Researchers Study Artificial Intelligence Tool to Detect Esophageal Cancer

University of Colorado (CU) Cancer Center researchers are assessing whether an artificial intelligence-powered diagnostic platform can assist endoscopists in identifying esophageal cancer in patients with Barrett’s esophagus.

Barrett’s esophagus, a premalignant condition for esophageal adenocarcinoma, develops when the esophagus lining becomes damaged due to acid reflux. The condition is diagnosed in 7 to 10 percent of individuals with chronic gastroesophageal reflux disease (GERD) and is present in approximately 1 to 2 percent of the general adult population.

According to the researchers, Barrett’s esophagus is associated with an increased risk of developing esophageal cancer. Therefore, physicians recommend regular biopsies for those with the condition to promote early detection.

When detected early, esophageal cancer is much more treatable than when it is discovered in its later stages.

“Esophageal adenocarcinoma is a highly lethal cancer with a five-year survival rate of less than 20 percent,” Sachin Wani, MD, study leader, and CU Cancer Center member, said in a press release. “What is really disappointing is that despite all the advances that we’ve made, the vast majority of patients with esophageal cancer still present with advanced-stage disease.”

In the study, Wani will test the effectiveness of CDx Diagnostics’ advanced diagnostic and artificial intelligence platform, Wide-Area Transepithelial Sampling with computer-assisted three-dimensional analysis (WATS3D), compared to the current standard of care known as the Seattle biopsy protocol.

“It’s a computer-assisted, three-dimensional analysis of samples that we obtain during endoscopy from the Barrett’s segment,” Wani said about the novel sampling technique in the news release. “Instead of using forceps biopsies, it’s a brush device that allows you to sample the Barrett’s segment extensively. Then, using the synthesized 3D images and neural network analyses, these samples get assessed, and abnormal cells get flagged for the pathologist to look at. The goal is to find patients early in their progression so that they can avoid having to go through chemotherapy, radiation, and esophagectomy, which are treatments we reserve for advanced-stage cancers.”

The trial will be conducted at approximately 14 centers across the United States, including the University of Colorado Division of Gastroenterology and CU Cancer Center.

According to Wani, it is important to study Barrett’s esophagus because it is the only identifiable premalignant condition for esophageal adenocarcinoma. Traditional endoscopy with biopsies can miss up to 30 percent of patients with Barrett’s esophagus-related dysplasia or early esophageal adenocarcinoma.

Wani hopes the study sets the stage for future research to predict the potential progression of esophageal cancer among patients with Barrett’s esophagus.

“We are excited to be embarking on such an important study that really will impact thousands of patients that are diagnosed with Barrett’s esophagus and esophageal cancer,” Wani said. “If the study shows that this sampling method detects more patients with dysplasia and early esophageal cancer and improves outcomes, this could have significant ramifications for the way we perform endoscopy in the future for this patient population.”