Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTowards High-throughput AI-based Segmentation in Oncological PET Imaging
119
0
0.0
(
0
)
Added by
Fereshteh Yousefirizi
Publication date
2021
fields
Physics
and research's language is
English
Ask ChatGPT about the research
No Arabic 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.
rate research
Read More
Tumor segmentation in oncological PET is challenging, a major reason being the partial-volume effects due to the low system resolution and finite voxel size. The latter results in tissue-fraction effects, i.e. voxels contain a mixture of tissue classes. Most conventional methods perform segmentation by exclusively assigning each voxel in the image as belonging to either the tumor or normal tissue classes. Thus, these methods are inherently limited in modeling the tissue-fraction effects. To address this inherent limitation, we propose an estimation-based approach to segmentation. Specifically, we develop a Bayesian method that estimates the posterior mean of fractional volume that the tumor occupies within each image voxel. The proposed method, implemented using an encoder-decoder network, was first evaluated using clinically realistic 2-D simulation studies with known ground truth, in the context of segmenting the primary tumor in PET images of patients with lung cancer. The evaluation studies demonstrated that the method accurately estimated the tumor-fraction areas and significantly outperformed widely used conventional methods, including a U-net-based method, on the task of segmenting the tumor. In addition, the proposed method was relatively insensitive to partial-volume effects and yielded reliable tumor segmentation for different clinical-scanner configurations. The method was then evaluated using clinical images of patients with stage II and III non-small cell lung cancer from ACRIN 6668/RTOG 0235 multi-center clinical trial. Here, the results showed that the proposed method significantly outperformed all other considered methods and yielded accurate tumor segmentation on patient images with dice similarity coefficient of 0.82 (95% CI: 0.78, 0.86). Overall, this study demonstrates the efficacy of the proposed method to accurately segment tumors in PET images.
Objective evaluation of new and improved methods for PET imaging requires access to images with ground truth, as can be obtained through simulation studies. However, for these studies to be clinically relevant, it is important that the simulated images are clinically realistic. In this study, we develop a stochastic and physics-based method to generate realistic oncological two-dimensional (2-D) PET images, where the ground-truth tumor properties are known. The developed method extends upon a previously proposed approach. The approach captures the observed variabilities in tumor properties from actual patient population. Further, we extend that approach to model intra-tumor heterogeneity using a lumpy object model. To quantitatively evaluate the clinical realism of the simulated images, we conducted a human-observer study. This was a two-alternative forced-choice (2AFC) study with trained readers (five PET physicians and one PET physicist). Our results showed that the readers had an average of ~ 50% accuracy in the 2AFC study. Further, the developed simulation method was able to generate wide varieties of clinically observed tumor types. These results provide evidence for the application of this method to 2-D PET imaging applications, and motivate development of this method to generate 3-D PET images.
Dynamic positron emission tomography (dPET) is currently a widely used medical imaging technique for the clinical diagnosis, staging and therapy guidance of all kinds of human cancers. Higher temporal imaging resolution for the early stage of radiotracer metabolism is desired; however, in this case, the reconstructed images with short frame durations always suffer from a limited image signal-to-noise ratio (SNR), which results in unsatisfactory image spatial resolution. In this work, we proposed a dPET processing method that denoises images with short frame durations via pixel-level time-activity curve (TAC) correction based on third-order Hermite interpolation (Pitch-In). The proposed method was validated using total-body dynamic PET image data and compared to several state-of-the-art methods to demonstrate its superior performance in terms of high temporal resolution dPET image noise reduction and imaging contrast. Higher stability and feasibility of the proposed Pitch-In method for future clinical application with high temporal resolution (HTR) dPET imaging can be expected.
We perform a parametric study of the newly developed time-of-flight (TOF) image reconstruction algorithm, proposed for the real-time imaging in total-body Jagiellonian PET (J-PET) scanners. The asymmetric 3D filtering kernel is applied at each most likely position of electron-positron annihilation, estimated from the emissions of back-to-back $gamma$-photons. The optimisation of its parameters is studied using Monte Carlo simulations of a 1-mm spherical source, NEMA IEC and XCAT phantoms inside the ideal J-PET scanner. The combination of high-pass filters which included the TOF filtered back-projection (FBP), resulted in spatial resolution, 1.5 $times$ higher in the axial direction than for the conventional 3D FBP. For realistic $10$-minute scans of NEMA IEC and XCAT, which require a trade-off between the noise and spatial resolution, the need for Gaussian TOF kernel components, coupled with median post-filtering, is demonstrated. The best sets of 3D filter parameters were obtained by the Nelder-Mead minimisation of the mean squared error between the resulting and reference images. The approach allows training the reconstruction algorithm for custom scans, using the IEC phantom, when the temporal resolution is below 50 ps. The image quality parameters, estimated for the best outcomes, were systematically better than for the non-TOF FBP.
Positron Emission Tomography (PET) is a widely-used imaging modality for medical research and clinical diagnosis. Here we demonstrate, through detailed experiments and simulations, an exploration of the benefits of exploiting the quantum entanglement of linear polarisation between the two positron annihilation photons utilised in PET. A new simulation, which includes the predicted influence of quantum entanglement on the interaction of MeV-scale photons with matter, is validated by comparison with experimental data from a cadmium zinc telluride (CZT) PET demonstrator apparatus. In addition, a modified setup enabled the first experimental constraint on entanglement loss for photons in the MeV regime. Quantum-entangled PET offers new methodologies to address key challenges in next generation imaging. As an indication of the potential benefits, we present a simple method to quantify and remove in-patient scatter and random backgrounds using only the quantum entanglement information in the PET events.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
