Real-Time Detection of an Undercarriage Based on Receptive Field Blocks and Coordinate Attention.

Currently, aeroplane images captured by camera sensors are characterized by their small size and intricate backgrounds, posing a challenge for existing deep learning algorithms in effectively detecting small targets. This paper incorporates the RFBNet (a coordinate attention mechanism) and the SIOU loss function into the YOLOv5 algorithm to address this issue. The result is developing the model for aeroplane and undercarriage detection. The primary goal is to synergize camera sensors with deep learning algorithms, improving image capture precision. YOLOv5-RSC enhances three aspects: firstly, it introduces the receptive field block based on the backbone network, increasing the size of the receptive field of the feature map, enhancing the connection between shallow and deep feature maps, and further improving the model's utilization of feature information. Secondly, the coordinate attention mechanism is added to the feature fusion network to assist the model in more accurately locating the targets of interest, considering attention in the channel and spatial dimensions. This enhances the model's attention to key information and improves detection precision. Finally, the SIoU bounding box loss function is adopted to address the issue of IoU's insensitivity to scale and increase the speed of model bounding box convergence. Subsequently, the Basler camera experimental platform was constructed for experimental verification. The results demonstrate that the AP values of the YOLOv5-RSC detection model for aeroplane and undercarriage are 92.4% and 80.5%, respectively. The mAP value is 86.4%, which is 2.0%, 5.4%, and 3.7% higher than the original YOLOv5 algorithm, respectively, with a detection speed reaching 89.2 FPS. These findings indicate that the model exhibits high detection precision and speed, providing a valuable reference for aeroplane undercarriage detection.

Transmembrane TNF-α preferentially expressed by leukemia stem cells and blasts is a potent target for antibody therapy.

To design an effective antibody therapy to improve clinical outcomes in leukemia, the identification of novel cell surface antigens is needed. Herein, we demonstrate a role for transmembrane tumor necrosis factor-α (tmTNF-α) in leukemia. To characterize tmTNF-α expression in acute leukemia (AL), normal hematopoietic cells, and nonhematopoietic tissues, we used a monoclonal antibody, termed C1, which specifically recognizes the tmTNF-α domain. We found that tmTNF-α was preferentially expressed by AL and leukemia stem cells (LSCs). More abundant expression correlated with poor risk stratification, extramedullary infiltration, and adverse clinical parameters. Moreover, knockdown of tmTNF-α(+) expression rendered leukemia cells more sensitive to chemotherapy in vitro and delayed regeneration of leukemia in NOD-SCID mice. Targeting tmTNF-α by C1 resulted in leukemia cell killing via antibody-dependent cell-mediated and complement-dependent cytotoxicity in vitro and inhibited leukemia cell growth in vivo while simultaneously sparing normal hematopoietic cells. Notably, C1 administration impaired the regeneration of leukemia in secondary serial transplantation into NOD-SCID mice. In conclusion, tmTNF-α has a favorable AL- and LSC-associated expression profile and is important for the survival and proliferation of these cells. C1-mediated targeting shows potent anti-LSC activity, indicating that tmTNF-α represents a novel target antigen in AL.

Can shoulder range of movement be measured accurately using the Microsoft Kinect sensor plus Medical Interactive Recovery Assistant (MIRA) software?

