|Artificial intelligence promises better healthcare. AI systems can better diagnose diseases and help patients prolong their lives. The technology has been involved in understanding diseases such as brain tumors, a collection, or mass, of abnormal cells in a person’s brain / Photo by: Sergey Nivens via 123RF|
Artificial intelligence promises better healthcare. AI systems can better diagnose diseases and help patients prolong their lives. The technology has been involved in understanding diseases such as brain tumors, a collection, or mass, of abnormal cells in a person’s brain. According to the Central Brain Tumor Registry of the US (CBTRUS), nearly 80,000 cases of primary brain tumors were diagnosed in 2018, with 32% of these being malignant.
Of these cases, more than 25,000 were primary malignant and 53,000 were non-malignant brain tumors. During that year, approximately 700,000 people in the US were living with a primary brain and central nervous system tumor. To find out if a person has an illness like this, medical professionals usually recommend several tests and procedures. This includes a neurological exam, imaging tests, and tests to find cancer in other parts of a person’s body. Doctors also collect and test a sample of abnormal tissue through biopsy.
Fortunately, AI in healthcare is growing even more, which means that patients can be handled better now. A 2019 report conducted by Zion Market Research projected that global AI in the healthcare market would reach approximately $17.8 billion by 2025, at a CAGR of 43.8% between 2019 and 2025. This is much higher compared to the market value of 1.4 billion in 2018. It is also predicted that Europe would hold a notable share of the market due to the early adoption of AI technology.
According to GlobeNewswire, an online site that provides press release distribution services globally, AI would significantly automate basic medical services. This is not only helpful to patients but also to medical professionals because it enables them to focus more on critical cases.
AI in Diagnosing Brain Tumors
Medical professionals usually rely on brain scans to diagnose a brain tumor because it is the most reliable method for them. But, a team of researchers from the National Cancer Research Institute found a way to diagnose a brain tumor through chemical analysis of blood samples, with the help of AI. This would help to prioritize which patients need to be scanned for brain cancer.
The team trialed the technology on blood samples from 400 people suspected of having brain tumors. Using an existing technique called infrared spectroscopy, they screened 20,000 chemicals in patients’ blood. After that, they used AI to identify the chemicals that signal a brain tumor. This new technique is important because diagnosing this illness is difficult.
“A headache could be a sign of a brain tumor, but it is more likely to be something else and it's not practical to send lots of people for a brain scan, just in case it's a tumor. The challenge is identifying who to prioritize for an urgent scan,” Dr. Paul Brennan, senior clinical lecturer and honorary consultant neurosurgeon at the University of Edinburgh, UK, said.
|Medical professionals usually rely on brain scans to diagnose a brain tumor because it is the most reliable method for them / Photo by: Viacheslav Iakobchuk via 123RF|
According to Science Daily, an American website that aggregates press releases and publishes lightly edited press releases about science, the researchers were able to correctly identify 82% of brain tumors and 84% who did not have brain tumors. Overall, the new technique was 92% accurate at determining which people had tumors. “This could ultimately speed up diagnosis, reduce the anxiety of waiting for tests and get patients treated as quickly as possible,” Dr. Matthew Baker, chief scientific officer at ClinSpec Diagnostics Ltd, said.
A recent study published in the scientific journal Nature Medicine introduced a new AI system that can accurately diagnose a brain tumor in two minutes. The researchers used stimulated Raman histology (SRH), an optical imaging technique, to create images that the AI algorithm assesses in less than 150 seconds. The study’s senior author Daniel A. Orringer, associate professor of Neurosurgery at New York University Grossman School of Medicine, stated that this technology could improve speed and accuracy in the operating room as well as reduce the risk of misdiagnosis.
According to The Hill, the premier source for policy and political news, this AI-based diagnosis has an accuracy rate of 94.6%, which is higher than the conventional human diagnosis of 93.9%. “With this imaging technology, cancer operations are safer and more effective than before,” Orringer said.
Assessing Treatment Response of Brain Tumors
AI can help not only in diagnosing brain tumors but also treating them. A 2019 study conducted by researchers from Heidelberg University Hospital and the German Cancer Research Center showed the potential of machine learning methods in radiological diagnostics. The team developed neuronal networks to assess and clinically validate the therapeutic response of brain tumors on the basis of MRI in a standardized and fully automated way.
As a result, the researchers created a new method for automated image analysis of brain tumors, which aims to establish radiological methods in the treatment of the illness. At the same time, they designed and evaluated a software infrastructure that enables the complete integration of the new technique into existing radiological infrastructure. "In this way, we are creating the prerequisites for broad application and fully automated processing and analysis of MRI scans of brain tumors within a few minutes," researcher Klaus Maier-Hein said.
AI truly plays a huge role in diagnosing and treating brain tumors. If this is possible with this illness, it could also be possible for others. This would help patients understand their illness more and find ways to cure it.
|AI can help not only in diagnosing brain tumors but also treating them. A 2019 study conducted by researchers from Heidelberg University Hospital and the German Cancer Research Center showed the potential of machine learning methods in radiological diagnostics / Photo by: Vadim Guzhva via 123RF|