Subjective Image Research Articles

Improved deep canonical correlation fusion approach for detection of early mild cognitive impairment.

Detection of early mild cognitive impairment (EMCI) is clinically challenging as it involves subtle alterations in multiple brain sub-anatomic regions. Among different brain regions, the corpus callosum and lateral ventricles are primarily affected due to EMCI. In this study, an improved deep canonical correlation analysis (CCA) based framework is proposed to fuse magnetic resonance (MR) image features from lateral ventricular and corpus callosal structures for the detection of EMCI condition. For this, obtained structural MR images of healthy controls and EMCI subjects are preprocessed. Lateral ventricles and corpus callosum structures are segmented from these images and features are extracted. Extracted features from different brain structures are fused using non-linear orthogonal iteration-based deep CCA. Fused features are employed to differentiate healthy controls and EMCI condition using extreme learning machine classifier. Results indicate that fused callosal and ventricular features are able to detect EMCI. Improved deep CCA algorithm with tuned hyperparameters achieves the highest classifier performance with an F-score of 82.15%. The proposed framework is compared with state-of-the-art CCA approaches, and the results demonstrate its improved performance in EMCI detection. This highlights the potential of the proposed framework in the automated diagnosis of preclinical MCI conditions.

Preliminary observations in cortical excitability changes using transcranial magnetic stimulation (TMS), it's correlation with diffusion tensor imaging (DTI) in subjects with neuromyelitis optica spectrum disorder (NMOSD).

Neuromyelitis optica spectrum disorder (NMOSD) is a relapsing central nervous system disease most commonly associated with aquaporin-4 antibodies (AQP4-Ab) and Myelin oligodendrocyte glycoprotein (MOG) antibodies. These demyelinating disorders influence cortical excitability, which has been studied using advanced imaging techniques and transcranial magnetic stimulation (TMS) in our study. This is a prospective study of 30 subjects. Ten subjects, each of AQP4, MOGAD, and dual seronegative (SN)-NMOSD, were recruited and compared to 30 healthy controls. All the subjects underwent TMS and MRI with diffusion tensor imaging (DTI). Resting motor threshold (RMT), central motor conduction time (CMCT), ipsilateral (ISP) and contralateral silent period (cSP), short interval intracortical inhibition (SICI) and intracortical facilitation (ICF) were the TMS parameters assessed. Fractional anisotropy (FA) and axial diffusivity (AD) were the DTI parameters studied. DTI findings were correlated with the TMS parameters. The study cohort had a male-to-female ratio of (M: F) = 13:17. RMT was highest in the AQP4-Ab subgroup (40.2 ± 11.9%) compared to SN NMOSD (36.2 ± 4.6%) and MOGAD (34.5 ± 6.7%). CMCT was maximum prolonged in subjects with MOGAD (9.6 ± 1.9 msec). The cSP was reduced in MOGAD (79.9 ± 36.3msec). SICI was lowest in the AQP4-Ab subgroup (1.27 ± 1.12) and was preserved in the MOGAD subgroup (0.88 ± 0.55). The DTI data demonstrated statistically significant, reduced FA and AD in AQP4-Ab and SN NMOSD subjects. This is the first study that looked at the cortical excitability changes in the three subgroups of NMOSD. It has been observed that AQP4 NMOSD and SN NMOSD had a severe form of demyelinating disease compared to MOGAD.

Interrelation Between BMI, Dietary Habits, Self-Rated Health, and Body Image Perception Among Korean Adolescents: The Korea Youth Risk Behavior Web-Based Survey (2022)

Background/Objectives: Adolescent obesity is highly likely to lead to adult obesity and is associated with dietary habits, subjective health, and body image perception. This study aimed to analyze the relationships between BMI, dietary habits, subjective health perception, and body image perception among Korean adolescents using data from the 18th Korea Youth Risk Behavior Survey conducted in 2022 to explore strategies for reducing adolescent obesity rates. Methods: Data from 50,427 participants were analyzed, including BMI, seven lifestyle factors (intake frequencies of water, milk, fruit, soft drinks, vegetables, breakfast, and late-night snacks), and responses to one item each for subjective health perception and body image perception. Results: Higher intake frequencies of breakfast, fruits, soft drinks, and late-night snacks were associated with lower BMI (p < 0.001). However, among high school students, those with lower water and breakfast intake but higher soft drink and late-night snack intake exhibited an increasing trend in BMI. Subjective health perception and body image perception were interrelated, with subjective health perception influencing body image perception (p < 0.001). Conclusions: Addressing nutritional issues within schools, including improving school meals, regulating accessible products, and providing nutritional intake guidelines, is essential. Additionally, developing tailored health education programs to promote healthy body image perceptions is necessary. This study can serve as a foundational resource for analyzing adolescent health and developing strategies to improve health behaviors in changing environments.