BACKGROUND: This study compared the accuracy of measuring shoulder range of movement (ROM) with a simple laptop-sensor combination vs. trained observers (shoulder physiotherapists and shoulder surgeons) using motion capture (MoCap) laboratory equipment as the gold standard. METHODS: The Microsoft Kinect sensor (Microsoft Corp., Redmond, WA, USA) tracks 3-dimensional human motion. Ordinarily used with an Xbox (Microsoft Corp.) video game console, Medical Interactive Recovery Assistant (MIRA) software (MIRA Rehab Ltd., London, UK) allows this small sensor to measure shoulder movement with a standard computer. Shoulder movements of 49 healthy volunteers were simultaneously measured by trained observers, MoCap, and the MIRA device. Internal rotation was assessed with the shoulder abducted 90° and external rotation with the shoulder adducted. Visual estimation and MIRA measurements were compared with gold standard MoCap measurements for agreement using Bland-Altman methods. RESULTS: There were 1670 measurements analyzed. The MIRA evaluations of all 4 cardinal shoulder movements were significantly more precise, with narrower limits of agreement, than the measurements of trained observers. MIRA achieved ±11° (95% confidence interval [CI], 8.7°-12.6°) for forward flexion vs. ±16° (95% CI, 14.6°-17.6°) by trained observers. For abduction, MIRA showed ±11° (95% CI, 8.7°-12.8°) against ±15° (95% CI, 13.4°-16.2°) for trained observers. MIRA attained ±10° (95% CI, 8.1°-11.9°) during external rotation measurement, whereas trained observers only reached ±21° (95% CI, 18.7°-22.6°). For internal rotation, MIRA achieved ±9° (95% CI, 7.2°-10.4°), which was again better than TOs at ±18° (95% CI, 16.0°-19.3°). CONCLUSIONS: A laptop combined with a Microsoft Kinect sensor and the MIRA software can measure shoulder movements with acceptable levels of accuracy. This technology, which can be easily set up, may also allow precise shoulder ROM measurement outside the clinic setting.

A Novel Adaptive Deformable Model for Automated Optic Disc and Cup Segmentation to Aid Glaucoma Diagnosis.

This paper proposes a novel Adaptive Region-based Edge Smoothing Model (ARESM) for automatic boundary detection of optic disc and cup to aid automatic glaucoma diagnosis. The novelty of our approach consists of two aspects: 1) automatic detection of initial optimum object boundary based on a Region Classification Model (RCM) in a pixel-level multidimensional feature space; 2) an Adaptive Edge Smoothing Update model (AESU) of contour points (e.g. misclassified or irregular points) based on iterative force field calculations with contours obtained from the RCM by minimising energy function (an approach that does not require predefined geometric templates to guide auto-segmentation). Such an approach provides robustness in capturing a range of variations and shapes. We have conducted a comprehensive comparison between our approach and the state-of-the-art existing deformable models and validated it with publicly available datasets. The experimental evaluation shows that the proposed approach significantly outperforms existing methods. The generality of the proposed approach will enable segmentation and detection of other object boundaries and provide added value in the field of medical image processing and analysis.

No-reference stereoscopic image-quality metric accounting for left and right similarity map and spatial structure degradation.

Blind quality assessment of 3D images is used to confront more real challenges than 2D images. In this Letter, we develop a no-reference stereoscopic image quality assessment (SIQA) model based on the proposed left and right (LR)-similarity map and structural degradation. In the proposed method, local binary pattern features are extracted from the cyclopean image that are effective for describing the distortion of 3D images. More importantly, we first propose the LR-similarity map that can indicate the stereopair quality and demonstrate that the use of LR-similarity information results in a consistent improvement in the performance. The massive experimental results on the LIVE 3D and IRCCyN IQA databases demonstrate that the designed model is strongly correlated to subjective quality evaluations and competitive to the state-of-the-art SIQA algorithms.

Transmembrane TNF-α promotes suppressive activities of myeloid-derived suppressor cells via TNFR2.

