The use of artificial intelligence in the medical field has been on the rise, with technology predicting heart attacks and detecting symptoms of Alzheimer’s disease. Now, it appears that AI might have another function, this time in the early detection of cancer.
The team compiled a database of more than 30,000 images of pre-cancerous and cancerous cells, training the AI to detect the differences between them. After the machine’s learning process was complete, the researchers fed it an image of a colorectal polyp that had been magnified by a factor of 500. The AI was able to tell within a second whether the tumor was cancerous or not.
Dr. Yuichi Mora from Showa University, lead author on the study, presented the team’s findings at the United European Gastroenterology Conference in Barcelona. The AI’s accuracy was pegged at 86% — an impressive feat.
Mori said in The Telegraph,
The most remarkable breakthrough with this system is that artificial intelligence enables real-time optical biopsy of colorectal polyps during colonoscopy, regardless of the endoscopists’ skill.
She further explained, “This allows the complete resection of adenomatous (cancerous) polyps and prevents unnecessary polypectomy (removal) of non-neoplastic polyps. We believe these results are acceptable for clinical application and our immediate goal is to obtain regulatory approval for the diagnostic system.”
Early detection is crucial in colorectal cancer, as it is highly treatable in its early stages. Unfortunately, most diagnoses arrive late, after the cancer cells have multiplied into the bloodstream. The cancer starts as benign polyps in the rectum and colon that morph into malignant growths.
If this AI could help detect colorectal cancer earlier on, it could help thousands get treatment before the cancer worsens.