Image Sequences Research Articles

Evaluating Foveal Avascular Zone Alterations in Type 2 Diabetes Mellitus and Their Association with C-Reactive Protein: A Comparative Study with Healthy Controls

Introduction: Recent technological progress in optical imaging—such as adaptive optics, interferometry and tomography—has greatly improved the resolution of retinal imaging. The ability to capture sequential images over time is particularly valuable for continuous monitoring and assessment of retinal diseases. Methods: This cross-sectional study involved patients with type 2 diabetes mellitus and age-matched controls from the Diabetes and Ophthalmology Department of the Emergency Military Clinical Hospital “Dr. Constantin Papilian” Cluj-Napoca between October 2023 and October 2024. These patients were assessed for inclusion and exclusion criteria and then categorized into two groups: the diabetes group and control group. Each participant underwent a comprehensive ophthalmological examination and retinal evaluation using SS-OCT (Spectralis Heidelberg Engineering, Heidelberg, Germany). The parameters measured included the superficial and deep foveal avascular zones (FAZ) in only one eye for each patient, selected based on image quality. Additionally, each patient underwent quantitative analysis of serum C-reactive protein (CRP) levels. Results: A total of 33 patients (33 eyes) featured, 13 men and 20 women. The DM group showed statistically significant higher results for CRP value compared to healthy subjects (p < 0.001). Also, both superficial and deep FAZ areas were statistically significantly higher for diabetes patients compared to the healthy controls (p < 0.05). The correlation analysis revealed that there was no significant correlation between CRP and either superficial FAZ (p = 0.809) or deep FAZ (p = 0.659). However, a significant positive moderate correlation was found between superficial FAZ and deep FAZ (r = 0.577, p = 0.015). Conclusions: Our findings showed a significantly enlarged FAZ in diabetic patients compared to healthy individuals, highlighting its potential as an early indicator of microvascular alterations in diabetes. While CRP levels were notably elevated in the diabetic group, no significant association was found between CRP and FAZ measurements, suggesting that FAZ changes may occur independently of systemic inflammatory status.

Advanced object detection for smart accessibility: a Yolov10 with marine predator algorithm to aid visually challenged people

A significant challenge for many visually impaired people is they cannot be entirely independent and are restricted by their vision. They face problems with such actions and object detection should be an essential feature they can rely on a regular basis. Object detection is applied to discover objects in the real world from an image of the world, like chairs, bicycles, tables, or doors, that are normal in the scenes of a blind predicated on their places. Computer vision (CV) involves the automated extraction, understanding, and analysis of valuable information from a sequence of images or a single image. Machine learning (ML) and deep learning (DL) are significant and robust learning architectures broadly established, especially for CV applications. This study proposes a novel Advanced Object Detection for Smart Accessibility using the Marine Predator Algorithm to aid visually challenged people (AODSA-MPAVCP) model. The main intention of the AODSA-MPAVCP model is to enhance object detection techniques using advanced models for disabled people. Initially, the image pre-processing stage applies adaptive bilateral filtering (ABF) to eliminate the unwanted noise in input image data. Furthermore, the proposed AODSA-MPAVCP model utilizes the YOLOv10 model for object detection. Moreover, the feature extraction process employs the VGG19 method to transform raw data into meaningful and informative features. The deep belief network (DBN) technique is used for the classification process. Finally, the marine predator algorithm (MPA)-based hyperparameter selection process is performed to optimize the classification results of the DBN technique. The experimental evaluation of the AODSA-MPAVCP approach is examined under the Indoor object detection dataset. The performance validation of the AODSA-MPAVCP approach portrayed a superior accuracy value of 99.63% over existing models.

Spatiotemporal modeling of host-pathogen interactions using level-set method.

Spatiotemporal modeling of host-pathogen interactions using level-set method.

FUSE: A framework for uncertainty-aware object assessment from image sequences in uncontrolled environments

FUSE: A framework for uncertainty-aware object assessment from image sequences in uncontrolled environments

A deep learning framework for reconstructing Breast Amide Proton Transfer weighted imaging sequences from sparse frequency offsets to dense frequency offsets.

A deep learning framework for reconstructing Breast Amide Proton Transfer weighted imaging sequences from sparse frequency offsets to dense frequency offsets.

Brain under pressure: Insights into diving-related lesions: a descriptive study.