It has been reported that TNFR2 is involved in regulatory T cell induction and myeloid-derived suppressor cell (MDSC) accumulation, two kinds of immunosuppressive cells contributing to tumor immune evasion. Because transmembrane TNF-α (tmTNF-α) is the primary ligand for TNFR2, we hypothesized that tmTNF-α is mainly responsible for the activation of MDSCs. Indeed, we found that tmTNF-α, rather than secretory TNF-α (sTNF-α), activated MDSCs with enhanced suppressive activities, including upregulating arginase-1 and inducible NO synthase transcription, promoting secretion of NO, reactive oxygen species, IL-10, and TGF-ß, and enhancing inhibition of lymphocyte proliferation. This effect of tmTNF-α was mediated by TNFR2, as TNFR2 deficiency significantly impaired tmTNF-α-induced release of IL-10 and NO and inhibition of T cell proliferation by MDSC supernatant. Furthermore, tmTNF-α caused p38 phosphorylation and NF-κB activation, whereas inhibition of NF-κB or p38 with an inhibitor pyrrolidine dithiocarbamate or SB203580 abrogated tmTNF-α-mediated increased suppression of lymphocyte proliferation by MDSCs. Consistently, our in vivo study showed that ectopic expression of uncleavable tmTNF-α mutant by 4T1 cells significantly promoted tumor progression and angiogenesis, accompanied with more accumulation of MDSCs and regulatory T cells in the tumor site, increased production of NO, IL-10, and TGF-ß, as well as poor lymphocyte infiltration. In contrast, enforced expression of sTNF-α mutant by 4T1 cells that only released sTNF-α without expression of surface tmTNF-α markedly reduced MDSC accumulation and induced more lymphocyte infiltration instead, showing obvious tumor regression. Our data suggest that tmTNF-α acts as a potent activator of MDSCs via TNFR2 and reveals another novel immunosuppressive effect of this membrane molecule that promotes tumor immune escape.

Biosignal-based transferable attention Bi-ConvGRU deep network for hand-gesture recognition towards online upper-limb prosthesis control.

BACKGROUND AND OBJECTIVE: Upper-limb amputation can significantly affect a person's capabilities with a dramatic impact on their quality of life. As a biological signal, surface electromyogram (sEMG) provides a non-invasive means to measure underlying muscle activation patterns, corresponding to specific hand gestures. This project aims to develop a real-time deep learning based recognition model to automatically and reliably recognise these complex signals of a wide range of daily hand gestures from amputees and non-amputees. METHODS: This paper proposes an attention bidirectional Convolutional Gated Recurrent Unit (Bi-ConvGRU) deep neural network for hand-gesture recognition. By training on sEMG data from both amputees and non-amputees, the model can learn to recognise a group of fine-grained hand movements. This is a significantly more challenging and underexplored area, compared to existing studies on coarse-control in lower limbs. One dimensional CNNs are initially used to extract intra-channel features. The novel use of a bidirectional sequential GRU (Bi-GRU) deep neural network allows the exploration of correlation of muscle activation among multi-channel sEMG signals from both prior and posterior time sequences. Importantly, the attention mechanism is employed following Bi-GRU layers. This enables the model to learn vital parts and feature weights, increasing robustness to bio-data noise and irregularity. Finally, we introduce the first of its kind transfer learning, demonstrating that a baseline model pre-trained with non-amputee data can be effectively refined with amputee data to build a personalised model for amputees. RESULTS: The attention Bi-ConvGRU was evaluated on the benchmark database Ninapro, and achieved an average accuracy of 88.7%, outperforming the state-of-the-art on 18 gesture recognition by 6.7%. CONCLUSIONS: To our knowledge, the developed end-to-end deep learning model is the first of its kind that enables reliable predictive decision making in short time windows (160ms). This reduced latency limits physiological awareness, enabling the potential for real-time, online and thus more intuitive bio-control of prosthetic devices for amputees.

Suppression of Transmembrane Tumor Necrosis Factor Alpha Processing by a Specific Antibody Protects Against Colitis-Associated Cancer.

Soluble tumor necrosis factor-α (sTNF-α) plays an important role in colitis-associated cancer (CAC); however, little is known about transmembrane TNF-α (tmTNF-α). Here, we observed an increase in sTNF-α mainly in colitis tissues from an azoxymethane/dextran sodium sulfate (DSS)-induced CAC mouse model whereas tmTNF-α levels were chiefly increased on epithelial cells at the tumor stage. The ratio of intracolonic tmTNF-α/sTNF-α was negatively correlated with the levels of pro-inflammatory mediators (IL-1ß, IL-6, and NO) and M1 macrophages but positively correlated with the infiltration of myeloid-derived suppressor cells, regulatory T cells, and the level of the anti-inflammatory cytokine IL-10, suggesting an anti-inflammatory effect of tmTNF-α. This effect of tmTNF-α was confirmed again by the induction of resistance to LPS in colonic epithelial cell lines NCM460 and HCoEpiC through the addition of exogenous tmTNF-α or transfection of the tmTNF-α leading sequence that lacks the extracellular segment but retains the intracellular domain of tmTNF-α. A tmTNF-α antibody was used to block tmTNF-α shedding after the first or second round of inflammation induction by DSS drinking to shift the time window of tmTNF-α expression ahead to the inflammation stage. Antibody treatment significantly alleviated inflammation and suppressed subsequent adenoma formation, accompanied by increased apoptosis. An antitumor effect was also observed when the antibody was administered at the malignant phase of CAC. Our results reveal tmTNF-α as a novel molecular marker for malignant transformation in CAC and provide a new insight into blocking the pathological process by targeting tmTNF-α processing.

