Image Sequences Research Articles

Magnetic resonance imaging fingerprints of status epilepticus: A case-control study.

Status epilepticus (SE) is frequently associated with peri-ictal magnetic resonance imaging (MRI) abnormalities (PMA). However, the anatomical distribution of these alterations has not been systematically studied. The aim of this study was to assess the localization patterns of PMA in patients with SE. In this prospective case-control study, we compared the distribution and combinations of diffusion-restricted PMA to diffusion-restricted lesions caused by other neurological conditions. All patients of the SE group and the control group underwent MRI including a diffusion-weighted imaging sequence. Patients with SE were imaged within 48 h after its onset. We enrolled 201 patients (51 with SE and 150 controls). The most frequent locations of PMA in SE were cortex (25/51, 49%), followed by hippocampus (20/51, 39%) and pulvinar of thalamus (10/51, 20%). In the control group, the cortex was involved in 80 of 150 (53%), white matter in 53 of 150 (35%), and basal ganglia in 33 of 150 (22%). In the control group, the pulvinar of thalamus was never affected and hippocampal structures were rarely involved (7/150, 5%). Involvement of the pulvinar of thalamus and the hippocampus had high specificity for SE at 100% (95% confidence interval [CI] = 98-100) and 95% (95% CI = 91-98), respectively. The sensitivity, however, was low for both locations (pulvinar of thalamus: 20%, 95% CI = 10-33; hippocampus: 39%, 95% CI = 26-54). Diffusion-restricted MRI lesions observed in the pulvinar of thalamus and hippocampus are strongly associated with SE. These changes may help physicians in diagnosing SE-related changes on MRI in an acute setting, especially in cases of equivocal clinical and electroencephalographic manifestations of SE.

Phase-sensitive deep reconstruction method for rapid multiparametric MR fingerprinting and quantitative susceptibility mapping in the brain

IntroductionThis study explores the potential of Magnetic Resonance Fingerprinting (MRF) with a novel Phase-Sensitivity Deep Reconstruction Network (PS-DRONE) for simultaneous quantification of T1, T2, Proton Density, B1+, phase and quantitative susceptibility mapping (QSM). MethodsData were acquired at 3 T in vitro and in vivo using an optimized EPI-based MRF sequence. Phantom experiments were conducted using a standardized phantom for T1 and T2 maps and a custom-made agar-based gadolinium phantom for B1 and QSM maps. In vivo experiments included five healthy volunteers and one patient diagnosed with brain metastasis. PSDRONE maps were compared to reference maps obtained through standard imaging sequences. ResultsTotal scan time was 2 min for 32 slices and a resolution of [1 mm, 1 mm, 4.5 mm]. The reconstruction of T1, T2, Proton Density, B1+ and phase maps were reconstructed within 1 s. In the phantoms, PS-DRONE analysis presented accurate and strongly correlated T1 and T2 maps (r = 0.99) compared to the reference maps. B1 maps from PS-DRONE showed slightly higher values, though still correlated (r = 0.6) with the reference. QSM values showed a small bias but were strongly correlated (r = 0.99) with reference data. In the in vivo analysis, PS-DRONE-derived T1 and T2 values for gray and white matter matched reference values in healthy volunteers. PS-DRONE B1 and QSM maps showed strong correlations with reference values. ConclusionThe PS-DRONE network enables concurrent acquisition of T1, T2, PD, B1+, phase and QSM maps, within 2 min of acquisition time and 1 s of reconstruction time.

Abstract 36: Clinical Guidelines May Help Mitigate the Impact of Physician Implicit Bias on Patient Care and Treatment

