Deep learning–based denoising of low-dose SPECT myocardial perfusion images: quantitative assessment and clinical performance

Purpose This work was set out to investigate the feasibility of dose reduction in SPECT myocardial perfusion imaging (MPI) without sacrificing diagnostic accuracy. A deep learning approach was proposed to synthesize full-dose images from the corresponding low-dose images at different dose reduction levels in the projection space. Methods Clinical SPECT-MPI images of 345 patients acquired on a dedicated cardiac SPECT camera in list-mode format were retrospectively employed to predict standard-dose from low-dose images at half-, quarter-, and one-eighth-dose levels. To simulate realistic low-dose projections, 50%, 25%, and 12.5% of the events were randomly selected from the list-mode data through applying binomial subsampling. A generative adversarial network was implemented to predict non-gated standard-dose SPECT images in the projection space at the different dose reduction levels. Well-established metrics, including peak signal-to-noise ratio (PSNR), root mean square error (RMSE), and structural similarity index metrics (SSIM) in addition to Pearson correlation coefficient analysis and clinical parameters derived from Cedars-Sinai software were used to quantitatively assess the predicted standard-dose images. For clinical evaluation, the quality of the predicted standard-dose images was evaluated by a nuclear medicine specialist using a seven-point (− 3 to + 3) grading scheme. Results The highest PSNR (42.49 ± 2.37) and SSIM (0.99 ± 0.01) and the lowest RMSE (1.99 ± 0.63) were achieved at a half-dose level. Pearson correlation coefficients were 0.997 ± 0.001, 0.994 ± 0.003, and 0.987 ± 0.004 for the predicted standard-dose images at half-, quarter-, and one-eighth-dose levels, respectively. Using the standard-dose images as reference, the Bland–Altman plots sketched for the Cedars-Sinai selected parameters exhibited remarkably less bias and variance in the predicted standard-dose images compared with the low-dose images at all reduced dose levels. Overall, considering the clinical assessment performed by a nuclear medicine specialist, 100%, 80%, and 11% of the predicted standard-dose images were clinically acceptable at half-, quarter-, and one-eighth-dose levels, respectively. Conclusion The noise was effectively suppressed by the proposed network, and the predicted standard-dose images were comparable to reference standard-dose images at half- and quarter-dose levels. However, recovery of the underlying signals/information in low-dose images beyond a quarter of the standard dose would not be feasible (due to very poor signal-to-noise ratio) which will adversely affect the clinical interpretation of the resulting images.

Detailed visual assessment of striatal dopaminergic depletion in patients with idiopathic normal pressure hydrocephalus: Unremarkable or not?

Background Dopamine transporter (DAT) imaging may enable clinicians to discriminate idiopathic normal pressure hydrocephalus (iNPH) from other parkinsonian disorders. However, a specific pattern of dopaminergic loss in DAT imaging of iNPH patients remains to be further elucidated. Methods In this preliminary study, 11 patients with iNPH in our hospital between March 2017 and February 2019 were finally enrolled. A diagnosis of iNPH was made according to the two established criteria. For visual analysis of DAT imaging, a striatum was divided into five domains. A semi-quantitative visual assessment was performed with a consensus between a nuclear medicine specialist and an experienced neurologist who were blinded to the clinical diagnosis. Results Striatal dopaminergic deficits were abnormal in 90.9% (10/11) of patients with iNPH. The degree of dopaminergic reduction was mild and heterogeneous. However, a tendency of preferential striatal DAT loss in the caudate nucleus (90.9%, 10/11) than in the putamen (72.7%, 8/11) was observed, whereas ventral portion (9.1%, 1/11) was relatively preserved. Conclusion Striatal dopaminergic depletion might be mild and heterogeneous in patients with iNPH. These dopaminergic deficits were more common in the caudate nucleus than in the putamen, suggesting a pattern different from other degenerative parkinsonian disorders.

E-learning for medical imaging specialists: introducing blended learning in a nuclear medicine specialist course

Background While e-learning has become an important tool in teaching medical students, the training of specialists in medical imaging is still dominated by lecture-based courses. Purpose To assess the potential of e-learning in specialist education in medical imaging. Material and Methods An existing lecture-based five-day course in Clinical Nuclear Medicine (NM) was enhanced by e-learning resources and activities, including practical exercises. An anonymized survey was conducted after participants had completed and passed the multiple choice electronic course examination. Results Twelve out of 15 course participants (80%) responded. Overall satisfaction with the new course format was high, but 25% of the respondents wanted more interactive elements such as discussions and practical exercises. The importance of lecture handouts and supplementary online material such as selected original articles and professional guidelines was affirmed by all the respondents (92% fully, 8% partially), while 75% fully and 25% partially agreed that the lectures had been interesting and relevant. Conclusion E-learning represents a hitherto unrealized potential in the education of medical specialists. It may expedite training of medical specialists while at the same time containing costs.

Incorporating a holistic view into the art of healing

<p>Nuclear Medicine Specialist Dr. Kornélia Kajȧry recalls the period during her childhood when her parents’ career had helped spark her interest in medicine. “Both of my parents worked in the field of health. My father practiced his profession as a general practitioner, therefore medicine became a part of everyday life in our family. When I was a child, my father told me and explained a lot about his work, which made me more interested in the art of healing,” the Researcher in Spotlight reminisces.</p>

Lymphoscintigraphy and Radiation – Occupational Exposure During Sentinel Node Assay

Ionizing radiation has many practical applications, but it is also, as it is well known, dangerous to human health. The purpose of this study was to estimate the dose and exposure for medical staff involved in sentinel node assay and to determine how safe this assay really is. The theoretical method was used for calculation. Three groups of medical staff were selected: nuclear medicine specialist, nuclear medicine technologist and a surgeon. The results obtained show that the most exposed staff member is nuclear medicine specialist and that dose received by the surgeon is smaller then the dose limit.