Clinical Characteristics of Hemophagocytic Lymphohistiocytosis Associated with Non-Hodgkin B-Cell Lymphoma: A Multicenter Retrospective Study.

BACKGROUND: Hemophagocytic lymphohistiocytosis (HLH) associated with B-cell lymphoma is a highly aggressive disease with unclear clinical features and has no standard treatment. PATIENTS AND METHODS: We analyzed the clinical characteristics of 31 patients from two individual centers. RESULTS: The median overall survival was only 1.5 months. Both univariate and multivariate analyses, based on lymphoma or HLH-related characteristics, revealed that patients with high Epstein-Barr virus (EBV) DNA load and ≥ 2 extranodal lesions, or hypofibrinogenemia, respectively, showed significantly poorer overall survival. Interestingly, some patients with high EBV DNA load had EBV-positive natural killer (NK) and/or T cells, which may be related to the coexistence of immunodeficiency and/or chronic active EBV infection. Molecular genetics examination confirmed that 47.4% (9/19) of patients had complex karyotypes, 37.5% (3/8) of patients had TP53 deletions, and 21.34% (3/14) of patients had TP53 mutation or alteration of malignancy-related pathways, including BCR/NF-κB, JAK-STAT, and epigenetic regulatory pathways, which may provide clues to choose targets for therapy. Treatment regimens containing etoposide, anti-CD20 monoclonal antibodies, or anthracyclines improved patient prognosis (P = .0183, .025, and .0436, respectively). Patients with infections had significantly shorter survival than those without infections (P = .00019). CONCLUSION: The patients' performance status, number of extranodal lesions, high EBV DNA load, and hypofibrinogenemia are poor prognostic factors for HLH associated with B-cell lymphoma. Molecular genetic high-risk factors are of particular importance because these factors can provide information for prognosis prediction, treatment decisions, and disease surveillance.

A Deep Evaluator for Image Retargeting Quality by Geometrical and Contextual Interaction.

An image is compressed or stretched during the multidevice displaying, which will have a very big impact on perception quality. In order to solve this problem, a variety of image retargeting methods have been proposed for the retargeting process. However, how to evaluate the results of different image retargeting is a very critical issue. In various application systems, the subjective evaluation method cannot be applied on a large scale. So we put this problem in the accurate objective-quality evaluation. Currently, most of the image retargeting quality assessment algorithms use simple regression methods as the last step to obtain the evaluation result, which are not corresponding with the perception simulation in the human vision system (HVS). In this paper, a deep quality evaluator for image retargeting based on the segmented stacked AutoEnCoder (SAE) is proposed. Through the help of regularization, the designed deep learning framework can solve the overfitting problem. The main contributions in this framework are to simulate the perception of retargeted images in HVS. Especially, it trains two separated SAE models based on geometrical shape and content matching. Then, the weighting schemes can be used to combine the obtained scores from two models. Experimental results in three well-known databases show that our method can achieve better performance than traditional methods in evaluating different image retargeting results.

Perceptually Validated Cross-Renderer Analytical BRDF Parameter Remapping.

