Search

Your search keyword '"Reader, Andrew J."' showing total 389 results
Start Over Author "Reader, Andrew J."
389 results on '"Reader, Andrew J."'

1. Label Dropout: Improved Deep Learning Echocardiography Segmentation Using Multiple Datasets With Domain Shift and Partial Labelling

Author

Islam, Iman, Puyol-Antón, Esther, Ruijsink, Bram, Reader, Andrew J., and King, Andrew P.

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Echocardiography (echo) is the first imaging modality used when assessing cardiac function. The measurement of functional biomarkers from echo relies upon the segmentation of cardiac structures and deep learning models have been proposed to automate the segmentation process. However, in order to translate these tools to widespread clinical use it is important that the segmentation models are robust to a wide variety of images (e.g. acquired from different scanners, by operators with different levels of expertise etc.). To achieve this level of robustness it is necessary that the models are trained with multiple diverse datasets. A significant challenge faced when training with multiple diverse datasets is the variation in label presence, i.e. the combined data are often partially-labelled. Adaptations of the cross entropy loss function have been proposed to deal with partially labelled data. In this paper we show that training naively with such a loss function and multiple diverse datasets can lead to a form of shortcut learning, where the model associates label presence with domain characteristics, leading to a drop in performance. To address this problem, we propose a novel label dropout scheme to break the link between domain characteristics and the presence or absence of labels. We demonstrate that label dropout improves echo segmentation Dice score by 62% and 25% on two cardiac structures when training using multiple diverse partially labelled datasets., Comment: 10 pages, 5 figures, ASMUS 2024, Held in Conjunction with MICCAI 2024

Published
2024

3. Self-Supervised and Supervised Deep Learning for PET Image Reconstruction

Author

Reader, Andrew J.

Subjects
Electrical Engineering and Systems Science - Image and Video Processing
Abstract

A unified self-supervised and supervised deep learning framework for PET image reconstruction is presented, including deep-learned filtered backprojection (DL-FBP) for sinograms, deep-learned backproject then filter (DL-BPF) for backprojected images, and a more general mapping using a deep network in both the sinogram and image domains (DL-FBP-F). The framework allows varying amounts and types of training data, from the case of having only one single dataset to reconstruct through to the case of having numerous measured datasets, which may or may not be paired with high-quality references. For purely self-supervised mappings, no reference or ground truth data are needed. The self-supervised deep-learned reconstruction operators all use a conventional image reconstruction objective within the loss function (e.g. maximum Poisson likelihood, maximum a posteriori). If it is desired for the reconstruction networks to generalise (i.e. to need either no or minimal retraining for a new measured dataset, but to be fast, ready to reuse), then these self-supervised networks show potential even when previously trained from just one single dataset. For any given new measured dataset, finetuning is however often necessary, and of course the initial training set should ideally go beyond just one dataset if a generalisable network is sought. Example results for the purely self-supervised single-dataset case are shown, but the networks can be i) trained uniquely for any measured dataset to reconstruct from, ii) pretrained on multiple datasets and then used with no retraining for new measured data, iii) pretrained and then finetuned for new measured data, iv) optionally trained with high-quality references. The framework, with its optional inclusion of supervised learning, provides a spectrum of reconstruction approaches by making use of whatever (if any) training data quantities and types are available.

Published
2023

5. Motion-corrected and high-resolution anatomically-assisted (MOCHA) reconstruction of arterial spin labelling MRI

Author

Mehranian, Abolfazl, McGinnity, Colm J., Neji, Radhouene, Prieto, Claudia, Hammers, Alexander, De Vita, Enrico, and Reader, Andrew J.

Subjects
Physics - Medical Physics, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

