Joint regional uptake quantification of thorium-227 and radium-223 using a multiple-energy-window projection-domain quantitative SPECT method.

Thorium-227 (227Th)-based α-particle radiopharmaceutical therapies (α-RPTs) are currently being investigated in several clinical and pre-clinical studies. After administration, 227Th decays to 223Ra, another α-particle-emitting isotope, which redistributes within the patient. Reliable dose quantification of both 227Th and 223Ra is clinically important, and SPECT may perform this quantification as these isotopes also emit X- and γ-ray photons. However, reliable quantification is challenging for several reasons: the orders-of-magnitude lower activity compared to conventional SPECT, resulting in a very low number of detected counts, the presence of multiple photopeaks, substantial overlap in the emission spectra of these isotopes, and the image-degrading effects in SPECT. To address these issues, we propose a multiple-energy-window projection-domain quantification (MEW-PDQ) method that jointly estimates the regional activity uptake of both 227Th and 223Ra directly using the SPECT projection data from multiple energy windows. We evaluated the method with realistic simulation studies conducted with anthropomorphic digital phantoms, including a virtual imaging trial, in the context of imaging patients with bone metastases of prostate cancer who were treated with 227Th-based α-RPTs. The proposed method yielded reliable (accurate and precise) regional uptake estimates of both isotopes and outperformed state-of-the-art methods across different lesion sizes and contrasts, as well as in the virtual imaging trial. This reliable performance was also observed with moderate levels of intra-regional heterogeneous uptake as well as when there were moderate inaccuracies in the definitions of the support of various regions. Additionally, we demonstrated the effectiveness of using multiple energy windows and the variance of the estimated uptake using the proposed method approached the Cramér-Rao-lower-bound-defined theoretical limit. These results provide strong evidence in support of this method for reliable uptake quantification in 227Th-based α-RPTs.

Deep learning generation of preclinical positron emission tomography (PET) images from low-count PET with task-based performance assessment.

BACKGROUND: Preclinical low-count positron emission tomography (LC-PET) imaging offers numerous advantages such as facilitating imaging logistics, enabling longitudinal studies of long- and short-lived isotopes as well as increasing scanner throughput. However, LC-PET is characterized by reduced photon-count levels resulting in low signal-to-noise ratio (SNR), segmentation difficulties, and quantification uncertainties. PURPOSE: We developed and evaluated a novel deep-learning (DL) architecture-Attention based Residual-Dilated Net (ARD-Net)-to generate standard-count PET (SC-PET) images from LC-PET images. The performance of the ARD-Net framework was evaluated for numerous low count realizations using fidelity-based qualitative metrics, task-based segmentation, and quantitative metrics. METHOD: Patient Derived tumor Xenograft (PDX) with tumors implanted in the mammary fat-pad were subjected to preclinical [18F]-Fluorodeoxyglucose (FDG)-PET/CT imaging. SC-PET images were derived from a 10 min static FDG-PET acquisition, 50 min post administration of FDG, and were resampled to generate four distinct LC-PET realizations corresponding to 10%, 5%, 1.6%, and 0.8% of SC-PET count-level. ARD-Net was trained and optimized using 48 preclinical FDG-PET datasets, while 16 datasets were utilized to assess performance. Further, the performance of ARD-Net was benchmarked against two leading DL-based methods (Residual UNet, RU-Net; and Dilated Network, D-Net) and non-DL methods (Non-Local Means, NLM; and Block Matching 3D Filtering, BM3D). The performance of the framework was evaluated using traditional fidelity-based image quality metrics such as Structural Similarity Index Metric (SSIM) and Normalized Root Mean Square Error (NRMSE), as well as human observer-based tumor segmentation performance (Dice Score and volume bias) and quantitative analysis of Standardized Uptake Value (SUV) measurements. Additionally, radiomics-derived features were utilized as a measure of quality assurance (QA) in comparison to true SC-PET. Finally, a performance ensemble score (EPS) was developed by integrating fidelity-based and task-based metrics. Concordance Correlation Coefficient (CCC) was utilized to determine concordance between measures. The non-parametric Friedman Test with Bonferroni correction was used to compare the performance of ARD-Net against benchmarked methods with significance at adjusted p-value ≤0.01. RESULTS: ARD-Net-generated SC-PET images exhibited significantly better (p ≤ 0.01 post Bonferroni correction) overall image fidelity scores in terms of SSIM and NRMSE at majority of photon-count levels compared to benchmarked DL and non-DL methods. In terms of task-based quantitative accuracy evaluated by SUVMean and SUVPeak, ARD-Net exhibited less than 5% median absolute bias for SUVMean compared to true SC-PET and lower degree of variability compared to benchmarked DL and non-DL based methods in generating SC-PET. Additionally, ARD-Net-generated SC-PET images displayed higher degree of concordance to SC-PET images in terms of radiomics features compared to non-DL and other DL approaches. Finally, the ensemble score suggested that ARD-Net exhibited significantly superior performance compared to benchmarked algorithms (p ≤ 0.01 post Bonferroni correction). CONCLUSION: ARD-Net provides a robust framework to generate SC-PET from LC-PET images. ARD-Net generated SC-PET images exhibited superior performance compared other DL and non-DL approaches in terms of image-fidelity based metrics, task-based segmentation metrics, and minimal bias in terms of task-based quantification performance for preclinical PET imaging.