Introduction: We previously found that physician pro-White implicit bias was associated with the performance of low-value revascularization procedures for Black patients with claudication. These treatments are commonly considered risk greater than benefit but are not expressly discouraged by guidelines. We sought to investigate whether implicit bias is less likely to impact care in settings with well-defined Class Ia-supported guidelines. Hypothesis: We hypothesized that a physician’s implicit bias would not be associated with the performance of clinical practices as outlined in the 2016 AHA/ACC Guidelines on the Management of Patients with Lower Extremity Peripheral Artery Disease. Methods: We measured implicit bias via the race Implicit Association Test (IAT) using a sample of physicians from the Society for Vascular Surgery’s Vascular Quality Initiative (VQI). The IAT asks participants to classify sequential images of Black and White faces to positive and negative attributes. Based on reaction times and responses on the IAT, physicians were categorized as having no bias, pro-Black bias, or pro-White bias. IAT results were then weighted to reflect the overall VQI demographics and linked to peripheral revascularization data. We used mixed effects logistic regression models to assess the association of physician implicit bias category with pre-operative prescriptions of antiplatelets (ASA, P2Y12) and statins, as well as current smoking status (reported as aORs). All models included a random intercept for the physician and were adjusted for year, physician race/ethnicity, and patient factors of race/ethnicity, diabetes, and hypertension. We examined effect modification by patient race/ethnicity through the inclusion of an interaction term with physician implicit bias category. Finally, we calculated a summary index across the four primary clinical practices and assessed the association with physician implicit bias category via a mixed effects Poisson model (reported as IRRs). Results: A total of 218 physicians successfully completed the IAT and were linked to 6,588 peripheral revascularizations they completed for claudication. We found no significant associations between the physician’s implicit bias category and the performance of any of the assessed guideline metrics for their Black or White patients (Summary Index - IRR: 1.02, 95% CI: 0.98-1.06). Additionally, we found no evidence of effect modification by patient race/ethnicity (ASA - aOR: 0.91, 95% CI: 0.61-1.34; P2Y12 - aOR: 1.22, 95% CI: 0.88-1.69; Statin - aOR: 1.12, 95% CI: 0.76-1.67). Conclusions: The performance of guideline-driven practices were not associated with a physician’s measured racial implicit bias. We provide preliminary evidence that appropriately designed guidelines could be successful in combatting Black-White health inequities stemming from the implicit bias of physicians.

Design and analysis of shadow detection and removal scheme in real-time still images

This research’s main objective is to study and evaluate the detection and removal of undesired shadows from still images since these shadows might mask important information caused by light sources and other obstructions. A variety of methods for detecting and eliminating shadows as well as object tracking approaches based on movement estimation and identification are investigated. This includes shadow removal methods like background subtraction, which are intended to improve obstacle recognition of the source item and increase the accuracy of shadow removal from objects. When new items enter the frame, they are first distinguished from the background using a reference frame. The tracking procedure is made more difficult by the merging of the shadow with the foreground object. The approach highlights the difficulties in object detection owing to frequent occurrences of obstacles by using morphological procedures for shadow identification and removal. The proposed approach uses feature extraction is also discussed, highlighting its importance in image processing research and the use of suggested methods to get over obstacles in image sequences. The proposed method for shadow identification and removal offers a novel approach to improve image processing when dealing with still images. The purpose of this technique is to better detect and remove shadows from images, which will increase the precision of object tracking and detection. Depending on the type of images being processed, the process begins with initializing a background model, which is based on a static image background.

ADF-Net: An Attention-Guided Dual-Branch Fusion Network for Building Change Detection near the Shanghai Metro Line Using Sequences of TerraSAR-X Images

Building change detection (BCD) plays a vital role in city planning and development, ensuring the timely detection of urban changes near metro lines. Synthetic Aperture Radar (SAR) has the advantage of providing continuous image time series with all-weather and all-time capabilities for earth observation compared with optical remote sensors. Deep learning algorithms have extensively been applied for BCD to realize the automatic detection of building changes. However, existing deep learning-based BCD methods with SAR images suffer limited accuracy due to the speckle noise effect and insufficient feature extraction. In this paper, an attention-guided dual-branch fusion network (ADF-Net) is proposed for urban BCD to address this limitation. Specifically, high-resolution SAR images collected by TerraSAR-X have been utilized to detect building changes near metro line 8 in Shanghai with the ADF-Net model. In particular, a dual-branch structure is employed in ADF-Net to extract heterogeneous features from radiometrically calibrated TerraSAR-X images and log ratio images (i.e., difference images (DIs) in dB scale). In addition, the attention-guided cross-layer addition (ACLA) blocks are used to precisely locate the features of changed areas with the transformer-based attention mechanism, and the global attention mechanism with the residual unit (GAM-RU) blocks is introduced to enhance the representation learning capabilities and solve the problems of gradient fading. The effectiveness of ADF-Net is verified using evaluation metrics. The results demonstrate that ADF-Net generates better building change maps than other methods, including U-Net, FC-EF, SNUNet-CD, A2Net, DMINet, USFFCNet, EATDer, and DRPNet. As a result, some building area changes near metro line 8 in Shanghai have been accurately detected by ADF-Net. Furthermore, the prediction results are consistent with the changes derived from high-resolution optical remote sensing images.

