Improving the Accuracy of Simultaneously Reconstructed Activity and Attenuation Maps Using Deep Learning

Abstract

Simultaneous reconstruction of activity and attenuation using the maximum-likelihood reconstruction of activity and attenuation (MLAA) augmented by time-of-flight information is a promising method for PET attenuation correction. However, it still suffers from several problems, including crosstalk artifacts, slow convergence speed, and noisy attenuation maps (μ-maps). In this work, we developed deep convolutional neural networks (CNNs) to overcome these MLAA limitations, and we verified their feasibility using a clinical brain PET dataset. We applied the proposed method to one of the most challenging PET cases for simultaneous image reconstruction (F-fluorinated--3-fluoropropyl-2-β-carboxymethoxy-3-β-(4-iodophenyl)nortropane [F-FP-CIT] PET scans with highly specific binding to striatum of the brain). Three different CNN architectures (convolutional autoencoder [CAE], Unet, and Hybrid of CAE) were designed and trained to learn a CT-derived μ-map (μ-CT) from the MLAA-generated activity distribution and μ-map (μ-MLAA). The PET/CT data of 40 patients with suspected Parkinson disease were used for 5-fold cross-validation. For the training of CNNs, 800,000 transverse PET and CT slices augmented from 32 patient datasets were used. The similarity to μ-CT of the CNN-generated μ-maps (μ-CAE, μ-Unet, and μ-Hybrid) and μ-MLAA was compared using Dice similarity coefficients. In addition, we compared the activity concentration of specific (striatum) and nonspecific (cerebellum and occipital cortex) binding regions and the binding ratios in the striatum in the PET activity images reconstructed using those μ-maps. The CNNs generated less noisy and more uniform μ-maps than the original μ-MLAA. Moreover, the air cavities and bones were better resolved in the proposed CNN outputs. In addition, the proposed deep learning approach was useful for mitigating the crosstalk problem in the MLAA reconstruction. The Hybrid network of CAE and Unet yielded the most similar μ-maps to μ-CT (Dice similarity coefficient in the whole head = 0.79 in the bone and 0.72 in air cavities), resulting in only about a 5% error in activity and binding ratio quantification. The proposed deep learning approach is promising for accurate attenuation correction of activity distribution in time-of-flight PET systems.

Generation of PET Attenuation Map for Whole-Body Time-of-Flight 18F-FDG PET/MRI Using a Deep Neural Network Trained with Simultaneously Reconstructed Activity and Attenuation Maps

“…Similar to our previous results (22), the activity information enhances the CNN performance. Supplemental Figure 3 shows the results of CNNs trained with and without l-MLAA as input.…”

“…Deep learning-based approaches have been suggested to improve the accuracy of regional PET attenuation correction. In our recent work (22), to mitigate the limitations of MLAA in brain PET, deep convolutional neural networks (CNNs) were trained to learn a true CT-derived attenuation map with the MLAA activity and attenuation maps as their inputs. The CNNs generated less noisy and more uniform attenuation maps than original MLAA, resulting in only 5% errors in activity and binding ratio quantification in the most challenging brain PET cases for simultaneous image reconstruction (dopamine transporter imaging).…”

“…In this study, we investigated the feasibility of the deep learningbased approach to whole-body PET/MRI attenuation correction without use of zero echo time or ultrashort echo time data. Similarly to our previous work on the brain PET studies (22), we use MLAAbased activity and attenuation maps as inputs to CNN to learn a CTderived attenuation map. However, we conducted 3-dimensional (3D) patch-based learning instead of 2-dimensional slice-by-slice mapping because whole-body structures are more complex than head region and 3D learning allows better continuity of image intensity in the axial direction.…”

Denoising of Scintillation Camera Images Using a Deep Convolutional Neural Network: A Monte Carlo Simulation Approach

“…There have been recent publications on the use of machine learning algorithms for classification and segmentation purposes (6)(7)(8)(9)(10). CNNs have been used to obtain standard-dose CT and PET images from low-dose data (11,12) and to enhance images by determining scatter correction parameters (13) and CNN-augmented emission-based attenuation correction (14) in PET. Recently, Gong et al used computersimulated PET images to pretrain a denoising CNN and then fine-tuned the CNN with patient data (15).…”

Multi-atlas cardiac PET segmentation

“…Whether denoising images will improve our template-based segmentation is an interesting future research topic [32]. In addition, segmenting myocardium in PET using fast-growing deep learning approach that outperforms conventional signal and image processing algorithms for some applications is of interest [33][34][35][36][37]. Also, the generation of synthetic lesions in PET images will be a useful method to compare the performance of different approaches for myocardial segmentation [32,38,39].…”