作者: Anura Hiraman , Serestina Viriri , Mandlenkosi Gwetu
DOI: 10.1109/ICTAS.2019.8703625
关键词:
摘要: Deep learning has become a methodology of choice in medical imaging; one the applications being classification tasks. The research presented this paper aims to obtain region interest for liver segmentation with aid convolutional neural network classify 2D slices 3D CT volume. This is done by detect containing pelvis and chest so that they can be removed while maintaining abdomen within which occurs. approach evaluated on Medical Image Computing Computer Assisted Intervention (MICCAI) 2007 grand challenge datasets evaluation metrics used are accuracy, recall precision. proved perform well models achieved an accuracy rate 0.99 slice 0.97 classification.