Latent diffusion model-based MRI superresolution enhances mild cognitive impairment prognostication and Alzheimer's disease classification.

INTRODUCTION: Timely diagnosis and prognostication of Alzheimer's disease (AD) and mild cognitive impairment (MCI) are pivotal for effective intervention. Artificial intelligence (AI) in neuroradiology may aid in such appropriate diagnosis and prognostication. This study aimed to evaluate the potential of novel diffusion model-based AI for enhancing AD and MCI diagnosis through superresolution (SR) of brain magnetic resonance (MR) images. METHODS: 1.5T brain MR scans of patients with AD or MCI and healthy controls (NC) from Alzheimer's Disease Neuroimaging Initiative 1 (ADNI1) were superresolved to 3T using a novel diffusion model-based generative AI (d3T*) and a convolutional neural network-based model (c3T*). Comparisons of image quality to actual 1.5T and 3T MRI were conducted based on signal-to-noise ratio (SNR), naturalness image quality evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE). Voxel-based volumetric analysis was then conducted to study whether 3T* images offered more accurate volumetry than 1.5T images. Binary and multiclass classifications of AD, MCI, and NC were conducted to evaluate whether 3T* images offered superior AD classification performance compared to actual 1.5T MRI. Moreover, CNN-based classifers were used to predict conversion of MCI to AD, to evaluate the prognostication performance of 3T* images. The classification performances were evaluated using accuracy, sensitivity, specificity, F1 score, Matthews correlation coefficient (MCC), and area under the receiver-operating curves (AUROC). RESULTS: Analysis of variance (ANOVA) detected significant differences in image quality among the 1.5T, c3T*, d3T*, and 3T groups across all metrics. Both c3T* and d3T* showed superior image quality compared to 1.5T MRI in NIQE and BRISQUE with statistical significance. While the hippocampal volumes measured in 3T* and 3T images were not significantly different, the hippocampal volume measured in 1.5T images showed significant difference. 3T*-based AD classifications showed superior performance across all performance metrics compared to 1.5T-based AD classification. Classification performance between d3T* and actual 3T was not significantly different. 3T* images offered superior accuracy in predicting the conversion of MCI to AD than 1.5T images did. CONCLUSIONS: The diffusion model-based MRI SR enhances the resolution of brain MR images, significantly improving diagnostic and prognostic accuracy for AD and MCI. Superresolved 3T* images closely matched actual 3T MRIs in quality and volumetric accuracy, and notably improved the prediction performance of conversion from MCI to AD.

Design and validation of a wearable dynamometry system for knee extension-flexion torque measurement.

Muscle strength assessments are vital in rehabilitation, orthopedics, and sports medicine. However, current methods used in clinical settings, such as manual muscle testing and hand-held dynamometers, often lack reliability, and isokinetic dynamometers (IKD), while reliable, are not easily portable. The aim of this study was to design and validate a wearable dynamometry system with high accessibility, accuracy, and reliability, and to validate the device. Therefore, we designed a wearable dynamometry system (WDS) equipped with knee joint torque sensors. To validate this WDS, we measured knee extension and flexion strength in 39 healthy adults using both the IKD and WDS. Comparing maximal isometric torque measurements, WDS and IKD showed strong correlation and good reliability for extension (Pearson's r: 0.900; intraclass correlation coefficient [ICC]: 0.893; standard error of measurement [SEM]: 9.85%; minimal detectable change [MDC]: 27.31%) and flexion (Pearson's r: 0.870; ICC: 0.857; SEM: 11.93%; MDC: 33.07%). WDS demonstrated excellent inter-rater (Pearson's r: 0.990; ICC: 0.993; SEM: 4.05%) and test-retest (Pearson's r: 0.970; ICC: 0.984; SEM: 6.15%) reliability during extension/flexion. User feedback from 35 participants, including healthcare professionals, underscores WDS's positive user experience and clinical potential. The proposed WDS is a suitable alternative to IKD, providing high accuracy, reliability, and potentially greater accessibility.

A portable articulated dynamometer for ankle dorsiflexion and plantar flexion strength measurement: a design, validation, and user experience study.

Monitoring ankle strength is crucial for assessing daily activities, functional ability, and preventing lower extremity injuries. However, the current methods for measuring ankle strength are often unreliable or not easily portable to be used in clinical settings. Therefore, this study proposes a portable dynamometer with high reliability capable of measuring ankle dorsiflexion and plantar flexion. The proposed portable dynamometer comprised plates made of aluminum alloy 6061 and a miniature tension-compression load cell. A total of 41 healthy adult participants applied maximal isometric dorsiflexor and plantar flexor forces on a Lafayette Handheld Dynamometer (HHD) and the portable dynamometer. The results were cross-validated, using change in mean, and two independent examiners evaluated the inter-rater and test-retest reliabilities in separate sessions using intraclass correlation coefficients, standard error of measurement, and minimal detectable change. Both dorsiflexion and plantar flexion measurements demonstrated a strong correlation with the HHD (r = 0.827; r = 0.973) and showed high inter-rater and test-retest reliabilities. Additionally, the participant responses to the user experience questionnaire survey indicated vastly superior positive experiences with the portable dynamometer. The study findings suggest that the designed portable dynamometer can provide accurate and reliable measurements of ankle strengths, making it a potential alternative to current methods in clinical settings.

Development and validation of a portable articulated dynamometry system to assess knee extensor muscle strength.

