Model observers designed to predict human observers in detection tasks are important tools for assessing task-based image quality and optimizing imaging systems, protocol, and reconstruction algorithms. Linear model observers have been widely studied to predict human detection performance, and recently, deep learning model observers (DLMOs) have been developed to improve the prediction accuracy. Most existing DLMOs utilize convolutional neural network (CNN) architectures, which are capable of learning local features while not good at extracting long-distance relations in images. To further improve the performance of CNN-based DLMOs, we investigate a hybrid CNN-Swin Transformer (CNN-SwinT) network as DLMO for PET lesion detection. The hybrid network combines CNN and SwinT encoders, which can capture both local information and global context. We trained the hybrid network on the responses of 8 human observers including 4 radiologists in a two-alternative forced choice (2AFC) experiment with PET images generated by adding simulated lesions to clinical data. We conducted a 9-fold cross-validation experiment to evaluate the proposed hybrid DLMO, compared to conventional linear model observers such as a channelized Hotelling observer (CHO) and a non-prewhitening matched filter (NPWMF). The hybrid CNN-SwinT DLMO predicted human observer responses more accurately than the linear model observers and DLMO with only the CNN encoder. This work demonstrates that the proposed hybrid CNN-SwinT DLMO has the potential as an improved tool for task-based image quality assessment.
Motion artefacts created by patient motion during an MRI scan occur frequently in practice, often rendering the scans clinically unusable and requiring a re-scan. While many methods have been employed to ameliorate the effects of patient motion, these often fall short in practice. In this paper we propose a novel method for detecting and timing patient motion during an MR scan and correcting for the motion artefacts using a deep neural network. The deep neural network contains two input branches that discriminate between patient poses using the motion’s timing. The first branch receives a subset of the k-space data collected during a single dominant patient pose, and the second branch receives the remaining part of the collected k-space data. The proposed method can be applied to artefacts generated by multiple movements of the patient. Furthermore, it can be used to correct motion for the case where k-space has been under-sampled to shorten the scan time, as is common when using methods such as parallel imaging or compressed sensing. Experimental results on both simulated and real MRI data show the efficacy of our approach.
Model observers that replicate human observers are useful tools for assessing image quality based on detection tasks. Linear model observers including nonprewhitening matched filters (NPWMFs) and channelized Hotelling observers (CHOs) have been widely studied and applied successfully to evaluate and optimize detection performance. However, there is still room for improvement in predicting human observer responses in detection tasks. In this study, we used a convolutional neural network to predict human observer responses in a two-alternative forced choice (2AFC) task for PET imaging. Lesion-absent and lesion-present images were reconstructed from clinical PET data with simulated lesions added to the liver and lungs and were used for the 2AFC task. We trained the convolutional neural network to discriminate images that human observers chose as lesion-present and lesion-absent in the 2AFC task. We evaluated the performance of the trained network by calculating the concordance between human observer responses and predicted responses from the network output and compared it to those of NPWMF and CHO. The trained network showed better agreement with human observers than the linear NPWMF and CHO model observers. The results demonstrate the potential for convolutional neural networks as model observers that better predict human performance. Such model observers can be used for optimizing scanner design, imaging protocols, and image reconstruction to improve lesion detection in PET imaging.
We have previously developed a convergent penalized likelihood (PL) image reconstruction algorithm using the relative difference prior (RDP) and showed that it achieves more accurate lesion quantitation compared to ordered subsets expectation maximization (OSEM). We evaluated the detectability of low-contrast liver and lung lesions using the PL-RDP algorithm compared to OSEM. We performed a two-alternative forced choice study using a channelized Hotelling observer model that was previously validated against human observers. Lesion detectability showed a stronger dependence on lesion size for PL-RDP than OSEM. Lesion detectability was improved using time-of-flight (TOF) reconstruction, with greater benefit for the liver compared to the lung and with increasing benefit for decreasing lesion size and contrast. PL detectability was statistically significantly higher than OSEM for 20 mm liver lesions when contrast was ≥0.5 (p<0.05), and TOF PL detectability was statistically significantly higher than TOF OSEM for 15 and 20 mm liver lesions with contrast ≥0.5 and ≥0.25, respectively. For all other cases, there was no statistically significant difference between PL and OSEM (p>0.05). For the range of studied lesion properties, lesion detectability using PL-RDP was equivalent or improved compared to using OSEM.
