Deep Learning-Based Attenuation Correction Improves Diagnostic Accuracy of Cardiac SPECT

Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach

BACKGROUND

Computed tomography attenuation correction (CTAC) is commonly used in cardiac SPECT imaging to reduce soft-tissue attenuation artifacts. However, CTAC is prone to inaccuracies due to CT artifacts and SPECT-CT mismatch, along with additional radiation exposure to patients. Thus, these limitations have led to increasing interest in CT-free AC, with deep learning (DL) offering promising solutions. We proposed a new DL-based CT-free AC methods for cardiac SPECT.

METHODS

We developed a feature alignment attenuation correction network (FA-ACNet) based on the 3D U-Net framework to generate predicted DL-based AC SPECT (Deep AC). The network was trained on 167 cardiac SPECT/CT studies using 5-fold cross validation and tested in an independent testing set (n = 35), with CTAC serving as the reference. During training, multi-scale features from non-attenuation-corrected (NAC) SPECT and CT were processed separately and then aligned with the encoded features from NAC SPECT using adversarial learning and distance metric learning techniques. The performance of FA-ACNet was evaluated using mean square error (MSE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). Additionally, semi-quantitative evaluation of Deep AC images was performed and compared to CTAC using Bland-Altman plots.

RESULTS

FA-ACNet achieved an MSE of 16.94 ± 2.03 × 10- 6, SSIM of 0.9955 ± 0.0006 and PSNR of 43.73 ± 0.50 after 5-fold cross validation. Compared to U-Net, MSE and PSNR improved by aligning multi-scale features from NAC SPECT and CT with those from NAC SPECT. In the testing set, FA-ACNet achieved an MSE of 11.98 × 10- 6, SSIM of 0.9976 and PSNR of 45.54. The 95% limits of agreement (LoAs) between the Deep AC and CTAC images for the summed stress/rest scores (SSS/SRS) were [- 2.3, 2.8] and [-1.9,2.1] in the training set and testing set respectively. Changes in perfusion categories were observed in 4.19% and 5.9% of studies assessed for global perfusion scores in the training set and testing set.

CONCLUSION

We propose a novel DL-based CT-free AC approach for cardiac SPECT, which can generate AC images without the need for a CT scan. By leveraging multi-scale features from both NAC SPECT and CT, the performance of CT-free AC is significantly enhanced, offering a promising alternative for future DL-based AC strategies.

On the Effect of the Patient Table on Attenuation in Myocardial Perfusion Imaging SPECT

BACKGROUND

The topic of the effect of the patient table on attenuation in myocardial perfusion imaging (MPI) SPECT is gaining new relevance due to deep learning methods. Existing studies on this effect are old, rare and only consider phantom measurements, not patient studies. This study investigates the effect of the patient table on attenuation based on the difference between reconstructions of phantom scans and polar maps of patient studies.

METHODS

Jaszczak phantom scans are acquired according to quality control and MPI procedures. An algorithm is developed to automatically remove the patient table from the CT for attenuation correction. The scans are then reconstructed with attenuation correction either with or without the patient table in the CT. The reconstructions are compared qualitatively and on the basis of their percentage difference. In addition, a small retrospective cohort of 15 patients is examined by comparing the resulting polar maps. Polar maps are compared qualitatively and based on the segment perfusion scores.

RESULTS

The phantom reconstructions look qualitatively similar in both the quality control and MPI procedures. The percentage difference is highest in the lower part of the phantom, but it always remains below 17.5%. Polar maps from patient studies also look qualitatively similar. Furthermore, the segment scores are not significantly different (p=0.83).

CONCLUSIONS

The effect of the patient table on attenuation in MPI SPECT is negligible.

