Validation of the Subaxial Cervical Spine Injury Classification score in children: a single-institution experience at a level 1 pediatric trauma center.

OBJECTIVE: The Subaxial Cervical Spine Injury Classification (SLIC) score has not been previously validated for a pediatric population. The authors compared the SLIC treatment recommendations for pediatric subaxial cervical spine trauma with real-world pediatric spine surgery practice. METHODS: A retrospective cohort study at a pediatric level 1 trauma center was conducted in patients < 18 years of age evaluated for trauma from 2012 to 2021. An SLIC score was calculated for each patient, and the subsequent recommendations were compared with actual treatment delivered. Percentage misclassification, sensitivity, specificity, positive (PPV) and negative predictive value (NPV), and area under the receiver operating characteristic (ROC) curve (AUC) were calculated. RESULTS: Two hundred forty-three pediatric patients with trauma were included. Twenty-five patients (10.3%) underwent surgery and 218 were managed conservatively. The median SLIC score was 2 (interquartile range = 2). Sixteen patients (6.6%) had an SLIC score of 4, for which either conservative or surgical treatment is recommended; 27 children had an SLIC score ≥ 5, indicating a recommendation for surgical treatment; and 200 children had an SLIC score ≤ 3, indicating a recommendation for conservative treatment. Of the 243 patients, 227 received treatment consistent with SLIC score recommendations (p < 0.001). SLIC sensitivity in determining surgically treated patients was 79.2% and the specificity for accurately determining who underwent conservative treatment was 96.1%. The PPV was 70.3% and the NPV was 97.5%. There was a 5.7% misclassification rate (n = 13) using SLIC. Among patients for whom surgical treatment would be recommended by the SLIC, 29.6% (n = 8) did not undergo surgery; similarly, 2.5% (n = 5) of patients for whom conservative management would be recommended by the SLIC had surgery. The ROC curve for determining treatment received demonstrated excellent discriminative ability, with an AUC of 0.96 (OR 3.12, p < 0.001). Sensitivity decreased when the cohort was split by age (< 10 and ≥ 10 years old) to 0.5 and 0.82, respectively; specificity remained high at 0.98 and 0.94. CONCLUSIONS: The SLIC scoring system recommended similar treatment when compared with the actual treatment delivered for traumatic subaxial cervical spine injuries in children, with a low misclassification rate and a specificity of 96%. These findings demonstrate that the SLIC can be useful in guiding treatment for pediatric patients with subaxial cervical spine injuries. Further investigation into the score in young children (< 10 years) using a multicenter cohort is warranted.

Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G.

Diabetic retinopathy disease contains lesions (e.g., exudates, hemorrhages, and microaneurysms) that are minute to the naked eye. Determining the lesions at pixel level poses a challenge as each pixel does not reflect any semantic entities. Furthermore, the computational cost of inspecting each pixel is expensive because the number of pixels is high even at low resolution. In this work, we propose a hybrid image processing method. Simple Linear Iterative Clustering with Gaussian Filter (SLIC-G) for the purpose of overcoming pixel constraints. The SLIC-G image processing method is divided into two stages: (1) simple linear iterative clustering superpixel segmentation and (2) Gaussian smoothing operation. In such a way, a large number of new transformed datasets are generated and then used for model training. Finally, two performance evaluation metrics that are suitable for imbalanced diabetic retinopathy datasets were used to validate the effectiveness of the proposed SLIC-G. The results indicate that, in comparison to prior published works' results, the proposed SLIC-G shows better performance on image classification of class imbalanced diabetic retinopathy datasets. This research reveals the importance of image processing and how it influences the performance of deep learning networks. The proposed SLIC-G enhances pre-trained network performance by eliminating the local redundancy of an image, which preserves local structures, but avoids over-segmented, noisy clips. It closes the research gap by introducing the use of superpixel segmentation and Gaussian smoothing operation as image processing methods in diabetic retinopathy-related tasks.

Development of a Tag/Catcher-mediated capsid virus-like particle vaccine presenting the conserved Neisseria gonorrhoeae SliC antigen that blocks human lysozyme.