Material appearance of rendered objects depends on the underlying BRDF implementation used by rendering software packages. A lack of standards to exchange material parameters and data (between tools) means that artists in digital 3D prototyping and design, manually match the appearance of materials to a reference image. Since their effect on rendered output is often non-uniform and counter intuitive, selecting appropriate parameterisations for BRDF models is far from straightforward. We present a novel BRDF remapping technique, that automatically computes a mapping (BRDF Difference Probe) to match the appearance of a source material model to a target one. Through quantitative analysis, four user studies and psychometric scaling experiments, we validate our remapping framework and demonstrate that it yields a visually faithful remapping among analytical BRDFs. Most notably, our results show that even when the characteristics of the models are substantially different, such as in the case of a phenomenological model and a physically-based one, our remapped renderings are indistinguishable from the original source model.

A Blind Stereoscopic Image Quality Evaluator with Segmented Stacked Autoencoders Considering The Whole Visual Perception Route.

Most of the current blind stereoscopic image quality assessment (SIQA) algorithms cannot show reliable accuracy. One reason is that they do not have the deep architectures and the other reason is that they are designed on the relatively weak biological basis, compared with findings on human visual system (HVS). In this paper, we propose a Deep Edge and COlor Signal INtegrity Evaluator (DECOSINE) based on the whole visual perception route from eyes to the frontal lobe, and especially focus on edge and color signal processing in retinal ganglion cells (RGC) and lateral geniculate nucleus (LGN). Furthermore, to model the complex and deep structure of the visual cortex, Segmented Stacked Auto-encoder (S-SAE) is used, which has not utilized for SIQA before. The utilization of the S-SAE complements weakness of deep learning-based SIQA metrics that require a very long training time. Experiments are conducted on popular SIQA databases, and the superiority of DECOSINE in terms of prediction accuracy and monotonicity is proved. The experimental results show that our model about the whole visual perception route and utilization of S-SAE are effective for SIQA.

[Effect of lycopene on immunity in rats with acute lung injury].

OBJECTIVE: To investigate the effects of lycopene on T lymphocyte subpopulations and pulmonary alveolar macrophagic (PAM) functions in rats with acute lung injury (ALI). METHODS: Rats were randomly divided into the following groups. (1) Control group, (2) ALI model group, (3) Low dose group,(4) Mid dose group and (5) High dose group. Control group and ALI model group were treated with solvent of lycopene, and the other groups were gastrically incubated with lycopene. Thirty-five days later, control group were given physiological saline, ALI model group and lycopene administrated groups were injected with lipopolysaccharide (LPS) (6.0 mg/kg) to induce ALI. One hour, four hours or six hours after LPS or physiological saline challenged, abdominal aorta blood for measuring lymphocyte subpopulations and bronchoalveolar lavage fluid for measuring function of PAM were gathered respectively. RESULTS: (1) At h 1, the percentages of CD3(+), CD4(+) and CD8(+) of lycopene administrated groups compared with control group were not significantly different. At h 4, the percentage of CD4(+) was similar to that at h 1. As for the percentages of CD3(+), except high dose group [(28.8+/-9.9)%] was significantly lower, low dose, mid dose and ALI model group showed no significant difference compared with control group[(39.5+/- 4.5)%]. The percentages of CD8(+) of ALI model and lycopene administrated rats, separately (10.2+/-3.9)%, (10.3+/-2.8)%, (9.8+/-2.8)%, (10.1+/-3.5)% , had been significantly reduced compared with control group[(15.1+/-2.5)%]; between ALI model and lycopene administrated groups there was no significant difference. The instance at h 6 was the same as that at h 4. The percentage ratios of CD4(+) T-lymphocyte to CD8(+) T-lymphocyte of ALI model rats were not significantly different compared with control group or lycopene administrated groups at h 1 and h 6. At h 4, the ratio of the CD4(+) and CD8(+) in Low dose and Mid dose groups had significant difference and ALI model, high dose hadn't when they were compared with control group. (2) Lycopene increased the phagocytic function of PAMs significantly at h 1(P<0.01), the optical density of PAM of control group, ALI model group, low dose group, mid dose group, high dose group was 0.136+/-0.025, 0.215+/-0.095, 0.239+/-0.052, 0.275+/-0.068 and 0.297+/-0.049; what happened at h 4 was similar to that at h 1; Phagocytic function of PAM of lycopene administrated groups was increased compared with control group. (3) The concentrations of tumor necrosis factor-alpha (TNF-alpha) in control group, ALI model group, low dose group, mid dose group, high dose groups were 1.50+/-0.30, 1.87+/-0.30, 1.76+/-0.40, 1.74+/- 0.38,1.62+/-0.35 microg/L;and those of IL-8 were 0.82+/-0.08, 0.99+/-0.14, 0.82+/-0.16, 0.84+/-0.16, 0.83+/-0.11 microg/L. The concentrations of TNF-alpha and interleukin-8 (IL-8) in BALF were decreased by lycopene, especially the levels of IL-8 were reduced significantly. CONCLUSION: Lycopene might attenuate lipopolysaccharide-induced impairment of lungs and improve ALI prognosis by increasing the phagocytic function of PAMs significantly and restraining the secretion of TNF-alpha and IL-8.