ISIT-QA: In Silico Imaging Trial to Evaluate a Low-Count Quantitative SPECT Method Across Multiple Scanner-Collimator Configurations for 223Ra-Based Radiopharmaceutical Therapies.

Personalized dose-based treatment planning requires accurate and reproducible noninvasive measurements to ensure safety and effectiveness. Dose estimation using SPECT is possible but challenging for alpha (α)-particle-emitting radiopharmaceutical therapy (α-RPT) because of complex γ-emission spectra, extremely low counts, and various image-degrading artifacts across a plethora of scanner-collimator configurations. Through the incorporation of physics-based considerations and skipping of the potentially lossy voxel-based reconstruction step, a recently developed projection-domain low-count quantitative SPECT (LC-QSPECT) method has the potential to provide reproducible, accurate, and precise activity concentration and dose measures across multiple scanners, as is typically the case in multicenter settings. To assess this potential, we conducted an in silico imaging trial to evaluate the LC-QSPECT method for a 223Ra-based α-RPT, with the trial recapitulating patient and imaging system variabilities. Methods: A virtual imaging trial titled In Silico Imaging Trial for Quantitation Accuracy (ISIT-QA) was designed with the objectives of evaluating the performance of the LC-QSPECT method across multiple scanner-collimator configurations and comparing performance with a conventional reconstruction-based quantification method. In this trial, we simulated 280 realistic virtual patients with bone-metastatic castration-resistant prostate cancer treated with 223Ra-based α-RPT. The trial was conducted with 9 simulated SPECT scanner-collimator configurations. The primary objective of this trial was to evaluate the reproducibility of dose estimates across multiple scanner-collimator configurations using LC-QSPECT by calculating the intraclass correlation coefficient. Additionally, we compared the reproducibility and evaluated the accuracy of both considered quantification methods across multiple scanner-collimator configurations. Finally, the repeatability of the methods was evaluated in a test-retest study. Results: In this trial, data from 268 223RaCl2 treated virtual prostate cancer patients, with a total of 2,903 lesions, were used to evaluate LC-QSPECT. LC-QSPECT provided dose estimates with good reproducibility across the 9 scanner-collimator configurations (intraclass correlation coefficient > 0.75) and high accuracy (ensemble average values of recovery coefficients ranged from 1.00 to 1.02). Compared with conventional reconstruction-based quantification, LC-QSPECT yielded significantly improved reproducibility across scanner-collimator configurations, accuracy, and test-retest repeatability ([Formula: see text] Conclusion: LC-QSPECT provides reproducible, accurate, and repeatable dose estimations in 223Ra-based α-RPT as evaluated in ISIT-QA. These findings provide a strong impetus for multicenter clinical evaluations of LC-QSPECT in dose quantification for α-RPTs.

Need for Objective Task-Based Evaluation of Image Segmentation Algorithms for Quantitative PET: A Study with ACRIN 6668/RTOG 0235 Multicenter Clinical Trial Data.