Virus-like particles (VLPs) are promising nanotools for the development of subunit vaccines due to high immunogenicity and safety. Herein, we explored the versatile and effective Tag/Catcher-AP205 capsid VLP (cVLP) vaccine platform to address the urgent need for the development of an effective and safe vaccine against gonorrhea. The benefits of this clinically validated cVLP platform include its ability to facilitate unidirectional, high-density display of complex/full-length antigens through an effective split-protein Tag/Catcher conjugation system. To assess this modular approach for making cVLP vaccines, we used a conserved surface lipoprotein, SliC, that contributes to the Neisseria gonorrhoeae defense against human lysozyme, as a model antigen. This protein was genetically fused at the N- or C-terminus to the small peptide Tag enabling their conjugation to AP205 cVLP, displaying the complementary Catcher. We determined that SliC with the N-terminal SpyTag, N-SliC, retained lysozyme-blocking activity and could be displayed at high density on cVLPs without causing aggregation. In mice, the N-SliC-VLP vaccines, adjuvanted with AddaVax or CpG, induced significantly higher antibody titers compared to controls. In contrast, similar vaccine formulations containing monomeric SliC were non-immunogenic. Accordingly, sera from N-SliC-VLP-immunized mice also had significantly higher human complement-dependent serum bactericidal activity. Furthermore, the N-SliC-VLP vaccines administered subcutaneously with an intranasal boost elicited systemic and vaginal IgG and IgA, whereas subcutaneous delivery alone failed to induce vaginal IgA. The N-SliC-VLP with CpG (10 µg/dose) induced the most significant increase in total serum IgG and IgG3 titers, vaginal IgG and IgA, and bactericidal antibodies.

More appropriate DenseNetBL classifier for small sample tree species classification using UAV-based RGB imagery.

To effectively classify tree species within datasets characterized by limited samples, we introduced a novel approach named DenseNetBL, founded upon the fusion of the DenseNet architecture and a pivotal bottleneck layer. This bottleneck layer, encompassing a compact convolutional component, played a central role in our methodology. The evaluation of DenseNetBL was conducted under varying conditions, encompassing small-sample tree species data, extensive remote sensing datasets, and state-of-the-art classifiers. Furthermore, a quantitative assessment was executed to extract tree species areas. This was achieved by quantifying pixel areas within manually delineated tree species maps and classifier-generated counterparts. The findings of our study indicated that, in scenarios devoid of pre-trained weights, DenseNetBL consistently outperformed its DenseNet counterpart with equivalent layer numbers. In the realm of small-sample situations, both the Swin Transformer and Vision Transformer exhibited inferior performance when juxtaposed with DenseNet and DenseNetBL. Remarkably, among the shallow architectures, DenseNet33BL showcased superior aptitude for small-sample tree species classification, culminating in the most commendable results (Overall Accuracy (OA) = 0.901, Kappa = 0.892). Conversely, the Vision Transformer yielded the least favorable classification outcomes (OA = 0.767, Kappa = 0.708). The amalgamation of DenseNet33BL and simple linear iterative clustering emerged as the optimal strategy for attaining robust tree species area extraction results across two prototypical forests. In contrast, DenseNet121 exhibited suboptimal performance in the same forests, attaining the least satisfactory tree species area extraction results. These comprehensive findings underscore the efficacy of our DenseNetBL approach in addressing the challenges associated with small-sample tree species classification and accurate tree species area extraction.

Teachability of lower cervical spine injury classifications / Educabilidad de las clasificaciones de lesiones de la columna cervical subaxial

Objectives To compare the teachability of the Allen–Ferguson, Harris, Argenson, AOSpine, Subaxial Cervical Spine Injury Classification (SLIC), Subaxial Cervical Spine Injury Classification (CSISS) and to identify the classification that a group of residents and junior neurosurgeons find easiest to learn. Methods We used data from 64 consecutive patients. Answers of nine residents and junior neurosurgeons and four experienced surgeons in two assessment procedures were used. Six raters (workshop group) participated in special seminars between assessments. Three other raters formed the control group. Experienced surgeon's answers were used for comparison. Teachability was measured as the median value of the difference (ΔK) in the interrater agreement on the same patients by the same pairs of subjects. Results Median Δ K for the Allen–Ferguson, Harris, Argenson and AOSpine classifications were: (1) 0.01, 0.02, 0.29, and 0.39 for the workshop group; (2). 0.09, −0.03, 0.06 and 0.04 for the control group, respectively. Between numerical scales, median ΔK was higher for SLIC but did not exceed 0.16. Interrater consistency with expert's opinion was increased in the workshop group for Allen–Ferguson, Argenson and AOSpine and did not differ in either group for SLIC and CSISS. Conclusion The AOSpine classification was the most teachable. Among numeric scales, SLIC demonstrated better results. The successful application of these classifications by residents and junior neurosurgeons was possible after a short educational course. The use of these scales in educational cycles at the stage of residency can significantly simplify the communication between specialists, especially at the stage of patient admission (AU)