The role of deep learning in myocardial perfusion imaging for diagnosis and prognosis: A systematic review

The development of state-of-the-art algorithms for computer visualization has led to a growing interest in applying deep learning (DL) techniques to the field of medical imaging. DL-based algorithms have been extensively utilized in various aspects of cardiovascular imaging, and one notable area of focus is single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI), which is regarded as the gold standard for non-invasive diagnosis of myocardial ischemia. However, due to the complex decision-making process of DL based on convolutional neural networks (CNNs), the explainability of DL results has become a significant area of research, particularly in the field of medical imaging. To better harness the potential of DL and to be well prepared for the ongoing DL revolution in nuclear imaging, this review aims to summarize the recent applications of DL in MPI, with a specific emphasis on the methods in explainable DL for the diagnosis and prognosis of MPI. Furthermore, the challenges and potential directions for future research are also discussed.

A medical disease assisted diagnosis method based on lightweight fuzzy SZGWO-ELM neural network model

The application of neural network model in intelligent diagnosis usually encounters challenges such as continuous adjustment of network parameters and significant cost in training the network facing numerous complex physiological data. To address this challenge, this paper introduces a fuzzy SZGWO-ELM neural network model for medical disease aid diagnosis with fuzzy membership function and ELM network to refine the improved Gray Wolf optimization algorithm. Firstly, the Z-type membership function is introduced as the inertia weight to get a balance for the grey wolf in seeking the optimal solution globally and locally and ensuring fast convergence. Secondly, the S-type membership function is utilized as the adaptive weight to flexibly adjust the grey wolf search step size to facilitate a quick approximation of the optimal solution. Finally, the improved Gray Wolf optimization algorithm is used to optimize the parameters of the ELM neural network model, termed as SZGWO-ELM. This method can eliminate the need for extensive network parameter adjustments and quickly locate the optimal solution to the problem using a lightweight neural network. The performance of the SZGWO is assessed by using metrics like convergence, mean, and standard deviation. Multiple experiments reveal that this method shows superior performance. Furthermore, five publicly accessible medical disease datasets from UCI were conducted to evaluate the performance of SZGWO-ELM network model comparing with different classify model, and the results in terms of precision, sensitivity, specificity and accuracy can achieve 99.52%, 94.14%, 99.26% and 96.08%, respectively, which illustrate that the proposed SZGWO-ELM neural network significantly enhance the model's accuracy, providing better support for doctors in disease diagnosis.

Artificial intelligence-based CT-free quantitative thyroid SPECT for thyrotoxicosis: study protocol of a multicentre, prospective, non-inferiority study

INTRODUCTION

Technetium thyroid uptake (TcTU) measured by single-photon emission CT/CT (SPECT/CT) is an important diagnostic tool for the differential diagnosis of Graves' disease and destructive thyroiditis. Artificial intelligence (AI) may reduce CT-induced radiation exposure by substituting the role of CT in attenuation correction (AC) and thyroid segmentation, thus realising CT-free SPECT. This study aims to compare the diagnostic accuracy for the differential diagnosis of thyrotoxicosis between CT-free SPECT and SPECT/CT.

METHODS AND ANALYSIS

The AI-based CT-free SPECT is a single-blind, multicentre, prospective, non-inferiority, clinical trial with a paired design conducted in the Republic of Korea. Eligible participants are adult (≥19 years old) thyrotoxicosis patients without a previous history of hyperthyroidism or hypothyroidism. Approximately 160 subjects will be screened for quantitative thyroid SPECT/CT using Tc-99m pertechnetate. CT-free thyroid SPECT will be realised using only SPECT data by the trained convolutional neural networks. TcTU will be calculated by SPECT/CT and CT-free SPECT in each subject. The primary endpoint is the accuracy of diagnosing Graves' disease using TcTU. The trial will continue until 152 completed datasets have been enrolled to assess whether the 95% (two-sided) lower confidence limit of the accuracy difference (CT-free SPECT accuracy-SPECT/CT accuracy) for Graves' disease is greater than -0.1. The secondary endpoints include the accuracy of diagnosing destructive thyroiditis and predicting the need for antithyroid drug prescription within 1 month of the SPECT/CT.