Deep learning-based image domain reconstruction enhances image quality and pulmonary nodule detection in ultralow-dose CT with adaptive statistical iterative reconstruction-V.

To evaluate the image quality and lung nodule detectability of ultralow-dose CT (ULDCT) with adaptive statistical iterative reconstruction-V (ASiR-V) post-processed using a deep learning image reconstruction (DLIR)-based image domain compared to low-dose CT (LDCT) and ULDCT without DLIR. A total of 210 patients undergoing lung cancer screening underwent LDCT (mean ± SD, 0.81 ± 0.28 mSv) and ULDCT (0.17 ± 0.03 mSv) scans. ULDCT images were reconstructed with ASiR-V (ULDCT-ASiR-V) and post-processed using DLIR (ULDCT-DLIR). The quality of the three CT images was analyzed. Three radiologists detected and measured pulmonary nodules on all CT images, with LDCT results serving as references. Nodule conspicuity was assessed using a five-point Likert scale, followed by further statistical analyses. A total of 463 nodules were detected using LDCT. The image noise of ULDCT-DLIR decreased by 60% compared to that of ULDCT-ASiR-V and was lower than that of LDCT (p < 0.001). The subjective image quality scores for ULDCT-DLIR (4.4 [4.1, 4.6]) were also higher than those for ULDCT-ASiR-V (3.6 [3.1, 3.9]) (p < 0.001). The overall nodule detection rates for ULDCT-ASiR-V and ULDCT-DLIR were 82.1% (380/463) and 87.0% (403/463), respectively (p < 0.001). The percentage difference between diameters > 1 mm was 2.9% (ULDCT-ASiR-V vs. LDCT) and 0.5% (ULDCT-DLIR vs. LDCT) (p = 0.009). Scores of nodule imaging sharpness on ULDCT-DLIR (4.0 ± 0.68) were significantly higher than those on ULDCT-ASiR-V (3.2 ± 0.50) (p < 0.001). DLIR-based image domain improves image quality, nodule detection rate, nodule imaging sharpness, and nodule measurement accuracy of ASiR-V on ULDCT. Question Deep learning post-processing is simple and cheap compared with raw data processing, but its performance is not clear on ultralow-dose CT. Findings Deep learning post-processing enhanced image quality and improved the nodule detection rate and accuracy of nodule measurement of ultralow-dose CT. Clinical relevance Deep learning post-processing improves the practicability of ultralow-dose CT and makes it possible for patients with less radiation exposure during lung cancer screening.

Spectral Graph Sample Weighting for Interpretable Sub-cohort Analysis in Predictive Models for Neuroimaging.

Recent advancements in medicine have confirmed that brain disorders often comprise multiple subtypes of mechanisms, developmental trajectories, or severity levels. Such heterogeneity is often associated with demographic aspects (e.g., sex) or disease-related contributors (e.g., genetics). Thus, the predictive power of machine learning models used for symptom prediction varies across subjects based on such factors. To model this heterogeneity, one can assign each training sample a factor-dependent weight, which modulates the subject's contribution to the overall objective loss function. To this end, we propose to model the subject weights as a linear combination of the eigenbases of a spectral population graph that captures the similarity of factors across subjects. In doing so, the learned weights smoothly vary across the graph, highlighting sub-cohorts with high and low predictability. Our proposed sample weighting scheme is evaluated on two tasks. First, we predict initiation of heavy alcohol drinking in young adulthood from imaging and neuropsychological measures from the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA). Next, we detect Dementia vs. Mild Cognitive Impairment (MCI) using imaging and demographic measurements in subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Compared to existing sample weighting schemes, our sample weights improve interpretability and highlight sub-cohorts with distinct characteristics and varying model accuracy.

Evaluation of a Deep Learning Denoising Algorithm for Dose Reduction in Whole-Body Photon-Counting CT Imaging: A Cadaveric Study.