Objetivos Comparar la educabilidad de las clasificaciones de Allen-Ferguson, Harris, Argenson, AOSpine, Subaxial Cervical Spine Injury Classification (SLIC), Subaxial Cervical Spine Injury Classification (CSISS) e identificar la clasificación que un grupo de residentes y neurocirujanos jóvenes encuentran más fácil para aprender. Métodos Usamos los datos de 64 pacientes consecutivos. Se utilizaron las respuestas de 9 residentes y neurocirujanos jóvenes y 4 cirujanos experimentados en 2 procedimientos de evaluación. Seis evaluadores (grupo de talleres) participaron en seminarios especiales entre evaluaciones. Otros 3 evaluadores formaron el grupo de control. Se utilizaron las respuestas de cirujanos experimentados a modo de comparación. La educabilidad se midió como el valor mediano de la diferencia (ΔK) en el acuerdo entre observadores sobre los mismos pacientes por los mismos pares de evaluadores. Resultados La mediana de ΔK para las clasificaciones de Allen-Ferguson, Harris, Argenson y AOSpine fue: 1) 0,01; 0,02; 0,29 y 0,39 para el grupo del taller; 2) 0,09; −0,03; 0,06 y 0,04 para el grupo de control, respectivamente. Entre las escalas numéricas, la mediana de ΔK fue mayor para SLIC pero no excedió 0,16. La coherencia entre evaluadores y los expertos aumentó en el grupo de taller para Allen-Ferguson, Argenson y AOSpine y no difirió en ninguno de los grupos para SLIC y CSISS. Conclusión La clasificación AOSpine tuvo la mejor educabilidad. Entre las escalas numéricas, SLIC demostró mejores resultados. La aplicación exitosa de estas clasificaciones por residentes y neurocirujanos junior fue posible después de un breve curso educativo. El uso de estas escalas en los ciclos educativos en la etapa de residencia puede simplificar significativamente la comunicación entre especialistas, principalmente en la etapa de ingreso del paciente (AU)

A Sequence- and Ligation-Independent Cloning (SLIC) Procedure for the Insertion of Genes into a Plasmid Vector.

Molecular cloning is a routine technique for many laboratories with applications from genetic engineering to recombinant protein expression. While restriction-ligation cloning can be slow and inefficient, ligation-independent cloning uses long single-stranded overhangs generated by T4 DNA polymerase's 3' exonuclease activity to anneal the insert and plasmid vector prior to transformation. This chapter describes a fast, high-efficiency protocol for inserting one or more genes into a vector using sequence- and ligation-independent cloning (SLIC).

Teachability of lower cervical spine injury classifications.

OBJECTIVES: To compare the teachability of the Allen-Ferguson, Harris, Argenson, AOSpine, Subaxial Cervical Spine Injury Classification (SLIC), Subaxial Cervical Spine Injury Classification (CSISS) and to identify the classification that a group of residents and junior neurosurgeons find easiest to learn. METHODS: We used data from 64 consecutive patients. Answers of nine residents and junior neurosurgeons and four experienced surgeons in two assessment procedures were used. Six raters (workshop group) participated in special seminars between assessments. Three other raters formed the control group. Experienced surgeon's answers were used for comparison. Teachability was measured as the median value of the difference (ΔK) in the interrater agreement on the same patients by the same pairs of subjects. RESULTS: Median Δ K for the Allen-Ferguson, Harris, Argenson and AOSpine classifications were: (1) 0.01, 0.02, 0.29, and 0.39 for the workshop group; (2). 0.09, -0.03, 0.06 and 0.04 for the control group, respectively. Between numerical scales, median ΔK was higher for SLIC but did not exceed 0.16. Interrater consistency with expert's opinion was increased in the workshop group for Allen-Ferguson, Argenson and AOSpine and did not differ in either group for SLIC and CSISS. CONCLUSION: The AOSpine classification was the most teachable. Among numeric scales, SLIC demonstrated better results. The successful application of these classifications by residents and junior neurosurgeons was possible after a short educational course. The use of these scales in educational cycles at the stage of residency can significantly simplify the communication between specialists, especially at the stage of patient admission.