A model-based reconstruction framework is proposed for MOtion-Corrected and High-resolution anatomically-Assisted (MOCHA) reconstruction of ASL data. In this framework, all low-resolution ASL control-label pairs are used to reconstruct a single high-resolution cerebral blood flow (CBF) map, corrected for rigid motion, point-spread-function (PSF) blurring and partial-volume effect (PVE).Six volunteers were recruited for CBF imaging using PCASL labelling, 2-shot 3D-GRASE sequences and high-resolution T1-weighted MRI. For two volunteers, high-resolution scans with double and triple resolution in the partition direction were additionally collected. Simulations were designed for evaluations against a high-resolution ground-truth CBF map, including a simulated hyper-perfused lesion and hyper/hypo-perfusion abnormalities. MOCHA was compared to standard reconstruction and a 3D linear regression (3DLR) PVE correction method and was further evaluated for acquisitions with reduced control-label pairs and k-space undersampling. MOCHA reconstructions of low-resolution ASL data showed enhanced image quality particularly in the partition direction. In simulations, both MOCHA and 3DLR provided more accurate CBF maps than the standard reconstruction, however MOCHA resulted in the lowest errors and well delineated the abnormalities. MOCHA reconstruction of standard-resolution in-vivo data showed good agreement with higher-resolution scans requiring 4x and 9x longer acquisitions. MOCHA was found to be robust for 4x-accelerated ASL acquisitions, achieved by reduced control-label pairs or k-space undersampling. Conclusion: MOCHA reconstruction reduces PVE by direct reconstruction of CBF maps in the high-resolution space of the corresponding anatomical image, incorporating motion correction and PSF modelling. Following further evaluation, MOCHA should promote the clinical application of ASL., Comment: Original paper

Published
2019

7. Deep learned triple-tracer multiplexed PET myocardial image separation.

Author

Pan, Bolin, Marsden, Paul K., and Reader, Andrew J.

Subjects
NOISE control, COMPUTER simulation, RESEARCH funding, DEEP learning, ANALYSIS of variance, CONCEPTUAL structures, EMISSION-computed tomography, DIGITAL image processing
Abstract

Introduction: In multiplexed positron emission tomography (mPET) imaging, physiological and pathological information from different radiotracers can be observed simultaneously in a single dynamic PET scan. The separation of mPET signals within a single PET scan is challenging due to the fact that the PET scanner measures the sum of the PET signals of all the tracers. The conventional multitracer compartment modeling (MTCM) method requires staggered injections and assumes that the arterial input functions (AIFs) of each tracer are known. Methods: In this work, we propose a deep learning-based method to separate triple-tracer PET images without explicitly knowing the AIFs. A dynamic tripletracer noisy MLEM reconstruction was used as the network input, and dynamic single-tracer noisy MLEM reconstructions were used as training labels. Results: A simulation study was performed to evaluate the performance of the proposed framework on triple-tracer ([18F]FDG+82Rb+[94mTc]sestamibi) PET myocardial imaging. The results show that the proposed methodology substantially reduced the noise level compared to the results obtained from single-tracer imaging. Additionally, it achieved lower bias and standard deviation in the separated single-tracer images compared to the MTCM-based method at both the voxel and region of interest (ROI) levels. Discussion: As compared to MTCM separation, the proposed method uses spatiotemporal information for separation, which improves the separation performance at both the voxel and ROI levels. The simulation study also demonstrates the feasibility and potential of the proposed DL-based method for the application to pre-clinical and clinical studies. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

8. Self-supervised and supervised deep learning for PET image reconstruction.

Author

Reader, Andrew J.

Subjects
*DEEP learning, *IMAGE reconstruction, *POSITRON emission tomography, *SUPERVISED learning
Abstract

A unified self-supervised and supervised deep learning framework for PET image reconstruction is presented, including deep-learned filtered backprojection (DL-FBP) for sinograms, deep-learned backproject then filter (DL-BPF) for backprojected images, and a more general mapping using a deep network in both the sinogram and image domains (DL-FBP-F). The framework accommodates varying amounts and types of training data, from the case of having only one single dataset to reconstruct through to the case of having numerous measured datasets, which may or may not be paired with high-quality references. For purely self-supervised mappings, no reference or ground truth data are required at all, but at minimum just the measured dataset to reconstruct from. Instead of a supplied reference, the output reconstruction from the trainable mapping is forward modelled, and the input data serve as a reference target for this forward-modelled data. The self-supervised deep learned reconstruction operators presented here all use a conventional image reconstruction objective within the loss function (e.g. maximum Poisson likelihood, maximum a posteriori). If it is desired for the reconstruction networks to generalise (i.e. to need either no or minimal retraining for a new measured dataset, but to be fast, ready to reuse), then these self-supervised networks show potential even when previously trained from just one single dataset. For any given new measured dataset, finetuning is however usually necessary for improved agreement with the reconstruction objective, and of course the initial training set should ideally go beyond just one dataset if a generalisable network is sought. This work presents preliminary results for the purely self-supervised single-dataset case, but the proposed networks can be i) trained uniquely for any measured dataset in hand to reconstruct, ii) pretrained on multiple datasets and then used with no retraining for new measured data, iii) pretrained and then finetuned for new measured data, iv) optionally trained with high-quality references. The overall unified framework, with its optional inclusion of supervised learning, provides a wide spectrum of reconstruction approaches by making use of whatever (if any) training data quantities and types are available for image reconstruction. Such a spectrum of reconstruction methods (ranging from purely self-supervised model-driven for a single measured dataset in hand only, through to non-model / fully-data driven) can provide a balance between a conventional reconstruction objective (e.g. data fidelity, with or without regularisation) and the potential risks/benefits of supervised regularisation (which uses training data with high-quality references). [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

