The fight against Cancer has been seeing a lot of developments with the increasing improvements in technology. However, it seems like the people from Yokohama, Japan have perfected a new development in Cancer Research. This Artificial Intelligence could help detect colorectal cancer even before benign tumors become malignant.
The way this works is the AI observes a colorectal polyp magnified by 500 times in order to spot its variations. Afterwards, the program cross-references these variations against a database of over 30,000 images of pre-cancerous and cancerous cells that were used to train the machine-learning program.
With all of this knowledge the AI has found itself to be capable of detecting Cancer as fast as under a second. This is the first time an AI like this is used for this specific purpose under this sort of training. And the results are nothing short of amazing, as the accuracy has been a whopping 86% of matching results.
“Overall, 306 polyps were assessed real-time by using the AI-assisted system, providing a sensitivity of 94 percent specificity of 79 percent, accuracy of 86 percent, and positive and negative predictive values of 79 percent and 93 percent respectively, in identifying neoplastic changes.” Mentions the lead behind the project, Dr. Yuichi Mori
Dr. Yuichi Mori hails from the Showa University in Japan. This study has been presented to the United European Gastroenterology Conference in Barcelona. All to show the improvements of Artificial Intelligence on the Medical field in recent generations.
Let’s remind the readers that colorectal cancer is the second deadliest form of cancer, right behind lung cancer. The reason for this is in its later stages, the cancerous cells can exit the thin tissue of the colon, rectum, and intestine, and enter directly into the bloodstream. Spreading much quicker as a result.
“We believe these results are acceptable for clinical application and our immediate goal is to obtain regulatory approval for the diagnostic system,” he said in a statement to Inverse. Since this study has the potential to increase survival rates even further. The sooner it’s used to perfect the AI’s capabilities, the better.