AI tool reads brain tumors during surgery to guide decisions.
AI tool reads brain tumors during surgery to guide decisions.
AI Tool Deciphers Brain Tumor Genetic Code during Surgery
Scientists have developed an artificial intelligence (AI) tool called CHARM that can decipher the genetic code of brain tumors in real-time during surgery. This breakthrough technology promises to speed up diagnosis and personalize treatment for patients with brain cancer.
Gliomas are the most common type of brain cancer in adults. However, there are three subtypes of gliomas, each with different genetic features, levels of aggressiveness, and treatment options. Currently, pathologists analyze gliomas for genetic markers to determine the appropriate treatment. However, this process takes several days to weeks.
In contrast, the AI tool developed by Dr. Kun-Hsing Yu and his team at Harvard Medical School can perform molecular diagnosis in just 10 to 15 minutes. This means that real-time genetic analysis can be done during surgery, allowing doctors to make immediate treatment decisions.
The accuracy of the AI tool is highly impressive. When tested with previously unseen glioma samples, CHARM correctly distinguished the three different molecular subtypes with 93% accuracy. This level of precision is crucial, as it can significantly impact a patient’s treatment plan.
- Marijuana use linked to surgical complications
- European regulators are investigating the risk of suicidal thoughts...
- Testing the entire genome is twice as effective as targeted tests i...
Less aggressive gliomas can be treated with less invasive surgical techniques to minimize side effects. On the other hand, more aggressive gliomas, such as glioblastoma, require more aggressive treatment, including maximal removal of the cancer and the use of chemotherapy drugs implanted directly into the brain.
“This breakthrough technology has the potential to guide surgical decisions by providing real-time molecular diagnosis during brain tumor surgeries,” said Dr. Atique Ahmed, an associate professor of neurological surgery at Northwestern University Feinberg School of Medicine.
Although the 93% accuracy of CHARM is impressive, there is room for improvement. Dr. Ahmed emphasizes that the 7% inaccuracy represents patients with aggressive diseases who could greatly benefit from more precise diagnoses. Dr. Yu also acknowledges the potential for further refinement and the need for real-world testing and approval from the U.S. Food and Drug Administration.
The researchers are collaborating with several hospitals worldwide to conduct real-world testing of CHARM. If successful, this technology could revolutionize the field of brain tumor diagnosis and treatment.
Interest in using AI for medical diagnoses has grown significantly. The goal is to utilize AI algorithms to assist specialists in analyzing various medical images, such as mammograms and CT scans, for faster and more accurate diagnoses. However, Dr. Yu emphasizes that the aim is not to replace doctors but to use AI as a tool to enhance their capabilities.
CHARM, which stands for Cryosection Histopathology Assessment and Review Machine, was developed using over 2,300 frozen tumor samples from 1,524 glioma patients treated at various U.S. hospitals.
This study is not the only effort to improve glioma diagnosis using AI. Other tools, such as DeepGlioma, are also under investigation. Dr. Daniel Orringer, a neurosurgeon at NYU Langone’s Perlmutter Cancer Center, is involved in the development of DeepGlioma. He explains that molecular diagnosis of glioma is currently time-consuming, expensive, and not available in all hospitals. AI has the potential to democratize molecular testing, making it accessible to more patients.
According to Dr. Orringer, CHARM is particularly attractive because it can be used at any hospital capable of digitizing histology slides. This capability makes it more accessible than other AI tools that require specialized microscopes.
Furthermore, CHARM has the potential for versatility, as it can be trained to aid in the diagnosis of other brain tumor types as well. This potential makes it an exciting prospect for the future of precise and rapid molecular diagnosis during brain tumor surgeries.
In conclusion, the development of CHARM represents a significant leap forward in brain tumor diagnosis and personalized treatment. By providing real-time genetic analysis during surgery, this AI tool has the potential to revolutionize surgical decisions and improve patient outcomes.