Improving Vessel Segmentation with Multi-Task Learning and Auxiliary Data Available Only During Model Training

Liver vessel segmentation in magnetic resonance imaging data is important for the computational analysis of vascular remodeling, associated with a wide spectrum of diffuse liver diseases. Existing approaches rely on contrast enhanced imaging data, but the necessary dedicated imaging sequences are not uniformly acquired. Images without contrast enhancement are acquired more frequently, but vessel segmentation is challenging, and requires large-scale annotated data. We propose a multi-task learning framework to segment vessels in liver MRI without contrast. It exploits auxiliary contrast enhanced MRI data available only during training to reduce the need for annotated training examples. Our approach draws on paired native and contrast enhanced data with and without vessel annotations for model training. Results show that auxiliary data improves the accuracy of vessel segmentation, even if they are not available during inference. The advantage is most pronounced if only few annotations are available for training, since the feature representation benefits from the shared task structure. A validation of this approach to augment a model for brain tumor segmentation confirms its benefits across different domains. An auxiliary informative imaging modality can augment expert annotations even if it is only available during training.

ECMS-NET:A multi-task model for early endometrial cancer MRI sequences classification and segmentation of key tumor structures

Endometrial cancer, one of the three major malignant tumors of the female genitalia, has seen an increase in incidence in recent years. The 5-year survival rate for early endometrial cancer is approximately 80% to 90%. In clinical practice, the accurate segmentation of endometrial cancer tumors is crucial for assessing the extent of hyperplasia and guiding treatment decisions. Developing a deep learning (DL)-based tumor segmentation method for Magnetic Resonance Imaging (MRI) sequences in cases of Endometrial Cancer (EC) can significantly improve the accuracy and efficiency of this process. We proposed an multi-task framework: ECMS-Net. We established a classification model based on the Transformer algorithm to discern images containing tumors within the sequence and U2-Net segmentation model was trained to perform automated and precise segmentation of early endometrial cancer tumor regions. Our results show that we have firstly proposed a sequence classification method and achieved an accuracy of 0.985 and this is the best result of the study so far, followed by a tumor segmentation maxF1 value of 0.970, which highlights the excellent performance of our proposed method. The entire experimental process aligns closely with the demands of the clinical imaging department, promising to enhance the efficiency of medical professionals, alleviate workload stress, and better cater to the requirements of the medical field.

Enhancing Image Alignment in Time-Lapse-Ground-Penetrating Radar through Dynamic Time Warping

Ground-penetrating radar (GPR) is a rapid and non-destructive geophysical technique widely employed to detect and quantify subsurface structures and characteristics. Its capability for time lapse (TL) detection provides essential insights into subsurface hydrological dynamics, including lateral flow and soil water distribution. However, during TL-GPR surveys, field conditions often create discrepancies in surface geometry, which introduces mismatches across sequential TL-GPR images. These discrepancies may generate spurious signal variations that impede the accurate interpretation of TL-GPR data when assessing subsurface hydrological processes. In responding to this issue, this study introduces a TL-GPR image alignment method by employing the dynamic time warping (DTW) algorithm. The purpose of the proposed method, namely TLIAM–DTW, is to correct for geometric mismatch in TL-GPR images collected from the identical survey line in the field. We validated the efficacy of the TLIAM–DTW method using both synthetic data from gprMax V3.0 simulations and actual field data collected from a hilly, forested area post-infiltration experiment. Analyses of the aligned TL-GPR images revealed that the TLIAM–DTW method effectively eliminates the influence of geometric mismatch while preserving the integrity of signal variations due to actual subsurface hydrological processes. Quantitative assessments of the proposed methods, measured by mean absolute error (MAE) and root mean square error (RMSE), showed significant improvements. After performing the TLIAM–DTW method, the MAE and RMSE between processed TL-GPR images and background images were reduced by 96% and 78%, respectively, in simple simulation scenarios; in more complex simulations, MAE declined by 27–31% and RMSE by 17–43%. Field data yielded reductions in MAE and RMSE of >82% and 69%, respectively. With these substantial improvements, the processed TL-GPR images successfully depict the spatial and temporal transitions associated with subsurface lateral flows, thereby enhancing the accuracy of monitoring subsurface hydrological processes under field conditions.