Reliable performance of PET segmentation algorithms on clinically relevant tasks is required for their clinical translation. However, these algorithms are typically evaluated using figures of merit (FoMs) that are not explicitly designed to correlate with clinical task performance. Such FoMs include the Dice similarity coefficient (DSC), the Jaccard similarity coefficient (JSC), and the Hausdorff distance (HD). The objective of this study was to investigate whether evaluating PET segmentation algorithms using these task-agnostic FoMs yields interpretations consistent with evaluation on clinically relevant quantitative tasks. Methods: We conducted a retrospective study to assess the concordance in the evaluation of segmentation algorithms using the DSC, JSC, and HD and on the tasks of estimating the metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of primary tumors from PET images of patients with non-small cell lung cancer. The PET images were collected from the American College of Radiology Imaging Network 6668/Radiation Therapy Oncology Group 0235 multicenter clinical trial data. The study was conducted in 2 contexts: (1) evaluating conventional segmentation algorithms, namely those based on thresholding (SUVmax40% and SUVmax50%), boundary detection (Snakes), and stochastic modeling (Markov random field-Gaussian mixture model); (2) evaluating the impact of network depth and loss function on the performance of a state-of-the-art U-net-based segmentation algorithm. Results: Evaluation of conventional segmentation algorithms based on the DSC, JSC, and HD showed that SUVmax40% significantly outperformed SUVmax50%. However, SUVmax40% yielded lower accuracy on the tasks of estimating MTV and TLG, with a 51% and 54% increase, respectively, in the ensemble normalized bias. Similarly, the Markov random field-Gaussian mixture model significantly outperformed Snakes on the basis of the task-agnostic FoMs but yielded a 24% increased bias in estimated MTV. For the U-net-based algorithm, our evaluation showed that although the network depth did not significantly alter the DSC, JSC, and HD values, a deeper network yielded substantially higher accuracy in the estimated MTV and TLG, with a decreased bias of 91% and 87%, respectively. Additionally, whereas there was no significant difference in the DSC, JSC, and HD values for different loss functions, up to a 73% and 58% difference in the bias of the estimated MTV and TLG, respectively, existed. Conclusion: Evaluation of PET segmentation algorithms using task-agnostic FoMs could yield findings discordant with evaluation on clinically relevant quantitative tasks. This study emphasizes the need for objective task-based evaluation of image segmentation algorithms for quantitative PET.

Joint regional uptake quantification of Thorium-227 and Radium-223 using a multiple-energy-window projection-domain quantitative SPECT method.

Thorium-227-based alpha-particle radiopharmaceutical therapies ({\alpha}-RPTs) are being investigated in several clinical and pre-clinical studies. After administration, Thorium-227 decays to Radium-223, another alpha-particle-emitting isotope, which redistributes within the patient. Reliable dose quantification of both Thorium-227 and Radium-223 is clinically important, and SPECT may perform this quantification as these isotopes also emit X- and gamma-ray photons. However, reliable quantification is challenged by the orders-of-magnitude lower activity compared to conventional SPECT, resulting in a very low number of detected counts, the presence of multiple photopeaks, substantial overlap in the emission spectra of these isotopes, and the image-degrading effects in SPECT. To address these issues, we propose a multiple-energy-window projection-domain quantification (MEW-PDQ) method that jointly estimates the regional activity uptake of both Thorium-227 and Radium-223 directly using the SPECT projection from multiple energy windows. We evaluated the method with realistic simulation studies using anthropomorphic digital phantoms, in the context of imaging patients with bone metastases of prostate cancer and treated with Thorium-227-based {\alpha}-RPTs. The proposed method yielded reliable (accurate and precise) regional uptake estimates of both isotopes and outperformed state-of-the-art methods across different lesion sizes and contrasts, in a virtual imaging trial, as well as with moderate levels of intra-regional heterogeneous uptake and with moderate inaccuracies in the definitions of the support of various regions. Additionally, we demonstrated the effectiveness of using multiple energy windows and the variance of the estimated uptake using the proposed method approached the Cram\'er-Rao-lower-bound-defined theoretical limit.

A quality assurance framework for routine monitoring of deep learning cardiac substructure computed tomography segmentation models in radiotherapy.

BACKGROUND: For autosegmentation models, the data used to train the model (e.g., public datasets and/or vendor-collected data) and the data on which the model is deployed in the clinic are typically not the same, potentially impacting the performance of these models by a process called domain shift. Tools to routinely monitor and predict segmentation performance are needed for quality assurance. Here, we develop an approach to perform such monitoring and performance prediction for cardiac substructure segmentation. PURPOSE: To develop a quality assurance (QA) framework for routine or continuous monitoring of domain shift and the performance of cardiac substructure autosegmentation algorithms. METHODS: A benchmark dataset consisting of computed tomography (CT) images along with manual cardiac substructure delineations of 241 breast cancer radiotherapy patients were collected, including one "normal" image domain of clean images and five "abnormal" domains containing images with artifact (metal, contrast), pathology, or quality variations due to scanner protocol differences (field of view, noise, reconstruction kernel, and slice thickness). The QA framework consisted of an image domain shift detector which operated on the input CT images and a shape quality detector on the output of an autosegmentation model, and a regression model for predicting autosegmentation model performance. The image domain shift detector was composed of a trained denoising autoencoder (DAE) and two hand-engineered image quality features to detect normal versus abnormal domains in the input CT images. The shape quality detector was a variational autoencoder (VAE) trained to estimate the shape quality of the auto-segmentation results. The output from the image domain shift and shape quality detectors was used to train a regression model to predict the per-patient segmentation accuracy, measured by Dice coefficient similarity (DSC) to physician contours. Different regression techniques were investigated including linear regression, Bagging, Gaussian process regression, random forest, and gradient boost regression. Of the 241 patients, 60 were used to train the autosegmentation models, 120 for training the QA framework, and the remaining 61 for testing the QA framework. A total of 19 autosegmentation models were used to evaluate QA framework performance, including 18 convolutional neural network (CNN)-based and one transformer-based model. RESULTS: When tested on the benchmark dataset, all abnormal domains resulted in a significant DSC decrease relative to the normal domain for CNN models ( p < 0.001 $p < 0.001$ ), but only for some domains for the transformer model. No significant relationship was found between the performance of an autosegmentation model and scanner protocol parameters ( p = 0.42 $p = 0.42$ ) except noise ( p = 0.01 $p = 0.01$ ). CNN-based autosegmentation models demonstrated a decreased DSC ranging from 0.07 to 0.41 with added noise, while the transformer-based model was not significantly affected (ANOVA, p = 0.99 $p=0.99$ ). For the QA framework, linear regression models with bootstrap aggregation resulted in the highest mean absolute error (MAE) of 0.041 ± 0.002 $0.041 \pm 0.002$ , in predicted DSC (relative to true DSC between autosegmentation and physician). MAE was lowest when combining both input (image) detectors and output (shape) detectors compared to output detectors alone. CONCLUSIONS: A QA framework was able to predict cardiac substructure autosegmentation model performance for clinically anticipated "abnormal" domain shifts.

