecting breast cancer. AI technology is at the heart of many systems used in apps such as Google Photos, and the neural network is modelled on how the human brain processes information from different sources. A.I. evangelists thought the technology would easily be applied to detect illness and disease. In 2020, there were 2.3 million breast cancer diagnoses and 685,000 deaths from the disease, according to the World Health Organization.
However, AI technology is not a complete solution to detecting breast cancer. Clinical trials are needed to ensure that the system can be more widely adopted as an automated second or third reader of breast cancer screens. Furthermore, the tool must show that it can produce accurate results on women of all ages, ethnicities and body types. Additionally, the technology must prove it can recognise more complex forms of breast cancer and cut down on false-positives that are not cancerous. Therefore, there is still some way to go before the technology is widely adopted.