Sequential deep learning image enhancement models improve diagnostic confidence, lesion detectability, and image reconstruction time in PET

BackgroundInvestigate the potential benefits of sequential deployment of two deep learning (DL) algorithms namely DL-Enhancement (DLE) and DL-based time-of-flight (ToF) (DLT). DLE aims to enhance the rapidly reconstructed ordered-subset-expectation-maximisation algorithm (OSEM) images towards block-sequential-regularised-expectation-maximisation (BSREM) images, whereas DLT aims to improve the quality of BSREM images reconstructed without ToF. As the algorithms differ in their purpose, sequential application may allow benefits from each to be combined. 20 FDG PET-CT scans were performed on a Discovery 710 (D710) and 20 on Discovery MI (DMI; both GE HealthCare). PET data was reconstructed using five combinations of algorithms:1. ToF-BSREM, 2. ToF-OSEM + DLE, 3. OSEM + DLE + DLT, 4. ToF-OSEM + DLE + DLT, 5. ToF-BSREM + DLT. To assess image noise, 30 mm-diameter spherical VOIs were drawn in both lung and liver to measure standard deviation of voxels within the volume. In a blind clinical reading, two experienced readers rated the images on a five-point Likert scale based on lesion detectability, diagnostic confidence, and image quality.ResultsApplying DLE + DLT reduced noise whilst improving lesion detectability, diagnostic confidence, and image reconstruction time. ToF-OSEM + DLE + DLT reconstructions demonstrated an increase in lesion SUVmax of 28 ± 14% (average ± standard deviation) and 11 ± 5% for data acquired on the D710 and DMI, respectively. The same reconstruction scored highest in clinical readings for both lesion detectability and diagnostic confidence for D710.ConclusionsThe combination of DLE and DLT increased diagnostic confidence and lesion detectability compared to ToF-BSREM images. As DLE + DLT used input OSEM images, and because DL inferencing was fast, there was a significant decrease in overall reconstruction time. This could have applications to total body PET.

3D SHINKEI MR neurography in evaluation of traumatic brachial plexus

3D SHINKEI neurography is a new sequence for imaging the peripheral nerves. The study aims at assessing traumatic brachial plexus injury using this sequence. Fifty-eight patients with suspected trauma induced brachial plexus injury underwent MR neurography (MRN) imaging in 3D SHINKEI sequence at 3 T. Surgery and intraoperative somatosensory evoked potentials or clinical follow-up results were used as the reference standard. MRN, surgery and electromyography (EMG) findings were recorded at four levels of the brachial plexus-roots, trunks, cords and branches. Fifty-eight patients had pre- or postganglionic injury. The C5–C6 nerve postganglionic segment was the most common (average 42%) among the postganglionic injuries detected by 3D SHINKEI MRN. The diagnostic accuracy (83.75%) and the specificity (90.30%) of MRN higher than that of EMG (p < 0.001). There was no significant difference in the diagnostic sensitivity of MRN compared with EMG (p > 0.05). Eighteen patients with brachial plexus injury underwent surgical exploration after MRN examination and the correlation between MRN and surgery was 66.7%. Due to the high diagnostic accuracy and specificity, 3D SHINKEI MRN can comprehensively display the traumatic brachial plexus injury. This sequence has great potential in the accurate diagnosis of traumatic brachial plexus injury.

Altered Dynamics of Brain Spontaneous Activity and Functional Networks Associated With Cognitive Impairment in Patients With Type 2 Diabetes.