Photon Counting CT (PCCT) offers advanced imaging capabilities with potential for substantial radiation dose reduction; however, achieving this without compromising image quality remains a challenge due to increased noise at lower doses. This study aims to evaluate the effectiveness of a deep learning (DL)-based denoising algorithm in maintaining diagnostic image quality in whole-body PCCT imaging at reduced radiation levels, using real intraindividual cadaveric scans. Twenty-four cadaveric human bodies underwent whole-body CT scans on a PCCT scanner (NAEOTOM Alpha, Siemens Healthineers) at four different dose levels (100%, 50%, 25%, and 10% mAs). Each scan was reconstructed using both ADMIRE level 2 and a DL algorithm (ClariCT.AI, ClariPi Inc.), resulting in 192 datasets. Objective image quality was assessed by measuring CT value stability, image noise, and contrast-to-noise ratio (CNR) across consistent regions of interest (ROIs) in the liver parenchyma. Two radiologists independently evaluated subjective image quality based on overall image clarity, sharpness, and contrast. Inter-rater agreement was determined using Spearman's correlation coefficient, and statistical analysis included mixed-effects modeling to assess objective and subjective image quality. Objective analysis showed that the DL denoising algorithm did not significantly alter CT values (p ≥ 0.9975). Noise levels were consistently lower in denoised datasets compared to the Original (p < 0.0001). No significant differences were observed between the 25% mAs denoised and the 100% mAs original datasets in terms of noise and CNR (p ≥ 0.7870). Subjective analysis revealed strong inter-rater agreement (r ≥ 0.78), with the 50% mAs denoised datasets rated superior to the 100% mAs original datasets (p < 0.0001) and no significant differences detected between the 25% mAs denoised and 100% mAs original datasets (p ≥ 0.9436). The DL denoising algorithm maintains image quality in PCCT imaging while enabling up to a 75% reduction in radiation dose. This approach offers a promising method for reducing radiation exposure in clinical PCCT without compromising diagnostic quality.

Ultra-fast [18F]florbetapir PET imaging using the uMI Panorama PET/CT system

BackgroundThere is a need for faster amyloid PET scans to reduce patients’ discomfort, minimize movement artifacts, and increase throughput. The recently introduced uMI Panorama PET/CT system featuring enhanced spatial resolution and sub-200ps TOF offers the potential for shorter scan duration without sacrificing image quality or efficacy to detect Aβ deposition. The study aims to establish a faster acquisition protocol for [18F]florbetapir PET imaging using digital PET/CT scanner uMI Panorama, while ensuring adequate image quality and amyloid-β (Aβ) detectability comparable to the standard 10-minute scan.MethodsThirty-eight participants (29 Aβ positive and 9 Aβ negative) from a prospective dementia cohort at Peking Union Medical University Hospital underwent routine [18F]florbetapir PET scans using the uMI Panorama PET/CT scanner and a T1-weighted brain MRI scan. List-mode PET data were reconstructed into durations of 10 min, 2 min, 1 min, 45 s, and 30 s (G10min, G2min, G1min, G45s, G30s). Two trained nuclear medicine physicians independently evaluated the image quality using a 5-point scale and provided binary diagnosis. Standardized uptake value ratios (SUVr) of the composite cortex (frontal, lateral parietal, lateral temporal, and cingulate cortices) were calculated to discriminate Aβ status and coefficient of variation assessed objective image quality. Comparisons of image quality and Aβ detectability between various fast scan groups and G10min group were conducted.ResultsThe subjective image quality evaluation and Aβ detectability results from the two physicians showed both good intra-reader and inter-reader agreements (Cohen’s kappa coefficient: 0.759-1.000). The subjective and objective image qualities of the G2min scans were comparable to the G10min scans, whereas adequate image quality was achieved with the G1min and G45s scans (5-point score ≥ 3). Subjective visual diagnosis by two physicians yielded consistent accuracy for G10min, G2min, and G1min groups, but lower specificity for G45s and G30s groups. The objective detection of Aβ status by cortex SUVr across all scan durations maintained perfect discriminatory efficiency and relatively high effect size (Hedge’s G: 2.48–2.54).ConclusionsA 1-min ultra-fast scan is feasible for [18F]florbetapir PET imaging using uMI Panorama PET/CT, while maintaining adequate image quality and Aβ diagnostic efficiency.Clinical trial registrationNCT05023564. Registered September 2022 https://clinicaltrials.gov/search?term=NCT05023564.

