RESUMEN
To improve image quality for low-count bone scintigraphy using deep learning and evaluate their clinical applicability. Six hundred patients (training, 500; validation, 50; evaluation, 50) were included in this study. Low-count original images (75%, 50%, 25%, 10%, and 5% counts) were generated from reference images (100% counts) using Poisson resampling. Output (DL-filtered) images were obtained after training with U-Net using reference images as teacher data. Gaussian-filtered images were generated for comparison. Peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) to the reference image were calculated to determine image quality. Artificial neural network (ANN) value, bone scan index (BSI), and number of hotspots (Hs) were computed using BONENAVI analysis to assess diagnostic performance. Accuracy of bone metastasis detection and area under the curve (AUC) were calculated. PSNR and SSIM for DL-filtered images were highest in all count percentages. BONENAVI analysis values for DL-filtered images did not differ significantly, regardless of the presence or absence of bone metastases. BONENAVI analysis values for original and Gaussian-filtered images differed significantly at â¦25% counts in patients without bone metastases. In patients with bone metastases, BSI and Hs for original and Gaussian-filtered images differed significantly at â¦10% counts, whereas ANN values did not. The accuracy of bone metastasis detection was highest for DL-filtered images in all count percentages; the AUC did not differ significantly. The deep learning method improved image quality and bone metastasis detection accuracy for low-count bone scintigraphy, suggesting its clinical applicability.
Asunto(s)
Neoplasias Óseas , Aprendizaje Profundo , Humanos , Mejoramiento de la Calidad , Procesamiento de Imagen Asistido por Computador/métodos , Neoplasias Óseas/diagnóstico por imagen , Neoplasias Óseas/secundario , CintigrafíaRESUMEN
BACKGROUND: L-type amino acid transporter 1 (LAT1) is overexpressed in various cancers; therefore, radiohalogen-labeled amino acid derivatives targeting LAT1 have emerged as promising candidates for cancer radiotheranostics. However, 211At-labeled amino acid derivatives exhibit instability against deastatination in vivo, making it challenging to use 211At for radiotherapy. In this study, radiohalogen-labeled amino acid derivatives with high dehalogenation stability were developed. RESULTS: We designed and synthesized new radiohalogen-labeled amino acid derivatives ([211At]At-NpGT, [125I]I-NpGT, and [18F]F-NpGT) in which L-tyrosine was introduced into the neopentyl glycol (NpG) structure. The radiolabeled amino acid derivatives were recognized as substrates of LAT1 in the in vitro studies using C6 glioma cells. In a biodistribution study using C6 glioma-bearing mice, these agents exhibited high stability against in vivo dehalogenation and similar biodistributions. The similarity of [211At]At-NpGT and [18F]F-NpGT indicated that these pairs of radiolabeled compounds would be helpful in radiotheranostics. Moreover, [211At]At-NpGT exhibited a dose-dependent inhibitory effect on the growth of C6 glioma-bearing mice. CONCLUSIONS: [211At]At-NpGT exhibited a dose-dependent inhibitory effect on the tumor growth of glioma-bearing mice, and its biodistribution was similar to that of other radiohalogen-labeled amino acid derivatives. These findings suggest that radiotheranostics using [18F]F-NpGT and [123/131I]I-NpGT for diagnostic applications and [211At]At-NpGT and [131I]I-NpGT for therapeutic applications are promising.
RESUMEN
Background: Dementia with Lewy bodies (DLB) presents with various symptoms, posing challenges for early diagnosis challenging. Dopamine transporter (123I-FP-CIT) single-photon emission tomography (SPECT) and 123I-meta-iodobenzylguanidine (123I-MIBG) imaging are crucial diagnostic biomarkers. Hypothesis about body- and brain-first subtypes of DLB indicate that some DLB may show normal 123I-FP-CIT or 123I-MIBG results; but the characteristic expression of these two subtypes remains unclear. Objective: This study aimed to evaluate the diagnostic sensitivity of 123I-FP-CIT and 123I-MIBG imaging alone, combined in patients with DLB and explore symptoms associated with the abnormal imaging results. Methods: Demographic data, clinical status, and imaging results were retrospectively collected from patients diagnosed with possible DLB. Both images were quantified using semi-automated software, and the sensitivity of each imaging modality and their combination was calculated. Demographic data, cognition, and motor and non-motor symptoms were compared among the subgroups based on the imaging results. Symptoms related to each imaging abnormality were examined using binomial logistic regression analyses. Results: Among 114 patients with DLB, 80 underwent 123I-FP-CIT SPECT (sensitivity: 80.3%), 83 underwent 123I-MIBG imaging (68.2%), and 66 both (sensitivity of either abnormal result: 93.9%). Visual hallucinations differed among the four subgroups based on imaging results. Additionally, nocturia and orthostatic hypotension differed between abnormal and normal 123I-MIBG images. Conclusions: Overall, 123I-FP-CIT SPECT was slightly higher sensitivity than 123I-MIBG imaging, with combined imaging increasing diagnostic sensitivity. Normal results of a single imaging test may not refute DLB. Autonomic symptoms may lead to abnormal 123I-MIBG scintigraphy findings indicating body-first subtype of patients with DLB.