Applying machine learning to identify autistic adults using imitation: An exploratory study.

Autism spectrum condition (ASC) is primarily diagnosed by behavioural symptoms including social, sensory and motor aspects. Although stereotyped, repetitive motor movements are considered during diagnosis, quantitative measures that identify kinematic characteristics in the movement patterns of autistic individuals are poorly studied, preventing advances in understanding the aetiology of motor impairment, or whether a wider range of motor characteristics could be used for diagnosis. The aim of this study was to investigate whether data-driven machine learning based methods could be used to address some fundamental problems with regard to identifying discriminative test conditions and kinematic parameters to classify between ASC and neurotypical controls. Data was based on a previous task where 16 ASC participants and 14 age, IQ matched controls observed then imitated a series of hand movements. 40 kinematic parameters extracted from eight imitation conditions were analysed using machine learning based methods. Two optimal imitation conditions and nine most significant kinematic parameters were identified and compared with some standard attribute evaluators. To our knowledge, this is the first attempt to apply machine learning to kinematic movement parameters measured during imitation of hand movements to investigate the identification of ASC. Although based on a small sample, the work demonstrates the feasibility of applying machine learning methods to analyse high-dimensional data and suggest the potential of machine learning for identifying kinematic biomarkers that could contribute to the diagnostic classification of autism.

Transmembrane tumor necrosis factor-α promotes the recruitment of MDSCs to tumor tissue by upregulating CXCR4 expression via TNFR2.

Myeloid-derived suppressor cells (MDSCs) accumulated in tumor sites promote immune evasion. We found that TNFR deficiency-induced rejection of transplanted tumor was accompanied with markedly decreased accumulation of MDSCs. However, the mechanism(s) behind this phenomenon is not completely understood. Here, we demonstrated that TNFR deficiency did not affect the amount of MDSCs in bone marrow (BM), but decreased accumulation of Gr-1+CD11b+ MDSCs in the spleen and tumor tissues. The chemotaxis of Tnfr-/- MDSCs was prominently decreased in response to both tumor cell culture supernatants and tumor tissue homogenates from Tnfr-/- and wild-type mice, indicating an effect of TNFR signaling on chemokine receptor expression in MDSCs. We used real-time PCR to detect gene expression for several chemokine receptors in MDSCs from BM and found that CXCR4 was the most affected molecule at the transcriptional level in Tnfr-/- MDSCs. Neutralizing CXCR4 in wild-type MDSCs by a specific antibody blocked their chemotactic migration. Interestingly, it was tmTNF-α, but not sTNF-α, that induced CXCR4 expression in MDSCs. This effect of tmTNF-α was totally blocked in TNFR2-/- but not in TNFR1-/- MDSCs, and partially inhibited by PDTC or SB203580, an inhibitor of NF-κB or p38 MAPK pathway, respectively. Adoptive transfer of wild-type MDSCs restored MDSCs accumulation in tumors of Tnfr-/- mice, but this could be partially blocked by treatment with a CXCR4 inhibitor AMD3100. Our data suggest that tmTNF-α upregulates CXCR4 expression that promotes chemotaxis of MDSCs to tumor, and give a new insight into a novel mechanism by which tmTNF-α facilitates tumor immune evasion.

