A review of medical image detection for cancers in digestive system based on artificial intelligence

ABSTRACT

Introduction: At present, cancer imaging examination relies mainly on manual reading of doctors, which requests a high standard of doctors’ professional skills, clinical experience, and concentration. However, the increasing amount of medical imaging data has brought more and more challenges to radiologists. The detection of digestive system cancer (DSC) based on artificial intelligence (AI) can provide a solution for automatic analysis of medical images and assist doctors to achieve high-precision intelligent diagnosis of cancers.

Areas covered: The main goal of this paper is to introduce the main research methods of the AI based detection of DSC, and provide relevant reference for researchers. Meantime, it summarizes the main problems existing in these methods, and provides better guidance for future research.

Expert commentary: The automatic classification, recognition, and segmentation of DSC can be better realized through the methods of machine learning and deep learning, which minimize the internal information of images that are difficult for humans to discover. In the diagnosis of DSC, the use of AI to assist imaging surgeons can achieve cancer detection rapidly and effectively and save doctors’ diagnosis time. These can lay the foundation for better clinical diagnosis, treatment planning and accurate quantitative evaluation of DSC.

KEYWORDS:

• Digestive system cancer
• artificial intelligence
• medical imaging detection
• deep learning
• computer assist surgery

Article highlights

• The detection methods of DSC based on AI have proved to detect cancer automatically and rapidly and save doctors’ diagnosis time. But their accuracy and robustness need to be further improved.

• The detection methods of DSC based on AI can lay the foundation for better clinical diagnosis, treatment planning and accurate quantitative evaluation of DSC, which is of great significance for realizing intelligent diagnosis.

• Most algorithms are based on online public datasets, resulting in insufficient training data, poor diversity, and relatively single test sets. Therefore, establishing a more comprehensive and representative data set is crucial for algorithm research.

• The classification method of DSC based on AI has achieved much progress, but mainly concentrated on benign and malignant classification, and multi-type tumor classification remains to be studied more.

• At present, the detection network model of DSC can only be applied for specific organs, and the network model of transfer learning will be required in the future research.

Declaration of interest

The authors have no relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript. This includes 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 work was supported by grants from National Key R&D Program of China (2017YFB1104100; 2017YFB1302903), National Natural Science Foundation of China (81971709; 81828003), the Foundation of Ministry of Education of China Science and Technology Development Center (2018C01038), the Foundation of Science and Technology Commission of Shanghai Municipality (19510712200; 16441908400), and Shanghai Jiao Tong University Foundation on Medical and Technological Joint Science Research (YG2016ZD01; ZH20182DA15).