Potential utility of B-type natriuretic peptides in secondary prevention following percutaneous coronary intervention in remote communities of Western Australia.

INTRODUCTION: A third of all acute coronary events that present in the Australian population occur in patients with established coronary heart disease. This study assessed the prognostic value of combined B-type natriuretic peptides (BNP) measurement and quantitative myocardial perfusion scan (MPS) data for cardiac events (CE). MATERIAL AND METHODS: This retrospective cohort study involved 133 patients from rural Western Australia. The cut-off for normality was 6.0 for qualitative summed difference scores (SDS) of MPS and 400 pg/mL for BNP. RESULTS: Patients with no CE had a mean SDS and BNP (1.52 with a 95% CI of 0.34 to 2.69), (175.9 with a 95% CI of 112.7-239.1) that was lower than patients with CE (6.54 with 95% CI 4.18-9.89) (P = 0.0003), (669.1 with 95% CI 543.9-794.3) (P < 0.0001). The sensitivity and specificity of combined testing for predicting CE respectively were 79.6% and 86.3% for SDS, 84.6% and 94.1% for BNP, and 100% and 92.7% for SDS and BNP combined. DISCUSSION AND CONCLUSION: Elevated BNP is marginally superior to MPS in predicting CEs in patients who have previously undergone percutaneous coronary intervention (PCI); however, MPS can identify the region of myocardium most at risk. Routine BNP monitoring in this subgroup may serve as secondary prevention by identifying subclinical disease.

Rural communities are disproportionately affected by preventable coronary heart disease-related deaths and access to cardiac imaging techniques can be infrequent or unavailable.Secondary prevention strategies can reduce hospital readmissions and contribute to improving the management of chronic conditions.This study demonstrated that elevated B-type natriuretic peptides levels were marginally superior to myocardial perfusion scans in predicting cardiac events in patients with prior percutaneous coronary intervention.Monitoring BNP levels in rural patients with prior percutaneous coronary interventions is a relatively non-invasive and inexpensive, and may lead to improved risk estimation, identify the subclinical disease and provoke further investigation as clinically appropriate.

Australian perspectives on artificial intelligence in veterinary practice.

While artificial intelligence (AI) and recent developments in deep learning (DL) have sparked interest in medical imaging, there has been little commentary on the impact of AI on the veterinarian and veterinary imaging technologists. This survey study aimed to understand the attitudes, applications, and concerns among veterinarians and radiography professionals in Australia regarding the rapidly emerging applications of AI. An anonymous online survey was circulated to the members of three Australian veterinary professional organizations. The survey invitations were shared via email and social media with the survey open for 5 months. Among the 84 respondents, there was a high level of acceptance of lower order tasks (e.g., patient registration, triage, and dispensing) and less acceptance of high order task automation (e.g., surgery and interpretation). There was a low priority perception for the role of AI in higher order tasks (e.g., diagnosis, interpretation, and decision making) and high priority for those applications that automate complex tasks (e.g., quantitation, segmentation, reconstruction) or improve image quality (e.g., dose/noise reduction and pseudo CT for attenuation correction). Medico-legal, ethical, diversity, and privacy issues posed moderate or high concern while there appeared to be no concern regarding AI being clinically useful and improving efficiency. Mild concerns included redundancy, training bias, transparency, and validity. Australian veterinarians and veterinary professionals recognize important applications of AI for assisting with repetitive tasks, performing less complex tasks, and enhancing the quality of outputs in medical imaging. There are concerns relating to ethical aspects of algorithm development and implementation.

Concurrent measurement of serum and radiomic biomarkers in the clinical investigation of equine musculoskeletal injuries: A prospective pilot study.

The prevention of musculoskeletal injuries and their related welfare and economic impacts represent an immediate priority for the horse racing industry. This prospective pilot study aimed to evaluate a method to quantitatively analyze scintigraphic features of specific anatomical regions of the horse's appendicular skeleton in combination with secondary measures of musculoskeletal metabolism in blood. Twelve horses referred for scintigraphic assessment of lameness were enrolled. Blood samples were collected immediately prior to the administration of radiotracer. Serum concentrations associated with bone turnover were determined for the following biomarkers: C-terminal telopeptides of type I collagen, proteoglycans and sulfated glycosaminoglycans, collagen type II, osteocalcin, and procollagen II C-terminal propeptide. Scintigraphic images underwent radiomic analysis of discrete regions of the distal limbs and these data were correlated to bone turnover markers. Three lame horses demonstrated asymmetrical radiomic abnormalities. The concentration of osteocalcin in the lame horses was significantly higher when compared to the control group, while no significant changes were observed for the other screened serum biomarkers. Findings from the current study provided evidence that radiomic analysis of equine scintigraphy is feasible. This method has the potential to interrogate which serum markers are associated with musculoskeletal injuries.