ETHICS AND DISSEMINATION

The study protocol has been approved by the institutional review board of Seoul National University Bundang Hospital (IRB No. B-2304-824-301), Konkuk University Medical Center (IRB No. 2023-05-022-006) and Chonnam National University Hospital (IRB No. CNUH-2023-108). Findings will be disseminated as reports, presentations and peer-reviewed journal articles.

TRIAL REGISTRATION NUMBER

KCT0008387, Clinical Research Information Service of the Republic of Korea (CRIS).

Deep-learning-based attenuation map generation in kidney single photon emission computed tomography

BACKGROUND

Accurate attenuation correction (AC) is vital in nuclear medicine, particularly for quantitative single-photon emission computed tomography/computed tomography (SPECT/CT) imaging. This study aimed to establish a CT-free quantification technology in kidney SPECT imaging using deep learning to generate synthetic attenuation maps (μ-maps) from SPECT data, thereby reducing radiation exposure and eliminating the need for CT scans.

RESULTS

A dataset of 1000 Tc-99m DTPA SPECT/CT scans was analyzed for training (n = 800), validation (n = 100), and testing (n = 100) using a modified 3D U-Net for deep learning. The study investigated the use of primary emission and scattering SPECT data, normalization methods, loss function optimization, and up-sampling techniques for optimal μ-map generation. The problem of checkerboard artifacts, unique to μ-map generation from SPECT signals, and the effects of iodine contrast media were evaluated. The addition of scattering SPECT to primary emission SPECT imaging, logarithmic maximum normalization, the combination of absolute difference loss (L1) and three times the absolute gradient difference loss (3 × LGDL), and the nearest-neighbor interpolation significantly enhanced AI performance in μ-map generation (p < 0.00001). Checkerboard artifacts were effectively eliminated using the nearest-neighbor interpolation technique. The developed AI algorithm produced μ-maps neutral to the presence of iodine contrast and showed negligible contrast effects on quantitative SPECT measurement, such as glomerular filtration rate (GFR). The potential reduction in radiation exposure by transitioning to AI-based CT-free SPECT imaging ranges from 45.3 to 78.8%.

CONCLUSION

The study successfully developed and optimized a deep learning algorithm for generating synthetic μ-maps in kidney SPECT images, demonstrating the potential to transition from conventional SPECT/CT to CT-free SPECT imaging for GFR measurement. This advancement represents a significant step towards enhancing patient safety and efficiency in nuclear medicine.

Radiation Detectors and Sensors in Medical Imaging

Medical imaging instrumentation design and construction is based on radiation sources and radiation detectors/sensors. This review focuses on the detectors and sensors of medical imaging systems. These systems are subdivided into various categories depending on their structure, the type of radiation they capture, how the radiation is measured, how the images are formed, and the medical goals they serve. Related to medical goals, detectors fall into two major areas: (i) anatomical imaging, which mainly concerns the techniques of diagnostic radiology, and (ii) functional-molecular imaging, which mainly concerns nuclear medicine. An important parameter in the evaluation of the detectors is the combination of the quality of the diagnostic result they offer and the burden of the patient with radiation dose. The latter has to be minimized; thus, the input signal (radiation photon flux) must be kept at low levels. For this reason, the detective quantum efficiency (DQE), expressing signal-to-noise ratio transfer through an imaging system, is of primary importance. In diagnostic radiology, image quality is better than in nuclear medicine; however, in most cases, the dose is higher. On the other hand, nuclear medicine focuses on the detection of functional findings and not on the accurate spatial determination of anatomical data. Detectors are integrated into projection or tomographic imaging systems and are based on the use of scintillators with optical sensors, photoconductors, or semiconductors. Analysis and modeling of such systems can be performed employing theoretical models developed in the framework of cascaded linear systems analysis (LCSA), as well as within the signal detection theory (SDT) and information theory.

