Reducing scan time of paediatric 99mTc-DMSA SPECT via deep learning

Weight-based determination of administered activity in 99mTc-DMSA renal SPECT in infants: are minimum administered activities necessary?

BACKGROUND

The North American consensus guidelines recommend a weight-based administered activity for renal cortical scintigraphy with 99mTc-dimercaptosuccinic acid (DMSA; 1.85 MBq/kg or 0.05 mCi/kg). Patients weighing less than 10 kg are recommended to receive a minimum administered activity of 18.5 MBq (0.5 mCi), irrespective of their weight. This approach is presumably to provide sufficient counts for adequate image quality, but it has not been rigorously evaluated.

OBJECTIVE

To compare the adequacy of image quality of infant DMSA renal SPECT examinations obtained using the minimum administered activity recommended by the consensus guidelines with simulated data utilizing a strict weight-based dosage.

MATERIALS AND METHODS

Phase 1: Datasets of 55 infants (29 females, 26 males, median age 3.0 months and weight 5.6 kg) undergoing DMSA SPECT from 2016 to 2021 were identified with 7 used for training and 48 used for study analysis. Data from patients receiving the administered activity recommended by the consensus guidelines ("full dosage", group A) were processed using binomial resampling to add Poisson noise to mimic a strict weight-based scheme ("simulated reduced dosage", group A'). Three experienced nuclear medicine physicians, who were blinded to group membership and clinical information, independently evaluated adequacy of image quality for clinical interpretation on a 4-point scale. Student's paired t-test was utilized for group comparisons and inter-rater agreements were calculated using kappa statistics. Phase 2: Group A' simulated data were compared to a second cohort of 99mTc-DMSA SPECT cases where the administered activity followed a strict weight-based regime ("true reduced dosage", group B). Subjects weighing between 4-7 kg were selected (group A', 10 patients, 4 females, 6 males, median age 3.00 months and weight 5.35 kg) to compare with similar-weight group B subjects (10 patients, 5 females, 5 males, median age 2.50 months and weight 6.05 kg). The same observers and 4-point scale from phase 1 were used. The Wilcoxon rank sum test was utilized for analysis.

RESULTS

Observers' ratings were combined for analysis resulting in n=144 case-pairs (3 observers × 48 case-pairs) in phase 1. In phase 1, the ratings of groups A and A' were identical for 73.6% (106/144) of case-pairs and never differed by more than ±1 level. No significant rating difference was found between the groups (mean (SD) of 1.17 (0.93) versus 1.22 (0.98), P=0.20). Similarly, in phase 2, no significant rating difference was found between groups A' and B (mean (SD) of 0.80 (0.81) versus 0.50 (0.68), P=0.14).

CONCLUSION

There was no significant difference in the adequacy of image quality of 99mTc-DMSA SPECT examinations using a strict weight-based dosage compared to using the recommended minimum dosage for infants as small as 3 kg.

Deep learning-based approach for acquisition time reduction in ventilation SPECT in patients after lung transplantation

We aimed to evaluate the image quality and diagnostic performance of chronic lung allograft dysfunction (CLAD) with lung ventilation single-photon emission computed tomography (SPECT) images acquired briefly using a convolutional neural network (CNN) in patients after lung transplantation and to explore the feasibility of short acquisition times. We retrospectively identified 93 consecutive lung-transplant recipients who underwent ventilation SPECT/computed tomography (CT). We employed a CNN to distinguish the images acquired in full time from those acquired in a short time. The image quality was evaluated using the structural similarity index (SSIM) loss and normalized mean square error (NMSE). The correlation between functional volume/morphological volume (F/M) ratios of full-time SPECT images and predicted SPECT images was evaluated. Differences in the F/M ratio were evaluated using Bland-Altman plots, and the diagnostic performance was compared using the area under the curve (AUC). The learning curve, obtained using MSE, converged within 100 epochs. The NMSE was significantly lower (P < 0.001) and the SSIM was significantly higher (P < 0.001) for the CNN-predicted SPECT images compared to the short-time SPECT images. The F/M ratio of full-time SPECT images and predicted SPECT images showed a significant correlation (r = 0.955, P < 0.0001). The Bland-Altman plot revealed a bias of -7.90% in the F/M ratio. The AUC values were 0.942 for full-time SPECT images, 0.934 for predicted SPECT images and 0.872 for short-time SPECT images. Our findings suggest that a deep-learning-based approach can significantly curtail the acquisition time of ventilation SPECT, while preserving the image quality and diagnostic accuracy for CLAD.

