Application and prospect of artificial intelligence in digestive endoscopy

ABSTRACT

Introduction

With the progress of science and technology, artificial intelligence represented by deep learning has gradually begun to be applied in the medical field. Artificial intelligence has been applied to benign gastrointestinal lesions, tumors, early cancer, inflammatory bowel disease, gallbladder, pancreas, and other diseases. This review summarizes the latest research results on artificial intelligence in digestive endoscopy and discusses the prospect of artificial intelligence in digestive system diseases.

Areas covered

We retrieved relevant documents on artificial intelligence in digestive tract diseases from PubMed and Medline. This review elaborates on the knowledge of computer-aided diagnosis in digestive endoscopy.

Expert opinion

Artificial intelligence significantly improves diagnostic accuracy, reduces physicians’ workload, and provides a shred of evidence for clinical diagnosis and treatment. Shortly, artificial intelligence will have high application value in the field of medicine.

KEYWORDS:

• Artificial intelligence
• deep learning
• digestive system
• endoscopic
• diagnosis

Article highlights

• Deep learning (DL), represented by convolutional neural networks (CNN), is the most widely used artificial intelligence (AI) in medicine.

• Several prospective randomised controlled trials have demonstrated the effectiveness of computer-aided diagnosis (CADx).

• Computer-aided detection (CADe) and CADx can improve the detection rate of early gastrointestinal cancer.

• The DL of endoscopes has been extensively studied. Cutting-edge research has been transformed from image recognition to video recognition.

• Real-time monitoring will become a critical point in endoscopic research.

• There are also many pieces of research on AI in pathology, imaging, and laboratory tests, and these tests should be integrated in the future to develop CADx with higher diagnostic performance.

Declaration of interests

The authors have no relevant affiliations or financial involvement with any organisation or entity, including employment, consultancies, honoraria, stock ownership or options, expert testimony, grants or patents received or pending, or royalties.

Reviewer disclosures

Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.

Additional information

Funding

This paper was not funded.