Artificial Intelligence in Nuclear Cardiology: An Update and Future Trends

Myocardial perfusion imaging (MPI), using either single photon emission computed tomography (SPECT) or positron emission tomography (PET), is one of the most commonly ordered cardiac imaging tests, with prominent clinical roles for disease diagnosis and risk prediction. Artificial intelligence (AI) could potentially play a role in many steps along the typical MPI workflow, from image acquisition through to clinical reporting and risk estimation. AI can be utilized to improve image quality, reducing radiation exposure and image acquisition times. Once images are acquired, AI can help optimize motion correction and image registration during image reconstruction or provide direct image attenuation correction. Utilizing these image sets, AI can segment a number of anatomic features from associated computed tomographic imaging or even generate synthetic attenuation imaging. Lastly, AI may play an important role in disease diagnosis or risk prediction by combining the large number of potentially important clinical, stress, and imaging-related variables. This review will focus on the most recent developments in the field, providing clinicians and researchers with a timely update on the field. Additionally, it will discuss future trends including applications of AI during multiple points of the typical MPI workflow to maximize clinical utility and methods to maximize the information that can be obtained from hybrid imaging.

Current status and future directions in artificial intelligence for nuclear cardiology

INTRODUCTION

Myocardial perfusion imaging (MPI) is one of the most commonly ordered cardiac imaging tests. Accurate motion correction, image registration, and reconstruction are critical for high-quality imaging, but this can be technically challenging and has traditionally relied on expert manual processing. With accurate processing, there is a rich variety of clinical, stress, functional, and anatomic data that can be integrated to guide patient management.

AREAS COVERED

PubMed and Google Scholar were reviewed for articles related to artificial intelligence in nuclear cardiology published between 2020 and 2024. We will outline the prominent roles for artificial intelligence (AI) solutions to provide motion correction, image registration, and reconstruction. We will review the role for AI in extracting anatomic data for hybrid MPI which is otherwise neglected. Lastly, we will discuss AI methods to integrate the wealth of data to improve disease diagnosis or risk stratification.

EXPERT OPINION

There is growing evidence that AI will transform the performance of MPI by automating and improving on aspects of image acquisition and reconstruction. Physicians and researchers will need to understand the potential strengths of AI in order to benefit from the full clinical utility of MPI.

Myocardial blood flow quantification with SPECT

INTRODUCTION

The addition of absolute myocardial blood flow (MBF) data improves the diagnostic and prognostic accuracy of relative perfusion imaging with nuclear medicine. Cardiac-specific gamma cameras allow measurement of MBF with SPECT.

METHODS

This paper reviews the evidence supporting the use of SPECT to measure myocardial blood flow (MBF). Studies have evaluated SPECT MBF in large animal models and compared it in humans with invasive angiographic measurements and against the clinical standard of PET MBF. The repeatability of SPECT MBF has been determined in both single-site and multi-center trials.

RESULTS

SPECT MBF has excellent correlation with microspheres in an animal model, with the number of stenoses and fractional flow reserve, and with PET-derived MBF. The inter-user coefficient of variability is ∼20% while the COV of test-retest MBF is ∼30%. SPECT MBF improves the sensitivity and specificity of the detection of multi-vessel disease over relative perfusion imaging and provides incremental value in predicting adverse cardiac events.

CONCLUSION

SPECT MBF is a promising technique for providing clinically valuable information in the assessment of coronary artery disease.

Clinical Feasibility of Deep Learning-Based Attenuation Correction Models for Tl-201 Myocardial Perfusion SPECT

PURPOSE

We aimed to develop deep learning (DL)-based attenuation correction models for Tl-201 myocardial perfusion SPECT (MPS) images and evaluate their clinical feasibility.