Intelligent imaging: Applications of machine learning and deep learning in radiology.

Artificial intelligence (AI) in radiology is transforming medical image analysis. While applications in triaging for priority reporting and radiomic feature analysis have been widely reported, perhaps the most important applications lie in noise reduction, image optimization following dose reduction strategies, image reconstruction direct from projection data and generation of pseudo-CT for attenuation correction. There are common beneficial applications, and potential risks, between human radiology and veterinary radiology. Artificial intelligence may see recrafting of some responsibilities but offers AI augmentation of human driven systems. The redundancy afforded by human augmentation of AI and AI autonomy are not on the horizon, but rather are already here.

The deep radiomic analytics pipeline.

Radiomics refers to the process of extracting useful imaging features from radiological data. Conventional radiomics like standard uptake value, intensity histograms, or phase images involve hand-crafted (manual) or automated regions of interest (computer generated), however, artificial intelligence (AI) segmentation (AI-augmented radiomics) has recently emerged. Radiomic feature extraction extends image insights beyond simply data quantitation and provides additional insights to aid semantic reporting. Deeper layers of a convolutional neural network produce more abstract radiomic features that are referred to as deep radiomics. The application of radiomics in veterinary radiology is already firmly entrenched using hand-crafted and automated computer-generated radiomic features in X-ray, nuclear medicine, CT, ultrasound, and MRI. There is an opportunity for veterinary radiology to capitalize on advances in AI, machine learning, and deep learning to enrich imaging interpretation using deep radiomic feature extraction. This manuscript aims to provide a general understanding of radiomics and deep radiomics, and to arm readers with the vernacular to progress discussion and development of deep radiomics in veterinary imaging.

ChatGPT and Patient Information in Nuclear Medicine: GPT-3.5 Versus GPT-4.

The GPT-3.5-powered ChatGPT was released in late November 2022 powered by the generative pretrained transformer (GPT) version 3.5. It has emerged as a readily accessible source of patient information ahead of medical procedures. Although ChatGPT has purported benefits for supporting patient education and information, actual capability has not been evaluated. Moreover, the March 2023 emergence of paid subscription access to GPT-4 promises further enhanced capabilities requiring evaluation. Methods: ChatGPT was used to generate patient information sheets suitable for gaining informed consent for 7 common procedures in nuclear medicine. Responses were generated independently for both GPT-3.5 and GPT-4 architectures. Specific procedures were selected that had a long-standing history of use to avoid any bias associated with the September 2021 learning cutoff that constrains both GPT-3.5 and GPT-4 architectures. Each information sheet was independently evaluated by 3 expert assessors and ranked on the basis of accuracy, appropriateness, currency, and fitness for purpose. Results: ChatGPT powered by GPT-3.5 provided patient information that was appropriate in terms of being patient-facing but lacked accuracy and currency and omitted important information. GPT-3.5 produced patient information deemed not fit for the purpose. GPT-4 provided patient information enhanced across appropriateness, accuracy, and currency, despite some omission of information. GPT-4 produced patient information that was largely fit for the purpose. Conclusion: Although ChatGPT powered by GPT-3.5 is accessible and provides plausible patient information, inaccuracies and omissions present a risk to patients and informed consent. Conversely, GPT-4 is more accurate and fit for the purpose but, at the time of writing, was available only through a paid subscription.

PET/MRI, Part 3: Protocols and Procedures.