Efficient COVID-19 super pixel segmentation algorithm using MCFO-based SLIC.

In computer vision segmentation field, super pixel identity has become an important index in the recently segmentation algorithms especially in medical images. Simple Linear Iterative Clustering (SLIC) algorithm is one of the most popular super pixel methods as it has a great robustness, less sensitive to the image type and benefit to the boundary recall in different kinds of image processing. Recently, COVID-19 severity increased with the lack of an effective treatment or vaccine. As the Corona virus spreads in an unknown manner, th-ere is a strong need for segmenting the lungs infected regions for fast tracking and early detection, no matter how small. This may consider difficult to be achieved with traditional segmentation techniques. From this perspective, this paper presents an efficient modified central force optimization (MCFO)-based SLIC segmentation algorithm to discuss chest CT images for detecting the positive COVID-19 cases. The proposed MCFO-based SLIC segmentation algorithm performance is evaluated and compared with the thresholding segmentation algorithm using different evaluation metrics such as accuracy, boundary recall, F-measure, similarity index, MCC, Dice, and Jaccard. The outcomes demonstrated that the proposed MCFO-based SLIC segmentation algorithm has achieved better detection for the small infected regions in CT lung scans than the thresholding segmentation.

Optimized method for segmentation of ancient mural images based on superpixel algorithm.

High-precision segmentation of ancient mural images is the foundation of their digital virtual restoration. However, the complexity of the color appearance of ancient murals makes it difficult to achieve high-precision segmentation when using traditional algorithms directly. To address the current challenges in ancient mural image segmentation, an optimized method based on a superpixel algorithm is proposed in this study. First, the simple linear iterative clustering (SLIC) algorithm is applied to the input mural images to obtain superpixels. Then, the density-based spatial clustering of applications with noise (DBSCAN) algorithm is used to cluster the superpixels to obtain the initial clustered images. Subsequently, a series of optimized strategies, including (1) merging the small noise superpixels, (2) segmenting and merging the large noise superpixels, (3) merging initial clusters based on color similarity and positional adjacency to obtain the merged regions, and (4) segmenting and merging the color-mixing noisy superpixels in each of the merged regions, are applied to the initial cluster images sequentially. Finally, the optimized segmentation results are obtained. The proposed method is tested and compared with existing methods based on simulated and real mural images. The results show that the proposed method is effective and outperforms the existing methods.

Fuzzy Color Aura Matrices for Texture Image Segmentation.

Fuzzy gray-level aura matrices have been developed from fuzzy set theory and the aura concept to characterize texture images. They have proven to be powerful descriptors for color texture classification. However, using them for color texture segmentation is difficult because of their high memory and computation requirements. To overcome this problem, we propose to extend fuzzy gray-level aura matrices to fuzzy color aura matrices, which would allow us to apply them to color texture image segmentation. Unlike the marginal approach that requires one fuzzy gray-level aura matrix for each color channel, a single fuzzy color aura matrix is required to locally characterize the interactions between colors of neighboring pixels. Furthermore, all works about fuzzy gray-level aura matrices consider the same neighborhood function for each site. Another contribution of this paper is to define an adaptive neighborhood function based on information about neighboring sites provided by a pre-segmentation method. For this purpose, we propose a modified simple linear iterative clustering algorithm that incorporates a regional feature in order to partition the image into superpixels. All in all, the proposed color texture image segmentation boils down to a superpixel classification using a simple supervised classifier, each superpixel being characterized by a fuzzy color aura matrix. Experimental results on the Prague texture segmentation benchmark show that our method outperforms the classical state-of-the-art supervised segmentation methods and is similar to recent methods based on deep learning.

A novel event-related fMRI supervoxels-based representation and its application to schizophrenia diagnosis.