PATIENTS AND METHODS

We conducted a retrospective study of patients with suspected or known coronary artery disease. We proposed a DL-based image-to-image translation technique to transform non-attenuation-corrected images into CT-based attenuation-corrected (CT AC ) images. The model was trained using a modified U-Net with structural similarity index (SSIM) loss and mean squared error (MSE) loss and compared with other models. Segment-wise analysis using a polar map and visual assessment for the generated attenuation-corrected (GEN AC ) images were also performed to evaluate clinical feasibility.

RESULTS

This study comprised 657 men and 328 women (age, 65 ± 11 years). Among the various models, the modified U-Net achieved the highest performance with an average mean absolute error of 0.003, an SSIM of 0.990, and a peak signal-to-noise ratio of 33.658. The performance of the model was not different between the stress and rest datasets. In the segment-wise analysis, the myocardial perfusion of the inferior wall was significantly higher in GEN AC images than in the non-attenuation-corrected images in both the rest and stress test sets ( P < 0.05). In the visual assessment of patients with diaphragmatic attenuation, scores of 4 (similar to CT AC images) or 5 (indistinguishable from CT AC images) were assigned to most GEN AC images (65/68).

CONCLUSIONS

Our clinically feasible DL-based attenuation correction models can replace the CT-based method in Tl-201 MPS, and it would be useful in case SPECT/CT is unavailable for MPS.

Activity quantification and dosimetry in radiopharmaceutical therapy with reference to 177Lutetium

Radiopharmaceutical therapy has been widely adopted owing primarily to the development of novel radiopharmaceuticals. To fully utilize the potential of these RPTs in the era of precision medicine, therapy must be optimized to the patient's tumor characteristics. The vastly disparate dosimetry methodologies need to be harmonized as the first step towards this. Multiple factors play a crucial role in the shift from empirical activity administration to patient-specific dosimetry-based administrations from RPT. Factors such as variable responses seen in patients with presumably similar clinical characteristics underscore the need to standardize and validate dosimetry calculations. These efforts combined with ongoing initiatives to streamline the dosimetry process facilitate the implementation of radiomolecular precision oncology. However, various challenges hinder the widespread adoption of personalized dosimetry-based activity administration, particularly when compared to the more convenient and resource-efficient approach of empiric activity administration. This review outlines the fundamental principles, procedures, and methodologies related to image activity quantification and dosimetry with a specific focus on 177Lutetium-based radiopharmaceuticals.

Deep learning approach using SPECT-to-PET translation for attenuation correction in CT-less myocardial perfusion SPECT imaging

OBJECTIVE

Deep learning approaches have attracted attention for improving the scoring accuracy in computed tomography-less single photon emission computed tomography (SPECT). In this study, we proposed a novel deep learning approach referring to positron emission tomography (PET). The aims of this study were to analyze the agreement of representative voxel values and perfusion scores of SPECT-to-PET translation model-generated SPECT (SPECTSPT) against PET in 17 segments according to the American Heart Association (AHA).

METHODS

This retrospective study evaluated the patient-to-patient stress, resting SPECT, and PET datasets of 71 patients. The SPECTSPT generation model was trained (stress: 979 image pairs, rest: 987 image pairs) and validated (stress: 421 image pairs, rest: 425 image pairs) using 31 cases of SPECT and PET image pairs using an image-to-image translation network. Forty of 71 cases of left ventricular base-to-apex short-axis images were translated to SPECTSPT in the stress and resting state (stress: 1830 images, rest: 1856 images). Representative voxel values of SPECT and SPECTSPT in the 17 AHA segments against PET were compared. The stress, resting, and difference scores of 40 cases of SPECT and SPECTSPT were also compared in each of the 17 segments.

