Algorithm

Obscure gastrointestinal bleeding

Computer science

Radiology

Segmentation

Pattern recognition (psychology)

Predictive value

Internal medicine

Artificial intelligence

Medicine

Artificial neural network

Convolutional neural network

Capsule endoscopy

Gastrointestinal Endoscopy

Background and Aims GI angiectasia (GIA) is the most common small-bowel (SB) vascular lesion, with an inherent risk of bleeding. SB capsule endoscopy (SB-CE) is the currently accepted diagnostic procedure. The aim of this study was to develop a computer-assisted diagnosis tool for the detection of GIA. Methods Deidentified SB-CE still frames featuring annotated typical GIA and normal control still frames were selected from a database. A semantic segmentation images approach associated with a convolutional neural network (CNN) was used for deep-feature extractions and classification. Two datasets of still frames were created and used for machine learning and for algorithm testing. Results The GIA detection algorithm yielded a sensitivity of 100%, a specificity of 96%, a positive predictive value of 96%, and a negative predictive value of 100%. Reproducibility was optimal. The reading process for an entire SB-CE video would take 39 minutes. Conclusions The developed CNN-based algorithm had high diagnostic performances, allowing detection of GIA in SB-CE still frames. This study paves the way for future automated CNN-based SB-CE reading softwares. GI angiectasia (GIA) is the most common small-bowel (SB) vascular lesion, with an inherent risk of bleeding. SB capsule endoscopy (SB-CE) is the currently accepted diagnostic procedure. The aim of this study was to develop a computer-assisted diagnosis tool for the detection of GIA. Deidentified SB-CE still frames featuring annotated typical GIA and normal control still frames were selected from a database. A semantic segmentation images approach associated with a convolutional neural network (CNN) was used for deep-feature extractions and classification. Two datasets of still frames were created and used for machine learning and for algorithm testing. The GIA detection algorithm yielded a sensitivity of 100%, a specificity of 96%, a positive predictive value of 96%, and a negative predictive value of 100%. Reproducibility was optimal. The reading process for an entire SB-CE video would take 39 minutes. The developed CNN-based algorithm had high diagnostic performances, allowing detection of GIA in SB-CE still frames. This study paves the way for future automated CNN-based SB-CE reading softwares.

A neural network algorithm for detection of GI angiectasia during small-bowel capsule endoscopy