New Method of Differentiating Colon Tumors May Reduce Surgery

Researchers at the University of Maryland have developed a new method of identifying and differentiating among several types of colon tumors, helping physicians make diagnoses that may reduce unnecessary surgery.

The method uses "artificial neural networks" (ANNs) to analyze thousands of genes at one time.

Patients suffering from Crohn's disease and ulcerative colitis have a higher risk of developing one of two types of cancer.

"Sporadic" or common colon cancers can often be removed without radical surgery, while inflammatory bowel disease-related growths and cancers are far more aggressive and are most often treated by removal of the entire colon.

Researchers extracted DNA from 39 tumor samples from patients who had well-documented cases of "sporadic" cancers or cancers related to inflammatory bowel disease. They used high-tech gene microarray equipment to analyze 8,064 genes to determine the level at which they were present in each sample.

These "gene expression" levels were translated into numbers, which were processed by "artificial neural networks," multi-layer mathematical programs that work like the human brain and can recognize complex patterns in large amounts of data.

Investigators were able to "train" the neural network to recognize the two types of colon cancer, and then gave it information from 12 samples it had never seen. The correct diagnosis was made in all 12 cases, the researchers reported in Gastroenterology.

The researchers were able to reduce the number of genes necessary to make a correct diagnosis from 8,064 to 97.

"This study helps to establish a new method, called artificial neural networks that can be used in a wide variety of disease settings, not just in cancer," said Dr. Stephen J. Meltzer, professor of medicine and senior author of the study. "These networks mimic the human brain, in that they can be trained to recognize specific disease lesions or subtle differences within disease categories. Ultimately, we hope that ANNs will greatly aid in the diagnosis and classification of human disease states."

Researchers are hopeful that this new technology will have a significant impact on the early detection and treatment of colon cancer in people with inflammatory bowel disease.

Other Sources: University of Maryland Medical Center