Beyond Average: α-Particle Distribution and Dose Heterogeneity in Bone Metastatic Prostate Cancer.

α-particle emitters are emerging as a potent modality for disseminated cancer therapy because of their high linear energy transfer and localized absorbed dose profile. Despite great interest and pharmaceutical development, there is scant information on the distribution of these agents at the scale of the α-particle pathlength. We sought to determine the distribution of clinically approved [223Ra]RaCl2 in bone metastatic castration-resistant prostate cancer at this resolution, for the first time to our knowledge, to inform activity distribution and dose at the near-cell scale. Methods: Biopsy specimens and blood were collected from 7 patients 24 h after administration. 223Ra activity in each sample was recorded, and the microstructure of biopsy specimens was analyzed by micro-CT. Quantitative autoradiography and histopathology were segmented and registered with an automated procedure. Activity distributions by tissue compartment and dosimetry calculations based on the MIRD formalism were performed. Results: We revealed the activity distribution differences across and within patient samples at the macro- and microscopic scales. Microdistribution analysis confirmed localized high-activity regions in a background of low-activity tissue. We evaluated heterogeneous α-particle emission distribution concentrated at bone-tissue interfaces and calculated spatially nonuniform absorbed-dose profiles. Conclusion: Primary patient data of radiopharmaceutical therapy distribution at the small scale revealed that 223Ra uptake is nonuniform. Dose estimates present both opportunities and challenges to enhance patient outcomes and are a first step toward personalized treatment approaches and improved understanding of α-particle radiopharmaceutical therapies.

Need for objective task-based evaluation of AI-based segmentation methods for quantitative PET.

Artificial intelligence (AI)-based methods are showing substantial promise in segmenting oncologic positron emission tomography (PET) images. For clinical translation of these methods, assessing their performance on clinically relevant tasks is important. However, these methods are typically evaluated using metrics that may not correlate with the task performance. One such widely used metric is the Dice score, a figure of merit that measures the spatial overlap between the estimated segmentation and a reference standard (e.g., manual segmentation). In this work, we investigated whether evaluating AI-based segmentation methods using Dice scores yields a similar interpretation as evaluation on the clinical tasks of quantifying metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of primary tumor from PET images of patients with non-small cell lung cancer. The investigation was conducted via a retrospective analysis with the ECOG-ACRIN 6668/RTOG 0235 multi-center clinical trial data. Specifically, we evaluated different structures of a commonly used AI-based segmentation method using both Dice scores and the accuracy in quantifying MTV/TLG. Our results show that evaluation using Dice scores can lead to findings that are inconsistent with evaluation using the task-based figure of merit. Thus, our study motivates the need for objective task-based evaluation of AI-based segmentation methods for quantitative PET.

A list-mode multi-energy window low-count SPECT reconstruction method for isotopes with multiple emission peaks.