Brain under pressure: Insights into diving-related lesions: a descriptive study.

Intraoperative cerebral perfusion monitoring with ultrafast power doppler imaging

Brain perfusion monitoring during cerebrovascular surgery is highly desirable; however, this technology is not yet available to surgeons. Our center has developed and implemented a dedicated ultrafast power Doppler imaging (UPDI) sequence along with a novel postprocessing analysis. This method enables intraoperative, real-time (1 Hz) detection of changes in cerebral blood volume (CBV) at high spatial resolution (100 μm). We performed continuous UPDI acquisitions in 10 patients undergoing surgery for intracranial aneurysm clipping, AVM resection, or cerebrovascular bypass surgery. When temporary clipping was required during surgery, we recorded perfusion in the parenchyma within the vascular territory of the affected artery. Recordings began with a 30-second baseline and continued for up to 60 s after clip release. The UPDI sequence successfully demonstrated cerebral perfusion up to the level of the penetrating arterioles. The time-series data captured vascular phenomena such as ischemia, collateral recruitment, and hyperperfusion in both the cortex and white matter following the placement and removal of temporary clips. UPDI shows promise as a tool for continuous CBV monitoring during (cerebrovascular) surgery, as it enables quantitative vascular monitoring of the parenchyma.

FPGA implementation of deep learning architecture for ankylosing spondylitis detection from MRI

Ankylosing Spondylitis (AS), commonly known as Bechterew’s disease, is a complex, potentially disabling disease that develops slowly over time and progresses to radiographic sacroiliitis. The etiology of this disease is poorly understood, making it difficult to diagnose. Therefore, treatment is also delayed. This study aims to diagnose AS with an automated system that classifies axial magnetic resonance imaging (MRI) sequences of AS patients. Recently, the application of deep learning neural networks (DLNNs) for MRI classification has become widespread. The implementation of this process on computer-independent end devices is advantageous due to its high computational power and low latency requirements. In this research, an MRI dataset containing images from 527 individuals was used. A deep learning architecture on a Field Programmable Gate Array (FPGA) card was implemented and analyzed. The results show that the classification performed on FPGA in AS diagnosis yields successful results close to the classification performed on CPU.

Do Intact Collateral Ligaments Play a Role in the Overall Clinical and Radiological Results of Rotating Hinge Knee Arthroplasties?

Rotating hinge knee arthroplasty (RHKA) implants are often utilized as a salvage procedure in cases where bone stock is compromised. The aim of this retrospective study was to investigate whether residual collateral ligament integrity affects functional and radiographic outcomes in patients undergoing revision surgery with RHKA. Patients treated with RHKA between 2011 and 2021 were eligible. Inclusion criteria were patients who had undergone an RHKA as a revision or a primary procedure, had complete radiological and clinical data, and had a minimum follow-up of 2 years. There were 79 knees that were included. Patients were evaluated with standing radiographs and two-dimensional multi-acquisition variable-resonance imaging combination selective (MAVRIC) magnetic resonance imaging (MRI) sequences to assess ligament integrity. Range of motion (ROM), Visual Analog Scale (VAS), Knee Society Scores (KSS), and Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) scores were recorded. The mean age was 66 years (range, 39 to 79), and the mean follow-up was 54.6 months (approximately 4.5 years). The integrity of the collateral was successfully determined by the magnetic resonance imaging scans and patients were divided into three groups: those who had both collateral ligaments (n = 53), isolated medial collateral ligament damage (n = 14), and those who had both collateral ligaments damaged (n = 12). No significant difference was observed between the groups with regard to both radiological data and clinical scores (P > 0.05). KSS, KSS-F, and Western Ontario and McMaster Universities Osteoarthritis Index function scores at the last follow-up were significantly higher in patients treated for secondary osteoarthritis (complex primaries). No significant difference in functional outcomes was detected in patients treated with RHKA, independent of collateral ligament integrity, at an average of 54 months postoperatively. When an RHKA is indicated as the first treatment option, results are more satisfactory in comparison to revision cases.

A neuromorphic model of active vision shows how spatiotemporal encoding in lobula neurons can aid pattern recognition in bees.