Nuclear medicine and pediatric nephro-urology: a long-lasting successful partnership

Congenital anomalies of the kidney and urinary tract, as well as urinary infections, are very frequent in children. After the clinical and laboratory evaluation, the first imaging procedure to be done is a renal and bladder ultrasound, but afterwards, a main contribution comes from nuclear medicine. Through minimally invasive and sedation-free procedures, nuclear medicine allows the evaluation of the functional anatomy of the urinary tract, and the quantification of renal function and drainage. If pediatric dosage cards provided by scientific societies are used, radiation exposure can also be low. In the pediatric conditions previously mentioned, nuclear medicine is used both for initial diagnosis and follow-up, mostly in cases of suspicion of ureteropelvic or ureterovesical junction syndromes, as well as vesicoureteral reflux or renal scars of febrile infectious episodes. Pediatric nephro-urology constitutes a significant workload of pediatric nuclear medicine departments. The following paragraphs are a revision of the renal radiopharmaceuticals, as well as the nuclear nephro-urology procedures - dynamic and static renal scintigraphy, and direct and indirect radionuclide cystography. A summary of the techniques, main indications, interpretation criteria and pitfalls will be provided. Some future directions for the field are also pointed out, among which the most relevant is the need for nuclear medicine professionals to use standardized protocols and integrate multidisciplinary teams with other pediatric and adult health professionals that manage these life-long pediatric pathologies, which are recognized as an important cause of adult chronic kidney disease.

Artificial Intelligence for PET and SPECT Image Enhancement

Nuclear medicine imaging modalities such as PET and SPECT are confounded by high noise levels and low spatial resolution, necessitating postreconstruction image enhancement to improve their quality and quantitative accuracy. Artificial intelligence (AI) models such as convolutional neural networks, U-Nets, and generative adversarial networks have shown promising outcomes in enhancing PET and SPECT images. This review article presents a comprehensive survey of state-of-the-art AI methods for PET and SPECT image enhancement and seeks to identify emerging trends in this field. We focus on recent breakthroughs in AI-based PET and SPECT image denoising and deblurring. Supervised deep-learning models have shown great potential in reducing radiotracer dose and scan times without sacrificing image quality and diagnostic accuracy. However, the clinical utility of these methods is often limited by their need for paired clean and corrupt datasets for training. This has motivated research into unsupervised alternatives that can overcome this limitation by relying on only corrupt inputs or unpaired datasets to train models. This review highlights recently published supervised and unsupervised efforts toward AI-based PET and SPECT image enhancement. We discuss cross-scanner and cross-protocol training efforts, which can greatly enhance the clinical translatability of AI-based image enhancement tools. We also aim to address the looming question of whether the improvements in image quality generated by AI models lead to actual clinical benefit. To this end, we discuss works that have focused on task-specific objective clinical evaluation of AI models for image enhancement or incorporated clinical metrics into their loss functions to guide the image generation process. Finally, we discuss emerging research directions, which include the exploration of novel training paradigms, curation of larger task-specific datasets, and objective clinical evaluation that will enable the realization of the full translation potential of these models in the future.

The Past, Present, and Future Role of Artificial Intelligence in Ventilation/Perfusion Scintigraphy: A Systematic Review

Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are amongst the few performed in the emergency setting. V/Q studies have witnessed a long fluctuation in adoption rates in parallel to continuous advances in image processing and computer vision techniques. This review provides an overview on the status of artificial intelligence (AI) in V/Q scintigraphy. To clearly assess the past, current, and future role of AI in V/Q scans, we conducted a systematic Ovid MEDLINE(R) literature search from 1946 to August 5, 2022 in addition to a manual search. The literature was reviewed and summarized in terms of methodologies and results for the various applications of AI to V/Q scans. The PRISMA guidelines were followed. Thirty-one publications fulfilled our search criteria and were grouped into two distinct categories: (1) disease diagnosis/detection (N = 22, 71.0%) and (2) cross-modality image translation into V/Q images (N = 9, 29.0%). Studies on disease diagnosis and detection relied heavily on shallow artificial neural networks for acute pulmonary embolism (PE) diagnosis and were primarily published between the mid-1990s and early 2000s. Recent applications almost exclusively regard image translation tasks from CT to ventilation or perfusion images with modern algorithms, such as convolutional neural networks, and were published between 2019 and 2022. AI research in V/Q scintigraphy for acute PE diagnosis in the mid-90s to early 2000s yielded promising results but has since been largely neglected and thus have yet to benefit from today's state-of-the art machine-learning techniques, such as deep neural networks. Recently, the main application of AI for V/Q has shifted towards generating synthetic ventilation and perfusion images from CT. There is therefore considerable potential to expand and modernize the use of real V/Q studies with state-of-the-art deep learning approaches, especially for workflow optimization and PE detection at both acute and chronic stages. We discuss future challenges and potential directions to compensate for the lag in this domain and enhance the value of this traditional nuclear medicine scan.