BACKGROUND: Single-photon emission computed tomography (SPECT) provides a mechanism to perform absorbed-dose quantification tasks for [Formula: see text]-particle radiopharmaceutical therapies ([Formula: see text]-RPTs). However, quantitative SPECT for [Formula: see text]-RPT is challenging due to the low number of detected counts, the complex emission spectrum, and other image-degrading artifacts. Towards addressing these challenges, we propose a low-count quantitative SPECT reconstruction method for isotopes with multiple emission peaks. METHODS: Given the low-count setting, it is important that the reconstruction method extracts the maximal possible information from each detected photon. Processing data over multiple energy windows and in list-mode (LM) format provide mechanisms to achieve that objective. Towards this goal, we propose a list-mode multi energy window (LM-MEW) ordered-subsets expectation-maximization-based SPECT reconstruction method that uses data from multiple energy windows in LM format and include the energy attribute of each detected photon. For computational efficiency, we developed a multi-GPU-based implementation of this method. The method was evaluated using 2-D SPECT simulation studies in a single-scatter setting conducted in the context of imaging [[Formula: see text]Ra]RaCl[Formula: see text], an FDA-approved RPT for metastatic prostate cancer. RESULTS: The proposed method yielded improved performance on the task of estimating activity uptake within known regions of interest in comparison to approaches that use a single energy window or use binned data. The improved performance was observed in terms of both accuracy and precision and for different sizes of the region of interest. CONCLUSIONS: Results of our studies show that the use of multiple energy windows and processing data in LM format with the proposed LM-MEW method led to improved quantification performance in low-count SPECT of isotopes with multiple emission peaks. These results motivate further development and validation of the LM-MEW method for such imaging applications, including for [Formula: see text]-RPT SPECT.

A Projection-Domain Low-Count Quantitative SPECT Method for α-Particle-Emitting Radiopharmaceutical Therapy.

Single-photon emission-computed tomography (SPECT) provides a mechanism to estimate regional isotope uptake in lesions and at-risk organs after administration of α-particle-emitting radiopharmaceutical therapies (α-RPTs). However, this estimation task is challenging due to the complex emission spectra, the very low number of detected counts (~20 times lower than in conventional SPECT), the impact of stray-radiation-related noise at these low counts, and the multiple image-degrading processes in SPECT. The conventional reconstruction-based quantification methods are observed to be erroneous for α-RPT SPECT. To address these challenges, we developed a low-count quantitative SPECT (LC-QSPECT) method that directly estimates the regional activity uptake from the projection data (obviating the reconstruction step), compensates for stray-radiation-related noise, and accounts for the radioisotope and SPECT physics, including the isotope spectra, scatter, attenuation, and collimator-detector response, using a Monte Carlo-based approach. The method was validated in the context of 3-D SPECT with 223Ra, a commonly used radionuclide for α-RPT. Validation was performed using both realistic simulation studies, including a virtual clinical trial, and synthetic and 3-D-printed anthropomorphic physical-phantom studies. Across all studies, the LC-QSPECT method yielded reliable regional-uptake estimates and outperformed the conventional ordered subset expectation-maximization (OSEM)-based reconstruction and geometric transfer matrix (GTM)-based post-reconstruction partial-volume compensation methods. Furthermore, the method yielded reliable uptake across different lesion sizes, contrasts, and different levels of intralesion heterogeneity. Additionally, the variance of the estimated uptake approached the Cramér-Rao bound-defined theoretical limit. In conclusion, the proposed LC-QSPECT method demonstrated the ability to perform reliable quantification for α-RPT SPECT.

Need for objective task-based evaluation of AI-based segmentation methods for quantitative PET.

Artificial intelligence (AI)-based methods are showing substantial promise in segmenting oncologic positron emission tomography (PET) images. For clinical translation of these methods, assessing their performance on clinically relevant tasks is important. However, these methods are typically evaluated using metrics that may not correlate with the task performance. One such widely used metric is the Dice score, a figure of merit that measures the spatial overlap between the estimated segmentation and a reference standard (e.g., manual segmentation). In this work, we investigated whether evaluating AI-based segmentation methods using Dice scores yields a similar interpretation as evaluation on the clinical tasks of quantifying metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of primary tumor from PET images of patients with non-small cell lung cancer. The investigation was conducted via a retrospective analysis with the ECOG-ACRIN 6668/RTOG 0235 multi-center clinical trial data. Specifically, we evaluated different structures of a commonly used AI-based segmentation method using both Dice scores and the accuracy in quantifying MTV/TLG. Our results show that evaluation using Dice scores can lead to findings that are inconsistent with evaluation using the task-based figure of merit. Thus, our study motivates the need for objective task-based evaluation of AI-based segmentation methods for quantitative PET.

Observer-study-based approaches to quantitatively evaluate the realism of synthetic medical images.