Cognitive impairment is increasingly recognized as an important comorbidity and complication of type 2 diabetes (T2D), affecting patients' quality of life and diabetes management. Dynamic brain activity indicators can reflect changes in key neural activity patterns of cognition and behavior. To investigate dynamic functional connectivity (DFC) changes and spontaneous brain activity based on resting-state functional magnetic resonance imaging (rs-fMRI) in patients with T2D, exploring their correlations with clinical features. Retrospective. Forty-five healthy controls (HCs) (22 males and 23 females) and 102 patients with T2D (57 males and 45 females). 3.0 T/T1-weighted imaging and rs-fMRI with gradient-echo planar imaging sequence. Functional networks were created using independent component analysis. DFC states were determined using sliding window approach and k-means clustering. Spontaneous brain activity was assessed using dynamic regional homogeneity (dReHo) variability. One-way analysis of variance and post hoc analysis were used to compare the essential information including demographics, clinical data, and features of DFC and dReHo among groups. Diagnostic performance was assessed using receiver operating characteristic (ROC) curve. P-values <0.05 were taken to indicate statistical significance. T2D group had significantly decreased mean dwell time and fractional windows in state 4 compared to HC. T2D with mild cognitive impairment showed significantly increased dReHo variability in left superior occipital gyrus compared to T2D with normal cognition. Mean dwell time and number of fractional windows of state 4 both showed significant positive correlations with the Montreal cognitive assessment scores (r = 0.309; r = 0.308, respectively) and the coefficient of variation of dReHo was significantly positively correlated with high-density lipoprotein cholesterol (r = 0.266). The integrated index had an area under the curve of 0.693 (95% confidence interval = 0.592-0.794). Differences in DFC and dynamic characteristic of spontaneous brain activity associated with T2D-related functional impairment may serve as indicators for predicting symptom progression and assessing cognitive dysfunction. 2 TECHNICAL EFFICACY: Stage 2.

Visualization of Ice Crystal Behavior in Mouse Oocytes During High-Speed Quench Cooling and Ice Inhibition by Antifreezing Hydrogels.

Oocyte vitrification has become a widely adopted method in clinical practice. However, the solidification behavior and its impact on oocytes during the ultrarapid cooling process remain poorly understood. In this study, we established a system and methodology to observe crystallization behavior in oocytes during quench cooling and warming. Subsequently, the threshold concentration of cryoprotective agents (CPAs) required for oocyte vitrification was determined through a visualization method. The results demonstrated that the ice front could not be observed in the image sequence when using 16.5% DMSO +16.5% EG during high-speed quench cooling (2821.58°C/min). Finally, oocytes were encapsulated with an antifreezing hydrogel (7.5% EG +7.5% DMSO +0.5% alginate) and subjected to high-speed quench cooling. No ice crystals appeared in the antifreezing hydrogel-encapsulated oocytes at a low concentration of osmotic CPA (2.4 M). This research opens up new possibilities for oocyte vitrification with a reduced concentration of CPA.

Attention mechanism enhanced spatiotemporal-based deep learning approach for classifying barely visible impact damages in CFRP materials

Most existing machine learning approaches for analysing thermograms mainly focus on either thermal images or pixel-wise temporal profiles of specimens. To fully leverage useful information in thermograms, this article presents a novel spatiotemporal-based deep learning model incorporating an attention mechanism. Using captured thermal image sequences, the model aims to better characterise barely visible impact damages (BVID) in composite materials caused by different impact energy levels. This model establishes the relationship between patterns of BVID in thermography and their corresponding impact energy levels by learning from spatial and temporal information simultaneously. Validation of the model using 100 composite specimens subjected to five different low-velocity impact forces demonstrates its superior performance with a classification accuracy of over 95%. The proposed approach can contribute to Structural Health Monitoring (SHM) community by enabling cause analysis of impact incidents based on predicting the potential impact energy levels. This enables more targeted predictive maintenance, which is especially significant in the aviation industry, where any impact incidents can have catastrophic consequences.