9. Quantification of [11C]ABP688 binding in human brain using cerebellum as reference region: biological interpretation and limitations

Author

Milella, Michele Stanislaw, primary, minuzzi, luciano, additional, benkelfat, chawki, additional, soucy, jean-paul, additional, kirlow, alexandre, additional, Schirrmacher, esther, additional, angle, mark, additional, Verhaeghe, Jeroen, additional, massarweh, gassan, additional, reader, andrew j, additional, aliaga, antonio, additional, Peixoto-Santos, Jose Eduardo, additional, guiot, Marie-Christine, additional, kobayashi, eliane, additional, rosa-neto, pedro, additional, and Leyton, Marco, additional

Published
2024
Full Text
View/download PDF

12. Non‐rigid motion‐compensated 3D whole‐heart T2 mapping in a hybrid 3T PET‐MR system.

Author

Schneider, Alina, Munoz, Camila, Hua, Alina, Ellis, Sam, Jeljeli, Sami, Kunze, Karl P., Neji, Radhouene, Reader, Andrew J., Reyes, Eliana, Ismail, Tevfik F., Botnar, René M., and Prieto, Claudia

Subjects
MAGNETIC resonance imaging, POSITRON emission tomography, THREE-dimensional imaging, CARDIAC magnetic resonance imaging, DIAGNOSIS
Abstract

Purpose: Simultaneous PET‐MRI improves inflammatory cardiac disease diagnosis. However, challenges persist in respiratory motion and mis‐registration between free‐breathing 3D PET and 2D breath‐held MR images. We propose a free‐breathing non‐rigid motion‐compensated 3D T2‐mapping sequence enabling whole‐heart myocardial tissue characterization in a hybrid 3T PET‐MR system and provides non‐rigid respiratory motion fields to correct also simultaneously acquired PET data. Methods: Free‐breathing 3D whole‐heart T2‐mapping was implemented on a hybrid 3T PET‐MRI system. Three datasets were acquired with different T2‐preparation modules (0, 28, 55 ms) using 3‐fold undersampled variable‐density Cartesian trajectory. Respiratory motion was estimated via virtual 3D image navigators, enabling multi‐contrast non‐rigid motion‐corrected MR reconstruction. T2‐maps were computed using dictionary‐matching. Approach was tested in phantom, 8 healthy subjects, 14 MR only and 2 PET‐MR patients with suspected cardiac disease and compared with spin echo reference (phantom) and clinical 2D T2‐mapping (in‐vivo). Results: Phantom results show a high correlation (R2 = 0.996) between proposed approach and gold standard 2D T2 mapping. In‐vivo 3D T2‐mapping average values in healthy subjects (39.0 ± 1.4 ms) and patients (healthy tissue) (39.1 ± 1.4 ms) agree with conventional 2D T2‐mapping (healthy = 38.6 ± 1.2 ms, patients = 40.3 ± 1.7 ms). Bland–Altman analysis reveals bias of 1.8 ms and 95% limits of agreement (LOA) of −2.4‐6 ms for healthy subjects, and bias of 1.3 ms and 95% LOA of −1.9 to 4.6 ms for patients. Conclusion: Validated efficient 3D whole‐heart T2‐mapping at hybrid 3T PET‐MRI provides myocardial inflammation characterization and non‐rigid respiratory motion fields for simultaneous PET data correction. Comparable T2 values were achieved with both 3D and 2D methods. Improved image quality was observed in the PET images after MR‐based motion correction. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

13. SIRF: Synergistic Image Reconstruction Framework

Author

Ovtchinnikov, Evgueni, Brown, Richard, Kolbitsch, Christoph, Pasca, Edoardo, da Costa-Luis, Casper, Gillman, Ashley G., Thomas, Benjamin A., Efthimiou, Nikos, Mayer, Johannes, Wadhwa, Palak, Ehrhardt, Matthias J., Ellis, Sam, Jørgensen, Jakob S., Matthews, Julian, Prieto, Claudia, Reader, Andrew J., Tsoumpas, Charalampos, Turner, Martin, Atkinson, David, and Thielemans, Kris

