866 The Use of Deep Learning for The Detection, Characterisation and Prediction of Metastatic Disease From CT: A Systematic Review. (12th October 2021)

• Record Type: Journal Article
• Authors: Shivakumar, N; Chandrashekar, A; Handa, A; Lee, R
• Is Part Of: British journal of surgery. Volume 108:Supplement 6(2021)
• Publication Date: 2021-10-12
• Subjects: Surgery -- Periodicals; 617.005
• DOI: 10.1093/bjs/znab259.939
• Languages: English
• ISSNs: 0007-1323

Abstract

Abstract: Introduction: Computed tomography (CT) is widely used in the clinical setting for the diagnosis, staging and management of cancer. The presence of metastatic disease in cancer has significant implications on most effective treatment options as well as prognosis. With advances in computing technology, deep learning - a form of machine learning - where layers of programmed algorithms are able interpret and recognise patterns may have a potential role in CT image analysis. This review aims to provide an overview on the use of deep learning in CT image analysis in the diagnostic evaluation of metastatic disease. Method: A systematic search on databases Medline, Embase and Central was performed. Retrieved studies were screened as per the inclusion and exclusion criteria. A total of 29 studies were included for which a narrative synthesis was provided Results: With regards to metastatic disease, the studies could be grouped together into three areas of research. Firstly, the use of deep learning on the detection of metastatic disease from CT imaging. Secondly, its use on the characterisation of lesions on CT into metastatic disease. Finally, the use of deep learning to predict the presence or development of metastatic disease based on the primary tumour. Conclusions: Deep learning in CT image analysis could have a potential role in evaluating metastatic disease, however, prospective clinical trials investigating its clinical value is required.