Characterization of real-time cine MR imaging distortion on 0.35 T MRgRT with concentric cine imaging QA phantom

Objective. Real-time MRgRT uses 2D-cine imaging for target tracking and motion evaluation. Rotation of gantry induced B 0 off-resonance, resulting in image artifacts and imaging isocenter-shift precluding MR-guided arc therapy. Standard MRI phantoms designed for higher resolution images face challenges when low-resolution cine imaging is needed to achieve high frame rates. This work aimed to examine the spatial accuracy including geometric distortion and isocenter shift in real-time during gantry rotation on a 0.35 T MR-Linac using the concentric Cine imaging quality assurance (QA) phantom and its associated image analysis software. Approach. The Cine imaging QA phantom consists of two concentric shells of low-T1 mineral oil and a central alignment structure. The phantom was scanned on three different MRI systems; 0.55 T Siemens Free.Max, 1.5 T Philips Ingenia, and 0.35 T ViewRay MRIdian MR-Linac using 2D balanced steady-state free precession (bSSFP) imaging sequence. In addition, bSSFP cine MRI with the banding artifact correction was tested on 0.35 T ViewRay MR-Linac. Images from the MR-Linac were acquired with the Linac gantry stationary and rotating from gantry 300°→ 0° and vice versa. Three orthogonal image planes were scanned excluding the 1.5 T Philips Ingenia, where only the axial plane was scanned. The image analysis software calculated the distortion values as well as the isocenter position for each cine frame. Main results. The geometric distortion of cine imaging on MRIs and MR-Linac at gantry stationary are within 1 mm while the substantial geometric distortion of 2 and 2.2 mm were observed on 0.35 T MR-Linac while rotating the gantry clockwise (300°→ 0°) and counterclockwise 0°→ 300° respectively. The average imaging isocenter shift was 0.1 mm for both MRIs and the static gantry and imaging isocenter shift of ≤1.5 mm was observed during the gantry rotation. The imaging isocenter shift decreased by 1 ± 0.2 mm clockwise and counterclockwise with B 0 compensation. Significance. The concentric Cine imaging QA phantom and its associated software effectively demonstrate the image distortion on real-time cine imaging on regular MRIs and 0.35 T MR-Linac. The results of significant geometric distortion with a rotating gantry in the MR-Linac system require further investigation to alleviate the extent of the image distortion.

Depth-Guided Filtering-Based Null-Domain Background Suppression for Graphic Image Enhancement in Visual Communication Design

Background noise, for example, can influence the outcome of target recognition in the visual communication design of weak target images, lowering the visual communication effect. In order to achieve this, this paper proposes a visual communication design method for weak target images based on spatiotemporal domain filtering. It uses guided filtering to smooth the image and raise the gray level of weak target points, and then obtains the background baseline of target points in the image sequence through the micro-partial equation to complete the image’s spatiotemporal domain background suppression. The best visual communication design result is achieved. The experimental findings demonstrate that the suggested approach has a good visual communication effect and that the pace of communication is not constrained by the size of the images.

Violent Video Recognition by Using Sequential Image Collage.

Identifying violent activities is important for ensuring the safety of society. Although the Transformer model contributes significantly to the field of behavior recognition, it often requires a substantial volume of data to perform well. Since existing datasets on violent behavior are currently lacking, it will be a challenge for Transformers to identify violent behavior with insufficient datasets. Additionally, Transformers are known to be computationally heavy and can sometimes overlook temporal features. To overcome these issues, an architecture named MLP-Mixer can be used to achieve comparable results with a smaller dataset. In this research, a special type of dataset to be fed into the MLP-Mixer called a sequential image collage (SIC) is proposed. This dataset is created by aggregating frames of video clips into image collages sequentially for the model to better understand the temporal features of violent behavior in videos. Three different public datasets, namely, the dataset of National Hockey League hockey fights, the dataset of smart-city CCTV violence detection, and the dataset of real-life violence situations were used to train the model. The results of the experiments proved that the model trained using the proposed SIC is capable of achieving high performance in violent behavior recognition with fewer parameters and FLOPs needed compared to other state-of-the-art models.

Windows on the Womb and Guiding Trains of Light: Figuring the Real in Plate XXVI of William Hunter's Anatomy of the Human Gravid Uterus

AbstractEschewing the symbolic in favour of commitment to the unmediated replication of exactly that which is actually observed, Hunter's attitude to the images in his Anatomy of the Human Gravid Uterus embraces a juridical ideal of scientific representation: images should tell the truth, the whole truth and nothing but the truth. Contemporary scholars have questioned this appeal to objectivity, maintaining representation always exists inside culture and arguing gender frequently inflects purportedly neutral scientific vision. I extend that debate via a reading of Plate XXVI, which is frequently misunderstood as representing something completely different to what it actually depicts. Its sequence of images, I argue, chart a narrative of enlightenment wherein folk mythologies of the uterus are subdued by the controlling scientific gaze. I also suggest a previously unrecognised correspondence between Plate XXVI and one of the plaster casts of the dissected bodies preserved in the University of Glasgow's Anatomy Museum.