Published
2020
Full Text
View/download PDF

17. Evaluation of Strategies for PET Motion Correction - Manifold Learning vs. Deep Learning

Author

Clough, James R., Balfour, Daniel R., Prieto, Claudia, Reader, Andrew J., Marsden, Paul K., King, Andrew P., Hutchison, David, Series Editor, Kanade, Takeo, Series Editor, Kittler, Josef, Series Editor, Kleinberg, Jon M., Series Editor, Mattern, Friedemann, Series Editor, Mitchell, John C., Series Editor, Naor, Moni, Series Editor, Pandu Rangan, C., Series Editor, Steffen, Bernhard, Series Editor, Terzopoulos, Demetri, Series Editor, Tygar, Doug, Series Editor, Weikum, Gerhard, Series Editor, Stoyanov, Danail, editor, Taylor, Zeike, editor, Kia, Seyed Mostafa, editor, Oguz, Ipek, editor, Reyes, Mauricio, editor, Martel, Anne, editor, Maier-Hein, Lena, editor, Marquand, Andre F., editor, Duchesnay, Edouard, editor, Löfstedt, Tommy, editor, Landman, Bennett, editor, Cardoso, M. Jorge, editor, Silva, Carlos A., editor, Pereira, Sergio, editor, and Meier, Raphael, editor

Published
2018
Full Text
View/download PDF

18. Efficient Deformable Motion Correction for 3-D Abdominal MRI Using Manifold Regression

Author

Chen, Xin, Balfour, Daniel R., Marsden, Paul K., Reader, Andrew J., Prieto, Claudia, King, Andrew P., Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Weikum, Gerhard, Series Editor, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Descoteaux, Maxime, editor, Maier-Hein, Lena, editor, Franz, Alfred, editor, Jannin, Pierre, editor, Collins, D. Louis, editor, and Duchesne, Simon, editor

Published
2017
Full Text
View/download PDF

21. Dynamic Volume Reconstruction from Multi-slice Abdominal MRI Using Manifold Alignment

Author

Chen, Xin, Usman, Muhammad, Balfour, Daniel R., Marsden, Paul K., Reader, Andrew J., Prieto, Claudia, King, Andrew P., Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Weikum, Gerhard, Series Editor, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Ourselin, Sebastien, editor, Joskowicz, Leo, editor, Sabuncu, Mert R., editor, Unal, Gozde, editor, and Wells, William, editor

Published
2016
Full Text
View/download PDF

22. Deep Learned Segmentations of Inflammation for Novel ⁹⁹ m Tc-maraciclatide Imaging of Rheumatoid Arthritis.

Author

Cobb, Robert, Cook, Gary J. R., and Reader, Andrew J.

Subjects
MACHINE learning, RHEUMATOID arthritis, CONVOLUTIONAL neural networks, JOINT pain, DOPPLER ultrasonography
Abstract

Rheumatoid arthritis (RA) is an autoimmune disease that causes joint pain, stiffness, and erosion. Power Doppler ultrasound and MRI are imaging modalities used in detecting and monitoring the disease, but they have limitations. ⁹⁹mTc-maraciclatide gamma camera imaging is a novel technique that can detect joint inflammation at all sites in a single examination and has been shown to correlate with power Doppler ultrasound. In this work, we investigate if machine learning models can be used to automatically segment regions of normal, low, and highly inflamed tissue from 192 ⁹⁹mTc-maraciclatide scans of the hands and wrists from 48 patients. Two models were trained: a thresholding model that learns lower and upper threshold values and a neural-network-based nnU-Net model that uses a convolutional neural network (CNN). The nnU-Net model showed 0.94 ± 0.01, 0.51 ± 0.14, and 0.76 ± 0.16 modified Dice scores for segmenting the normal, low, and highly inflamed tissue, respectively, when compared to clinical segmented labels. This outperforms the thresholding model, which achieved modified Dice scores of 0.92 ± 0.01, 0.14 ± 0.07, and 0.35 ± 0.21, respectively. This is an important first step in developing artificial intelligence (AI) tools to assist clinicians' workflow in the use of this new radiopharmaceutical. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