RESULTS

For AHA 17-segment-wise analysis, stressed SPECT but not SPECTSPT voxel values showed significant error from PET at basal anterior regions (segments #1, #6), and at mid inferoseptal regions (segments #8, #9, and #10). SPECT, but not SPECTSPT, voxel values at resting state showed significant error at basal anterior regions (segments #1, #2, and #6), and at mid inferior regions (segments #8, #9, and #11). Significant SPECT overscoring was observed against PET in basal-to-apical inferior regions (segments #4, #10, and #15) during stress. No significant overscoring was observed in SPECTSPT at stress, and only moderate over and underscoring in the basal inferior region (segment #4) was found in the resting and difference states.

CONCLUSIONS

Our PET-supervised deep learning model is a new approach to correct well-known inferior wall attenuation in SPECT myocardial perfusion imaging. As standalone SPECT systems are used worldwide, the SPECTSPT generation model may be applied as a low-cost and practical clinical tool that provides powerful auxiliary information for the diagnosis of myocardial blood flow.

Diagnostic performance of a novel deep learning attenuation correction software for MPI using a cardio dedicated CZT camera. Experience in the clinical practice

PURPOSE

To evaluate the diagnostic performance of a novel deep learning attenuation correction software (DLACS) for myocardial perfusion imaging (MPI) using a cadmium-zinc-telluride (CZT) cardio dedicated camera with invasive coronary angiography (ICA) correlation for the diagnosis of coronary artery disease (CAD) in a high-risk population.

METHODS

Retrospective study of 300 patients (196 males [65%], mean age 68 years) from September 2014 to October 2019 undergoing MPI, followed by ICA and evaluated by means of quantitative angiography software, within six months after the MPI. The mean pre-test probability score for coronary disease according to the European Society of Cardiology criteria was 37% for the whole cohort. The MPI was performed in a dedicated CZT cardio camera (D-SPECT Spectrum Dynamics) with a two-day protocol, according to the European Association of Nuclear Medicine guidelines. MPI was retrospectively evaluated with and without the DLACS.

RESULTS

The overall diagnostic accuracy of MPI without DLACS to identify patients with any obstructive CAD at ICA was 87%, sensitivity 94%, specificity 57%, Positive Predictive Value 91% and Negative Predictive Value 64%. Using DLACS the overall diagnostic accuracy was 90%, sensitivity 91%, specificity 86%, Positive Predictive Value 97% and Negative Predictive Value 66%.

CONCLUSION

Use of the novel DLACS enhances performance of the MPI using the CZT D-SPECT camera and achieves improved results, especially avoiding artefacts and reducing the number of false positive results.

Observer studies of image quality of denoising reduced-count cardiac single photon emission computed tomography myocardial perfusion imaging by three-dimensional Gaussian post-reconstruction filtering and deep learning

BACKGROUND

The aim of this research was to asses perfusion-defect detection-accuracy by human observers as a function of reduced-counts for 3D Gaussian post-reconstruction filtering vs deep learning (DL) denoising to determine if there was improved performance with DL.

METHODS

SPECT projection data of 156 normally interpreted patients were used for these studies. Half were altered to include hybrid perfusion defects with defect presence and location known. Ordered-subset expectation-maximization (OSEM) reconstruction was employed with the optional correction of attenuation (AC) and scatter (SC) in addition to distance-dependent resolution (RC). Count levels varied from full-counts (100%) to 6.25% of full-counts. The denoising strategies were previously optimized for defect detection using total perfusion deficit (TPD). Four medical physicist (PhD) and six physician (MD) observers rated the slices using a graphical user interface. Observer ratings were analyzed using the LABMRMC multi-reader, multi-case receiver-operating-characteristic (ROC) software to calculate and compare statistically the area-under-the-ROC-curves (AUCs).

RESULTS

For the same count-level no statistically significant increase in AUCs for DL over Gaussian denoising was determined when counts were reduced to either the 25% or 12.5% of full-counts. The average AUC for full-count OSEM with solely RC and Gaussian filtering was lower than for the strategies with AC and SC, except for a reduction to 6.25% of full-counts, thus verifying the utility of employing AC and SC with RC.

