|Google is taking it a step higher with using artificial intelligence in the medical field by teaching AI to spot breast cancer / Jane Rix via Shutterstock|
Breast cancer among young women has more aggressive features compared to the type that afflicts older patients.
According to sciencedaily.com, young age is not a factor to provide intensive treatment.
The main cause of death for cancer patients is late detection. This is often the result when testing facilities have inadequate equipment, or due to human factors, such as lack of concentration and fatigue, as well as lack of experience. Sometimes, the cause is the patient themselves who try to put off seeing a specialist because they fear what they might uncover.
What are the causes of an incorrect breast cancer diagnosis?
There are times when the lack of experience and knowledge results in a doctor's inability to diagnose rare diseases. Since they are usually specializing in a particular organ, these physicians do not see the picture as a whole. Doctors do not have time to interpret anamneses (patients’ recollection of their medical history) because of the methods and the time spent on documentation. Using X-rays, CT scans, MRIs, and other imaging methods may not be enough to determine a disease.
This is a complicated process that is performed by trained radiologists. Their skills are important in early detection and cancer diagnosis. However, there can sometimes be false negative results where diagnoses are missed or overlooked.
Google is taking it a step higher with using artificial intelligence in the medical field. They are now teaching AI to spot breast cancer. According to outerplaces.com, there is a new study titled "Artificial Intelligence-Based Breast Cancer Nodal Metastasis Detection." This research is about an AI called LYNA (Lymph Node Assistant) that can be trained on how to spot breast cancer that has spread beyond its original location and has put other healthy lymph nodes at risk. By identifying the degree by which cancer has spread, TNM staging can be done. This is a process that classifies cancer by stages.
The spread of cancer to the lymph nodes is essential in the staging process and it can be tricky too. Based on the official Google blog post, 1 in 4 metastatic lymph nodes stage assessments would be revised in retrospect. Thirty-eight percent of small metastases were spotted by pathologists who have very little time to examine different slides. This is where LYNA becomes useful. According to the Google AI blog, "...LYNA was able to correctly distinguish a slide with metastatic cancer from a slide without cancer 99% of the time. Further, LYNA was able to accurately pinpoint the location of both cancers and other suspicious regions within each slide, some of which were too small to be consistently detected by pathologists. As such, we reasoned that one potential benefit of LYNA could be to highlight these areas of concern for pathologists to review and determine the final diagnosis."
Thanks to LYNA, Google found that AI can help pathologist cut the amount of time in half in reviewing slide samples. This just shows that artificial intelligence can be used in various problems and can help millions of people from undetected diseases. ESMO Spokesperson Dr. Matteo Lambertini said, "Women under 40 years of age tend to be diagnosed with more aggressive breast cancer types—for example, their tumors are more likely to be triple negative and HER2 positive. Despite this, survival and local recurrence rates are similar to those of the general population of breast cancer patients provided they receive appropriate treatment."
AI has been welcomed by some radiologists but others saw it as suspicious. There are also other researchers who found that AI is good at detecting breast cancers.
AI can be used to detect other prevalent cancers in the future so it is important that both patient and medical professional know that the result is correct. Since the AI systems are still under research, these still cannot be used to detect cancer in patients. However, the results are promising as it can detect more patients with breast cancer and other cancers as well.
This is a start-up company based in Moscow. They are building up a blockchain infrastructure that can train and use AI for medical diagnosis. This is now nearing completion as they publish their ANN or Artificial Neural Network.
The AI of Skychain can recognize diseases and pathologies with the use of trained neural networks that know how to detect cancer cells.
|Google found that AI can help pathologist cut the amount of time in half in reviewing slide samples / Chompoo Suriyo via Shutterstock|
Factors that can affect accuracy
As of today, the accuracy is around 85% that can be attributed to the thermography. However, thermography is also dependent on various factors, such as breast symmetry, temperature, and temperature stability.
The ANN by Skychain has the ability to recognize different tumor tissues "through the segmentation of healthy from malignant cells via thermography to determine the type of a tumor," according to hackandcraft.com.
Soon enough, this technology can be launched for human use. When this happens, there will be a huge crowd of people who will want to avail of the new tech.