29. Cocaine cue-induced dopamine release in the human prefrontal cortex

Author

Milella, Michele S., Fotros, Aryandokht, Gravel, Paul, Casey, Kevin F., Larcher, Kevin, Verhaeghe, Jeroen A.J., Cox, Sylvia M.L., Reader, Andrew J., Dagher, Alain, Benkelfat, Chawki, and Leyton, Marco

Subjects
Dopamine -- Health aspects, Prefrontal cortex -- Health aspects, Cocaine -- Health aspects, Health, Psychology and mental health
Abstract

Background: Accumulating evidence indicates that drug-related cues can induce dopamine (DA) release in the striatum of substance abusers. Whether these same cues provoke DA release in the human prefrontal cortex remains unknown. Methods: We used high-resolution positron emission tomography with [[sup.18]F]fallypride to measure cortical and striatal DA D2/3 receptor availability in the presence versus absence of drug-related cues in volunteers with current cocaine dependence. Results: Twelve individuals participated in our study. Among participants reporting a craving response (9 of 12), exposure to the cocaine cues significantly decreased [[sup.18]F]fallypride binding potential ([BP.sub.ND]) values in the medial orbitofrontal cortex and striatum. In all 12 participants, individual differences in the magnitude of craving correlated with [BP.sub.ND] changes in the medial orbitofrontal cortex, dorsolateral prefrontal cortex, anterior cingulate, and striatum. Consistent with the presence of autoreceptors on mesostriatal but not mesocortical DA cell bodies, midbrain [BP.sub.ND] values were significantly correlated with changes in [BP.sub.ND] within the striatum but not the cortex. The lower the midbrain D2 receptor levels, the greater the striatal change in [BP.sub.ND] and self-reported craving. Limitations: Limitations of this study include its modest sample size, with only 2 female participants. Newer tracers might have greater sensitivity to cortical DA release. Conclusion: In people with cocaine use disorders, the presentation of drug-related cues induces DA release within cortical and striatal regions. Both effects are associated with craving, but only the latter is regulated by midbrain autoreceptors. Together, the results suggest that cortical and subcortical DA responses might both influence drug-focused incentive motivational states, but with separate regulatory mechanisms., Introduction The prefrontal cortex (PFC) integrates and interprets sensory information, processing value, directing attention, and planning actions based on experience. (1,2) In cocaine-dependent individuals, these regions and processes are engaged [...]

Published
2016
Full Text
View/download PDF

30. Atlas Construction for Dynamic (4D) PET Using Diffeomorphic Transformations

Author

Bieth, Marie, Lombaert, Hervé, Reader, Andrew J., Siddiqi, Kaleem, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Mori, Kensaku, editor, Sakuma, Ichiro, editor, Sato, Yoshinobu, editor, Barillot, Christian, editor, and Navab, Nassir, editor

Published
2013
Full Text
View/download PDF

43. Memory-Efficient Training for Fully Unrolled Deep Learned PET Image Reconstruction with Iteration-Dependent Targets

Author

Corda-D’Incan, Guillaume, Schnabel, Julia A., and Reader, Andrew J.

Subjects
Deep learning, PET reconstruction
Abstract

We propose a new version of the forward-backward splitting expectation-maximisation network (FBSEM-Net) along with a new memory-efficient training method enabling the training of fully unrolled implementations of 3D FBSEM-Net. FBSEM-Net unfolds the maximum a posteriori expectation-maximisation algorithm and replaces the regularisation step by a residual convolutional neural network. Both the gradient of the prior and the regularisation strength are learned from training data. In this new implementation, three modifications of the original framework are included. First, iteration-dependent networks are used to have a customised regularisation at each iteration. Second, iteration-dependent targets and losses are introduced so that the regularised reconstruction matches the reconstruction of noise-free data at every iteration. Third, sequential training is performed, making training of large unrolled networks far more memory efficient and feasible. Since sequential training permits unrolling a high number of iterations, there is no need for artificial use of the regularisation step as a leapfrogging acceleration. The results obtained on 2D and 3D simulated data show that FBSEM-Net using iteration-dependent targets and losses improves the consistency in the optimisation of the network parameters over different training runs. We also found that using iteration-dependent targets increases the generalisation capabilities of the network. Furthermore, unrolled networks using iteration-dependent regularisation allowed a slight reduction in reconstruction error compared to using a fixed regularisation network at each iteration. Finally, we demonstrate that sequential training successfully addresses potentially serious memory issues during the training of deep unrolled networks. In particular, it enables the training of 3D fully unrolled FBSEM-Net, not previously feasible, by reducing the memory usage by up to 98% compared to a conventional end-to-end training. We also note that the truncation of the backpropagation (due to sequential training) does not notably impact the network’s performance compared to conventional training with a full backpropagation through the entire network.