The effects of objective body type and subjective body image on self-perceived oral health by sex

The effects of objective body type and subjective body image on self-perceived oral health by sex

Psychological predictors of motivational saturation within professional life at the stage of professional education

Introduction. The main problem of this research is the insufficiency of psychological concepts about motivational saturation as a mechanism regulating relevant behavior for constructing and maintaining a subjective picture of a person's professional life at the stage of professional education. The purpose of the article is to theoretically substantiate and empirically identify differences in psychological factors that affect the overall motivational saturation of the subjective picture of a person's professional life, as well as the motivational saturation of the professional future of university students. Materials and Methods. The research methodology is based on the ideas and principles of synergetic, system-activity and causometric approaches, within the framework of which motivational saturation is interpreted as filling professional life with causal and target connections between significant events, and the image of the professional future is considered as an ‘attractor’ of professional development. 188 students of the Russian State Professional Pedagogical University took part in the survey. The empirical data were collected using the following methods: the method of studying the subjective picture of the life path "Causometry" (A.A. Kronik, E.I. Golovakha, R.A. Akhmerov), a version adapted for studying the subjective picture of the professional life of an individual); the questionnaire of time perspective (ZTPI, F. Zimbardo); the method "Ability to forecast" (L.A. Regush); the method "Diagnostics of the level of development of reflexivity" (A.V. Karpova); the questionnaire "Diagnostics of the features of self-organization" (A.D. Ishkov). In order to process the obtained results, the methods of mathematical statistics in the IBM SPSS Statistics 22 programme were used. Results. In the course of theoretical analysis, it was revealed that the key psychological factors that have an effect on motivational saturation, and accordingly the desire to realize the subjective picture of life according to a certain scenario, are time perspective, prognostic and reflexive abilities, as well as self-organization indicators. It was suggested that, despite the commonality of factors for motivational saturation in general and motivational saturation of the future, they are built on different components of these factors. Indeed, as a result of the regression analysis, it was found that the predictors of motivational saturation of the professional life of university students are the characteristics of time orientation ("Fatalism in the present", "Hedonism in the present") and self-control, which correlates with the psycho-age portrait of a university student. In turn, the image of the professional future is determined by such variables of the presented factors as "Goal setting", "Correction" and "Volitional efforts", which creates a vector in the direction of the mode of the future. These results can be used in the system of psychological support of universities to improve professional choice based on the construction of a personal professional perspective and correction of the subjective image of professional life. Conclusions. The conducted mathematical and statistical analysis confirms the importance of self-organization components in building the image of the future and professional and life trajectory. The obtained results can be used in the development of measures for psychological and teaching support of professional self-determination of young people in the process of revision and correction of their professional choice.

The use of dual and triple rule-out computerized tomography angiography by using diagnostic low-dose contrast material and radiation in acute chest pain.

Triple rule-out computed tomography angiography (CTA) provides imaging of the coronary arteries, pulmonary arteries, and thoracic aorta filled with contrast material (CM) to exclude or diagnose the pathologies of these three systems. Although dual rule-out adapted to exclude aortic and pulmonary pathologies. Iodinated CM may result in contrast-induced nephropathy, which lengthens hospital stay. To compare image quality of dual/triple rule-out CTA by reducing the radiation dose by using relatively high mAs with less contrast material and low kilovoltage without affecting the diagnostic value. We acquired standard dual/triple rule-out CTA 120 kilovoltage peak (kVp) with 95 mL contrast material. The low-dose group acquired 80 Kvp with total 60 contrast material. There were 91 patients in the standard-dose group and 88 patients in the low-dose group. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated separately. There was no significant difference in CNR values between the two groups in the aorta and pulmonary and coronary arteries; however, a significant difference was found in SNR values. In subjective image quality evaluation, no significant difference was found between the standard- and low-dose patients. The radiation dose was reduced by 63.80% and the contrast material by 31.5% in the low-dose group in comparison to the standard dose. Our study showed that dual/triple rule-out CTA can be performed with low-dose radiation and low-volume contrast material. Low-dose CTA may be preferred in emergencies situations that patients with borderline renal function tests or the risk group.

Application of T1-weighted and augmented T1-weighted images of multi-parametric MR sequence in detecting neonatal punctate white matter lesions.

