Researchers from the University of Edinburgh developed a new method that could improve the early detection and monitoring of breast cancer. According to Sky News, the team combined laser analysis with machine learning, creating a fast and non-invasive technique that reveals subtle changes in the bloodstream occurring during the initial phases of breast cancer, known as stage 1a, which are not detectable with existing tests. The advancement offers hope for better patient outcomes.
The pilot study, published in the Journal of Biophotonics, involved 12 samples from breast cancer patients and 12 healthy controls. By optimizing a laser analysis technique known as Raman spectroscopy and using machine learning algorithms, the researchers could interpret the results, identifying similar features and helping to classify samples. The device used, a spectrometer, analyzes the properties of light after it interacts with blood plasma, revealing tiny changes in the chemical makeup of cells and tissues—early indicators of disease.
"Early diagnosis is key to long-term survival, and we finally have the technology required. We just need to apply it to other cancer types and build up a database before this can be used as a multi-cancer test," said Dr. Andy Downes from the University of Edinburgh, according to Sky News. The study's findings indicate that the new screening method could recognize the first signals of cancer with an effectiveness of 98%, surpassing tumor markers obtained with liquid biopsy.
In addition to advances in blood-based detection methods, artificial intelligence is also being applied to imaging techniques. BBC News reported on the case of Sheila Tooth, a 68-year-old woman from Littlehampton, West Sussex, who is "deeply grateful" to artificial intelligence for finding her breast cancer after she was given the all clear following a routine scan. Tooth had a mammogram at University Hospitals Sussex NHS Foundation Trust, where the AI system Mammography Intelligent Assessment is being tested to improve breast cancer screening by spotting cancer that human readers might miss.
"When I talk to friends, we just can't believe this AI can detect what the human eye can't always see. I just feel so lucky," Tooth expressed, according to BBC News. Her cancerous cells were almost undetectable and had not been spotted before being found by the AI technology.
Gizmodo reported that DeepHealth, an AI firm owned by radiology giant RadNet, presented findings at the annual meeting of the Radiological Society of North America (RSNA). The study revealed that cancer was 21% more likely to be detected for women who paid extra for an AI-enhanced breast cancer screening program. In a study involving 747,604 women who underwent mammography screening over a 12-month period, the overall cancer detection rates were 43% higher for those enrolled in the AI program.
"This program uses AI in an innovative process to ensure that women with suspicious results receive the specialized care that can help identify more breast cancers at earlier stages," said Bryan Haslam, chief product officer at DeepHealth who led the study, according to Gizmodo. The X-ray test results of women enrolled in this program were initially reviewed by a breast radiologist and then examined by the AI software, serving as a "second set of eyes" to help radiologists spot anomalies.
The Financial Times noted that artificial intelligence is increasingly becoming a force to be reckoned with in the medical field and has medical applications. However, uncertainty remains about how AI can best be harnessed to deliver better, more efficient care and improve the experiences of patients and healthcare staff. Financial costs are a challenge to effectively using AI in medical practice, and investment remains a barrier to AI in healthcare administration.
Science Daily reported that advancements in AI-assisted breast cancer risk prediction are providing new opportunities to identify women at the highest risk of developing breast cancer. AI-generated mammographic features have the potential to be stronger predictors of breast cancer risk than any other known risk factor. "Critically, we need to identify the pathobiology associated with mammographic features and the underlying mechanisms that link them with breast cancer oncogenesis," stated Erik Thompson, senior study author from the Queensland University of Technology in Brisbane, Australia.
In India, efforts are underway to leverage artificial intelligence for early breast cancer detection. The Indian Express reported that AIIMS Delhi secured funding to lead the healthcare Centre of Excellence in partnership with IIT Delhi, aiming to improve early breast cancer detection and reduce mortality among Indian women. ASHA workers, the backbone of India's primary healthcare system, will collect data guided by a formatted questionnaire, which will be fed into an AI tool.
"For this, we will be using ASHA workers to collect the data, which will be fed into the AI tool. It will extract common risk factors and then recommend mammograms for women it thinks are cancer-prone. It will also help codify what constitutes a no-risk category," said Dr. Krithika Rangarajan, according to The Indian Express. The AI-trained systems can learn to recognize complex features in mammograms that indicate cancer, reducing the need for a radiologist on-site and lowering screening costs.
This article was written in collaboration with generative AI company Alchemiq