CE credit: For CE credit, you can access the test for this article, as well as additional JNMT CE tests, online at https://www.snmmilearningcenter.org Complete the test online no later than March 2025. Your online test will be scored immediately. You may make 3 attempts to pass the test and must answer 75% of the questions correctly to receive Continuing Education Hour (CEH) credit. Credit amounts can be found in the SNMMI Learning Center Activity. SNMMI members will have their CEH credit added to their VOICE transcript automatically; nonmembers will be able to print out a CE certificate upon successfully completing the test. The online test is free to SNMMI members; nonmembers must pay $15.00 by credit card when logging onto the website to take the test.The emergence of PET and MRI as a hybrid modality has demanded new approaches to protocols and procedures. Although protocols for MRI and PET individually lend themselves to synergistic and simultaneous approaches, there are a number of unique challenges and patient preparations that require consideration. This article provides insight into the protocols, procedures, and challenges associated with simultaneous PET/MRI in both adult and pediatric populations. Although protocols may be specific to applications or pathologies of interest, a richer discussion of the clinical applications of PET/MRI is beyond the scope of this article and will be detailed in part 4 of the series. The foundation of PET/MRI protocols is an understanding of the various MRI sequences, which are outlined succinctly. The principles outlined for protocols and procedures are general, and specific application will vary among departments. Given that the procedures for PET are well established among the readership of this journal, this article emphasizes MRI factors unless specific variations in standard PET protocols or procedures are driven by the simultaneous MRI. This article is the third in a 4-part integrated series sponsored by the PET/MR and Publication Committees of the Society of Nuclear Medicine and Molecular Imaging-Technologist Section.

Intelligent Imaging: Anatomy of Machine Learning and Deep Learning.

The emergence of artificial intelligence (AI) in nuclear medicine and radiology has been accompanied by AI commentators and experts predicting that AI would make radiologists, in particular, extinct. More realistic perspectives suggest significant changes will occur in medical practice. There is no escaping the disruptive technology associated with AI, neural networks, and deep learning, the most significant perhaps since the early days of Roentgen, Becquerel, and Curie. AI is an omen, but it need not be foreshadowing a negative event; rather, it is heralding great opportunity. The key to sustainability lies not in resisting AI but in having a deep understanding and exploiting the capabilities of AI in nuclear medicine while mastering those capabilities unique to the human resources.

Intelligent Imaging: Radiomics and Artificial Neural Networks in Heart Failure.

BACKGROUND: Our previous work with 123iodine meta-iodobenzylguanidine (123I-mIBG) radionuclide imaging among patients with cardiomyopathy reported limitations associated with the prognostic power of global parameters derived from planar imaging [1]. Employing multivariate analysis, we further showed the regional washout associated with territories adjacent to infarcted myocardium obtained from single-photon emission computed tomography imaging (SPECT) yielded superior prognostic power over the other planar and SPECT indices in predicting future cardiac events [1]. The aim of this study was to apply an artificial neural network (Neural Analyser version 2.9.5) to the original data from the same patient cohort to evaluate the most potent prognostic index for future cardiac events among patient with cardiomyopathy. METHODS: The original data were reevaluated using an artificial neural network (Neural Analyser version 2.9.5). There were 84 input variables in the original 22 patients from clinical data, electrocardiogram (rest, stress, and continuous ambulatory electrocardiogram recording), transthoracic echocardiography, coronary angiogram, sestamibi myocardial perfusion SPECT, planar and SPECT 123I-mIBG, and genetic and biomarkers, detailed in the previous work. A single binary output was a cardiac event or no cardiac event in the follow-up period. RESULTS: Following training and validation phases, the optimal number of inputs was determined to be two with a training loss of 0.025 and selection loss <0.001. The final architecture had inputs of a change in left ventricular ejection fraction (Δ > -10%) and 123I-mIBG planar global washout (>30%), two hidden layers of 6 and 1 node, respectively, and a binary output. Using receiver operator characteristics analysis demonstrated an area under the curve of 0.75 correlating to a sensitivity of 100% and specificity of 50%. CONCLUSION: The premise that regional washout of 123I-mIBG SPECT from noninfarcted tissue is the best predictor of cardiac events was built on has a sound and logical foundation. By artificial neural network analysis; however, 123I-mIBG planar global washout of >30% was shown to be the best indicator for risk of cardiac event when accompanied by a decline in left ventricular ejection fraction of >10%. Further investigation should be undertaken assessing assimilation into big data and the potential for automated feature extraction from raw image datasets with convolutional neural networks.