BACKGROUND AND OBJECTIVE: The schizophrenia diagnosis represents a difficult task because of the confusing descriptions of symptoms given by the patient, their similarity among several disorders, the lower familiarity with genetic predisposition, and the probably inadequate response to the treatment. Neuro-biological markers of schizophrenia, as a quantitative relationship between the psychiatrist's reports and the biology of the brain, could be used. Functional Magnetic Resonance Imaging (fMRI) obtain the subject's performance in cognitive tasks and may find significant differences between the patient's data and controls. The input data of classifiers may imply alterations in diagnosis; therefore, it is essential to ensure an adequate representation to describe the entire dataset classified. METHODS: We propose a supervoxels-based representation calculated by two main steps: the short-range connectivity, supervoxels' generation using a Fuzzy Iterative Clustering algorithm, and the long-range connectivity, employing Detrended Cross-Correlation Analysis among supervoxels. The unrelated supervoxels, through a statistical test based on critical points calculated empirically, are removed. The remainder supervoxels are the input for feature selectors to extract the discriminative supervoxels. We implement support vector machine classifiers using the correlation coefficient of the significant supervoxels. The dataset of 1.5 Tesla was downloaded from the SchizConnect site, where the fMRI data, during an auditory oddball task, was acquired. We calculate the performance of the classifiers using a leave-one-out cross-validation and compute the area under the Receiver Operating Characteristic curve and a permutation test to ensure no bias in the classifiers. RESULTS: According to the permutation test, with p-values less than the significance level of 0.05, the classifiers extract discriminative class structure from data where no bias is shown. Our supervoxels-based representation gets the maximum values of sensitivity, specificity, and accuracy of 92.9%, 100%, and 96.4%, respectively. The discriminative brain regions, to discern among patients and controls, are extracted; these regions also are mentioned by the related works. CONCLUSIONS: The proposed representation, based on supervoxels, is a data-driven model that does not use predefined models of the signal nor pre-relocated brain regions of interest. The results are competitive against the related works, and the relevant supervoxels are related to the schizophrenia diagnosis.

An Automated Approach for Electric Network Frequency Estimation in Static and Non-Static Digital Video Recordings.

Electric Network Frequency (ENF) is embedded in multimedia recordings if the recordings are captured with a device connected to power mains or placed near the power mains. It is exploited as a tool for multimedia authentication. ENF fluctuates stochastically around its nominal frequency at 50/60 Hz. In indoor environments, luminance variations captured by video recordings can also be exploited for ENF estimation. However, the various textures and different levels of shadow and luminance hinder ENF estimation in static and non-static video, making it a non-trivial problem. To address this problem, a novel automated approach is proposed for ENF estimation in static and non-static digital video recordings. The proposed approach is based on the exploitation of areas with similar characteristics in each video frame. These areas, called superpixels, have a mean intensity that exceeds a specific threshold. The performance of the proposed approach is tested on various videos of real-life scenarios that resemble surveillance from security cameras. These videos are of escalating difficulty and span recordings from static ones to recordings, which exhibit continuous motion. The maximum correlation coefficient is employed to measure the accuracy of ENF estimation against the ground truth signal. Experimental results show that the proposed approach improves ENF estimation against the state-of-the-art, yielding statistically significant accuracy improvements.

External Multicenter Study of Reliability and Reproducibility for Lower Cervical Spine Injuries Classification Systems-Part 2: An Analysis of the Subaxial Cervical Spine Injury Classification and Cervical Spine Injury Severity Score Scale.

STUDY DESIGN: A multicenter observational survey. OBJECTIVE: To quantify and compare inter- and intraobserver reliability of the subaxial cervical spine injury classification (SLIC) and the cervical spine injury severity score (CSISS) in a multicentric survey of neurosurgeons with different experience levels. METHODS: Data concerning 64 consecutive patients who had undergone cervical spine surgery between 2013 and 2017 was evaluated, and we surveyed 37 neurosurgeons from 7 different clinics. All raters were divided into 3 groups depending on their level of experience. Two assessment procedures were performed. RESULTS: For the SLIC, we observed excellent agreement regarding management among experienced surgeons, whereas agreement among less experienced neurosurgeons was moderate and almost twice as unlikely. The sensitivity of SLIC relating to treatment tactics reached as high as 92.2%. For the CSISS, agreement regarding management ranged from medium to substantial, depending on a neurosurgeon's experience. For less experienced neurosurgeons, the level of agreement concerning surgical management was the same as for the SLIC in not exceeding a moderate level. However, this scale had insufficient sensitivity (slightly exceeding 50%). The reproducibility of both scales was excellent among all raters regardless of their experience level. CONCLUSIONS: Our study demonstrated better management reliability, sensitivity, and reproducibility for the SLIC, which provided moderate interrater agreement with moderate to excellent intraclass correlation coefficient indicators for all raters. The CSISS demonstrated high reproducibility; however, large variability in answers prevented raters from reaching a moderate level of agreement. Magnetic resonance imaging integration may increase sensitivity of CSISS in relation to fracture management.