Punctate White Matter Lesion (PWML) is common in neonates. Multi-parametric MR imaging with flexible design (MULTIPLEX, MTP) generates multiple requires only about 6 min for full-head coverage. This study aimed to evaluate the value of T1WI and aT1WI contrasts of MTP in detecting neonatal punctate white matter lesions. Twenty-one neonates with punctate white matter damage underwent multi-parametric MR imaging between November 2022 to July 2024. For subjective image quality, two pediatric neuroradiologists assessed overall image quality, and visualization of structures using a 4-point assessment scale. To analyze objective image quality, the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), contrast, number and sharpness of lesions were quantified. With regard to sharpness of the lesion, MTP T1WI and aT1WI are comparable to conventional T1W. For subjective assessment, MTP-T1WI exhibited superior overall image quality and anatomical structure display compared to conventional T1WI (P < 0.01). Regarding objective assessment, MTP-T1WI had significantly higher SNR values for gray matter, white matter and lesions than the other two groups. The CNR values of MTP-T1WI and MTP-aT1WI of the white matter to lesion (WM-Lesion) were higher than conventional T1WI. The contrast of aT1WI surpassed that of the other two groups in WM-Lesion contrast. MTP-aT1W can detect more white matter lesions than conventional T1WI (conventional T1WI vs MTP-T1WI vs MTP-aT1WI,123 vs 165 vs 161). The MTP-T1W and aT1W images can enhance lesion contrast and precisely delineate the extent and boundaries of the lesions, and could be more sensitive to PWML than conventional T1WI.

Microstructural Characteristics of Cervical Spinal Cord Using High Angular Resolution Diffusion Imaging (HARDI) and Tractography in Healthy Subjects.

This study aimed to characterize spinal cord microstructure in healthy subjects using high angular resolution diffusion imaging (HARDI) and tractography. Forty-nine healthy subjects (18-50years, divided into 2 age groups) were included in aprospective study. HARDI of the cervical spinal cord were acquired using a3T MRI scanner with: 64directions, b‑value: 1000s/mm2, reduced field-of-view (zonally magnified oblique multi-slice), and opposed phase-encoding directions. Distortions were corrected using the FSL software package. Fiber tracking was performed using adeterministic approach with DSI-Studio software. Tensor metrics-fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), radial diffusivity (RD)-and tractography statistics were then extracted, at each spine level, and after grey-white matter segmentation. The microstructural organization of the spinal cord differed between upper and lower cervical spine levels: FA, and AD significantly decreased (p < 0.001); and RD significantly increased (p < 0.05) in lower levels, demonstrating changes in axonal density and myelinated fibers according to acranio-caudal axis. FA, MD, AD, and RD values were significantly higher in spinal cord white matter (p < 0.0001), compared to grey matter. Age was not associated with asignificant change in FA, while there is for MD, AD and RD (p < 0.05). Spinal cord tractography may provide information on the architectural organization of fibers and spinal tracts. This study proposes adatabase in cervical spinal cord HARDI, allowing to study the microstructural organization of the spinal cord in healthy subjects, and providing afoundation for comparison with patients presenting spinal cord pathologies.

Optimizing Radiation Dose and Image Quality in Stroke CT Protocols: Proposed Diagnostic Reference Levels for Multiphase CT Angiography and Perfusion Imaging.

In suspected acute ischemic stroke, it is now reasonable to expand the conventional "stroke protocol" (non-contrast computed tomography (NCCT), arterial CT angiography (CTA), and optionally CT perfusion (CTP)) to early and late venous head scans yielding a multiphase CTA (MP-CTA) to increase diagnostic confidence. Diagnostic reference levels (DRLs) have been defined for neither MP-CTA nor CTP. We therefore present dosimetry data, while also considering image quality, for a large, unselected patient cohort. A retrospective single-center study of 1790 patients undergoing the extended stroke protocol with three scanners (2× dual-source, DSCT; 1× single-source, SSCT) between 07/21 and 12/23 was conducted. For each sequence, we analyzed the radiation dose (volumetric CT dose index (CTDIvol); dose length product; effective dose); objective image quality using manually placed regions of interest (contrast-to-noise ratio (CNR)); and subjective image quality (4-point scale: 1 = non-diagnostic, 4 = excellent). The DRL was defined as the 75% percentile of the CTDIvol distribution. The Kruskal-Wallis test was used initially to test for overall equality of median values in each data group. Single post-test comparisons were performed with Dunn's test, with an overall statistical significance level of 0.05. Dosimetry values were significantly higher for SSCT (p < 0.001, each). Local DRLs ranged between 37.3 and 49.1 mGy for NCCT, 3.6-5.5 mGy for arterial CTA, 1.2-2.5 mGy each for early/late venous CTA, and 141.1-220.5 mGy for CTP. Protocol adjustment (DSCT-1: CTP) yielded a 28.2% dose reduction. The highest/lowest CNRs (arterial/early venous CTA, respectively) were recorded for SSCT/DSCT-2 (p < 0.001). Subjective image quality was rated excellent except for slightly increased MP-CTA noise at DSCT-2 (median = 3). Our data imply that additive MP-CTA scans only yield a minor increase in radiation exposure, particularly when using DSCT. CTP should be limited to selected patients.

