Anatomically aided PET image reconstruction using deep neural networks

Autor: Evren Asma, Xuezhu Zhang, Jinyi Qi, Tiantian Li, Zhaoheng Xie, Wenyuan Qi
Rok vydání: 2021
Předmět:
anatomical prior
positron emission tomography
Neural Networks
Image quality
Computer science
Image Processing
Oncology and Carcinogenesis
Biomedical Engineering
Bioengineering
Iterative reconstruction
Convolutional neural network
Article
Computer
Computer-Assisted
Positron Emission Tomography Computed Tomography
Image Processing
Computer-Assisted
Humans
Penalty method
Tomography
Artificial neural network
business.industry
Deep learning
deep learning
Pattern recognition
General Medicine
image reconstruction
X-Ray Computed
Other Physical Sciences
Nuclear Medicine & Medical Imaging
Networking and Information Technology R&D (NITRD)
Kernel (image processing)
Positron-Emission Tomography
Biomedical Imaging
Neural Networks
Computer
Artificial intelligence
Tomography
X-Ray Computed
business
Encoder
Zdroj: Med Phys
Medical physics, vol 48, iss 9
ISSN: 2473-4209
0094-2405
DOI: 10.1002/mp.15051
Popis: Purpose The developments of PET/CT and PET/MR scanners provide opportunities for improving PET image quality by using anatomical information. In this paper, we propose a novel co-learning three-dimensional (3D) convolutional neural network (CNN) to extract modality-specific features from PET/CT image pairs and integrate complementary features into an iterative reconstruction framework to improve PET image reconstruction. Methods We used a pretrained deep neural network to represent PET images. The network was trained using low-count PET and CT image pairs as inputs and high-count PET images as labels. This network was then incorporated into a constrained maximum likelihood framework to regularize PET image reconstruction. Two different network structures were investigated for the integration of anatomical information from CT images. One was a multichannel CNN, which treated PET and CT volumes as separate channels of the input. The other one was multibranch CNN, which implemented separate encoders for PET and CT images to extract latent features and fed the combined latent features into a decoder. Using computer-based Monte Carlo simulations and two real patient datasets, the proposed method has been compared with existing methods, including the maximum likelihood expectation maximization (MLEM) reconstruction, a kernel-based reconstruction and a CNN-based deep penalty method with and without anatomical guidance. Results Reconstructed images showed that the proposed constrained ML reconstruction approach produced higher quality images than the competing methods. The tumors in the lung region have higher contrast in the proposed constrained ML reconstruction than in the CNN-based deep penalty reconstruction. The image quality was further improved by incorporating the anatomical information. Moreover, the liver standard deviation was lower in the proposed approach than all the competing methods at a matched lesion contrast. Conclusions The supervised co-learning strategy can improve the performance of constrained maximum likelihood reconstruction. Compared with existing techniques, the proposed method produced a better lesion contrast versus background standard deviation trade-off curve, which can potentially improve lesion detection.
Databáze: OpenAIRE
Externí odkaz: