Search

Interest in virus-based therapeutics for the treatment of genetic and oncolytic diseases has created a demand for high-yield, low-cost virus-manufacturing processes. However, traditional analytical methods of assessing infectious virus titer require multiple processing steps and manual counting, limiting sample throughput, and increasing human error. This bottleneck severely limits the development of new manufacturing unit operations to drive down costs. In this work, we utilize an Incucyte Live-Cell Analysis System to develop a high-throughput infectious titer assay for adenovirus expressing a GFP-transgene. Although previous studies have demonstrated live-cell imaging's potential for use with other viruses, they provide little guidance regarding the selection of the viewing and analysis parameters. To fill this gap, we develop an algorithmic approach to identify the optimum viewing and analysis parameters and create a statistical workflow for quantifying infectious adenovirus in a sample dilution series in a standard 24-well microplate. The developed assay is comparable to Hexon staining, the gold-standard for adenovirus infectious titer, with a Pearson correlation coefficient of 0.9. Finally, the developed algorithmic approach and statistical workflow were applied to create an assay for adenovirus titer using a 96-well microplate, allowing five times more samples to be quantified compared to the standard 24-well plate. While this assay uses a GFP-insert that precludes its use in a clinical environment, the key learnings surrounding the careful use of viewing and analysis parameters, and the statistical workflow are widely applicable to implementing life-cell imaging for dilution-series-based assays. Moreover, this method directly enables the fast and accurate evaluation of virus samples in a preclinical environment. • A preclinical live-cell imaging assay for infectious titer was validated against gold standard methods. • Titer estimates are significantly impacted by viewing and imaging analysis parameters. • Scale-up an automated workflow technique from 24-well microplates to 96-well microplates. [ABSTRACT FROM AUTHOR]

Acute radiation dermatitis (ARD) is the most common side effect reported by patients undergoing radiation therapy (RT). Currently, the assessment of the severity of the reaction is based on the visual assessment of the skin, which is a subjective method, depending on many factors. The main aim of this study was to investigate the usefulness of hyperspectral imaging (HSI) in the assessment of ARD and find physiological factors that could be correlated with ARD. In this clinical pilot trial, weekly acquisitions of hyperspectral camera images of irradiated skin were performed for 5 weeks of RT and at the posttreatment follow-up visit which took place 30 to 40 days after the last fraction of RT. At the same time, the severity of radiodermatitis was assessed based on the criteria of the National Cancer Institute Common Terminology Criteria for Adverse Events (CTCAE). The content and concentration of chromophores in irradiated skin were quantitatively determined using a hyperspectral camera. The use of HSI supported by image analysis and processing methods allowed for the determination of the content and distribution of hemoglobin and melanin in the irradiated skin. It was found that the hemoglobin concentration is correlated with the subjective assessment made according to the CTCAE protocol. HSI is a sensitive and specific method of analyzing the concentration of chromophores in the skin, including hemoglobin. A clear correlation was found between hemoglobin concentration and CTCAE v.5 scale because of which HSI can be considered as an objective method of skin assessment during RT. [ABSTRACT FROM AUTHOR]

To compare the features detected by high resolution magnetic resonance vessel wall imaging (HR-VWI) between posterior circulation atherosclerosis and intramural hematoma (IMH)-type dissection, and to identify indicators related to cerebral ischemic events. Clinical and HR-VWI data of 55 patients with posterior circulation IMH-type dissection and 132 patients with posterior circulation atherosclerosis collected between October 2017 and October 2023 were analyzed retrospectively. Two radiologists independently extracted the imaging features. Multivariable logistic regression was used to identify factors independently associated with stroke. Compared with patients with atherosclerosis, those with IMH-type dissection were younger, with a lower prevalence of diabetes and hypertriglyceridemia, lower hypertension grade, enhanced grade, remodeling index (RI), vertebrobasilar artery/brainstem ratio, and prevalence of nonsmooth surface, and higher prevalence of intraluminal thrombus (ILT), lumen (LA), wall area (WA), and total vessel area (TVA). In patients with stroke, those with IMH-type dissection were younger, with a lower prevalence of diabetes, and degree of hypertension, and higher RI, WA, TVA, and the prevalence of ILT. Multivariable logistic regression showed that RI (odds ratio [OR], 0.37; 95% CI, 0.17–0.77) and normalized wall index (NWI) (OR, 39.02; 95% CI, 2.19–695.35) were risk factors for stroke in patients with dissection, and LA (OR, 1.52; 95% CI, 1.12–2.06) and NWI (OR, 60.84; 95% CI 3.70–998.06) were risk factors for atherosclerotic stroke. Patients with posterior circulation IMH-type dissection had greater potential for positive remodeling than those with atherosclerosis. The arterial remodeling capacity was closely related to stroke risk. • Remodeling capacity is related to stroke in atherosclerosis and IMH type dissection. • The remodeling capacity of IMH-type dissection is greater than atherosclerosis. • HR-VWI has a good ability to identify atherosclerotic lesions and IMH type dissection. [ABSTRACT FROM AUTHOR]

Myocardial contrast echocardiography (MCE) plays a crucial role in diagnosing ischemia, infarction, masses and other cardiac conditions. In the realm of MCE image analysis, accurate and consistent myocardial segmentation results are essential for enabling automated analysis of various heart diseases. However, current manual diagnostic methods in MCE suffer from poor repeatability and limited clinical applicability. MCE images often exhibit low quality and high noise due to the instability of ultrasound signals, while interference structures can further disrupt segmentation consistency. To overcome these challenges, we proposed a deep-learning network for the segmentation of MCE. This architecture leverages dilated convolutions to capture high-scale information without sacrificing positional accuracy and modifies multi-head self-attention to enhance global context and ensure consistency, effectively overcoming issues related to low image quality and interference. Furthermore, we also adapted the cascade application of transformers with convolutional neural networks for improved segmentation in MCE. In our experiments, our architecture achieved the best Dice score of 84.35% for standard MCE views compared with that of several state-of-the-art segmentation models. For non-standard views and frames with interfering structures (mass), our models also attained the best Dice scores of 83.33% and 83.97%, respectively. These studies proved that our architecture is of excellent shape consistency and robustness, which allows it to deal with segmentation of various types of MCE. Our relatively precise and consistent myocardial segmentation results provide fundamental conditions for the automated analysis of various heart diseases, with the potential to discover underlying pathological features and reduce healthcare costs. [ABSTRACT FROM AUTHOR]

The optic nerve canal (ONC) is a fine skeletal structure that contains the optic nerve. However, it has not been thoroughly examined. This necessitates establishing a baseline knowledge of the geometrical and volumetric parameters of the ONC. The data of twenty patients who received a cone beam computed tomography examination were prepared using a voxel-based segmentation. The measurement was performed separately by two examiners on virtual skull models in stereolithography format in Geomagic Wrap®. The results showed that the volume of the ONC varied between 92.48 mm3 and 162.7 mm3 (M = 123.46 mm3, SD = 26.61 mm3). Sex-specific statistically significant differences in volume were detected only for the right side. The angle of the ONC to the skull base was independent of the diameter of the canal. Both the intrarater and interrater comparisons of the measurements showed high values of reproducibility of the results. This study showed that a virtual anatomical model provides a feasible and reliable method to investigate the ONC. The examination technique could have a wider range of application in anthropology and application in clinical medicine. Advances in the automation of radiological diagnostics and the digital analysis of X-ray images could help to reduce examination times. [ABSTRACT FROM AUTHOR]

Cobalt removal is considered a common method to improve the performance of polycrystalline diamond compact (PDC). To effectively reduce the pollution during the process of cobalt removal, a neutral electrolyte was used in this work to remove cobalt from PDC by electrolysis with ultrasonication. The electrode process and mass transfer model of cobalt removal in a NaCl–KCl solution were established by performing electrochemical impedance spectroscopy (EIS) measurements. Different electrode potentials and electrolytic durations were set to investigate the limits of cobalt removal in the neutral electrolyte. Cobalt removal was assessed by conducting potentiodynamic polarisation, scanning electron microscopy (SEM), and energy dispersive spectroscopy (EDS) measurements. The ImageJ2x image analysis software was used to study the collected spectra. The experimental results indicated that cobalt was successfully removed in the neutral electrolyte and that ultrasonication enhanced its removal. The optimal electrode potential for cobalt removal in the NaCl–KCl solution was less than 500 mV or more than 2000 mV. As the electrolysis time increased, the porosity of the PDC surface first increased to 9.4 % and then decreased to 7.2 %, and the depth of cobalt removal was up to 224 μm. Over time, the rate of cobalt removal decreased, suggesting that the efficacy of ultrasonication in promoting the cobalt removal process gradually weakened as electrolysis products continued to accumulate. [ABSTRACT FROM AUTHOR]

Nighttime driving safety is a key focus in transportation research due to accidents caused by drivers' inability to clearly see road obstacles, leading to delayed or incorrect decisions. To address this, the use of mechanoluminescent materials on surfaces like roads and buildings offers a potential solution for better object contour detection in poor visibility. This study investigates the use of SrAl 2 O 4 as a phosphor matrix, exploring its luminescence characteristics and the effects of doping with Eu2+ and Dy3+. The optimal doping ratios were determined to be 2 % Eu and 1 % Dy by trap modulation, producing phosphors with significant mechanical luminescence and a prolonged afterglow. Spectroscopic analysis and image assessment demonstrated a visible afterglow lasting up to 60 min, along with impressive mechanical luminescence performance. By combining the developed SrAl 2 O 4 :Eu2+, Dy3+ phosphor-based coating with polydimethylsiloxane, a real-time surface stress sensing system was devised utilizing digital camera and other optical sensors. This advancement facilitates the visualization of stresses in complex or confined environments, potentially improving nighttime driving safety through enhanced object contour detection. [ABSTRACT FROM AUTHOR]

The often-perceived limitations of image analysis have for many years impeded the widespread application of such systems as first line characterisation tools. Image analysis has, however, undergone a notable resurgence in the pharmaceutical industry fuelled by developments system capabilities and the desire of scientists to characterize the morphological nature of their particles more adequately. The importance of particle shape as well as size is now widely acknowledged. With the increasing use of modelling and simulations, and ongoing developments though the integration of machine learning and artificial intelligence, the utility of image analysis is increasing significantly driven by the richness of the data obtained. Such datasets provide means to circumvent the requirement to rely on less informative descriptors and enable the move towards the use of whole distributions. Combining the improved particle size and shape measurement and description with advances in modelling and simulations is enabling improved means to elucidate the link between particle and bulk powder properties. In addition to improved capabilities to describe input materials, approaches to characterize single components within multicomponent systems are providing scientists means to understand how their material may change during manufacture thus providing a means to link the behaviour of final dosage forms with the particle properties at the point of action. The aim is to provide an overview of image analysis and update readers with innovations and capabilities to other methods in the small molecule arena. We will also describe the use of AI for the improved analysis using image analysis. [Display omitted] [ABSTRACT FROM AUTHOR]

• Deep learning is currently the leading artificial intelligence tool in medical image analysis. • The overall accuracy of the deep learning-based algorithm in the assessment of the fetal occiput position was 94.5 %. • The deep learning algorithm showed an accuracy of 98.3 % in identifying any subtype of fetal head malposition. To develop a deep learning (DL)-model using convolutional neural networks (CNN) to automatically identify the fetal head position at transperineal ultrasound in the second stage of labor. Prospective, multicenter study including singleton, term, cephalic pregnancies in the second stage of labor. We assessed the fetal head position using transabdominal ultrasound and subsequently, obtained an image of the fetal head on the axial plane using transperineal ultrasound and labeled it according to the transabdominal ultrasound findings. The ultrasound images were randomly allocated into the three datasets containing a similar proportion of images of each subtype of fetal head position (occiput anterior, posterior, right and left transverse): the training dataset included 70 %, the validation dataset 15 %, and the testing dataset 15 % of the acquired images. The pre-trained ResNet18 model was employed as a foundational framework for feature extraction and classification. CNN 1 was trained to differentiate between occiput anterior (OA) and non-OA positions, CNN 2 classified fetal head malpositions into occiput posterior (OP) or occiput transverse (OT) position, and CNN 3 classified the remaining images as right or left OT. The DL-model was constructed using three convolutional neural networks (CNN) working simultaneously for the classification of fetal head positions. The performance of the algorithm was evaluated in terms of accuracy, sensitivity, specificity, F1-score and Cohen's kappa. Between February 2018 and May 2023, 2154 transperineal images were included from eligible participants across 16 collaborating centers. The overall performance of the model for the classification of the fetal head position in the axial plane at transperineal ultrasound was excellent, with an of 94.5 % (95 % CI 92.0––97.0), a sensitivity of 95.6 % (95 % CI 96.8–100.0), a specificity of 91.2 % (95 % CI 87.3–95.1), a F1-score of 0.92 and a Cohen's kappa of 0.90. The best performance was achieved by the CNN 1 – OA position vs fetal head malpositions – with an accuracy of 98.3 % (95 % CI 96.9–99.7), followed by CNN 2 – OP vs OT positions – with an accuracy of 93.9 % (95 % CI 89.6–98.2), and finally, CNN 3 – right vs left OT position – with an accuracy of 91.3 % (95 % CI 83.5–99.1). We have developed a DL-model capable of assessing fetal head position using transperineal ultrasound during the second stage of labor with an excellent overall accuracy. Future studies should validate our DL model using larger datasets and real-time patients before introducing it into routine clinical practice. [ABSTRACT FROM AUTHOR]

/purpose In cases where oral squamous cell carcinoma (OSCC) invades the jawbone, clinicians frequently observe abnormal attenuation on computed tomography (CT) and pathologic signal intensity (SI) on magnetic resonance (MR) imaging of the affected underlying bone marrow. This study introduced a concept of "underlying bone change" to examine its association with clinicopathological features and prognosis of OSCC, as well as its correlation with medullary invasion. We enrolled 93 consecutive patients diagnosed with OSCC, who underwent mandibulectomy between 2010 and 2016. CT and MR images, along with electronic medical records, were reviewed to evaluate correlations between underlying bone changes, clinicopathological features, five-year overall survival, and medullary invasion. Of the 93 patients, 69 (74.2%) exhibited underlying bone sclerosis on CT, and 74 (79.6%) displayed pathological SI on MR images. These underlying bone changes correlated with the T stage and recurrence, but not with overall survival. Medullary invasion, observed in 61 (65.6%) patients, was strongly associated with T and TNM stages and was linked to poorer overall survival. The underlying bone changes on CT and MR images were positively associated with medullary invasion; however, no significant differences were found in the occurrence of underlying bone changes between the subtypes based on the extent of medullary invasion. Underlying bone changes on CT and MR images can provide valuable insights into the aggressiveness of bone invasion by OSCC. Accurate interpretation of these imaging findings might be crucial for correctly delineating surgical margins and preventing the overestimation of tumor extent. [ABSTRACT FROM AUTHOR]

Underwater concrete structure crack detection and structural health condition assessment based on image processing is a challenging task. The complex underwater environment and severe image degradation seriously affect the accuracy of crack detection. To solve these problems, a monocular vision and image-enhanced fractal-based fractal science based on computer vision and image processing techniques are proposed to carry out a non-contact detection study of underwater concrete cracks. In this study, a four-level structural health condition was established to assist in underwater crack measurement and safety assessment. The box-counting method was used as a practical tool to calculate the fractal dimension. To verify the effective distance of the algorithm, three distances of 0.5 m,0.8 m, and 1.2 m were set. The results show that the method proposed in this study can effectively detect cracks in submerged concrete members within 0.6 m and help managers correctly determine the health of the structure using the fractal dimension. [ABSTRACT FROM AUTHOR]

Phenol red (PR) is a commonly used compound in culture media as a pH indicator. However, it is unknown whether this compound can interfere with the pharmacological induction of ferroptosis. Here, using high-content live-cell imaging death analysis, we determined that the presence of PR in the culture medium preconditioned normal and tumor cells to ferroptosis induced by system x c − inhibition mediated by imidazole ketone erastin (IKE) or GPX4 blockade in response to RSL-3, but had no significant effects against treatment with the endoperoxide FINO 2. Mechanistically, we revealed that PR decreases the levels of the antiferroptotic genes Slc7a11, Slc3a2 , and Gpx4 , while promoting the overexpression de Acls4 , a key inducer of ferroptosis. Additionally, through superresolution analysis, we determined that the presence of PR mislocalizes the system x c − from the plasma membrane. Thus, our results show that the presence of PR in the culture medium can be a problematic artifact for the accurate interpretation of cell sensitivity to IKE or RSL-3-mediated ferroptosis induction. [Display omitted] • Phenol red determines sensitivity to ferroptosis inducers in normal and tumor cells. • Phenol red promotes ferroptosis induction by treatment with IKE and RSL-3. • Phenol red promotes overexpression of ACSL4. [ABSTRACT FROM AUTHOR]

There are several in vitro systems that enable evaluation of the absorption direction, but there are few quantitative systems that enable easy evaluation of the excretion direction. Enteroids, organoids derived from intestine, have been frozen and passaged for various research. But it is not clear how the freezing and passaging affect the expression and function of transporters. We investigated the effects of passage and cryopreservation of enteroids. We focused on P-gp (P-glycoprotein) and compared the transfer rates of rhodamine 123 (Rh123) into the lumen of enteroids with and without a P-gp inhibitor. mRNA expression levels did not change significantly before and after passage and cryopreservation. Accumulation of Rh123 in the lumen of enteroids was observed. With some P-gp inhibitors, excretion of Rh123 into the lumen of enteroids was inhibited and the nonexcreted Rh123 accumulated in enteroids epithelial cells. The transfer rate of Rh123 into the lumen of enteroids with a P-gp inhibitor was significantly decreased compared to that of without a P-gp inhibitor. Before and after passage and cryopreservation, the transfer rate was almost the same as that of primary cultured enteroids. We succeeded in easily evaluating whether a component is a substrate of P-gp using enteroids. [Display omitted] • mRNA expression level of efflux intestinal transporter was not changed before and after passage and number of culture days. • This method allows semi-quantitative evaluation of efflux transporters function regardless of the shapes of enteroids. • Our method enables to easily evaluate whether a component is a substrate of P-gp using enteroids. [ABSTRACT FROM AUTHOR]

To evaluate the performance of the multimodal model, termed variable Vision Transformer (vViT), in the task of predicting isocitrate dehydrogenase (IDH) status among adult patients with diffuse glioma. vViT was designed to predict IDH status using patient characteristics (sex and age), radiomic features, and contrast-enhanced T1-weighted images (CE-T1WI). Radiomic features were extracted from each enhancing tumor (ET), necrotic tumor core (NCR), and peritumoral edematous/infiltrated tissue (ED). CE-T1WI were split into four images and input to vViT. In the training, internal test, and external test, 271 patients with 1070 images (535 IDH wildtype, 535 IDH mutant), 35 patients with 194 images (97 IDH wildtype, 97 IDH mutant), and 291 patients with 872 images (436 IDH wildtype, 436 IDH mutant) were analyzed, respectively. Metrics including accuracy and AUC-ROC were calculated for the internal and external test datasets. Permutation importance analysis combined with the Mann–Whitney U test was performed to compare inputs. For the internal test dataset, vViT correctly predicted IDH status for all patients. For the external test dataset, an accuracy of 0.935 (95% confidence interval; 0.913–0.945) and AUC-ROC of 0.887 (0.798–0.956) were obtained. For both internal and external test datasets, CE-T1WI ET radiomic features and patient characteristics had higher importance than other inputs (p < 0.05). The vViT has the potential to be a competent model in predicting IDH status among adult patients with diffuse glioma. Our results indicate that age, sex, and CE-T1WI ET radiomic features have key information in estimating IDH status. • Multimodal analysis using demographics, radiomic features, and MRI was performed by vViT. • The accuracy vViT achieved for internal and external datasets was 1.00 and 0.935, respectively. • Our analyses revealed that the radiomic features of the contrast-enhanced part had key information for IDH prediction. [ABSTRACT FROM AUTHOR]

Data harmonization is necessary for removing confounding effects in multi-site diffusion image analysis. One such harmonization method, LinearRISH, scales rotationally invariant spherical harmonic (RISH) features from one site ("target") to the second ("reference") to reduce confounding scanner effects. However, reference and target site designations are not arbitrary and resultant diffusion metrics (fractional anisotropy, mean diffusivity) are biased by this choice. In this work we propose MidRISH: rather than scaling reference RISH features to target RISH features, we project both sites to a mid-space. We validate MidRISH with the following experiments: harmonizing scanner differences from 37 matched patients free of cognitive impairment, and harmonizing acquisition and study differences on 117 matched patients free of cognitive impairment. We find that MidRISH reduces bias of reference selection while preserving harmonization efficacy of LinearRISH. Users should be cautious when performing LinearRISH harmonization. To select a reference site is to choose diffusion metric effect-size. Our proposed method eliminates the bias-inducing site selection step. [ABSTRACT FROM AUTHOR]

To enhance the quality of low-resolution (LR) ultrasound images and mitigate artifacts and speckle noise, which can impede accurate medical diagnosis, a novel method called the dual frequency-domain guided adaptation model (DF-GAM) is proposed. The method aims to achieve high-quality image reconstruction across diverse domains, including different ultrasound machines, diseases and phantom images. DF-GAM utilizes a dual-branch network architecture combined with frequency-domain self-adaptation and self-supervised edge regression. This approach enables cross-domain enhancement by focusing on the reconstruction of clear tissue structures and speckle patterns. The model is designed to adapt to various ultrasound imaging (USI) scenarios, ensuring its applicability in real-world clinical settings. Experimental evaluations of DF-GAM were conducted using five different datasets. The results demonstrated the method's effectiveness, with DF-GAM outperforming existing enhancement techniques. The average peak signal-to-noise ratio (PSNR) achieved was 34.62, and the structural similarity index (SSIM) was 0.91, indicating a significant improvement in image quality compared to other methods. DF-GAM shows great potential in improving medical image diagnosis and interpretation. Its ability to enhance LR ultrasound images across various domains without the need for extensive training data makes it a valuable tool for clinical use. The high PSNR and SSIM scores validate the method's effectiveness, suggesting that DF-GAM could significantly contribute to the field of USI diagnostics. [ABSTRACT FROM AUTHOR]

To compare anterior chamber depth (ACD) and lens thickness (LT) measurements by ultrasound biomicroscopy (UBM), A-scan cross vector (CV) overlay with UBM, and immersion A-scan technique in pediatric eyes. This prospective comparative cohort study comprised 43 eyes of 25 pediatric participants (mean age: 2.3±2.2 y). UBM and immersion A-scan biometry were performed prior to dilation and intraocular surgery. ACD and LT were measured by UBM image analysis, A-scan CV UBM overlay, and immersion A-scan technique. ACD and LT measurements obtained using immersion A-scan were significantly greater than with UBM image analysis with mean differences of 0.52 mm and 0.62 mm, respectively (p < 0.001). Immersion A-scan and UBM measurements were moderately correlated (r = 0.70 and 0.64, p < 0.001). ACD and LT measurements obtained using CV overlay were not significantly different than UBM measurements and the values were strongly positively correlated (r = 0.95 and 0.93, p < 0.001). Immersion A-scan may overestimate ACD and LT compared to UBM in pediatric patients due to oblique placement of the A-scan probe relative to the optical axis. Supplemental use of UBM and/or CV overlay is indicated to improve measurement accuracy in pediatric patients who cannot reliably fixate due to the ability to confirm proper alignment of the probe with the pupil by visualizing the anterior segment. [ABSTRACT FROM AUTHOR]

Degenerative cervical myelopathy (DCM) is the most common form of atraumatic spinal cord injury globally. Degeneration of spinal discs, bony osteophyte growth and ligament pathology results in physical compression of the spinal cord contributing to damage of white matter tracts and grey matter cellular populations. This results in an insidious neurological and functional decline in patients which can lead to paralysis. Magnetic resonance imaging (MRI) confirms the diagnosis of DCM and is a prerequisite to surgical intervention, the only known treatment for this disorder. Unfortunately, there is a weak correlation between features of current commonly acquired MRI scans ("community MRI, cMRI") and the degree of disability experienced by a patient. This study examines the predictive ability of current MRI sequences relative to "advanced MRI" (aMRI) metrics designed to detect evidence of spinal cord injury secondary to degenerative myelopathy. We hypothesize that the utilization of higher fidelity aMRI scans will increase the effectiveness of machine learning models predicting DCM severity and may ultimately lead to a more efficient protocol for identifying patients in need of surgical intervention. Single institution analysis of imaging registry of patients with DCM. A total of 296 patients in the cMRI group and 228 patients in the aMRI group. Physiologic measures: accuracy of machine learning algorithms to detect severity of DCM assessed clinically based on the modified Japanese Orthopedic Association (mJOA) scale. Patients enrolled in the Canadian Spine Outcomes Research Network registry with DCM were screened and 296 cervical spine MRIs acquired in cMRI were compared with 228 aMRI acquisitions. aMRI acquisitions consisted of diffusion tensor imaging, magnetization transfer, T 2 -weighted, and T 2 *-weighted images. The cMRI group consisted of only T 2 -weighted MRI scans. Various machine learning models were applied to both MRI groups to assess accuracy of prediction of baseline disease severity assessed clinically using the mJOA scale for cervical myelopathy. Through the utilization of Random Forest Classifiers, disease severity was predicted with 41.8% accuracy in cMRI scans and 73.3% in the aMRI scans. Across different predictive model variations tested, the aMRI scans consistently produced higher prediction accuracies compared to the cMRI counterparts. aMRI metrics perform better in machine learning models at predicting disease severity of patients with DCM. Continued work is needed to refine these models and address DCM severity class imbalance concerns, ultimately improving model confidence for clinical implementation. [ABSTRACT FROM AUTHOR]

Laryngopharyngeal reflux disease (LPRD) is a common condition affecting patients reporting to an otolaryngologist. However, the diagnosis of this condition is usually hinged on the combination of largely non-specific symptoms, and clinical findings on laryngoscopy. This study aimed at evaluating the utility of digital image analysis to quantitatively evaluate the severity of signs as recorded with laryngoscopy in patients of LPRD. The study group included individuals who were aged between 18 and 65 years and reported to the ENT OPD. These were then divided into two groups depending on symptoms and laryngoscopic findings. The LPRD group had symptomatic patients with an Reflux finding score (RFS) score >7. Those with an RFS of <6 were designated as the 'Normal group'. The Laryngoscopic images were recorded and analyzed using Image J software as per the set protocol. The Red Green Blue (RGB) values of the laryngoscopic images of each group were obtained and subjected to statistical analysis. 200 participants were enrolled in the study with 100 participants in the LPRD group (mean age = 46.2, 40 males, 60 females) and 100 in the control group (mean age = 43.6, 55 males, 45 females). The measured RGB values were more in the LPRD group as compared to the control group and the results were statistically significant (P < 0.001). By providing an objective value to the degree of inflammation, RGB value measurement provides a quick, economical, adaptable tool for auxiliary and corroborative information for the diagnosis of LPRD. [ABSTRACT FROM AUTHOR]

This study evaluates the laboratory performance of Warm-Mix Asphalt (WMA) containing locally sourced Steel Slag (SS) and limestone (LS), focusing on stiffness and moisture sensitivity. Four asphalt mixes were tested: Hot mix with limestone (HL), hot mix with steel slag (HS), warm mix with limestone (WL), and warm mix with steel slag (WS). The binder used for all mixes was AC 60/70 penetration grade, and Aspha-min served as the warm mix additive. Testing included Marshall Stability, boiling water, indirect tensile strength, moisture-induced damage (TSR), and dynamic modulus. Image Analysis quantified the aggregate-retained coated area after the boiling test. Despite performance differences, all mixes met Egyptian code requirements for asphalt concrete mixes. Visual inspection and image analysis demonstrated the effectiveness of using steel slag to mitigate asphalt mix stripping. The retained coated area for limestone mixes ranged from 60 % to 75 %, while SS mixes exhibited over 95 %. Dynamic modulus tests indicated no significant stiffness difference with SS, and stability increased by 8 % and 14 % with and without the warm additive. Economic study confirmed the feasibility of utilizing SS. In conclusion, combining Aspha-Min and steel slag improves AC mix production and construction processes, offering a sustainable and advantageous option in Egypt. [ABSTRACT FROM AUTHOR]

In this work, the effects of high-voltage electrostatic field (HVEF) on enzyme activities and appearance of stored Musa sapientum were investigated as well as the intensity of spotting by Digital Image Analysis (DIA). By applying HVEF at 6 kV cm-1 during 7.5 minutes, color features on their surface after day 4, maintained stable values (R ≥ 191, G ≥ 165, L* ≥ 82, and b* ≥ 41), while control samples had lower figures of these parameters. Enzyme activities (expressed as Umg protein-1), for pectinmethylesterase in peel, HVEF treatments induced values ≤ 9 Umg-1, while control ≥ 16 Umg-1; polygalacturonase in peel; HVEF samples had activities ≤ 120 Umg-1 at days 6 and 8, while control samples ≥ 211 Umg-1; and, in pulp, after day 4, HVEF brought activities ≤ 37 Umg-1 while control samples were ≥ 71 Umg-1. Polyphenoloxidase, activities for treated samples were enhanced (in the peel, HVEF samples ≥553 Umg -1 and control ones ≤425 Umg-1; and for pulp, HVEF induced activities ≥979 Umg-1 while control ≤717 Umg -1). These results did not impact negatively in the spotting on the surface of the fruits. Results suggested that HVEF can extend the shelf life of M. sapientum. [ABSTRACT FROM AUTHOR]

A new generation of cell sorters combines cellular imaging with sorting cells based on brightfield or fluorescence microscopy information. Specialized imaging technologies allow for the acquisition of blur-free images of cells in flow. Rapid image analysis is key to high-speed sorting and can be realized by either simple parameter measurements or complex machine-learning analysis; each with trade-offs either in the complexity of phenotypes that can be distinguished or speed, respectively. The emergence of image-activated cell sorting heralds a new era for biomedical research, since it enables high-throughput screens and the enrichment of rare cells based on subcellular phenotypes. Commercialization or replication of these instruments provides robust, fast, and accessible platforms to meet the individual research needs of users. Over the past six decades, fluorescence-activated cell sorting (FACS) has become an essential technology for basic and clinical research by enabling the isolation of cells of interest in high throughput. Recent technological advancements have started a new era of flow cytometry. By combining the spatial resolution of microscopy with high-speed cell sorting, new instruments allow cell sorting based on simple image-derived parameters or sophisticated image analysis algorithms, thereby greatly expanding the scope of applications. In this review, we discuss the systems that are commercially available or have been described in enough methodological and engineering detail to allow their replication. We summarize their strengths and limitations and highlight applications that have the potential to transform various fields in basic life science research and clinical settings. [ABSTRACT FROM AUTHOR]

Early diagnosis of scapholunate ligament (SLL) injuries is crucial to prevent progression to debilitating osteoarthritis. Four-Dimensional Computed Tomography (4DCT) is a promising dynamic imaging modality for assessing such injuries. Capitalizing on the known correlation between SLL injuries and an increased scapholunate distance (SLD), this study aims to develop a fully automatic approach to evaluate the SLD continuously during wrist motion and to apply it to a dataset of healthy wrists to establish reference values. 50 healthy wrists were analysed in this study. All subjects performed radioulnar deviation (RUD), flexion-extension (FE), and clenching fist (CF) movements during 4DCT acquisition. A novel, automatic method was developed to continuously compute the SLD at five distinct locations within the scapholunate joint, encompassing a centre, volar, dorsal, proximal, and distal measurement. The developed algorithm successfully processed datasets from all subjects. Our results showed that the SLD remained below 2 mm and exhibited minimal changes (median ranges between 0.3 mm and 0.65 mm) during RUD and CF at all measured locations. During FE, the volar and dorsal SLD changed significantly, with median ranges of 0.90 and 1.27 mm, respectively. This study establishes a unique database of normal SLD values in healthy wrists during wrist motion. Our results indicate that, aside from RUD and CF, FE may also be important in assessing wrist kinematics. Given the labour-intensive and time-consuming nature of manual analysis of 4DCT images, the introduction of this automated algorithm enhances the clinical utility of 4DCT in diagnosing dynamic wrist injuries. • SL distance can be measured automatically during wrist motion using 4DCT. • SL distance in healthy wrists remains below 2 mm, showing minimal change. • SL distance measurements at different locations may provide extra information. • Automatic SL distances are slightly smaller compared to manual measurements. [ABSTRACT FROM AUTHOR]

To evaluate the role of diffusion kurtosis imaging (DKI) histogram analysis in the characterization of non–small cell lung cancer (NSCLC) and to correlate DKI parameters with tumor cellularity. Sixty-four patients with pathologically diagnosed NSCLCs were evaluated by DKI on a 3-T scanner. Regions of interest (ROIs) were drawn on the map of b 1000 manually. All NSCLCs were histologically graded according to the degree of tumor differentiation. Tumor cellularity was measured by the nuclear-to-cytoplasm (N/C) ratio and the number of tumor cell nuclei (NTCN), the expression of Ki-67 was detected using the streptavidin-peroxidase method. Histogram analysis was performed using voxel-based on raw data from each ROI. NSCLCs were classified as grades 1, 2, and 3 according to differentiation degree. Histogram parameters of apparent diffusion coefficient (ADC) and DKI could discriminate between different grades of tumors (p<0.001). Receiver operating characteristic (ROC) curve analysis showed that K app 75th exhibited the best performance with an AUC of 0.936 and sensitivity/specificity of 95.74%/80% (p<0.001) in distinguishing grade 1 from grade 2, ADC mean exhibited the best performance with an AUC of 0.923 and sensitivity/specificity of 92.33%/86.67% (p<0.001) in distinguishing grade 2 from 3. N/C ratio and Ki-67 changed significantly with grade (p<0.01). Negative correlations were found between the ADC mean and the N/C ratio, Ki-67, D app mean and N/C ratio, whereas K app mean and N/C ratio, Ki-67 were positively correlated. DKI histogram analysis could quantitatively characterize NSCLC with different grades by probing non-Gaussian diffusion properties related to changes in the tumor microenvironment or tissue complexities in the tumor. • DKI histogram analysis can differentiate different grades of NSCLC. • DKI parameters are correlated with tumor N/C ratio and Ki-67 index. • Tumor water molecules non-Gaussian diffusion can evaluate tumor cell structure. [ABSTRACT FROM AUTHOR]

This study investigated reliability and validity of muscle cross-sectional area and echo intensity using an automatic image analysis program. Methods: Twenty-two participants completed two data collection trials consisting of ultrasound imaging of the vastus lateralis (VL) at 10 and 12 MHz. Images were analyzed manually and with Deep Anatomical Cross-Sectional Area (DeepACSA). Reliability statistics (i.e., intraclass correlation coefficient [ICC] model 2,1, standard error of measure expressed as a percentage of the mean [SEM%], minimal differences [MD] values needed to be considered real) and validity statistics (i.e., constant error [CE], total error [TE], standard error of the estimate [SEE]) were calculated. Results: Automatic analyses of ACSA and EI demonstrated good reliability (10 MHz: ICC 2,1 = 0.83 – 0.90; 12 MHz: ICC 2,1 = 0.87–0.88), while manual analyses demonstrated moderate to excellent reliability (10 MHz: ICC 2,1 = 0.82–0.99; 12 MHz: ICC 2,1 = 0.73–0.99). Automatic analyses of ACSA presented greater error at 10 (CE = -0.76 cm2, TE = 4.94 cm2, SEE = 3.65 cm2) than 12 MHz (CE = 0.17 cm2, TE = 3.44 cm2, SEE = 3.11 cm2). Analyses of EI presented greater error at 10 (CE = 3.35 a.u., TE = 2.70 a.u., SEE = 2.58 a.u.) than at 12 MHz (CE = 3.21 a.u., TE = 2.61 a.u., SEE = 2.34 a.u.). Conclusion: The results suggest the DeepACSA program may be less reliable compared to manual analysis for VL ACSA but displayed similar reliability for EI. In addition, the results demonstrated the automatic program had low error for 10 and 12 MHz. [ABSTRACT FROM AUTHOR]

Cloud coverage poses a significant challenge to optical image interpretation, degrading ground information on Earth's surface. Synthetic aperture radar (SAR), with its ability to penetrate clouds, provides supplementary information to optical data. However, existing optical-SAR fusion methods predominantly focus on cloud-free scenarios, neglecting the practical challenge of semantic segmentation under cloudy conditions. To tackle this issue, we propose CloudSeg, a novel framework tailored for land cover mapping in the presence of clouds. It addresses the challenges posed by cloud cover from two aspects: reducing semantic ambiguity in areas of the cloudy image that are obscured by clouds and enhancing effective information in the unobstructed portions. Specifically, CloudSeg employs a multi-task learning strategy to simultaneously handle low-level visual task and high-level semantic understanding task, mitigating the semantic ambiguity caused by cloud cover by acquiring discriminative features through an auxiliary cloud removal task. Additionally, CloudSeg incorporates a knowledge distillation strategy, which utilizes the knowledge learned by the teacher network under cloud-free conditions to guide the student network to overcome the interference of cloud-covered areas, enhancing the valuable information from the unobstructed parts of cloud-covered images. Extensive experiments conducted on two datasets, M3M-CR and WHU-OPT-SAR , demonstrate the effectiveness and superiority of the proposed CloudSeg method for land cover mapping under cloudy conditions. Specifically, CloudSeg outperforms the state-of-the-art competitors by 3.16% in terms of mIoU on M3M-CR and by 5.56% on WHU-OPT-SAR , highlighting its substantial advantages for analyzing regions frequently obscured by clouds. Codes are available at https://github.com/xufangchn/CloudSeg. [ABSTRACT FROM AUTHOR]

Cross-modality image generation from magnetic resonance (MR) to positron emission tomography (PET) using the generative model can be expected to have complementary effects by addressing the limitations and maximizing the advantages inherent in each modality. This study aims to generate synthetic PET/MR fusion images from MR images using a combination of generative adversarial networks (GANs) and conditional denoising diffusion probabilistic models (cDDPMs) based on simultaneous 18F-fluorodeoxyglucose (18F-FDG) PET/MR image data. Retrospective study with prospectively collected clinical and radiological data. This study included 94 patients (60 men and 34 women) with thoraco-lumbar pyogenic spondylodiscitis (PSD) from February 2017 to January 2020 in a single tertiary institution. Quantitative and qualitative image similarity were analyzed between the real and synthetic PET/ T2-weighted fat saturation MR (T2FS) fusion images on the test data set. We used paired spinal sagittal T2FS and PET/T2FS fusion images of simultaneous 18F-FDG PET/MR imaging examination in patients with PSD, which were employed to generate synthetic PET/T2FS fusion images from T2FS images using a combination of Pix2Pix (U-Net generator + Least Squares GANs discriminator) and cDDPMs algorithms. In the analyses of image similarity between the real and synthetic PET/T2FS fusion images, we adopted the values of mean peak signal to noise ratio (PSNR), mean structural similarity measurement (SSIM), mean absolute error (MAE), and mean squared error (MSE) for quantitative analysis, while the discrimination accuracy by three spine surgeons was applied for qualitative analysis. Total of 2,082 pairs of T2FS and PET/T2FS fusion images were obtained from 172 examinations on 94 patients, which were randomly assigned to training, validation, and test data sets in 8:1:1 ratio (1664, 209, and 209 pairs). The quantitative analysis revealed PSNR of 30.634 ± 3.437, SSIM of 0.910 ± 0.067, MAE of 0.017 ± 0.008, and MSE of 0.001 ± 0.001, respectively. The values of PSNR, MAE, and MSE significantly decreased as FDG uptake increased in real PET/T2FS fusion image, with no significant correlation on SSIM. In the qualitative analysis, the overall discrimination accuracy between real and synthetic PET/T2FS fusion images was 47.4%. The combination of Pix2Pix and cDDPMs demonstrated the potential for cross-modal image generation from MR to PET images, with reliable quantitative and qualitative image similarities. [ABSTRACT FROM AUTHOR]

• Prediction of intraoperative hemorrhage is still challenging in placenta previa. • Radiomics analysis has been investigated as new evaluation for medical images. • We constructed prediction models, using radiomics in MRI images of placenta. • The best model predicted hemorrhage with an accuracy of 0.70 and an AUC of 0.69. • Radiomics features based on MRI were used as effective predictive variables. Prediction of intraoperative massive hemorrhage is still challenging in placenta previa. Radiomics analysis has been investigated as a new evaluation method for analyzing medical images. We used radiomics analysis on placental magnetic resonance imaging (MRI) images to predict intraoperative hemorrhage in placenta previa. We used the sagittal MRI T2-weighted sequence in placenta previa. Using the rectangular region from the uterine os to the anterior wall, we extracted 97 radiomics features. We also collected patient demographics and blood test data as clinical variables. Combining these radiomics features and clinical variables, logistic regression models with a stepwise method were built to predict the risk of hemorrhage, defined as blood loss of > 2000 ml. We evaluated the prediction performance of the models using accuracy and area under the curve (AUC), also analyzing the important variables for the prediction by stepwise methods. We enrolled a total of 63 placenta previa cases including 30 hemorrhage cases from two institutes. The model combining clinical variables and radiomics features showed the best prediction performance with an accuracy of 0.70 and an AUC of 0.69 in the internal validation data, and accuracy of 0.41 and an AUC of 0.70 in the external validation data, compared with human experts (accuracy of 0.62). Regarding variable selection, two radiomics features. 'original_glrlm_LowGrayLevelRunEmphasis,' and 'diagnostics_Image-original_Minimum,' were important predictors for hemorrhage by the stepwise method. Radiomics features based on MRI could be used as effective predictive variables for hemorrhage in placenta previa. Radiomics analysis of placental imaging could lead to further analysis of quantitative variables related to obstetric diseases. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI)–based auto-segmentation models hold promise for enhanced efficiency and consistency in organ contouring for adaptive radiation therapy and radiation therapy planning. However, their performance on pediatric computed tomography (CT) data and cross-scanner compatibility remain unclear. This study aimed to evaluate the performance of AI-based auto-segmentation models trained on adult CT data when applied to pediatric data sets and explore the improvement in performance gained by including pediatric training data. It also examined their ability to accurately segment CT data acquired from different scanners. Using the nnU-Net framework, segmentation models were trained on data sets of adult, pediatric, and combined CT scans for 7 pelvic/thoracic organs. Each model was trained on 290 to 300 cases per category and organ. Training data sets included a combination of clinical data and several open repositories. The study incorporated a database of 459 pediatric (0-16 years) CT scans and 950 adults (>18 years), ensuring all scans had human expert ground-truth contours of the selected organs. Performance was evaluated based on Dice similarity coefficients (DSC) of the model-generated contours. AI models trained exclusively on adult data underperformed on pediatric data, especially for the 0 to 2 age group: mean DSC was below 0.5 for the bladder and spleen. The addition of pediatric training data demonstrated significant improvement for all age groups, achieving a mean DSC of above 0.85 for all organs in every age group. Larger organs like the liver and kidneys maintained consistent performance for all models across age groups. No significant difference emerged in the cross-scanner performance evaluation, suggesting robust cross-scanner generalization. For optimal segmentation across age groups, it is important to include pediatric data in the training of segmentation models. The successful cross-scanner generalization also supports the real-world clinical applicability of these AI models. This study emphasizes the significance of data set diversity in training robust AI systems for medical image interpretation tasks. [ABSTRACT FROM AUTHOR]

• Two image analysis methods have been developed for viral vector characterization, and their performances were compared. • A combination of cryo-electron microscopy and image analysis enables the accurate assessment of the viral vector population. • Convolutional neural networks and morphological analysis quantified exiguous impurities in viral vector products with 90% purity. • The utility of convolutional neural networks to characterize wider adeno-associated viral products was demonstrated. • Image analysis methods based on cryo-electron micrographs might evaluate the slight difference in the viral vector population. Adeno-associated viruses (AAVs) are effective vectors for gene therapy. However, AAV drug products are inevitably contaminated with empty particles (EP), which lack a genome, owing to limitations of the purification steps. EP contamination can reduce the transduction efficiency and induce immunogenicity. Therefore, it is important to remove EPs and to determine the ratio of full genome-containing AAV particles to empty particles (F/E ratio). However, most of the existing methods fail to reliably evaluate F/E ratios that are greater than 90 %. In this study, we developed two approaches based on the image analysis of cryo-electron micrographs to determine the F/E ratios of various AAV products. Using our developed convolutional neural network (CNN) and morphological analysis, we successfully calculated the F/E ratios of various AAV products and determined the slight differences in the F/E ratios of highly purified AAV products (purity > 95 %). In addition, the F/E ratios calculated by analyzing more than 1000 AAV particles had good correlations with theoretical F/E ratios. Furthermore, the CNN reliably determined the F/E ratio with a smaller number of AAV particles than morphological analysis. Therefore, combining 100 keV cryo-EM with the developed image analysis methods enables the assessment of a wide range of AAV products. [ABSTRACT FROM AUTHOR]

To examine the polymerization shrinkage of different resin-based composite (RBC) restorations using optical coherence tomography (OCT) image-based digital image correlation (DIC) analysis. The refractive index (RI) of three RBCs, Filtek Z350XT (Z350), Z350Flowable (Z350F), and BulkFill Posterior (Bulkfill), was measured before and after polymerization to calibrate their axial dimensions under OCT. Class I cavities were prepared in bovine incisors and individually filled with these RBCs under nonbonded and bonded conditions. A series of OCT images of these restorations were captured during 20-s light polymerization and then input into DIC software to analyze their shrinkage behaviors. The interfacial adaptation was also examined using these OCT images. The RI of the three composites ranged from 1.52 to 1.53, and photopolymerization caused neglectable increases in the RI values. For nonbonded restorations, Z350F showed maximal vertical displacements on the top surfaces (−16.75 µm), followed by Bulkfill (−8.81 µm) and Z350 (−5.97 µm). In their bonded conditions, all showed increased displacements. High variations were observed in displacement measurements on the bottom surfaces. In the temporal analysis, the shrinkage of nonbonded Z350F and Bulkfill decelerated after 6–10 s. However, Z350 showed a rebounding upward displacement after 8.2 s. Significant interfacial gaps were found in nonbonded Z350 and Z350F restorations. The novel OCT image-based DIC analysis provided a comprehensive examination of the shrinkage behaviors and debonding of the composite restorations throughout the polymerization process. The flowable composite showed the highest shrinkage displacements. Changes in the shrinkage direction may occur in nonbonded conventional composite restorations. [Display omitted] • A novel digital image correlation analysis using OCT images was established. • Shrinkage displacements and temporal changes of three composites were examined. • Contraction behavior is affected by the type of composite and bond condition. • Nonbonded Z350 restoration showed changed shrinkage directions during curing. • Bulk-fill composite showed similar displacement maps in nonbonded and bonded conditions. [ABSTRACT FROM AUTHOR]

The integration of quantitative and qualitative knowledge from parasitologists plays a pivotal role in refining the performance of deep learning (DL) models. Knowledge-integrated DL models can be trained using different learning strategies that make use of labeled and unlabeled data, such as supervised learning, semi-supervised learning, and self-supervised learning. When choosing a backbone network – such as recurrent neural networks (RNNs), convolutional neural networks (CNNs), transformers, or graph neural networks (GNNs) – for parasitology research, it is essential to consider their advantages, disadvantages, and data characteristics. DL-based microscopy image analysis has been successfully applied in parasitology, including high-throughput parasite detection, quantitative analysis of host–pathogen interactions, and aberrated images correction. Microscopy image analysis plays a pivotal role in parasitology research. Deep learning (DL), a subset of artificial intelligence (AI), has garnered significant attention. However, traditional DL-based methods for general purposes are data-driven, often lacking explainability due to their black-box nature and sparse instructional resources. To address these challenges, this article presents a comprehensive review of recent advancements in knowledge-integrated DL models tailored for microscopy image analysis in parasitology. The massive amounts of human expert knowledge from parasitologists can enhance the accuracy and explainability of AI-driven decisions. It is expected that the adoption of knowledge-integrated DL models will open up a wide range of applications in the field of parasitology. [ABSTRACT FROM AUTHOR]

To compare the image quality of multiplexed sensitivity-encoding diffusion-weighted imaging (MUSE-DWI) and single-shot echo-planar imaging (SS-EPI-DWI) techniques in uterine MRI. Eighty-eight eligible patients underwent MUSE-DWI and SS-EPI-DWI examinations simultaneously using a 3.0 T MRI system. Two radiologists independently performed quantitative and qualitative analysis of the two groups of images using a double-blind method. The weighted Kappa test was used to evaluate the interobserver agreement. Wilcoxon's rank sum test was used for qualitative parameters, and paired t -test was used for quantitative parameters. Spearman rank correlation analysis was used to obtained correlation between pathological results and mean apparent diffusion coefficient (ADC) value. The qualitative and quantitative analysis of the images by the two radiologists were in good or excellent agreement, with weighted kappa value ranging from 0.636 to 0.981. The scores of total subjective image quality (15.4 ± 0.99) and signal-to-noise ratio (158.99 ± 60.71) of MUSE-DWI were significantly higher than those of SS-EPI-DWI (12.93 ± 1.62 P < 0.001; 130.23 ± 48.29 P < 0.05). It effectively reduced image distortion and artifact, and had better lesion conspicuity. There was no significant difference in contrast-to-noise ratio score and average ADC values between the two DWI sequences. The average ADC values of the two DWI sequences were highest in the normal uterus group and lowest in the endometrial cancer group, with statistically significant differences among groups (P < 0.01). In addition, the average ADC values of the two DWI sequences were negatively correlated with the type of lesions, decreasing with the malignancy of the lesions (r = −0.805 P < 0.01, r = −0.815 P < 0.01). Compared to SS-EPI-DWI, MUSE-DWI can significantly reduce distortion, artifacts, and fuzziness in MRI of uterine lesions, which is more conducive to lesion detection. [ABSTRACT FROM AUTHOR]

The recently discovered glymphatic system may support the removal of neurotoxic proteins, mainly during sleep, that are associated with neurodegenerative diseases such as Alzheimer's and Parkinson's Disease. Diffusion tensor image analysis along the perivascular space (DTI-ALPS) has been suggested as a method to index the health of glymphatic system (with higher values indicating a more intact glymphatic system). Indeed, in small-scale studies the DTI-ALPS index has been shown to correlate with age, cognitive health, and sleep, and is higher in females than males. To determine whether these relationships are stable we replicated previous findings associating the DTI-ALPS index with demographic, sleep-related, and cognitive markers in a large sample of participants from the UK Biobank. We calculated the DTI-ALPS index in UK Biobank participants (n = 17723). Using Bayesian and Frequentist analysis approaches, we replicate previously reported relationships between the DTI-ALPS index. We found the predicted associations between the DTI-ALPS index and age, longest uninterrupted sleep window (LUSWT) on a typical night, cognitive performance, and sex. However, these effects were substantially smaller than those found in previous studies. Parameter estimates from this study may be used as priors in subsequent studies using a Bayesian approach. These results suggest that the DTI-ALPS index is consistently, and therefore predictably, associated with demographics, LUWST, and cognition. We propose that the metric, calculated for the first time in a large-scale, population-based cohort, is a stable measure, but one for which stronger links to glymphatic system function are needed before it can be used to understand the relationships between glymphatic system function and health outcomes reported in the UK Biobank. • We calculated an index of diffusion along the perivascular space (DTI-ALPS index) in 44073 participants from the UK Biobank. • We replicated analyses from previous studies showing a relationship between the DTI-ALPS index, sex, age, sleep, & cognition. • Although these replications were broadly successful, the effect sizes were substantially smaller than previously reported. [ABSTRACT FROM AUTHOR]

Accurate cloud and shadow detection is a crucial prerequisite for optical remote sensing image analysis and application. Multi-temporal-based cloud and shadow detection methods are a preferable choice to detect clouds in complex scenes (e.g., thin clouds, broken clouds and clouds with interference from artificial surfaces with high reflectivity). However, such methods commonly require cloud-free reference images, and this may be difficult to achieve in time-series data since clouds are often prevalent and of varying spatial distribution in optical remote sensing images. Furthermore, current multi-temporal-based methods have limited feature extraction capability and rely heavily on prior assumptions. To address these issues, this paper proposes a Siamese network (Siamnet) for cloud and shadow detection based on Time-Series cloudy Images, namely TSI-Siamnet, which consists of two steps: 1) low-rank and sparse component decomposition of time-series cloudy images is conducted to construct a composite reference image to cope with dynamic changes in the cloud distribution in time-series images; 2) an extended Siamnet with optimal difference calculation module (DM) and multi-scale difference features fusion module (MDFM) is constructed to extract reliable disparity features and alleviate semantic information feature dilution during the decoder part. TSI-Siamnet was tested extensively on seven land cover types in the well-known Landsat 8 Biome dataset. Compared to six state-of-the-art methods (including four deep learning-based methods and two classical non-deep learning-based methods), TSI-Siamnet produced the best performance with an overall accuracy of 95.05% and MIoU of 84.37%. In three more challenging experiments, TSI-Siamnet showed enhanced detection of thin and broken clouds and greater anti-interference to highly reflective surfaces. TSI-Siamnet provides a novel strategy to explore comprehensively the valid information in time-series cloudy images and integrate the extracted spectral-spatial–temporal features for reliable cloud and shadow detection. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) is an efficient and widely used remote sensing tool. However, data extracted from SAR images are contaminated with speckle, which precludes the application of techniques based on the assumption of additive and normally distributed noise. One of the most successful approaches to describing such data is the multiplicative model, where intensities can follow a variety of distributions with positive support. The G I 0 model is among the most successful ones. Although several estimation methods for the G I 0 parameters have been proposed, there is no work exploring a regression structure for this model. Such a structure could allow us to infer unobserved values from available ones. In this work, we propose a G I 0 regression model and use it to describe the influence of intensities from other polarimetric channels. We derive some theoretical properties for the new model: Fisher information matrix, residual measures, and influential tools. Maximum likelihood point and interval estimation methods are proposed and evaluated by Monte Carlo experiments. Results from simulated and actual data show that the new model can be helpful for SAR image analysis. [Display omitted] • New regression model whose output is a general model for speckled data. • The regression model does not require transforming the observations. • Analysis tools based on residuals are provided. • The model predicts the co-polarized SAR intensity from the cross-polarized signal. • The model identifies changes in highly complex terrains. [ABSTRACT FROM AUTHOR]

With computer vision and machine learning, sports image analysis can enhance viewer engagement and contribute to the overall understanding of sports events. However, beneath the apparent simplicity of sports images lies a complex challenge of radial distortion, which can impede their accurate interpretation. The need for high precision and real-time performance is paramount. We present a new regression-based method for radial distortion correction that improves the accuracy of distortion model coefficient prediction by introducing a secondary learning task that compares the distortion level of two random training samples. The secondary task requires no additional annotation, and because it is also related to radial distortion, it encourages the common feature extractor component to learn more general and robust features while preventing overfitting and improving the efficiency of training data. We have evaluated our proposed method using two public datasets and compared it against five other methods. Our method surpassed them all, both in the accuracy of the radial distortion correction and speed as well. You can find the source code and trained models at https://vgg.fiit.stuba.sk/improving-radial. • We propose deep learning method for single image radial lens distortion correction. • We estimate polynomial distortion model with two independent coefficients. • We compare distortion level of random image pairs to increases data efficiency. • We encourage higher accuracy using distortion level penalty term during training. [ABSTRACT FROM AUTHOR]

Osteoporosis is prevalent among the elderly and requires precise diagnostic approaches for effective treatment and prevention. This work introduces a machine learning-based method for the accurate grading of osteoporosis via the analysis of high-resolution computed tomography (HRCT) images of the spine. This approach allows for the precise extraction of the trabecular component of vertebral bodies, thereby enabling accurate measurement of bone density. Evaluated in 183 individuals, our method demonstrated enhanced stability in bone density prediction and reduced bias when juxtaposed with traditional random sampling techniques. Despite the inherent risk of overestimation, the machine learning model more accurately approximates the actual bone quality compared to conventional clinical methods, which typically involve the random extraction of 3–4 trabecular bone slices from the spine. These findings offer a novel approach to the clinical assessment of osteoporosis, underscoring the significant potential of integrating machine learning into existing medical image analysis workflows. • HRCT. • Machine learning. • Changes in Bone Mineral Density. [ABSTRACT FROM AUTHOR]

There are reports on the relationship between periodontal treatment and the whole body. The purpose of the present study was to investigate the effect of periodontal initial treatment on brain function activity by improving periodontal tissue and the occlusal status of subjects with periodontitis. The subjects were 13 patients with periodontitis. Following the patient's informed written consent, the periodontal initial treatment provided to the patient included tooth brushing instruction, scaling and root planning, however, occlusal adjustment was not performed at this stage. Periodontal examination, occlusal force examination and fMRI results were also evaluated at the initial and the reevaluation examinations. After the periodontal initial treatment had been performed, periodontal tissue had significantly improved. In addition, cerebral blood flow in the insula and primary motor cortex was also improved, as confirmed by fMRI. This result suggests that the periodontal ligament has recovered and the periodontal ligament neuron have been further subjected to clenching in the insula. [ABSTRACT FROM AUTHOR]

This research possesses the producing and taking the assessment of a new deep learning structure, namely, Deep Convolutional BiLSTM Hybrid Network, specialized for arrhythmia recognition before ECG records. Through PhysioNet Challenge 2021 dataset, which has collected different styles of the ECG recordings from nine different arrhythmia types, this study is trying to respond to the critical need that non-attendant and accurate arrhythmia detection is required in the medical field. By utilizing both convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) units that allow our model to carry out spatial and temporal operations, which is essential to the native dynamics existing ECG signal, we are able to get in view a more fine-grained analysis surpassing other traditional approaches. The suggested algorithm which has achieved accuracy, precision, recall, and F-score of 98.5%, 98.2%, 98.2%, and 98.4% percent respectively has proven to be a novel and more accurate solution compared to the existing state-of-the-art model when similar kinds of tasks are performed. These results not only reveal the effectiveness of CNNs and BiLSTM toginger in understanding complicated biomedical signs but also shed a light on the prospect of deep learning in raising the standards of dairgocis and health care practices. The research outcome of arrhythmia diagnosis by arranging new standard carpatients would bring a lot of changes to the existing medical informatics that provide a scalable solution that would be implemented to every healthcare institution globally for timely and accurate diagnosis. [ABSTRACT FROM AUTHOR]

High-speed video recordings of slab burner experiments were analyzed using a machine learning approach with convolutional neural networks in order to compute the regression rate of hybrid rocket fuels over time. Combustion tests of paraffin-based fuel grains performed in two different hybrid rocket slab burners were recorded with high-speed video cameras and the resulting image data are analyzed in order to determine the height of the fuel in each frame. To this end, a deep neural network with U-net architecture is trained in a supervised fashion to segment the shape of the fuel slab. It is demonstrated that this approach is more capable to segment combustion images in unsteady flow conditions than classical computer vision methods based on thresholding or edge detection. Furthermore, methods in the area of uncertainty quantification of neural networks are applied to estimate the errors in the neural network prediction to new previously unseen data. Finally, the regression rate of the fuel is computed as the rate of change of this height. This method enables automatic analysis of a large amount of video data, taking full advantage of the optical access capabilities of slab burners. Additionally, the method delivers not only the time and space average values of the fuel regression rate, but also quantifies its variation over time and over the length of the slab, providing deeper insights into the combustion mechanics of hybrid rockets. • Shape of solid fuel detected in images from combustion test using a U-Net. • U-Net applied to a high-speed video enables measurement of the regression rate. • Regression rate can be resolved as time- and space-dependent quantity. • Method is applied to combustion tests performed at two different test facilities. • Tests under both atmospheric and super-critical pressure conditions were evaluated. [ABSTRACT FROM AUTHOR]

Plantar pressure, a common gait and foot biomechanics measurement, is typically analyzed using proprietary commercial software packages. Regional plantar pressure analysis is often reported in terms of underlying bony geometry, and recent advances in image processing and accessibility have made computed tomography, radiographs, magnetic resonance imaging, or other imaging methods more popular for incorporating bone analyses in biomechanics. Can a computed tomography-based regional mask provide comparable regional analysis to commercial plantar pressure software and can the increased flexibility of an in-house method obtain additional insight from common measurements? A plantar pressure analysis method was developed based on bony geometry from computed tomography scans to calculate peak pressure, pressure time integral incorporating sub-peak values, force time integral, pressure gradient, and pressure gradient angle. Static and dynamic plantar pressure were acquired for 4 subjects (male, 65 ± 2.4 years). Plantar pressure variables were calculated using commercial and computed tomography-based systems. Dynamic peak pressure, pressure time integral, and force-time integral computed using the bone-based software was 5 % (9kPa), 7 % (0.3kPa-s) and 13 % (0.3 N-s) different than the commercial software on average. Region masks of the metatarsals and toes differed between commercial and computed tomography-based software due to subject-specific bone geometry and toe shape. Pressure time integral values incorporating sub-peak pressure were higher and demonstrated higher relative hindfoot values compared to those without. Removing step-on frames to static pressure analysis decreased forefoot pressures. Regional maps of peak pressure and maximum pressure gradient demonstrate different peak locations. Computed tomography-based regional masks are comparable to commercial masks. Inclusion of static step-on frames and sub-peak pressures may change regional plantar pressure patterns. Differences in location of maximum pressure gradient and peak pressure may be useful for assessing subject specific injury risk. • Plantar pressure masks can be automatically generated from computed tomography • Locations of peak pressure gradients and peak pressures may be different • Including sub-peak pressures in pressure-time integral may change regional trends [ABSTRACT FROM AUTHOR]

Coating thickness is a critical quality attribute of many coated tablets. Functional coatings ensure correct drug release kinetics or protection from light, while non-functional coatings are generally applied for cosmetic reasons. Traditionally, coating thickness is assessed indirectly via offline methods, such as weight gain or diameter growth. In the past decade, several methods, including optical coherence tomography (OCT) and Raman spectroscopy, have emerged to perform in-line measurements of various subclasses of coating formulations. However, there are some obstacles. For example, when using OCT, a major challenge is scattering pigments, such as titanium dioxide and iron oxide, which make the interface between the coating and the tablet core difficult to detect. This work explores novel OCT image evaluation techniques using unsupervised machine learning to compute image metrics. Certain image metrics of highly scattering coatings are correlated with the tablet thickness, and hence indirectly with the coating thickness. The method was demonstrated using a titanium dioxide rich coating formulation. The results are expected to be applicable to other scattering coatings and will significantly broaden the applicability of OCT to at-line and in-line coating thickness measurements of a much larger class of coating formulations. [Display omitted] • Optical coherence tomography for indirect coating thickness measurement of highly scattering coatings. • Machine learning for image analysis to extract and quantify light reflection. • Non-destructive coating thickness measurement through light reflection properties. [ABSTRACT FROM AUTHOR]