Production of Multiprotein Complexes Using the Baculovirus Expression System: Homology-Based and Restriction-Free Cloning Strategies for Construct Design.

Most cellular processes are mediated by multi-subunit protein complexes which have attracted major interest in both academia and industry. Recombinant production of such entities in quantity and quality sufficient for functional and structural investigations may be extremely challenging and necessitate specific technologies. The baculovirus expression vector system is widely used for the production of eukaryotic multiprotein complexes, and a variety of strategies are available to assemble transfer vectors for the generation of recombinant baculoviruses. Here we detail applications of homology-based cloning techniques for one-step construction of dual promoter baculovirus transfer plasmids and of restriction-free (RF) cloning for the modification of existing constructs.

The case for the future role of evidence-based medicine in the management of cervical spine injuries, with or without fractures.

The authors believe that the standardized and systematic study of immobilization techniques, diagnostic modalities, medical and surgical treatment strategies, and ultimately outcomes and outcome measurement after cervical spinal trauma and cervical spinal fracture injuries, if performed using well-designed medical evidence-based comparative investigations with meaningful follow-up, has both merit and the remarkable potential to identify optimal strategies for assessment, characterization, and clinical management. However, they recognize that there is inherent difficulty in attempting to apply evidence-based medicine (EBM) to identify ideal treatment strategies for individual cervical fracture injuries. First, there is almost no medical evidence reported in the literature for the management of specific isolated cervical fracture subtypes; specific treatment strategies for specific fracture injuries have not been routinely studied in a rigorous, comparative way. One of the vulnerabilities of an evidenced-based scientific review in spinal cord injury (SCI) is the lack of studies in comparative populations and scientific evidence on a given topic or fracture pattern providing level II evidence or higher. Second, many modest fracture injuries are not associated with vascular or neural injury or spinal instability. The application of the science of EBM to the care of patients with traumatic cervical spine injuries and SCIs is invaluable and necessary. The dedicated multispecialty author groups involved in the production and publication of the two iterations of evidence-based guidelines on the management of acute cervical spine and spinal cord injuries have provided strategic guidance in the care of patients with SCIs. This dedicated service to the specialty has been carried out to provide neurosurgical colleagues with a qualitative review of the evidence supporting various aspects of care of these patients. It is important to state and essential to understand that the science of EBM and its rigorous application is important to medicine and to the specialty of neurosurgery. It should be embraced and used to drive and shape investigations of the management and treatment strategies offered patients. It should not be abandoned because it is not convenient or it does not support popular practice bias or patterns. It is the authors' view that the science of EBM is essential and necessary and, furthermore, that it has great potential as clinician scientists treat and study the many variations and complexities of patients who sustain acute cervical spine fracture injuries.

Homonuclear ADAPT: A general preparation route to long-lived nuclear singlet order.

We introduce a simple strategy to access and readout nuclear singlet order based on the alternate repetition of hard pulses and delays. We demonstrate the general applicability of the method by accessing nuclear singlet order in spin systems characterized by diverse coupling regimes. We show that the method is highly efficient in the strong-coupling and chemical equivalence regimes, and can overcome some limitations of other well-established and more elaborated pulse sequences. A simulation package is provided which allows the determination of pulse sequence parameters.

A novel technique for analysing histogram equalized medical images using superpixels.

We present a novel technique to distinguish between an original image and its histogram equalized version. Histogram equalization and superpixel segmentation such as SLIC (simple linear iterative clustering) are very popular image processing tools. Based on these two concepts, we introduce a method for finding whether an image (grayscale) is histogram equalized or not. Because sometimes we see images that look visually similar but they are actually processed or changed by some image enhancement process such as histogram equalization. We can merely infer whether the image is dark, bright or has a small dynamic range. Moreover, we also compare the result of SLIC superpixels with three other superpixel segmentation algorithms namely, quick shift, watersheds, and Felzenszwalb's segmentation algorithm.

SLIC Superpixel-Based l2,1-Norm Robust Principal Component Analysis for Hyperspectral Image Classification.

