Breast cancer is one of the most common cancers, with more than 2 million new cases diagnosed globally each year. As with all cancers, early detection greatly increases survival rates from breast cancer, as treatment is more effective when started soon after malignant growths are detected. AI, or artificial intelligence, has shown immense promise for significantly improving early breast cancer detection through better analysis of mammogram images.
AI accurate in detection of breast cancer
Recent research has demonstrated that AI is more accurate than human radiologists at finding malignant tumors in mammograms. Another article, this one in Lancet Oncology, said the use of AI has greatly reduced the workload, with no decline in effectiveness, for early detection of breast cancer.
In the study, conducted between April 2021 and July 2022, researchers analyzed scans of more than 80,000 women in Sweden. Half of the subjects had their mammograms analyzed by AI and one radiologist, and the other half had their scans read by two experienced radiologists. The results showed that in the scans performed by AI and one radiologist, 20% more cancers were detected.
How AI works in early detection of breast cancer
As with all other machine-learned artificial intelligence, the algorithms used for early detection of breast cancer are trained with thousands of high-quality mammogram images to identify very subtle differences between healthy breast tissue and early stage tumors. They learn to pick up on microscopic changes in shape, texture and density of tissue that indicates malignancy. The AI models don’t get tired or miss things the way the human eyes and brain can.
“It’s deep learning; it’s constantly learning. Not only does it point [cancer] out, but it points out the likelihood of malignancy,” said Dr. Rachel Brem, director of breast imaging and intervention and professor at George Washington University in an article for GovCIO Media & Research. “Every time a mammogram is analyzed, it’ll get analyzed by the algorithms. It’s really a bioimaging marker.”
By rapidly analyzing hundreds of images, the AI can highlight the most suspicious areas on a mammogram for radiologists to further examine. It draws their attention to aspects they may have initially missed. This allows more cancers to be caught at the earliest stages, when lumpectomy breast-conserving surgery may be possible, rather than full mastectomies on larger tumors.
With improved early breast cancer detection through AI, we can expect lower mortality rates, less invasive treatment, and reduced healthcare costs from cancer. Many leading hospitals and cancer centers are already using AI mammogram analysis tools to aid their clinicians. As technology improves further, AI promises to become an indispensable tool for early detection of breast cancer.