Ordered Subset Expectation Maximization (OSEM) is currently the most widely used image reconstruction algorithm for clinical PET. However, OSEM does not necessarily provide optimal image quality, and a number of alternative algorithms have been explored. We have recently shown that a penalized likelihood image reconstruction algorithm using the relative difference penalty, block sequential regularized expectation maximization (BSREM), achieves more accurate lesion quantitation than OSEM, and importantly, maintains acceptable visual image quality in clinical wholebody PET. The goal of this work was to evaluate lesion detectability with BSREM versus OSEM. We performed a twoalternative forced choice study using 81 patient datasets with lesions of varying contrast inserted into the liver and lung. At matched imaging noise, BSREM and OSEM showed equivalent detectability in the lungs, and BSREM outperformed OSEM in the liver. These results suggest that BSREM provides not only improved quantitation and clinically acceptable visual image quality as previously shown but also improved lesion detectability compared to OSEM. We then modeled this detectability study, applying both nonprewhitening (NPW) and channelized Hotelling (CHO) model observers to the reconstructed images. The CHO model observer showed good agreement with the human observers, suggesting that we can apply this model to future studies with varying simulation and reconstruction parameters.
KEYWORDS: Mirrors, Luminescence, Imaging systems, 3D image processing, Optical tomography, 3D image reconstruction, Optical filters, 3D metrology, Linear filtering, Electron multiplying charge coupled devices
We have designed a three dimensional (3D) fluorescence optical tomography system for small animal imaging based on
an innovative system geometry that uses a truncated conical mirror which permits the entire surface of the animal to be
viewed simultaneously by a single CCD camera. Compared with traditional approaches that employ a flat mirror, the
conical mirror system has approximately 3 times better measurement sensitivity. By utilizing a fast switching filter wheel
(switching time < 100 milliseconds), emission data at multiple wavelengths can be efficiently collected. An array of
appropriately shaped neutral density filters, mounted on a linear stage, can be used to increase the system measurement
dynamic range by 3 orders of magnitude. An x-y galvo mirror scanning system makes it possible to scan a collimated
laser beam to any location on the mouse surface. A pattern of structured light incident on the animal surface is used to
extract the surface geometry. A finite element based algorithm is applied to model photon propagation in the turbid
media and a preconditioned conjugate gradient (PCG) method is used to solve the large linear system matrix. The
reconstruction algorithm and the system performance are evaluated by phantom experiments.
KEYWORDS: Animal model studies, Tissues, 3D modeling, Finite element methods, Diffusion, Sensors, Bioluminescence, Fluorescence tomography, Optical properties, Data modeling
The forward problem of optical bioluminescence and fluorescence tomography seeks to determine, for a given
3D source distribution, the photon density on the surface of an animal. Photon transport through tissues is
commonly modeled by the diffusion equation. The challenge, then, is to accurately and efficiently solve the
diffusion equation for a realistic animal geometry and heterogeneous tissue types. Fast analytical solvers are
available that can be applied to arbitrary geometries but assume homogeneity of tissue optical properties and
hence have limited accuracy. The finite element method (FEM) with volume tessellation allows reasonably
accurate modeling of both animal geometry and tissue heterogeneity, but this approach is computationally
intensive. The computational challenge is heightened when one is working with multispectral data to improve
source localization and conditioning of the inverse problem. Here we present a fast forward model based on
the Born approximation that falls in between these two approaches. Our model introduces tissue heterogeneity
as perturbations in diffusion and absorption coefficients at rectangular grid points inside a mouse atlas. These
reflect as a correction term added to the homogeneous forward model. We have tested our model by performing
source localization studies first with a biolumnescence simulation setup and then with an experimental setup
using a fluorescent source embedded in an inhomogeneous phantom that mimicks tissue optical properties.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.