Objective.Synthetic images generated by simulation studies have a well-recognized role in developing and evaluating imaging systems and methods. However, for clinically relevant development and evaluation, the synthetic images must be clinically realistic and, ideally, have the same distribution as that of clinical images. Thus, mechanisms that can quantitatively evaluate this clinical realism and, ideally, the similarity in distributions of the real and synthetic images, are much needed.Approach.We investigated two observer-study-based approaches to quantitatively evaluate the clinical realism of synthetic images. In the first approach, we presented a theoretical formalism for the use of an ideal-observer study to quantitatively evaluate the similarity in distributions between the real and synthetic images. This theoretical formalism provides a direct relationship between the area under the receiver operating characteristic curve, AUC, for an ideal observer and the distributions of real and synthetic images. The second approach is based on the use of expert-human-observer studies to quantitatively evaluate the realism of synthetic images. In this approach, we developed a web-based software to conduct two-alternative forced-choice (2-AFC) experiments with expert human observers. The usability of this software was evaluated by conducting a system usability scale (SUS) survey with seven expert human readers and five observer-study designers. Further, we demonstrated the application of this software to evaluate a stochastic and physics-based image-synthesis technique for oncologic positron emission tomography (PET). In this evaluation, the 2-AFC study with our software was performed by six expert human readers, who were highly experienced in reading PET scans, with years of expertise ranging from 7 to 40 years (median: 12 years, average: 20.4 years).Main results.In the ideal-observer-study-based approach, we theoretically demonstrated that the AUC for an ideal observer can be expressed, to an excellent approximation, by the Bhattacharyya distance between the distributions of the real and synthetic images. This relationship shows that a decrease in the ideal-observer AUC indicates a decrease in the distance between the two image distributions. Moreover, a lower bound of ideal-observer AUC = 0.5 implies that the distributions of synthetic and real images exactly match. For the expert-human-observer-study-based approach, our software for performing the 2-AFC experiments is available athttps://apps.mir.wustl.edu/twoafc. Results from the SUS survey demonstrate that the web application is very user friendly and accessible. As a secondary finding, evaluation of a stochastic and physics-based PET image-synthesis technique using our software showed that expert human readers had limited ability to distinguish the real images from the synthetic images.Significance.This work addresses the important need for mechanisms to quantitatively evaluate the clinical realism of synthetic images. The mathematical treatment in this paper shows that quantifying the similarity in the distribution of real and synthetic images is theoretically possible by using an ideal-observer-study-based approach. Our developed software provides a platform for designing and performing 2-AFC experiments with human observers in a highly accessible, efficient, and secure manner. Additionally, our results on the evaluation of the stochastic and physics-based image-synthesis technique motivate the application of this technique to develop and evaluate a wide array of PET imaging methods.

Blind Image Restoration Enhances Digital Autoradiographic Imaging of Radiopharmaceutical Tissue Distribution.

Digital autoradiography (DAR) is a powerful tool to quantitatively determine the distribution of a radiopharmaceutical within a tissue section and is widely used in drug discovery and development. However, the low image resolution and significant background noise can result in poor correlation, even errors, between radiotracer distribution, anatomic structure, and molecular expression profiles. Differing from conventional optical systems, the point-spread function in DAR is determined by properties of radioisotope decay, phosphor, and digitizer. Calibration of an experimental point-spread function a priori is difficult, prone to error, and impractical. We have developed a content-adaptive restoration algorithm to address these problems. Methods: We model the DAR imaging process using a mixed Poisson-gaussian model and blindly restore the image by a penalized maximum-likelihood expectation-maximization algorithm (PG-PEM). PG-PEM implements a patch-based estimation algorithm with density-based spatial clustering of applications with noise to estimate noise parameters and uses L2 and Hessian Frebonius norms as regularization functions to improve performance. Results: First, PG-PEM outperformed other restoration algorithms at the denoising task (P < 0.01). Next, we implemented PG-PEM on preclinical DAR images (18F-FDG, treated mouse tumor and heart; 18F-NaF, treated mouse femur) and clinical DAR images (bone biopsy sections from 223RaCl2-treated castration-resistant prostate cancer patients). DAR images restored by PG-PEM of all samples achieved a significantly higher effective resolution and contrast-to-noise ratio and a lower SD of background (P < 0.0001). Additionally, by comparing the registration results between the clinical DAR images and the segmented bone masks from the corresponding histologic images, we found that the radiopharmaceutical distribution was significantly improved (P < 0.0001). Conclusion: PG-PEM is able to increase resolution and contrast while robustly accounting for DAR noise and demonstrates the capacity to be widely implemented to improve preclinical and clinical DAR imaging of radiopharmaceutical distribution.

Practical considerations for quantitative clinical SPECT/CT imaging of alpha particle emitting radioisotopes.