Ultrafast cadmium-zinc-telluride-based renal single-photon emission computed tomography: clinical validation

BACKGROUND

One of the main limitations of 99mtechnetium-dimercaptosuccinic acid (DMSA) scan is the long acquisition time.

OBJECTIVE

To evaluate the feasibility of short DMSA scan acquisition times using a cadmium-zinc-telluride-based single-photon emission computed tomography (SPECT) system in children.

MATERIALS AND METHODS

The data of 27 children (median age: 4 years; 16 girls) who underwent DMSA SPECT were retrospectively analyzed. Both planar and SPECT DMSA were performed. SPECT images were analyzed using coronal-simulated planar two-dimensional images. A reduction in SPECT acquisition time was simulated to provide 4 series (SPECT-15 min, SPECT-10 min, SPECT-5 min and SPECT-2.5 min). A direct comparison of the planar and SPECT series was performed, including semi-quantification reproducibility, image quality (mean quality score on a scale of 0 to 2) and inter- and intra-observer reproducibility of the scintigraphic patterns.

RESULTS

The overall image quality score (± standard deviation) was 1.3 (± 0.6) for the planar data set, 1.6 (± 0.5) for the SPECT-15 min data set, 1.4 (± 0.5) for the SPECT-10 min data set, 1.0 (± 0.5) for the SPECT-5 min data set and 0.6 (± 0.6) for the SPECT-2.5 min data set. Median Kappa coefficients for inter-observer agreement between planar and SPECT images were greater than 0.83 for all series and all readers except one reader for the SPECT-2.5 min series (median Kappa coefficient = 0.77).

CONCLUSION

Shortening SPECT acquisitions to 5 min is feasible with minimal impact on images in terms of quality and reproducibility.

Prediction of Recurrent Urinary Tract Infection in Paediatric Patients by Deep Learning Analysis of 99mTc-DMSA Renal Scan

Purpose: Tc-99m dimercaptosuccinic acid (^99mTc-DMSA) renal scan is an important tool for the assessment of childhood urinary tract infection (UTI), vesicoureteral reflux (VUR), and renal scarring. We evaluated whether a deep learning (DL) analysis of ^99mTc-DMSA renal scans could predict the recurrence of UTI better than conventional clinical factors. Methods: the subjects were 180 paediatric patients diagnosed with UTI, who underwent immediate post-therapeutic ^99mTc-DMSA renal scans. The primary outcome was the recurrence of UTI during the follow-up period. For the DL analysis, a convolutional neural network (CNN) model was used. Age, sex, the presence of VUR, the presence of cortical defects on the ^99mTc-DMSA renal scan, split renal function (SRF), and DL prediction results were used as independent factors for predicting recurrent UTI. The diagnostic accuracy for predicting recurrent UTI was statistically compared between independent factors. Results: The sensitivity, specificity and accuracy for predicting recurrent UTI were 44.4%, 88.9%, and 82.2% by the presence of VUR; 44.4%, 76.5%, and 71.7% by the presence of cortical defect; 74.1%, 80.4%, and 79.4% by SRF (optimal cut-off = 45.93%); and 70.4%, 94.8%, and 91.1% by the DL prediction results. There were no significant differences in sensitivity between all independent factors (p > 0.05, for all). The specificity and accuracy of the DL prediction results were significantly higher than those of the other factors. Conclusion: DL analysis of ^99mTc-DMSA renal scans may be useful for predicting recurrent UTI in paediatric patients. It is an efficient supportive tool to predict poor prognosis without visually demonstrable cortical defects in ^99mTc-DMSA renal scans.