CONCLUSION

We did not find any indication that at the dose levels investigated and with the DL network employed, that DL denoising was superior in AUC to optimized 3D post-reconstruction Gaussian filtering.

On the Use of Artificial Intelligence for Dosimetry of Radiopharmaceutical Therapies

Routine clinical dosimetry along with radiopharmaceutical therapies is key for future treatment personalization. However, dosimetry is considered complex and time-consuming with various challenges amongst the required steps within the dosimetry workflow. The general workflow for image-based dosimetry consists of quantitative imaging, the segmentation of organs and tumors, fitting of the time-activity-curves, and the conversion to absorbed dose. This work reviews the potential and advantages of the use of artificial intelligence to improve speed and accuracy of every single step of the dosimetry workflow.

Deep Learning for Cardiovascular Imaging: A Review

Importance

Artificial intelligence (AI), driven by advances in deep learning (DL), has the potential to reshape the field of cardiovascular imaging (CVI). While DL for CVI is still in its infancy, research is accelerating to aid in the acquisition, processing, and/or interpretation of CVI across various modalities, with several commercial products already in clinical use. It is imperative that cardiovascular imagers are familiar with DL systems, including a basic understanding of how they work, their relative strengths compared with other automated systems, and possible pitfalls in their implementation. The goal of this article is to review the methodology and application of DL to CVI in a simple, digestible fashion toward demystifying this emerging technology.

Observations

At its core, DL is simply the application of a series of tunable mathematical operations that translate input data into a desired output. Based on artificial neural networks that are inspired by the human nervous system, there are several types of DL architectures suited to different tasks; convolutional neural networks are particularly adept at extracting valuable information from CVI data. We survey some of the notable applications of DL to tasks across the spectrum of CVI modalities. We also discuss challenges in the development and implementation of DL systems, including avoiding overfitting, preventing systematic bias, improving explainability, and fostering a human-machine partnership. Finally, we conclude with a vision of the future of DL for CVI.

Conclusions and Relevance

Deep learning has the potential to meaningfully affect the field of CVI. Rather than a threat, DL could be seen as a partner to cardiovascular imagers in reducing technical burden and improving efficiency and quality of care. High-quality prospective evidence is still needed to demonstrate how the benefits of DL CVI systems may outweigh the risks.

Proceedings of the NHLBI Workshop on Artificial Intelligence in Cardiovascular Imaging: Translation to Patient Care

Artificial intelligence (AI) promises to revolutionize many fields, but its clinical implementation in cardiovascular imaging is still rare despite increasing research. We sought to facilitate discussion across several fields and across the lifecycle of research, development, validation, and implementation to identify challenges and opportunities to further translation of AI in cardiovascular imaging. Furthermore, it seemed apparent that a multidisciplinary effort across institutions would be essential to overcome these challenges. This paper summarizes the proceedings of the National Heart, Lung, and Blood Institute-led workshop, creating consensus around needs and opportunities for institutions at several levels to support and advance research in this field and support future translation.

Deep learning approximation of attenuation maps for myocardial perfusion SPECT with an IQ[Formula: see text]SPECT collimator

BACKGROUND

The use of CT images for attenuation correction of myocardial perfusion imaging with single photon emission computer tomography (SPECT) increases diagnostic confidence. However, acquiring a CT image registered to a SPECT image is often not possible because most scanners are SPECT-only. It is possible to approximate attenuation maps using deep learning, but this has not yet been shown to work for a SPECT scanner with an IQ[Formula: see text]SPECT collimator. This study investigates whether it is possible to approximate attenuation maps from non-attenuation-corrected (nAC) reconstructions acquired with a SPECT scanner equipped with an IQ[Formula: see text]SPECT collimator.

