Post written by Bing Hu, MD, from the Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu, China.
The focus of this study is to develop and validate a real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model.
Esophageal squamous cell carcinoma (ESCC) accounts for more than 90% of esophageal cancers in China. Because overall 5-year survival rate is <20%, early diagnosis of precancerous lesions and ESCCs is therefore essential for a favorable prognosis for patients. Unfortunately, it is not easy to identify these imaging features in ESCC at an early stage. A recent study on missed esophageal cancer found that 6.4% of patients had negative endoscopy results within 3 years before diagnosis. Computer-assisted diagnosis (CAD) using an artificial intelligence (AI) system has made remarkable progress in recent years. Automated polyp detection system has been demonstrated to increase adenoma detection rate (ADR) significantly in randomized controlled trials.
This study validated the performance of the resultant algorithm on 4prospectively collected independent datasets, including various ESCC sizes (5-130 mm), macroscopic types-Paris classifications (0-I/IIa/IIb/IIc/II), and tumor depths (LGD/HGD/LPM/MM/SM/uncertain), etc. The resultant deep learning algorithm was validated to have high performance on all datasets.
With sufficient sensitivity and specificity, randomized controlled trials should be conducted to see whether this AI system can be applied in real clinical settings to increase the detection rate of ESCC.
Figure 1. The architecture and workflow of the deep learning model. An artificial intelligence hot zone image was generated for any input endoscopic image. The yellow color indicates high possibility of a cancerous lesion, and the blue color indicates a noncancerous lesion. When CAD detects any precancerous lesion or early ESCC, the lesion of interest is covered with color. CAD, computer-assisted diagnosis; ESCC, esophageal squamous cell carcinoma; NBI, narrow-band imaging.
Read the full article online.
The information presented in Endoscopedia reflects the opinions of the authors and does not represent the position of the American Society for Gastrointestinal Endoscopy (ASGE). ASGE expressly disclaims any warranties or guarantees, expressed or implied, and is not liable for damages of any kind in connection with the material, information, or procedures set forth.