Search

Background: "Batch effect" in MR images, due to vendor‐specific features, MR machine generations, and imaging parameters, challenges image quality and hinders deep learning (DL) model generalizability. Purpose: We aim to develop a DL model using contrast adjustment and super‐resolution to reduce diffusion‐weighted images (DWIs) diversity across magnetic field strengths and imaging parameters. Study Type: Retrospective. Subjects: The DL model was built using an open dataset from one individual. The MR machine identification model was trained and validated on a dataset of 1134 adults (54% females, 46% males), with 1050 subjects showing no DWI abnormalities and 84 with conditions like stroke and tumors. The 21,000 images were divided into 80% for training, 20% for validation, and 3500 for testing. Field Strength/Sequence: Seven MR scanners from four manufacturers with 1.5 T and 3 T magnetic field strengths. DWIs were acquired using spin‐echo sequences and high‐resolution T2WIs using the T2‐SPACE sequence. Assessment: An experienced, board‐certified radiologist evaluated the effectiveness of restoring high‐resolution T2WI and harmonizing diverse DWI with metrics such as PSNR and SSIM, and the texture and frequency attributes were further analyzed using gray‐level co‐occurrence matrix and 1‐dimensional power spectral density. The model's impact on machine‐specific characteristics was gauged through the performance metrics of a ResNet‐50 model. Comprehensive statistical tests were employed for statistical robustness, including McNemar's test and the Dice index. Results: Our DL protocol reduced DWI contrast and resolution variation. ResNet‐50 model's accuracy decreased from 0.9443 to 0.5786, precision from 0.9442 to 0.6494, recall from 0.9443 to 0.5786, and F1 score from 0.9438 to 0.5587. The t‐SNE visualization indicated more consistent image features across multiple MR devices. Autoencoder halved learning iterations; Dice coefficient >0.74 confirmed signal reproducibility in 84 lesions. Conclusion: This study presents a DL strategy to mitigate batch effects in diffusion MR images, improving their quality and generalizability. Evidence Level: 3 Technical Efficacy: Stage 1 [ABSTRACT FROM AUTHOR]

Background and Objectives: Integrating large language models (LLMs) such as GPT-4 Turbo into diagnostic imaging faces a significant challenge, with current misdiagnosis rates ranging from 30–50%. This study evaluates how prompt engineering and confidence thresholds can improve diagnostic accuracy in neuroradiology. Methods: We analyze 751 neuroradiology cases from the American Journal of Neuroradiology using GPT-4 Turbo with customized prompts to improve diagnostic precision. Results: Initially, GPT-4 Turbo achieved a baseline diagnostic accuracy of 55.1%. By reformatting responses to list five diagnostic candidates and applying a 90% confidence threshold, the highest precision of the diagnosis increased to 72.9%, with the candidate list providing the correct diagnosis at 85.9%, reducing the misdiagnosis rate to 14.1%. However, this threshold reduced the number of cases that responded. Conclusions: Strategic prompt engineering and high confidence thresholds significantly reduce misdiagnoses and improve the precision of the LLM diagnostic in neuroradiology. More research is needed to optimize these approaches for broader clinical implementation, balancing accuracy and utility. [ABSTRACT FROM AUTHOR]

Aims/Introduction: Older adults with diabetes mellitus are susceptible to sarcopenia. Diffusion tensor imaging studies have also shown that patients with diabetes have altered white matter integrity. However, the relationship between these structural changes in white matter and sarcopenia remains poorly understood. Materials and Methods: The study included 284 older patients (aged ≥65 years) who visited the Tokyo Metropolitan Geriatric Hospital Frailty Clinic. We used diffusion tensor imaging to measure fractional anisotropy (FA) and mean diffusivity (MD) to evaluate changes in white matter integrity. We investigated the associations between sarcopenia, or its diagnostic components, and FA or MD in seven white matter tracts considered to be associated with sarcopenia according to the patients' diabetes status. Results: We found significantly low FA or high MD values in the bilateral anterior thalamic radiations (ATR) and right inferior fronto‐occipital fasciculus (IFOF) of patients with Asian Working Group for Sarcopenia 2019‐defined sarcopenia, in all patients and those with diabetes. Using binominal regression analyses, we associated low FA values in the left ATR and right IFOF with sarcopenia in all patients and those with diabetes, after adjusting for age, gender, HbA1c, blood pressure, cognitive function, physical activity, depression, nutritional status, and inflammation. Conclusions: White matter alterations in left ATR and right IFOF are associated with the prevalence of sarcopenia in patients with diabetes. Specific changes to the left ATR and right IFOF tracts could play critical roles in the occurrence of sarcopenia in patients with diabetes. [ABSTRACT FROM AUTHOR]

Aim: Gait impairment implies subtle cognitive impairment (CI) and is associated with severity of white matter hyperintensities (WMHs). However, cognitive differences in such an association are not yet fully understood. This study examined the association between WMHs and gait performance among three cognitively different older groups. Methods: Gait performance and WMHs were assessed in 150 community‐dwelling older adults, comprising 53 with CI (Mini‐Mental State Examination [MMSE] score <24), 63 with mild CI (MMSE score ≥24 and Montreal Cognitive Assessment [MoCA] score <25), and 34 who were cognitively normal or preserved (MMSE ≥24 and MoCA score ≥25). Gait velocity and variability were assessed on a 5‐m electronic walkway. Furthermore, WMH volume was derived by automated segmentation using 1.5 T magnetic resonance imaging. Results: Adjusted multiple regression analyses showed that greater WMHs were associated with slower gait velocity and greater temporal (stride time) and spatial (stride and step lengths) variabilities among older adults with CI. In contrast, WMH was only associated with spatial variability in older adults with mild CI and in cognitively normal or preserved older adults. Conclusions: Our findings suggest that gait variability measures are more sensitive to subtle underlying neurological pathologies including WMHs in older adults. The cognitive‐dependent differences found in the association between WMHs and gait performance suggests that the level of cognitive function interferes with the association between WMH and gait performance. Geriatr Gerontol Int 2021; ••: ••–••. [ABSTRACT FROM AUTHOR]