Muscle strength assessment is important in predicting clinical and functional outcomes in many disorders. Manual muscle testing, although commonly used, offers suboptimal accuracy and reliability. Isokinetic dynamometers (IKDs) have excellent accuracy and reliability; but are bulky and expensive, offering limited accessibility. This study aimed to design a portable dynamometer that is accessible, accurate and reliable, and to validate the device in a general population. The portable articulated dynamometry system (PADS) is a portable device with an embedded high-precision load cell, designed to measure muscle strength with optimal accuracy. Seventy-two participants underwent maximal isometric and isokinetic knee extensor torque measurement with the PADS and IKD, respectively. The PADS results were cross-validated against IKD results using change in mean (CIM). Interrater and intra-rater reliabilities were assessed using intraclass correlation coefficients, standard error of measurement, and minimal detectable change. The PADS maximal knee extensor strength results were not significantly different from those by IKD (CIM: - 2.13 Nm; 95% CI - 4.74, 0.49 Nm). The PADS showed interrater reliability (Pearson's r: 0.958; ICC: 0.979; SEM: 5.51%) and excellent intra-rater reliability (Pearson's r: 0.912; ICC: 0.954; SEM: 8.38%). The proposed PADS may be an effective alternative to IKD, offering good accuracy, reliability, and potentially better accessibility.

Evaluating diagnostic content of AI-generated chest radiography: A multi-center visual Turing test.

BACKGROUND: Accurate interpretation of chest radiographs requires years of medical training, and many countries face a shortage of medical professionals to meet such requirements. Recent advancements in artificial intelligence (AI) have aided diagnoses; however, their performance is often limited due to data imbalance. The aim of this study was to augment imbalanced medical data using generative adversarial networks (GANs) and evaluate the clinical quality of the generated images via a multi-center visual Turing test. METHODS: Using six chest radiograph datasets, (MIMIC, CheXPert, CXR8, JSRT, VBD, and OpenI), starGAN v2 generated chest radiographs with specific pathologies. Five board-certified radiologists from three university hospitals, each with at least five years of clinical experience, evaluated the image quality through a visual Turing test. Further evaluations were performed to investigate whether GAN augmentation enhanced the convolutional neural network (CNN) classifier performances. RESULTS: In terms of identifying GAN images as artificial, there was no significant difference in the sensitivity between radiologists and random guessing (result of radiologists: 147/275 (53.5%) vs result of random guessing: 137.5/275, (50%); p = .284). GAN augmentation enhanced CNN classifier performance by 11.7%. CONCLUSION: Radiologists effectively classified chest pathologies with synthesized radiographs, suggesting that the images contained adequate clinical information. Furthermore, GAN augmentation enhanced CNN performance, providing a bypass to overcome data imbalance in medical AI training. CNN based methods rely on the amount and quality of training data; the present study showed that GAN augmentation could effectively augment training data for medical AI.

Development and Validation of a New Scale to Assess Attitudes and Perspectives Toward Persons With Disabilities.

OBJECTIVE: To develop and validate a scale to assess people's attitudes and perspectives toward persons with disabilities. METHODS: The three-stage development of the scale included a preliminary version drafted from the literature review and a nominal group process. Thereafter, the draft was examined further and revised through two rounds of Delphi survey by 16 disability experts. Lastly, the psychometric properties of the scale were assessed through an online survey of 1,359 employees at three university hospitals. RESULTS: A 32-item scale, defined after two Delphi surveys, was refined into 14 items with four subcategories: community integration, discomfort, charitability, and sense of burdening. The Cronbach's alpha coefficient was 0.839 and domain reliability from 0.638 to 0.845. Recent education on disabilities yielded more positive attitudes toward persons with disabilities. Meaningful acquaintances with disabilities yielded more positive attitudes toward persons with disabilities. CONCLUSION: This newly developed scale that measures attitudes toward persons with disability is reliable and valid. A future use of the scale could be to measure attitudinal improvements toward persons with disabilities after awareness education.

Spasticity and preservation of skeletal muscle mass in people with spinal cord injury.

STUDY DESIGN: Cross-sectional OBJECTIVE: To investigate the association between skeletal muscle mass and spasticity in people with spinal cord injury (SCI). SETTING: Tertiary level hospital in Seoul, Korea METHODS: Spasticity was evaluated in 69 participants with SCI using the spasticity sum score (SSS), Penn Spasm Frequency Scale (PSFS), and Spinal Cord Assessment Tool for Spastic Reflexes (SCATS). Skeletal muscle mass was measured using a dual-energy X-ray absorptiometry scanner, and skeletal muscle index was calculated by dividing skeletal muscle mass by height squared. Laboratory parameters including hemoglobin, albumin, creatinine, fasting glucose, and cholesterol were measured. Spearman's correlation analysis was performed to assess the association between the skeletal muscle mass and spasticity scales. Multiple linear regression analysis was used to present the independent association between them. RESULTS: The participants' mean age was 41.8 years; 54 (78.3%) were male, and 46 (66.7%) were tetraplegic. Skeletal muscle index of lower extremities was significantly correlated with all spasticity scales. Spearman's correlation coefficients were 0.468, 0.467, 0.555, 0.506, and 0.474 for SSS, PSFS, SCATS clonus, SCATS flexor, and SCATS extensor with p-values < 0.001, respectively. After adjustment for age, sex, level of injury, body mass index, and serum creatinine, all spasticity scales were significantly associated with skeletal muscle index of lower extremities in multiple regression analysis. Standardized coefficients were 0.228, 0.274, 0.294, 0.210, and 0.227 for SSS, PSFS, SCATS clonus, SCATS flexor, and SCATS extensor. CONCLUSIONS: Spasticity was significantly correlated with the skeletal muscle mass even after adjusting for possible confounders. Spasticity may need to be considered as an influencing factor in interventions such as electrical stimulation to preserve skeletal muscle mass.