Machine Learning and Deep Learning in Medical Imaging: Intelligent Imaging.

Artificial intelligence (AI) in medical imaging is a potentially disruptive technology. An understanding of the principles and application of radiomics, artificial neural networks, machine learning, and deep learning is an essential foundation to weave design solutions that accommodate ethical and regulatory requirements, and to craft AI-based algorithms that enhance outcomes, quality, and efficiency. Moreover, a more holistic perspective of applications, opportunities, and challenges from a programmatic perspective contributes to ethical and sustainable implementation of AI solutions.

Regional Cardiac Sympathetic Nervous System Evaluation Using 123I-mIBG SPECT in Patients with Heart Failure.

BACKGROUND: Heart failure (HF) involves both mechanical and autonomic nervous system dysfunction that can lead to sudden cardiac death. In the failing human heart, there is increased release of norepinephrine from neurons and reduced uptake. Iodine-123-labeled metaiodobenzylguanidine (123I-mIBG) demonstrates reduced global uptake and increased washout associated with increased mortality in HF. This research examined the potential benefits of single-photon emission computed tomography (SPECT) regional quantitation in risk stratification of HF patients and its role in prediction of cardiac morbidity and mortality. METHODS: Twenty-two clinically diagnosed HF patients were recruited into this study. The subjects underwent myocardial perfusion SPECT and cardiac sympathetic imaging with 123I-mIBG. Early (at 15 min after injection) and delayed (four hours after injection) planar and SPECT were performed. Visual and semiquantitative analysis was conducted, and global (from planar imaging) and regional (from SPECT imaging) uptake and washout indices determined. The patients were clinically followed for up to two years, and the cardiac events (CEs) in these patients were recorded and correlated with the various parameters. RESULTS: The occurrence of a CE in HF was independent of the patients' demographics or the cause of HF. Genetic biomarkers were unable to reliably predict CEs. Global or regional uptake had limited ability to predict a CE, whereas regional washout from the inferior wall (P = .005) was a statistically significant predictor of CEs. Similarly, a high washout of 40% or more from the peri-infarcted and noninfarcted segments on myocardial perfusion scintigraphy was also a significant predictor of CEs (P = .035). CONCLUSION: HF is a complex, multifactorial, progressive disease that appears to begin regionally. 123I-mIBG provides a valuable tool in imaging the global and regional sympathetic nervous system innervation of the heart. This may allow early identification and stratification of patients at risk of sudden cardiac death.

Pediatric Brown Adipose Tissue on 18F-FDG PET: Diazepam Intervention.

Brown adipose tissue (BAT) has been widely reported to affect the efficacy of 18F-FDG PET in oncology. Several small studies have found that warming the patient both before 18F-FDG injection and during the uptake phase can reduce the frequency of BAT uptake. Pharmaceutical approaches such as propranolol and diazepam have also been used. Methods: We describe two case studies that demonstrated the impact of combined patient warming and diazepam administration on BAT uptake in pediatric 18F-FDG PET images. To support these findings, we performed a retrospective analysis of 139 patients: 71 who received warming only and 68 who received warming combined with diazepam. Results: BAT uptake was significantly less frequent in patients who received diazepam (16.2%) than in those who did not (33.8%) (P = 0.0167), particularly in female patients (7.4% vs. 26.7%) (P = 0.0486). Conclusion: Although patient warming alone reduces the frequency of BAT uptake, the addition of diazepam to patient warming significantly furthers the reduction in young patients, particularly female patients.

Twitter Journal Club in Medical Radiation Science.

INTRODUCTION: Social media has emerged as a powerful platform for engagement and learning. There is a growing trend toward the use of social media among health care professionals and professional groups to disseminate and discuss knowledge. Twitter is one tool that may enhance continuing professional development (CPD) for the medical radiation technologist. To evaluate the potential benefits of Twitter to CPD among medical radiation technologists, this study explored the integration of Bloom's taxonomy with Twitter-based professional activities. APPROACH: In 2015, the Medical Radiation Journal Club (https://medradjclub.wordpress.com/) commenced a monthly Twitter-based journal club for medical radiation professionals. This study investigates the application of Bloom's taxonomy of the Twitter-based journal club for CPD purposes. OUTCOME: The Twitter-based journal club provides a valuable platform for CPD. The combination of journal articles, supplementary reading, online blog, and the one-hour Twitter discussion engages all levels of Bloom's taxonomy; remember, understand, apply, analyze, evaluate, and create. A deeper insight revealed that the Twitter journal club provides an authentic learning environment suitable for CPD in which participants consume, collaborate, and produce. CONCLUSIONS: This evaluation demonstrated that the Twitter journal club can provide an authentic learning environment with all the cognitive dimensions afforded in a formal classroom or face-to-face journal club. Indeed, in some ways, these cognitive dimensions are enhanced in the Twittersphere.