Rationale: Alpha particle emitting radiopharmaceuticals are generating considerable interest for the treatment of disseminated metastatic disease. Molecular imaging of the distribution of these agents is critical to safely and effectively maximize the clinical potential of this emerging drug class. The present studies aim to investigate the feasibility and limitations of quantitative SPECT for 223Ra, 225Ac and 227Th. Methods: Three state-of-the-art SPECT/CT systems were investigated: the GE Discovery NM/CT 670, the GE Optima NM/CT 640, and the Siemens Symbia T6. A series of phantoms, including the NEMA IEC Body phantom, were used to compare and calibrate each camera. Additionally, anthropomorphic physical tumor and vertebrae phantoms were developed and imaged to evaluate the quantitative imaging protocol. Results: This work describes and validates a methodology to calibrate each clinical system. The efficiency of each gamma camera was analyzed and compared. Using the calibration factors obtained with the NEMA phantom, we were able to quantify the activity in 3D-printed tissue phantoms with an error of 2.1%, 3.5% and 11.8% for 223Ra, 225Ac, and 227Th, respectively. Conclusion: The present study validates that quantitative SPECT/CT imaging of 223Ra, 225Ac, and 227Th is achievable but that careful considerations for camera configuration are required. These results will aid in future implementation of SPECT-based patient studies and will help to identify the limiting factors for accurate image-based quantification with alpha particle emitting radionuclides.

Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging.

Artificial intelligence (AI) techniques for image-based segmentation have garnered much attention in recent years. Convolutional neural networks have shown impressive results and potential toward 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 bimodality scans. This work reviews existing AI techniques for segmentation tasks and the evaluation criteria for translational AI-based segmentation efforts toward routine adoption in clinical workflows.

A Bayesian approach to tissue-fraction estimation for oncological PET segmentation.

Tumor segmentation in oncological PET is challenging, a major reason being the partial-volume effects (PVEs) that arise due to low system resolution and finite voxel size. The latter results in tissue-fraction effects (TFEs), i.e. voxels contain a mixture of tissue classes. Conventional segmentation methods are typically designed to assign each image voxel as belonging to a certain tissue class. Thus, these methods are inherently limited in modeling TFEs. To address the challenge of accounting for PVEs, and in particular, TFEs, we propose a Bayesian approach to tissue-fraction estimation for oncological PET segmentation. Specifically, this Bayesian approach estimates the posterior mean of the fractional volume that the tumor occupies within each image voxel. The proposed method, implemented using a deep-learning-based technique, was first evaluated using clinically realistic 2D 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 PET segmentation methods, including a U-net-based method, on the task of segmenting the tumor. In addition, the proposed method was relatively insensitive to PVEs and yielded reliable tumor segmentation for different clinical-scanner configurations. The method was then evaluated using clinical images of patients with stage IIB/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 (DSC) of 0.82 (95% CI: 0.78, 0.86). In particular, the method accurately segmented relatively small tumors, yielding a high DSC of 0.77 for the smallest segmented cross-section of 1.30 cm2. Overall, this study demonstrates the efficacy of the proposed method to accurately segment tumors in PET images.

A physics-guided modular deep-learning based automated framework for tumor segmentation in PET.

An important need exists for reliable positron emission tomography (PET) tumor-segmentation methods for tasks such as PET-based radiation-therapy planning and reliable quantification of volumetric and radiomic features. To address this need, we propose an automated physics-guided deep-learning-based three-module framework to segment PET images on a per-slice basis. The framework is designed to help address the challenges of limited spatial resolution and lack of clinical training data with known ground-truth tumor boundaries in PET. The first module generates PET images containing highly realistic tumors with known ground-truth using a new stochastic and physics-based approach, addressing lack of training data. The second module trains a modified U-net using these images, helping it learn the tumor-segmentation task. The third module fine-tunes this network using a small-sized clinical dataset with radiologist-defined delineations as surrogate ground-truth, helping the framework learn features potentially missed in simulated tumors. The framework was evaluated in the context of segmenting primary tumors in 18F-fluorodeoxyglucose (FDG)-PET images of patients with lung cancer. The framework's accuracy, generalizability to different scanners, sensitivity to partial volume effects (PVEs) and efficacy in reducing the number of training images were quantitatively evaluated using Dice similarity coefficient (DSC) and several other metrics. The framework yielded reliable performance in both simulated (DSC: 0.87 (95% confidence interval (CI): 0.86, 0.88)) and patient images (DSC: 0.73 (95% CI: 0.71, 0.76)), outperformed several widely used semi-automated approaches, accurately segmented relatively small tumors (smallest segmented cross-section was 1.83 cm2), generalized across five PET scanners (DSC: 0.74 (95% CI: 0.71, 0.76)), was relatively unaffected by PVEs, and required low training data (training with data from even 30 patients yielded DSC of 0.70 (95% CI: 0.68, 0.71)). In conclusion, the proposed automated physics-guided deep-learning-based PET-segmentation framework yielded reliable performance in delineating tumors in FDG-PET images of patients with lung cancer.