The Colegio Mexicano de Reumatología (CMR) is a corporation whose brand has two elements—image and identity—that differentiate it from other corporations. We evaluated aspects of CMR's corporate image and identity. To assess corporate image, we designed a survey using proof-of-concept and discrete-choice-experiments approaches. It assessed which definition (orthopedist, rheumatologist, or rehabilitator) was most meaningful in four pain scenarios in healthy adults from the country's Western region. We used discourse analysis and five readability indices of the CMR website to assess corporate identity. In total, 700 respondents were included. For every rheumatologist chosen in the hand scenario, respondents chose 1.13 orthopedists and 0.70 rehabilitators. For every rheumatologist chosen in the knee scenario, respondents chose 2.36 orthopedists and 0.64 rehabilitators, whereas 0.85 orthopedists and 0.58 rehabilitators were chosen in the arthritis scenario. Only 38% of the respondents preferred the CMR's definition of a rheumatologist to describe a rheumatologist. The younger age group preferred orthopedists to rheumatologists (50% vs. 31%, p < 0.001). In the arthritis scenario, the choice of rheumatologist increased from 27% in the elementary school group to 49% in the university group (p < 0.001). Mother was the most influential in healthcare seeking. The discursive analysis revealed that the CMR is positioned as a "we" restricted to "colleagues;" the patient did not have agentive representation. The semiotic structure of the CMR's mission/vision was deemed imprecise and lacking in statements of value and purpose; the readability scores indicated that the text was challenging and dry. The CMR's corporate image does not differentiate it from other health providers. CMR's identity seems ambiguous with restricted directionality. It seems pertinent to redefine the CMR. [ABSTRACT FROM AUTHOR]

To investigate the feasibility of optical coherence tomography (OCT)-based digital image correlation (DIC) analysis and to identify the experimental parameters for measurements of polymerization shrinkage. Class I cavities were prepared on bovine incisors and filled with Filtek Z350XT Flowable (Z350F). One OCT image of the polymerized restoration was processed to generate virtually displaced images. In addition, the tooth specimen was physically moved under OCT scanning. A DIC software analyzed these virtual and physical transformation sets and assessed the effects of subset sizes on accuracy. The refractive index of unpolymerized and polymerized Z350F was measured via OCT images. Finally, different particles (70–80 µm glass beads, 150–212 µm glass beads, and 75–150 µm zirconia powder) were added to Z350F to inspect the analyzing quality. The analyses revealed a high correlation (>99.99%) for virtual movements within 131 pixels (639 µm) and low errors (<5.21%) within a 10-µm physical movement. A subset size of 51 × 51 pixels demonstrated the convergence of correlation coefficients and calculation time. The refractive index of Z350F did not change significantly after polymerization. Adding glass beads or zirconia particles caused light reflection or shielding in OCT images, whereas blank Z350F produced the best DIC analysis results. The OCT-based DIC analysis with the experimental conditions is feasible in measuring polymerization shrinkage of RBC restorations. The subset size in the DIC analysis should be identified to optimize the analysis conditions and results. Uses of hyper- or hypo-reflective particles is not recommended in this method. [Display omitted] [ABSTRACT FROM AUTHOR]

Automated medical image analysis solutions should closely mimic complete human actions to be useful in clinical practice. However, more often an automated image analysis solution represents only part of a human task, which restricts its practical utility. In the case of ultrasound-based fetal biometry, an automated solution should ideally recognize key fetal structures in freehand video guidance, select a standard plane from a video stream and perform biometry. A complete automated solution should automate all three subactions. In this article, we consider how to automate the complete human action of first-trimester biometry measurement from real-world freehand ultrasound. In the proposed hybrid convolutional neural network (CNN) architecture design, a classification regression-based guidance model detects and tracks fetal anatomical structures (using visual cues) in the ultrasound video. Several high-quality standard planes that contain the mid-sagittal view of the fetus are sampled at multiple time stamps (using a custom-designed confident-frame detector) based on the estimated probability values associated with predicted anatomical structures that define the biometry plane. Automated semantic segmentation is performed on the selected frames to extract fetal anatomical landmarks. A crown–rump length (CRL) estimate is calculated as the mean CRL from these multiple frames. Our fully automated method has a high correlation with clinical expert CRL measurement (Pearson's p = 0.92, R -squared [ R 2] = 0.84) and a low mean absolute error of 0.834 (weeks) for fetal age estimation on a test data set of 42 videos. A novel algorithm for standard plane detection employs a quality detection mechanism defined by clinical standards, ensuring precise biometric measurements. [ABSTRACT FROM AUTHOR]

In the realm of visual tasks, the estimation of orientation plays a pivotal role yet often remains an understudied aspect in the gamut of image analysis research. This paper endeavors to address this deficiency by conducting a comprehensive review of methods for orientation estimation within 2D imaging contexts. We aim to provide researchers with an exhaustive overview and detailed analysis of the techniques utilized for orientation estimation, thereby enhancing their understanding of this complex field. We introduce an organized classification of orientation estimation methods, segmented into approaches based on classification algorithms and those based on regression models. This classification not only sheds light on the distinct methodologies but also scrutinizes their underlying assumptions, practical applications. Additionally, the study identifies and underscores emerging research opportunities that hold the potential to enrich the discourse and technical advancements in orientation estimation, thereby encouraging deeper academic investigation and technological development. [ABSTRACT FROM AUTHOR]

• Visual AI showed that females, but not males, had lower perceived BF% than actual. • Body image distortion generated by DIA were associated with MBSRQ-AS subscales. • Body image dissatisfaction from DIA were associated with MBSRQ-AS subscales. • Remote smartphone-based DIA may provide a feasible analog to assessing body image. Given that mobile digital imaging analyses (DIA) are equipped to automate body composition and subsequently alter one's appearance at a given objective body fat percent (BF%), the purpose of this study was to validate the use of this tool for assessments of body image. Participants (f = 134, m = 89) from two separate centers underwent body composition scans using a mobile DIA and completed the Multidimensional Body Self-Relations Questionnaire–Appearance Scale (MBSRQ-AS). Using a DIA-generated avatar, participants altered their figure so that it represented their perceived body, ideal body, and what a partner would find attractive. Distortion was calculated as perceived minus actual BF% and dissatisfaction was calculated as either ideal or partner minus perceived BF%. The total sample and females (p < 0.050), but not males, had significantly lower perceived BF% compared to their actual. Ideal and partner BF% was significantly lower than the perceived BF% for all groups (all p < 0.050). Ideal and partner BF% mean differences (MD) from perceived were positively associated with appearance evaluation (AE) and body area satisfaction (BAS) and negatively associated with overweight preoccupation and self-classified weight for the total sample (all p < 0.050). Perceived MD demonstrated negative associations with AE and BAS (p < 0.050), but only for females when separated by sex. Perceptual body image measured by DIA is significantly associated with attitudinal body image and may allow practitioners to better quantify this growing issue. [ABSTRACT FROM AUTHOR]

Extended endoscopic endonasal approaches (EEAs) to petroclival chondrosarcomas (PCs) require a thorough understanding of skullbase anatomy, especially the anatomy of petrous internal carotid artery (pICA), as ICA injury is the most dreaded complication of extended EEAs. We conducted this study to determine the displacement patterns of pICA in patients with PCs. Contrast enhanced computed tomography scan and angiography images of patients with PCs were analyzed for following parameters—antero-posterior, cranio-caudal, medio-lateral, and direct distances between anterior genu of petrous internal carotid artery (AGpICA) and posterior end of Vidian canal (pVC). pICA encasement/narrowing by tumor was noted on magnetic resonance imaging. We studied 11 patients with histopathologically proven PCs. pICA encasement/narrowing and pVC destruction were observed in one patient each. The mean antero-posterior and cranio-caudal distances on tumor side/normal side were 7.7 ± 1.9/6.4 ± 1.0 mm & 4.5 ± 1.5/3.4 ± 0.9 mm, respectively. The overall displacement was posterior & superior. Medio-lateral displacement was seen in 4 patients (lateral in 3 and medial in 1). In rest, AGpICA was centered on pVC. The mean direct distance was 9.4 ± 2.5 mm. In 3 patients with displacement seen in all three axes, direct distance was measured by the "cuboid method." Overall, posterior-superior-lateral, posterior-superior, and anterior-inferior were the common displacement patterns of AGpICA relative to pVC. The displacement patterns of AGpICA in PCs are variable. An individualized approach with meticulous analysis of preoperative imaging can help in determining the relation between AGpICA and pVC. This detailed morphometric information can facilitate better orientation to altered anatomy, which can be helpful in preventing pICA injury during extended EEAs. [ABSTRACT FROM AUTHOR]

Subvisible particles may be encountered throughout the processing of therapeutic protein formulations. Flow imaging microscopy (FIM) and backgrounded membrane imaging (BMI) are techniques commonly used to record digital images of these particles, which may be analyzed to provide particle size distributions, concentrations, and identities. Although both techniques record digital images of particles within a sample, FIM analyzes particles suspended in flowing liquids, whereas BMI records images of dry particles after collection by filtration onto a membrane. This study compared the performance of convolutional neural networks (CNNs) in classifying images of subvisible particles recorded by both imaging techniques. Initially, CNNs trained on BMI images appeared to provide higher classification accuracies than those trained on FIM images. However, attribution analyses showed that classification predictions from CNNs trained on BMI images relied on features contributed by the membrane background, whereas predictions from CNNs trained on FIM features were based largely on features of the particles. Segmenting images to minimize the contributions from image backgrounds reduced the apparent accuracy of CNNs trained on BMI images but caused minimal reduction in the accuracy of CNNs trained on FIM images. Thus, the seemingly superior classification accuracy of CNNs trained on BMI images compared to FIM images was an artifact caused by subtle features in the backgrounds of BMI images. Our findings emphasize the importance of examining machine learning algorithms for image analysis with attribution methods to ensure the robustness of trained models and to mitigate potential influence of artifacts within training data sets. [ABSTRACT FROM AUTHOR]