Virtual Monoenergetic Imaging of Thoracoabdominal Computed Tomography Angiography on Photon-Counting Detector Computertomography: Assessment of Image Quality and Leveraging Low-keV Series for Salvaging Suboptimal Contrast Acquisitions.

The aim of this study was to assess the possibility of image improvement of ECG-gated, high-pitch computed tomography angiography (CTA) of the thoracoabdominal aorta before transaortic valve replacement (TAVR) on a novel dual-source photon-counting detector CT (PCD-CT) in the setting of suboptimal low-contrast attenuation. Continuously examined patients who underwent an ECG-gated, high-pitch CTA of the aorta on a PCD-CT with a contrast decrease of at least 50% between the ascending aorta and the common femoral arteries (CFA) were included. Patient characteristics were documented. Virtual monoenergetic imaging (VMI) reconstructions with three keV settings were generated. CT values and noise were measured for five vascular segments of the aorta and the CFA. Signal-to-noise (SNR) and contrast-to-noise ratios (CNR) were calculated. Two independent board-certified radiologists rated the images with the focus on vascular attenuation, vessel sharpness, and image quality using a 5-point Likert scale. Fifty-five patients (mean age 77.4 ± 8.5 years; 15 women) were included. The SNR was significantly higher at 40 and 45 keV VMI compared to reference 70 keV (p < 0.001 and p = 0.005, respectively). The same was shown for the CNR (p < 0.001 and p = 0.0049, respectively). Subjective image evaluation showed a significant increase in vessel attenuation in the lower keV reconstructions, while the overall image quality decreased only slightly. Furthermore, 50% (8/16) of primarily non-diagnostic scans were considered diagnostic when using low-keV reconstructions (p > 0.05). ECG-gated CTA of the aorta in high-pitch mode on PCD-CT with suboptimal contrast enhancement at the level of the CFA can be salvaged by using low-keV VMI. This implies the possibility of radiation dose reduction by eliminating the need for repeat scans.

Quantifying the Corneal Nerve Whorl Pattern.

The corneal nerves within the sub-basal nerve plexus (SBNP) display a distinctive whorl-like pattern, a highly dynamic structure that could be a marker of diseases. Previous studies have reported a decrease in whorl nerve density in patients with diabetes, indicating an avenue for noninvasive monitoring of diabetic neuropathy. However, conflicting results have since been reported, highlighting the need for improved quantitative analysis of the corneal whorl. We present an automated algorithm to characterize the whorl shape and test the hypothesis that the whorl organization is affected by diabetic neuropathy. The SBNP whorl was analyzed as a vector field, from which seven whorl metrics were calculated. The efficacy of these whorl metrics was demonstrated in synthetic images, ex vivo mouse corneas, and in a publicly available dataset of wide-field in vivo confocal microscopy (IVCM) images of diabetic and control subjects. Linear discriminant analysis and the Peacock test were used to test for statistical differences. Our analysis code is made freely available. Using our whorl metrics, we were able to quantify different whorl patterns in our patient population and statistically compare cohorts. We determined that whorl patterns tend to present bilaterally in patients (P < 0.001), but there were no significant differences between whorl patterns in patients with diabetes and control subjects, nor between patients with or without neuropathy symptoms. We present a generalizable framework to statistically compare corneal nerve patterns in cohorts of patients. SBNP whorl patterns could serve as a noninvasive marker for ocular diseases, whereas few quantitative IVCM endpoints have been identified to date.