Increased Gastric Activity on Myocardial Perfusion Imaging.

UNLABELLED: We anecdotally observed an increased accumulation of (99m)Tc-tetrofosmin in the stomach of myocardial perfusion patients when their uptake phase coincided with preparation of hamburgers in an adjacent room for gastric emptying studies on other patients. The potential for a scent-stimulated alteration of gastric biodistribution required further investigation. METHODS: An experimental group and a control group were enrolled (20 patients per group). The experimental group could smell food being prepared during the uptake phase. Stomach, heart, and background regions were drawn in multiple projections, and the resulting data were evaluated. RESULTS: The experimental and control groups did not significantly differ in stomach counts per pixel, background-corrected counts per pixel, or heart-to-stomach ratio. Further analysis of the data revealed that women had a significantly higher increase in stomach counts (P = 0.022) and background-corrected stomach counts (P = 0.018) than men. CONCLUSION: Women had a greater increase in gastric (99m)Tc-tetrofosmin activity than men during the radiopharmaceutical uptake phase, but there was no causal relationship between an increase in activity and olfactory stimulation from the cooking of food.

Publication Productivity in the Medical Radiation Sciences.

INTRODUCTION: The evidence-based foundation of the health professions is dependent on research and its dissemination through peer-reviewed journals. The growth of a health profession is dependent on the sharing of knowledge. Various metrics have been used to measure the quality of journals, articles, and authors. These metrics, however, have many flaws. Publication productivity and patterns provide better insights that can guide professional and journal strategy. METHODOLOGY: Bibliometric data were collected from seven key peer-reviewed, international journals for the medical radiation sciences. These key journals were examined over the period 2009-2013 inclusive (5 years). Medical radiation technologists (MRTs) who had published two or more articles in the seven journals during the study period were further investigated through PubMed and ResearchGate to produce a list of publications (excluding those already identified in the seven primary journals) from the 5-year period. Further analysis was performed on the most prolific authors. RESULTS: A total of 969 articles were published in the seven key peer-review journals that met the inclusion criteria. The 969 articles were written by a total of 2,083 different authors. Overall, 80.5% (1,676 of 2,083) of all authors only published once within the seven journals and 110 of these authors were the sole author of their article. A total of 165 MRTs were identified who had published three or more articles. CONCLUSION: MRTs contribute significantly to the knowledge base of both the medical radiation science professions and the wider health community through active research.

Publication productivity in nuclear medicine.

UNLABELLED: Publications form the knowledge base of any profession. Patterns in professional publications provide insight into the profession's maturity and global status. To our knowledge, publication productivity in nuclear medicine technology has not been reported. A recent study on publication productivity in radiography and radiation therapy provided interesting insight; however, a sampling bias resulted in study flaws. METHODS: The most productive medical radiation technologists were determined by collecting data from 7 key, international peer-reviewed journals for the medical radiation sciences over a 5-y period. A full list of the technologists' publications, for the 5-y period, was obtained using a PubMed and ResearchGate search, and the authors were analyzed. RESULTS: In total, 165 medical radiation technologists were identified who had published 3 or more articles between 2009 and 2013. Of these authors, 55.2% (91/165) were radiographers, 35.2% (58/165) were radiation therapists, and 9.6% (16/165) were nuclear medicine technologists. Overall, the majority of the most prolific authors were academics (104/165; 63.0%). After we applied a correction factor (the productivity per member of the registered workforce), radiography had the fewest authors publishing, compared with the relative workflow sizes. CONCLUSION: Nuclear medicine technologists demonstrated a high degree of productivity both absolutely and relatively. Consequently, nuclear medicine technologists have a productive research culture and command a large footprint within and outside the key medical radiation science journals.