Published
2021

45. Pre-Training, Transfer Learning and Pretext Learning for a Convolutional Neural Network Applied to Automated Assessment of Clinical PET Image Quality

Author

Hopson, Jessica B., Neji, Radhouene, Dunn, Joel T., McGinnity, Colm J., Flaus, Anthime, Reader, Andrew J., and Hammers, Alexander

Abstract

Positron emission tomography (PET) using a fraction of the usual injected dose would reduce the amount of radioligand needed, as well as the radiation dose to patients and staff, but would compromise reconstructed image quality. For performing the same clinical tasks with such images, a clinical (rather than numerical) image quality assessment is essential. This process can be automated with convolutional neural networks (CNNs). However, the scarcity of clinical quality readings is a challenge. We hypothesize that exploiting easily available quantitative information in pretext learning tasks or using established pre-trained networks could improve CNN performance for predicting clinical assessments with limited data. CNNs were pre-trained to predict injected dose from image patches extracted from eight real patient datasets, reconstructed using between 0.5% and 100% of the available data. Transfer learning with seven different patients was used to predict three clinically scored quality metrics ranging from 0–3: 1) global quality rating; 2) pattern recognition; and 3) diagnostic confidence. This was compared to pre-training via a VGG16 network at varying pre-training levels. Pre-training improved test performance for this task: the mean absolute error of 0.53 (compared to 0.87 without pre-training), was within clinical scoring uncertainty. Future work may include using the CNN for novel reconstruction methods performance assessment.

Published
2023
Full Text
View/download PDF

46. Multi‐modal synergistic PET and MR reconstruction using mutually weighted quadratic priors

Author

Mehranian, Abolfazl, Belzunce, Martin A., McGinnity, Colm J., Bustin, Aurelien, Prieto, Claudia, Hammers, Alexander, and Reader, Andrew J.

Subjects
Models, Statistical, Full Paper, Phantoms, Imaging, Normal Distribution, Brain, Contrast Media, synergistic reconstruction, Signal-To-Noise Ratio, Magnetic Resonance Imaging, White Matter, Healthy Volunteers, Full Papers—Computer Processing and Modeling, Multi‐modal imaging, Fluorodeoxyglucose F18, Positron-Emission Tomography, Image Processing, Computer-Assisted, Humans, Computer Simulation, Dementia, Gray Matter, Artifacts, PET‐MRI, Algorithms
Abstract

Purpose To propose a framework for synergistic reconstruction of PET‐MR and multi‐contrast MR data to improve the image quality obtained from noisy PET data and from undersampled MR data. Theory and Methods Weighted quadratic priors were devised to preserve common boundaries between PET‐MR images while reducing noise, PET Gibbs ringing, and MR undersampling artifacts. These priors are iteratively reweighted using normalized multi‐modal Gaussian similarity kernels. Synergistic PET‐MR reconstructions were built on the PET maximum a posteriori expectation maximization algorithm and the MR regularized sensitivity encoding method. The proposed approach was compared to conventional methods, total variation, and prior‐image weighted quadratic regularization methods. Comparisons were performed on a simulated [18F]fluorodeoxyglucose‐PET and T1/T2‐weighted MR brain phantom, 2 in vivo T1/T2‐weighted MR brain datasets, and an in vivo [18F]fluorodeoxyglucose‐PET and fluid‐attenuated inversion recovery/T1‐weighted MR brain dataset. Results Simulations showed that synergistic reconstructions achieve the lowest quantification errors for all image modalities compared to conventional, total variation, and weighted quadratic methods. Whereas total variation regularization preserved modality‐unique features, this method failed to recover PET details and was not able to reduce MR artifacts compared to our proposed method. For in vivo MR data, our method maintained similar image quality for 3× and 14× accelerated data. Reconstruction of the PET‐MR dataset also demonstrated improved performance of our method compared to the conventional independent methods in terms of reduced Gibbs and undersampling artifacts. Conclusion The proposed methodology offers a robust multi‐modal synergistic image reconstruction framework that can be readily built on existing established algorithms.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results