An investigation into the applicability of rapid artificial intelligence‐assisted compressed sensing in brain magnetic resonance imaging performed at 5 Tesla field strength

AbstractBackgroundBrain magnetic resonance imaging (MRI) at 5 T offers unprecedented spatial resolution but is often limited by long scan times. Acceleration techniques, such as compressed sensing (CS) and artificial intelligence‐assisted compressed sensing (ACS), have the potential to speed up the acquisition process while maintaining image quality. This study aims to evaluate and compare the performance of CS and ACS (with various acceleration factors) in brain MRI imaging at 5 T.MethodsIn this study, we enrolled 12 healthy volunteers and compared ACS‐accelerated 5 T brain MRI with conventional methods of CS. The ACS acceleration factors for the brain protocol, consisting of 3D T1‐weighted sequences and 2D T2‐weighted sequences, were optimized in a pilot study on healthy volunteers (acceleration factor, 2.06–3.41× in T2‐weighted imaging and 3.52–8.49× in T1‐weighted imaging). We evaluated the images acquired from patients using various acceleration methods on the basis of acquisition times, the signal‐to‐noise ratio (SNR), the contrast‐to‐noise ratio, subjective image quality, and diagnostic agreement.ResultsOur findings revealed that ACS acceleration significantly reduced the acquisition times for T1‐ and T2‐weighted sequences by up to 43% and 53%, respectively, compared with traditional CS at 5 T. Importantly, this acceleration was achieved while maintaining excellent image quality, demonstrated by higher or comparable SNR and contrast‐to‐noise ratio values.ConclusionsThe optimal ACS acceleration factors for 5 T brain MRI were determined to be 2.73× for 2D T2‐weighted sequences and 6.5× for 3D T1‐weighted sequences. ACS not only facilitates rapid imaging but also ensures comparable image quality and diagnostic performance, highlighting its potential to revolutionize high‐field MRI scanning.

Detection of three-rooted mandibular first molars on panoramic radiographs using deep learning

This study aimed to develop a deep learning system for the detection of three-rooted mandibular first molars (MFMs) on panoramic radiographs and to assess its diagnostic performance. Panoramic radiographs, together with cone beam computed tomographic (CBCT) images of the same subjects, were retrospectively collected from 730 patients, encompassing a total of 1444 MFMs (367 teeth were three-rooted and the remaining 1077 teeth were two-rooted). Five convolutional neural network (CNN) models (ResNet-101 and − 50, DenseNet-201, MobileNet-v3 and Inception-v3) were employed to classify three- and two-rooted MFMs on the panoramic radiographs. The diagnostic performance of each model was evaluated using standard metrics, including accuracy, sensitivity, specificity, precision, negative predictive value, and F1 score. Receiver operating characteristic (ROC) curve analyses were performed, with the CBCT examination taken as the gold standard.Among the five CNN models evaluated, ResNet-101 demonstrated superior diagnostic performance, and the AUC value attained was 0.907, significantly higher than that of all other models (all P < 0.01). The accuracy, sensitivity, and specificity were 87.5%, 83.6%, and 88.9%, respectively. DenseNet-201, however, showed the lowest diagnostic performance among the five models (all P < 0.01), with an AUC value of 0.701 and an accuracy of 73.2%. Overall, the performance of the CNNs diminished when using image patches containing only the distal half of MFMs, with AUC values ranging between 0.680 and 0.800. In contrast, the diagnostic performance of the two clinicians was poorer, with AUC values of only 0.680 and 0.632, respectively. In conclusion, the CNN-based deep learning system exhibited a high level of accuracy in the detection of three-rooted MFMs on panoramic radiographs.

Diffusion-weighted imaging of the head and neck: comparison between integrated slice-specific dynamic shimming and simultaneous multi-slice readout-segmented echo-planar sequences.