METHODS

Attenuation maps and reconstructions were acquired retrospectively for 150 studies. A U-Net was trained to predict attenuation maps from nAC reconstructions using the conditional generative adversarial network framework. Predicted attenuation maps are compared to real attenuation maps using the normalized mean absolute error (NMAE). Attenuation-corrected reconstructions were computed, and the resulting polar maps were compared by pixel and by average perfusion per segment using the absolute percent error (APE). The training and evaluation code is available at https://gitlab.ub.uni-bielefeld.de/thuxohl/mu-map .

RESULTS

Predicted attenuation maps are similar to real attenuation maps, achieving an NMAE of 0.020±0.007. The same is true for polar maps generated from reconstructions with predicted attenuation maps compared to CT-based attenuation maps. Their pixel-wise absolute distance is 3.095±3.199, and the segment-wise APE is 1.155±0.769.

CONCLUSIONS

It is feasible to approximate attenuation maps from nAC reconstructions acquired by a scanner with an IQ[Formula: see text]SPECT collimator using deep learning.

Synthetic Attenuation Correction Maps for SPECT Imaging Using Deep Learning: A Study on Myocardial Perfusion Imaging

(1) Background: The CT-based attenuation correction of SPECT images is essential for obtaining accurate quantitative images in cardiovascular imaging. However, there are still many SPECT cameras without associated CT scanners throughout the world, especially in developing countries. Performing additional CT scans implies troublesome planning logistics and larger radiation doses for patients, making it a suboptimal solution. Deep learning (DL) offers a revolutionary way to generate complementary images for individual patients at a large scale. Hence, we aimed to generate linear attenuation coefficient maps from SPECT emission images reconstructed without attenuation correction using deep learning. (2) Methods: A total of 384 SPECT myocardial perfusion studies that used ^99mTc-sestamibi were included. A DL model based on a 2D U-Net architecture was trained using information from 312 patients. The quality of the generated synthetic attenuation correction maps (ACMs) and reconstructed emission values were evaluated using three metrics and compared to standard-of-care data using Bland-Altman plots. Finally, a quantitative evaluation of myocardial uptake was performed, followed by a semi-quantitative evaluation of myocardial perfusion. (3) Results: In a test set of 66 test patients, the ACM quality metrics were MSSIM = 0.97 ± 0.001 and NMAE = 3.08 ± 1.26 (%), and the reconstructed emission quality metrics were MSSIM = 0.99 ± 0.003 and NMAE = 0.23 ± 0.13 (%). The 95% limits of agreement (LoAs) at the voxel level for reconstructed SPECT images were: [-9.04; 9.00]%, and for the segment level, they were [-11; 10]%. The 95% LoAs for the Summed Stress Score values between the images reconstructed were [-2.8, 3.0]. When global perfusion scores were assessed, only 2 out of 66 patients showed changes in perfusion categories. (4) Conclusion: Deep learning can generate accurate attenuation correction maps from non-attenuation-corrected cardiac SPECT images. These high-quality attenuation maps are suitable for attenuation correction in myocardial perfusion SPECT imaging and could obviate the need for additional imaging in standalone SPECT scanners.

Deep learning-enhanced nuclear medicine SPECT imaging applied to cardiac studies

Deep learning (DL) has a growing popularity and is a well-established method of artificial intelligence for data processing, especially for images and videos. Its applications in nuclear medicine are broad and include, among others, disease classification, image reconstruction, and image de-noising. Positron emission tomography (PET) and single-photon emission computerized tomography (SPECT) are major image acquisition technologies in nuclear medicine. Though several studies have been conducted to apply DL in many nuclear medicine domains, such as cancer detection and classification, few studies have employed such methods for cardiovascular disease applications. The present paper reviews recent DL approaches focused on cardiac SPECT imaging. Extensive research identified fifty-five related studies, which are discussed. The review distinguishes between major application domains, including cardiovascular disease diagnosis, SPECT attenuation correction, image denoising, full-count image estimation, and image reconstruction. In addition, major findings and dominant techniques employed for the mentioned task are revealed. Current limitations of DL approaches and future research directions are discussed.