Bees' remarkable visual learning abilities make them ideal for studying active information acquisition and representation. Here, we develop a biologically inspired model to examine how flight behaviours during visual scanning shape neural representation in the insect brain, exploring the interplay between scanning behaviour, neural connectivity, and visual encoding efficiency. Incorporating non-associative learning-adaptive changes without reinforcement-and exposing the model to sequential natural images during scanning, we obtain results that closely match neurobiological observations. Active scanning and non-associative learning dynamically shape neural activity, optimising information flow and representation. Lobula neurons, crucial for visual integration, self-organise into orientation-selective cells with sparse, decorrelated responses to orthogonal bar movements. They encode a range of orientations, biased by input speed and contrast, suggesting co-evolution with scanning behaviour to enhance visual representation and support efficient coding. To assess the significance of this spatiotemporal coding, we extend the model with circuitry analogous to the mushroom body, a region linked to associative learning. The model demonstrates robust performance in pattern recognition, implying a similar encoding mechanism in insects. Integrating behavioural, neurobiological, and computational insights, this study highlights how spatiotemporal coding in the lobula efficiently compresses visual features, offering broader insights into active vision strategies and bio-inspired automation.

Two-Dimensional Magnetic Resonance Imaging Sequences Correlate to Three-Dimensional Computed Tomography for Evaluation of Glenoid Bone Loss

Two-Dimensional Magnetic Resonance Imaging Sequences Correlate to Three-Dimensional Computed Tomography for Evaluation of Glenoid Bone Loss

Parallel Multi-Scale Semantic-Depth Interactive Fusion Network for Depth Estimation

Self-supervised depth estimation from monocular image sequences provides depth information without costly sensors like LiDAR, offering significant value for autonomous driving. Although self-supervised algorithms can reduce the dependence on labeled data, the performance is still affected by scene occlusions, lighting differences, and sparse textures. Existing methods do not consider the enhancement and interaction fusion of features. In this paper, we propose a novel parallel multi-scale semantic-depth interactive fusion network. First, we adopt a multi-stage feature attention network for feature extraction, and a parallel semantic-depth interactive fusion module is introduced to refine edges. Furthermore, we also employ a metric loss based on semantic edges to take full advantage of semantic geometric information. Our network is trained and evaluated on KITTI datasets. The experimental results show that the methods achieve satisfactory performance compared to other existing methods.

Multi-institutional recommendations on the use of 7T MRI in deep brain stimulation.

Deep brain stimulation (DBS) is an established therapeutic intervention for a range of neurological disorders, including Parkinson's disease, essential tremor, and epilepsy. The efficacy of DBS is predicated on the modulation of dysfunctional neural circuits through the application of electrical pulses. Recent advancements in MRI technology have facilitated the visualization of brain nuclei and their associated networks, which is critical for proper patient-specific targeting of electrodes in surgical procedures. This advancement aims to personalize surgical planning and postoperative programming by integrating patient-specific anatomical and connectivity models. The advent of clinical ultrahigh-field MRI, particularly 7T MRI, significantly enhances the targeting of DBS by improving spatial resolution, signal-to-noise ratio, and tissue contrast. Compared with lower field strengths, 7T MRI provides superior visualization of deeply situated brain nuclei and their extensive cortical projections, including the subthalamic nucleus, globus pallidus internus, and thalamus. This review synthesizes a multi-institutional consensus regarding the technical and clinical applications of 7T MRI, drawing on experience from more than 1000 procedures using 7T DBS. It encompasses both imaging acquisition and postprocessing techniques aimed at optimizing image quality. Our extensive clinical experience informs best practices for correcting distortions, mitigating image artifacts, and employing specific imaging sequences that enhance the visualization of common DBS targets. The insights and recommendations presented are intended to promote the safe and effective utilization of 7T MRI in DBS.

Energy efficiency and sensitivity benefits in a motion processing adaptive recurrent neural network.

Energy efficiency and sensitivity benefits in a motion processing adaptive recurrent neural network.

How Humans Evaluate AI Systems for Person Detection in Automatic Train Operation: Not All Misses Are Alike

If artificial intelligence (AI) is to be applied in safety-critical domains, its performance needs to be evaluated reliably. The present study investigated how humans evaluate AI systems for person detection in automatic train operation. In three experiments, participants viewed image sequences of people moving in the vicinity of railway tracks. A simulated AI system highlighted all detected people—sometimes correctly and sometimes not. Participants had to provide a numerical rating of the AI’s performance and then verbally explain their rating. The experiments manipulated several factors that might influence human ratings: the types and plausibility of AI mistakes, the number of affected images, the number of people present in an image, the position of people relevant to the tracks, and the methods used to elicit human evaluations. While all these factors influenced human ratings, some effects were unexpected or deviated from normative standards. For instance, the factor with the strongest impact was people’s position relative to the tracks, although participants had explicitly been instructed that the AI could not process such information. Taken together, the results suggest that humans may sometimes evaluate more than the AI’s performance on the assigned task. Such mismatches between AI capabilities and human expectations should be taken into consideration when conducting safety audits of AI systems.

