Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging

Abstract

Artificial intelligence (AI) techniques for image-based segmentation have garnered much attention in recent years. Convolutional neural networks (CNNs) have shown impressive results and potential towards fully automated segmentation in medical imaging, and particularly PET imaging. To cope with the limited access to annotated data needed in supervised AI methods, given tedious and prone-to-error manual delineations, semi-supervised and unsupervised AI techniques have also been explored for segmentation of tumors or normal organs in single and bi-modality scans. This work provides a review of existing AI techniques for segmentation tasks and the evaluation criteria for translational AI-based segmentation efforts towards routine adoption in clinical workflows.

arXiv commentThis manuscript has been accepted for publication in PET Clinics, Volume 16, Issue 4, 2021

References in corpus (10)

• Attention U-Net: Learning Where to Look for the Pancreas
• Image biomarker standardisation initiative
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• A review: Deep learning for medical image segmentation using multi-modality fusion
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
• Experiments on Parallel Training of Deep Neural Network using Model Averaging
• A Survey on Deep Learning of Small Sample in Biomedical Image Analysis
• CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss
• Machine learning methods for accurate delineation of tumors in PET images