Prototyping and evaluation of a novel machine vision system for real-time, automated quality grading of sweetpotatoes

Rapid advances in machine vision and artificial intelligence (AI) technologies have generated high interest in developing automated grading and sorting solutions for fresh produce of specialty crops. Sweetpotatoes are an economically important crop in the United States and beyond, but grading and sorting the commodity, especially for surface defects, remains a labor-intensive operation at commercial packing facilities. In addition to incurring high labor costs, manual grading is subjective and prone to human assessment error. This study was therefore aimed to develop automated grading technology based on machine vision and state-of-the-art AI to reduce labor dependence and improve quality assessment for sweetpotato packing lines. The developed grading system prototype consisted of a custom-designed roller conveyor to transport and rotate sweetpotatoes and an overhead color camera to perform full-surface quality assessment for size and surface defects. A YOLOv8-based computer vision pipeline was developed to segment and track each sweetpotato traveling on the conveyor and analyze sample quality conditions in real-time. The YOLOv8l model coupled with the BoT-SORT tracker achieved the overall Higher Order Tracking Accuracy (HOTA) score of 0.952. Based on the instance segmentation by YOLOv8l, the length and width of sweetpotatoes were estimated with percentage accuracies of 96.7 % and 90.3 %, respectively, while the instance segmentation for three classes of sweetpotatoes according to surface defect conditions yielded an overall accuracy of 82.6 %, regardless of samples. The final sample grading, which was realized by taking into account the quality information recorded from a sequence of multi-view images for each sample, achieved an overall accuracy of 91.7 % in grading four classes of sweetpotatoes. The developed prototype holds promise for next-stage integration with sorting mechanisms into a full-fledged sorting system and will be eventually beneficial for sweetpotatoes packers.

Exploring Spinal Cord Changes in Multiple Sclerosis Patients Using MRI

Multiple sclerosis (MS) is an autoimmune disease affecting the central nervous system (CNS). The diagnosis of MS is based on clinical signs and symptoms as well as findings in magnetic resonance imaging (MRI) sequences by demonstrating the spatial and temporal dispersion of white matter lesions, which are thought to be typical of MS in distribution, shape, extent, and signal abnormalities. Spinal cord MRI can identify asymptomatic lesions and rule out malignancies or spinal stenosis in patients for whom brain imaging is not helpful in making an MS diagnosis. This study examines the MRI features of Saudi Arabian patients clinically proven to have MS with typical lesions exclusively evident in the spinal cord. This retrospective cross-sectional study was carried out in 151 patients who are confirmed cases of MS based on clinical findings and MRI results. Patients’ MRI data were reviewed from the picture archiving and communication system (PACS). The study revealed that MS incidence was higher in females than males and that the number of people diagnosed with MS increased in middle age. Cervical cord plaques and cervical cord curve straightening were the most frequent changes (67% and 56%, respectively), indicating that MRI can complement and even replace clinical data in MS diagnosis, leading to earlier, more precise diagnoses and speedier starts to treatment.

Quality assessment of laser speckle image sequences for digital image correlation by Sequence-image Quality Evaluation Index

Digital Image Correlation (DIC) with laser speckle is effective for measuring strain in extreme conditions, but its limited resistance to disturbances and decorrelation issues limit its broader use. Addressing this, the Sequence-image Quality Evaluation Index (SQEI) has been introduced. SQEI evaluates laser speckle image sequences by considering individual image quality and their correlation. It improves upon previous standards by confirming speckle image quality for DIC accuracy and removing decorrelated images, enhancing DIC's precision and durability. Verified through metal thermal strain experiments, SQEI assesses the impact of factors like laser wavefront, temperature, and CCD angle. The results confirm SQEI's efficacy in evaluating laser speckle quality and guiding the optimization of optical devices, thus significantly boosting the accuracy and efficiency of DIC strain measurement with laser speckles.