Magnetic Resonance Imaging Sequences and Technologies in Adaptive Radiation Therapy.

Magnetic Resonance Imaging Sequences and Technologies in Adaptive Radiation Therapy.

Semi-supervised temporal attention network for lung 4D CT ventilation estimation.

Semi-supervised temporal attention network for lung 4D CT ventilation estimation.

Spatiotemporal semantic structural representation learning for image sequence prediction

Spatiotemporal semantic structural representation learning for image sequence prediction

Multivariate Framework of Metabolism in Advanced Prostate Cancer Using Whole Abdominal and Pelvic Hyperpolarized 13C MRI-A Correlative Study with Clinical Outcomes.

Background: Most of the existing hyperpolarized (HP) 13C MRI analyses use univariate rate maps of pyruvate-to-lactate conversion (kPL), and radiomic-style multiparametric models extracting complex, higher-order features remain unexplored. Purpose: To establish a multivariate framework based on whole abdomen/pelvis HP 13C-pyruvate MRI and evaluate the association between multiparametric features of metabolism (MFM) and clinical outcome measures in advanced and metastatic prostate cancer. Methods: Retrospective statistical analysis was performed on 16 participants with metastatic or local-regionally advanced prostate cancer prospectively enrolled in a tertiary center who underwent HP-pyruvate MRI of abdomen or pelvis between November 2020 and May 2023. Five patients were hormone-sensitive and eleven were castration-resistant. GMP-grade [1-13C]pyruvate was polarized using a 5T clinical-research DNP polarizer, and HP MRI used a set of flexible vest-transmit, array-receive coils, and echo-planar imaging sequences. Three basic metabolic maps (kPL, pyruvate summed-over-time, and mean pyruvate time) were created by semi-automatic segmentation, from which 316 MFMs were extracted using an open-source, radiomic-compliant software package. Univariate risk classifier was constructed using a biologically meaningful feature (kPL,median), and the multivariate classifier used a two-step feature selection process (ranking and clustering). Both were correlated with progression-free survival (PFS) and overall survival (OS) (median follow-up = 22.0 months) using Cox proportional hazards model. Results: In the univariate analysis, patients harboring tumors with lower-kPL,median had longer PFS (11.2 vs. 0.5 months, p < 0.01) and OS (NR vs. 18.4 months, p < 0.05) than their higher-kPL,median counterparts. Using a hypothesis-generating, age-adjusted multivariate risk classifier, the lower-risk subgroup also had longer PFS (NR vs. 2.4 months, p < 0.002) and OS (NR vs. 18.4 months, p < 0.05). By contrast, established laboratory markers, including PSA, lactate dehydrogenase, and alkaline phosphatase, were not significantly associated with PFS or OS (p > 0.05). Key limitations of this study include small sample size, retrospective study design, and referral bias. Conclusions: Risk classifiers derived from select multiparametric HP features were significantly associated with clinically meaningful outcome measures in this small, heterogeneous patient cohort, strongly supporting further investigation into their prognostic values.

Subarachnoid Fat Deposition After Lumber and Sacral Fractures: Case imaging.

A 28-year-old man with lumbar and sacral fractures after trauma developed intracisternal fat deposition, detected on head computed tomography (CT) five days post-admission. Spinal fusion surgery revealed no macroscopic dural injury, but CT myelography showed dural bulging without cerebrospinal fluid leakage. Magnetic resonance imaging findings indicated low intracranial pressure, suggesting dural damage as the entry point for fat into the subarachnoid space. Despite these imaging abnormalities, the patient remained asymptomatic, and follow-up CT confirmed persistent intracranial fat with gradual resolution of a subdural hematoma. This case highlights a rare phenomenon of fat deposition in the subarachnoid space after trauma and emphasizes the value of sequential imaging in complex cases.