Preclinical Single Photon Emission Computed Tomography of Alpha Particle-Emitting Radium-223.

Objective: Dose optimization and pharmacokinetic evaluation of α-particle emitting radium-223 dichloride (223RaCl2) by planar γ-camera or single photon emission computed tomography (SPECT) imaging are hampered by the low photon abundance and injected activities. In this study, we demonstrate SPECT of 223Ra using phantoms and small animal in vivo models. Methods: Line phantoms and mice bearing 223Ra were imaged using a dedicated small animal SPECT by detecting the low-energy photon emissions from 223Ra. Localization of the therapeutic agent was verified by whole-body and whole-limb autoradiography and its radiobiological effect confirmed by immunofluorescence. Results: A state-of-the-art commercial small animal SPECT system equipped with a highly sensitive collimator enables collection of sufficient counts for three-dimensional reconstruction at reasonable administered activities and acquisition times. Line sources of 223Ra in both air and in a water scattering phantom gave a line spread function with a full-width-at-half-maximum of 1.45 mm. Early and late-phase imaging of the pharmacokinetics of the radiopharmaceutical were captured. Uptake at sites of active bone remodeling was correlated with DNA damage from the α particle emissions. Conclusions: This work demonstrates the capability to noninvasively define the distribution of 223RaCl2, a recently approved α-particle-emitting radionuclide. This approach allows quantitative assessment of 223Ra distribution and may assist radiation-dose optimization strategies to improve therapeutic response and ultimately to enable personalized treatment planning.

Joint compensation of motion and partial volume effects by iterative deconvolution incorporating wavelet-based denoising in oncologic PET/CT imaging.

OBJECTIVES: We aim to develop and rigorously evaluate an image-based deconvolution method to jointly compensate respiratory motion and partial volume effects (PVEs) for quantitative oncologic PET imaging, including studying the impact of various reconstruction algorithms on quantification performance. PROCEDURES: An image-based deconvolution method that incorporated wavelet-based denoising within the Lucy-Richardson algorithm was implemented and assessed. The method was evaluated using phantom studies with signal-to-background ratios (SBR) of 4 and 8, and clinical data of 10 patients with 42 lung lesions ≤30 mm in diameter. In each study, PET images were reconstructed using four different algorithms: OSEM-basic, PSF, TOF, and TOFPSF. The performance was quantified using contrast recovery (CR), coefficient of variation (COV) and contrast-to-noise-ratio (CNR) metrics. Further, in each study, variabilities arising due to the four different reconstruction algorithms were assessed. RESULTS: In phantom studies, incorporation of wavelet-based denoising improved COV in all cases. Processing images using proposed method yielded significantly higher CR and CNR particularly in small spheres, for all reconstruction algorithms and all SBRs (P < 0.05). In patient studies, processing images using the proposed method yielded significantly higher CR and CNR (P < 0.05). The choice of the reconstruction algorithm impacted quantification performance for changes in motion amplitude, tumor size and SBRs. CONCLUSIONS: Our results provide strong evidence that the proposed joint-compensation method can yield improved PET quantification. The choice of the reconstruction algorithm led to changes in quantitative accuracy, emphasizing the need to carefully select the right combination of reconstruction-image-based compensation methods.

Practical no-gold-standard evaluation framework for quantitative imaging methods: application to lesion segmentation in positron emission tomography.

Recently, a class of no-gold-standard (NGS) techniques have been proposed to evaluate quantitative imaging methods using patient data. These techniques provide figures of merit (FoMs) quantifying the precision of the estimated quantitative value without requiring repeated measurements and without requiring a gold standard. However, applying these techniques to patient data presents several practical difficulties including assessing the underlying assumptions, accounting for patient-sampling-related uncertainty, and assessing the reliability of the estimated FoMs. To address these issues, we propose statistical tests that provide confidence in the underlying assumptions and in the reliability of the estimated FoMs. Furthermore, the NGS technique is integrated within a bootstrap-based methodology to account for patient-sampling-related uncertainty. The developed NGS framework was applied to evaluate four methods for segmenting lesions from F-Fluoro-2-deoxyglucose positron emission tomography images of patients with head-and-neck cancer on the task of precisely measuring the metabolic tumor volume. The NGS technique consistently predicted the same segmentation method as the most precise method. The proposed framework provided confidence in these results, even when gold-standard data were not available. The bootstrap-based methodology indicated improved performance of the NGS technique with larger numbers of patient studies, as was expected, and yielded consistent results as long as data from more than 80 lesions were available for the analysis.