Cancer continues to be a leading cause of death worldwide, accounting for nearly one in six deaths. But advancements in both cancer detection and treatment have significantly improved survival rates. According to a UK cancer study from Cancer Research UK, the death rates for middle aged people have dropped substantially since the early 1990s, despite a rise in cancer cases.
For example, the mortality rate for cervical cancer in women has fallen by more than 54%, and lung cancer deaths have dropped by over 53% in men due to reduced smoking rates. Additionally, earlier detection through improved screening methods for cancers such as breast and bowel cancer has allowed for faster and more effective treatment, further driving down cancer related deaths.
The overall decline in death rates provides a hopeful outlook. However, as cancer cases continue to rise, more advanced diagnostic methods are needed to keep up with this growing challenge.
Artificial intelligence (AI) in particular, is playing a pivotal role in this next phase of cancer care. AI models can detect cancers earlier, identify subtypes more effectively, and even predict patient outcomes, allowing for personalised and timely interventions. As research in AI-driven diagnostics progresses, it is poised to become a cornerstone of cancer care, improving outcomes and reducing mortality even further.
Using AI for cancer diagnosis
One of the most promising developments in this space comes from the University of Edinburgh. A research team has recently developed a groundbreaking and innovative diagnostic method combining AI with Raman spectroscopy to detect early-stage breast cancer through a routine blood test.
The pilot study demonstrated an impressive 98% accuracy in detecting stage 1a breast cancer using blood plasma samples. The method also successfully identified the four main subtypes of breast cancer with an effectiveness of over 90%. The initial motivation driving this development was to provide a non-invasive, rapid, and highly precise alternative to traditional mammograms, ultimately enhancing early detection and improving patient outcomes. This groundbreaking technique could pave the way for earlier cancer diagnoses, personalised treatment strategies, and a broader shift towards non-invasive diagnostic tools in oncology powered by AI.
However, the University of Edinburgh are not alone in this development. We’ve looked at recent publications from the patent literature and there has been a lot of activity in patent publications pursuing tech using AI and spectroscopy for cancer diagnosis.
While spectroscopy is a well established technique for molecular analysis, combining it with AI for diagnostic applications, particularly in cancer detection has seen lots of development recently. The proof is in the patents:
Chinese patent CN115078331B presents a method that integrates Surface Enhanced Raman Scattering (SERS) spectroscopy with AI, allowing for high-accuracy, non-invasive cancer detection. This approach, which employs silver nanowires as SERS probes, mixed with serum samples for analysis, can identify lung cancer and colorectal carcinoma with remarkable accuracy and within just an hour.
In the US, similar innovations are being patented. US patent US11129577B2 in the name of Telebyte Inc details a portable optical cancer detector for identifying breast cancer. This system uses Deep Optical Scanning (DEOS) combined with a multilayer neural network to assess cancerous tissue and track therapy responses. Olaris Inc’s US11366102B2 is another US patent that focuses on predicting drug response by analysing metabolites using NMR spectroscopy. Ultimately providing a personalised approach to treatment for breast cancer patients.
US patent US11747205B2, assigned to Deep Smart Light Ltd, describes a non-invasive, multispectral fluorescence technique for characterising biological tissues using machine and deep learning. The process involves obtaining an excitation-emission matrix through fluorescence spectroscopy and applying a machine learning model to classify the tissue or determine the concentration of a specific substance within it. The goal of this system is to improve medical diagnostics by enabling real-time, accurate tissue characterisation, with potential applications in cancer diagnostics.
The role of patents
Each of these patents focus on various spectroscopy methods and their applications in diagnostics, often incorporating AI for data analysis and interpretation. Patents like the ones above drive innovation in medical diagnostics by incentivising breakthroughs for AI-enabled cancer detection while expanding public knowledge and collaboration. They facilitate collaboration, promote quality standards, and encourage adaptations for new applications.
There is often a common misconception that AI-related inventions cannot be validly protected by patents. However, this isn’t the case and they can be validly protected by patents. In recent years, the number of AI-related patent applications has skyrocketed, the number of patents being granted has followed a similar trend, and the chance of grant for each patent application filed appears to have has increased.
We therefore wonder whether future developments will see the University of Edinburgh’s AI-related techniques expanded to other cancer types. If the method proves effective for breast cancer, an adaptation to a new cancer type could involve unique training datasets, biomarker identification, and spectral analysis techniques, which could be patented separately.
Conclusion
Evidenced by the above, it’s clear that cancer diagnosis technology is developing rapidly. The patent literature can provide valuable clues about a sector’s focus and potential future technologies. By leveraging these advancements, there is immense potential to not only improve early detection but also lower the mortality rate even further. It will be exciting to watch this space and see what other groundbreaking techniques arise.
