Semi-Supervised Segmentation Framework for Gastrointestinal Lesion Diagnosis in Endoscopic Images.

Zenebe Markos LonsekoWenju DuPrince Ebenezer AdjeiChengsi LuoDingcan HuTao GanLinlin ZhuNini Rao

Published in: Journal of personalized medicine (2023)

We explore a semi-supervised lesion segmentation method to employ the full use of multiple unlabeled endoscopic images to improve lesion segmentation accuracy. Experimental results confirmed the potential of our method and outperformed promising results compared with the current related works. The proposed CAD system can minimize diagnostic errors.

Keyphrases

convolutional neural network
deep learning
machine learning
ultrasound guided
coronary artery disease
patient safety
emergency department
optical coherence tomography
adverse drug