To compare integrated slice-specific dynamic shimming (iShim) and simultaneous multi-slice (SMS) readout-segmented echo-planar imaging (RESOLVE) for diffusion-weighted imaging (DWI) of malignant head and neck tumours. In this prospective study, 45 patients with malignant head and neck lesions underwent iShim- and SMS-RESOLVE imaging with two b-values (0, 800 s/mm2) at 3 T. Subjective image quality scores (lesion distortion, signal loss, fat saturation, and artefacts), quantitative lesion distortion, quantitative image quality [signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and SNR efficiency], ADC values, and total acquisition times of iShim- and SMS-RESOLVE imaging were evaluated and compared. iShim-RESOLVE (3 mins 7 s) had longer acquisition times than SMS-RESOLVE (2 min 1 s). iShim-RESOLVE images had much better overall image quality, geometric distortion, fat saturation, and signal loss than SMS-RESOLVE (P < .05). The quantitative tumour distortion in iShim-RESOLVE images was significantly smaller than those of SMS-RESOLVE, measured either with b = 0 s/mm2 or b = 800 s/mm2 (P < .05). Using the iShim technique, the SNR, CNR of high b-value images, and SNR efficiency were significantly higher than those of SMS-RESOLVE (P < .001). The ADC measurements with excellent agreement of iShim-RESOLVE images were higher than those of SMS-RESOLVE. iShim-RESOLVE can decrease lesion distortion and improve overall image quality compared with SMS-RESOLVE in head and neck region. iShim-RESOLVE DWI may serve as a promising technique for reducing distortion and assessing head and neck lesions in clinical practice.

Changes in Hippocampal Volume after Traumatic Brain Injury (TBI).

To investigate hippocampal volume changes in moderate to severe traumatic brain injury (TBI) patients compared to healthy controls and assess their association with post-traumatic epilepsy (PTE), focusing on age-related effects. Imaging and demographic data for TBI patients were obtained from the Epilepsy Bioinformatics Study for Antiepileptogenic Therapy (EpiBioS4Rx) database; healthy controls matched by age and sex were sourced from Alzheimer's Disease Neuroimaging Initiative (ADNI), the National Institute of Mental Health (NIMH) Intramural Healthy Volunteer Dataset, the Parkinson's Progression Markers Initiative (PPMI), and the Autism Brain Imaging Data Exchange (ABIDE). MRI images for TBI subjects were obtained within 14-32 days post-injury. MRI data were preprocessed and segmented using FreeSurfer's recon-all pipeline and the hippocampal subfield segmentation module. TBI patients showed significantly smaller average hippocampal volumes than controls (β = -191.0, p = 8.33e-04, FDR p = 1.47e-03, Cohen's d = -0.36), notably in the right and left CA1 head regions. No significant hippocampal volume differences were found between TBI+ and TBI- patients overall. In patients aged 60+, TBI+ patients had significantly larger volumes in the right CA1 head than TBI- patients (β = 57.43, p = 0.0300, FDR p = 0.040; Cohen's d = 1.06). Hippocampal atrophy is evident in TBI patients but not directly linked to PTE development in most age groups. In patients over 60, hypertrophy in the right CA1 head may be associated with PTE, suggesting age and regional hippocampal changes influence epilepsy risk post-TBI. These findings highlight the complexity of hippocampal involvement in PTE and suggest potential shared mechanisms with neurodegenerative disorders such as Alzheimer's disease.

Utilization of double contrast-enhancement boost for lower-extremity CT angiography.

We aimed to compare the efficacy of the double contrast enhancement (CE)-boost technique with that of conventional methods to improve vascular contrast attenuation in lower-extremity computed tomography (CT) angiography. This retrospective study enrolled 45 patients (mean age, 70 years; range, 26 to 90 years; 30 males). To generate the CE-boost image, the degree of CE was determined by subtracting the post-contrast CT images from the pre-contrast CT images. The double CE-boost technique involves the application of this CE process twice. Both objective assessments (CT attenuation, noise level, signal-to-noise ratio [SNR], contrast-to-noise ratio [CNR], and image sharpness) and subjective quality evaluations were conducted on three types of images (conventional, CE-boost, and double CE-boost images). Double CE-boost images demonstrated significantly reduced noise in Hounsfield units (HUs) compared with conventional and CE-boost images ( ). CT attenuation values (HUs) were substantially higher in all different locations of the lower extremity with double CE-boost images ( ), as opposed to conventional ( ) and CE-boost images ( ). The SNR and CNR were notably improved in the double CE-boost image compared with both conventional and CE-boost images. Image sharpness analysis of the popliteal artery ( ), anterior tibial artery ( ), and dorsalis pedis artery ( ) revealed consistency across conventional, CE-boost, and double CE-boost images. Subjective image analysis indicated superior ratings for the double CE-boost compared with other types. The implementation of the double CE-boost technique improves image quality by decreasing image noise, increasing CT attenuation, and improving SNR, CNR, and subjective assessment compared with CE-boost and conventional imaging.