Hyperspectral Images (HSIs) contain enriched information due to the presence of various bands, which have gained attention for the past few decades. However, explosive growth in HSIs' scale and dimensions causes "Curse of dimensionality" and "Hughes phenomenon". Dimensionality reduction has become an important means to overcome the "Curse of dimensionality". In hyperspectral images, labeled samples are more difficult to collect because they require many labor and material resources. Semi-supervised dimensionality reduction is very important in mining high-dimensional data due to the lack of costly-labeled samples. The promotion of the supervised dimensionality reduction method to the semi-supervised method is mostly done by graph, which is a powerful tool for characterizing data relationships and manifold exploration. To take advantage of the spatial information of data, we put forward a novel graph construction method for semi-supervised learning, called SLIC Superpixel-based l 2 , 1 -norm Robust Principal Component Analysis (SURPCA2,1), which integrates superpixel segmentation method Simple Linear Iterative Clustering (SLIC) into Low-rank Decomposition. First, the SLIC algorithm is adopted to obtain the spatial homogeneous regions of HSI. Then, the l 2 , 1 -norm RPCA is exploited in each superpixel area, which captures the global information of homogeneous regions and preserves spectral subspace segmentation of HSIs very well. Therefore, we have explored the spatial and spectral information of hyperspectral image simultaneously by combining superpixel segmentation with RPCA. Finally, a semi-supervised dimensionality reduction framework based on SURPCA2,1 graph is used for feature extraction task. Extensive experiments on multiple HSIs showed that the proposed spectral-spatial SURPCA2,1 is always comparable to other compared graphs with few labeled samples.

Automatic cell segmentation in histopathological images via two-staged superpixel-based algorithms.

The analysis of cell characteristics from high-resolution digital histopathological images is the standard clinical practice for the diagnosis and prognosis of cancer. Yet, it is a rather exhausting process for pathologists to examine the cellular structures manually in this way. Automating this tedious and time-consuming process is an emerging topic of the histopathological image-processing studies in the literature. This paper presents a two-stage segmentation method to obtain cellular structures in high-dimensional histopathological images of renal cell carcinoma. First, the image is segmented to superpixels with simple linear iterative clustering (SLIC) method. Then, the obtained superpixels are clustered by the state-of-the-art clustering-based segmentation algorithms to find similar superpixels that compose the cell nuclei. Furthermore, the comparison of the global clustering-based segmentation methods and local region-based superpixel segmentation algorithms are also compared. The results show that the use of the superpixel segmentation algorithm as a pre-segmentation method improves the performance of the cell segmentation as compared to the simple single clustering-based segmentation algorithm. The true positive ratio (TPR), true negative ratio (TNR), F-measure, precision, and overlap ratio (OR) measures are utilized as segmentation performance evaluation. The computation times of the algorithms are also evaluated and presented in the study. Graphical Abstract The visual flowchart of the proposed automatic cell segmentation in histopathological images via two-staged superpixel-based algorithms.

Predictors of Neurological Outcome Following Subaxial Cervical Spine Trauma.

Background The treatment of traumatic subaxial cervical spine injuries remains controversial. The American Spinal Injury Association (ASIA) impairment scale (AIS) is a widely-used metric to score neurological function after spinal cord injury (SCI). Here, we evaluated the outcomes of patients who underwent treatment of subaxial cervical spine injuries to identify predictors of neurologic function after injury and treatment. Methods We performed a retrospective logistic regression analysis to determine predictors of neurological outcome; 76 patients met the inclusion criteria and presented for a three-month follow-up. The mean age was 50.6±18.7 years old and the majority of patients were male (n=49, 64%). Results The majority of patients had stable AIS scores at three months (n=56, 74%). A subset of patients showed improvement at three months (n=16, 21%), while a small subset of patients had neurological decline at three months (n=4, 5%). In our model, increasing patient age (odds ratio [OR] 1.39, 1.10-2.61 95% confidence interval [CI], P<0.001) and a previous or current diagnosis of cancer (OR 22.4, 1.25-820 95% CI, P=0.04) significantly increased the odds of neurological decline at three months. In patients treated surgically, we found that delay in surgical treatment (>24 hours) was associated with a decreased odds of neurological improvement (OR 0.24, 0.05-0.99 95% CI, P=0.048). Cervical spine injuries are heterogeneous and difficult to manage. Conclusion We found that increasing patient age and an oncologic history were associated with neurological deterioration while a delay in surgical treatment was associated with decreased odds of improvement. These predictors of outcome may be used to guide prognosis and treatment decisions.