Retinal area detector from scanning laser ophthalmoscope (SLO) images for diagnosing retinal diseases.

Scanning laser ophthalmoscopes (SLOs) can be used for early detection of retinal diseases. With the advent of latest screening technology, the advantage of using SLO is its wide field of view, which can image a large part of the retina for better diagnosis of the retinal diseases. On the other hand, during the imaging process, artefacts such as eyelashes and eyelids are also imaged along with the retinal area. This brings a big challenge on how to exclude these artefacts. In this paper, we propose a novel approach to automatically extract out true retinal area from an SLO image based on image processing and machine learning approaches. To reduce the complexity of image processing tasks and provide a convenient primitive image pattern, we have grouped pixels into different regions based on the regional size and compactness, called superpixels. The framework then calculates image based features reflecting textural and structural information and classifies between retinal area and artefacts. The experimental evaluation results have shown good performance with an overall accuracy of 92%.

Study on the Relationship between Lipoprotein(a) Receptor and LDL Receptor.

Lp(a) receptor and LDL receptor on rhesus monkey liver cellular membrane were studied by Western blotting, to investigate whether Lp(a) and LDL metabolize through the same route. The experiment demonstrated Lp(a) receptor ( 300kD) and LDL receptor ( 185kD) to be different kinds of receptors. The result reveals that Lp(a) has its own metabolic pathway.

Articulated pose identification with sparse point features.

We propose a general algorithm for identifying an arbitrary pose of an articulated subject with sparse point features. The algorithm aims to identify a one-to-one correspondence between a model point-set and an observed point-set taken from freeform motion of the articulated subject. We avoid common assumptions such as pose similarity or small motions with respect to the model, and assume no prior knowledge from which to infer an initial or partial correspondence between the two point-sets. The algorithm integrates local segment-based correspondences under a set of affine transformations, and a global hierarchical search strategy. Experimental results, based on synthetic pose and real-world human motion data demonstrate the ability of the algorithm to perform the identification task. Reliability is increasingly compromised with increasing data noise and segmental distortion, but the algorithm can tolerate moderate levels. This work contributes to establishing a crucial self-initializing identification in model-based point-feature tracking for articulated motion.

Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review.

Glaucoma is a group of eye diseases that have common traits such as, high eye pressure, damage to the Optic Nerve Head and gradual vision loss. It affects peripheral vision and eventually leads to blindness if left untreated. The current common methods of pre-diagnosis of Glaucoma include measurement of Intra-Ocular Pressure (IOP) using Tonometer, Pachymetry, Gonioscopy; which are performed manually by the clinicians. These tests are usually followed by Optic Nerve Head (ONH) Appearance examination for the confirmed diagnosis of Glaucoma. The diagnoses require regular monitoring, which is costly and time consuming. The accuracy and reliability of diagnosis is limited by the domain knowledge of different ophthalmologists. Therefore automatic diagnosis of Glaucoma attracts a lot of attention. This paper surveys the state-of-the-art of automatic extraction of anatomical features from retinal images to assist early diagnosis of the Glaucoma. We have conducted critical evaluation of the existing automatic extraction methods based on features including Optic Cup to Disc Ratio (CDR), Retinal Nerve Fibre Layer (RNFL), Peripapillary Atrophy (PPA), Neuroretinal Rim Notching, Vasculature Shift, etc., which adds value on efficient feature extraction related to Glaucoma diagnosis.

Estimating skeletal muscle fascicle curvature from B-mode ultrasound image sequences.

We address the problem of tracking in vivo muscle fascicle shape and length changes using ultrasound video sequences. Quantifying fascicle behavior is required to improve understanding of the functional significance of a muscle's geometric properties. Ultrasound imaging provides a noninvasive means of capturing information on fascicle behavior during dynamic movements; to date however, computational approaches to assess such images are limited. Our approach to the problem is novel because we permit fascicles to take up nonlinear shape configurations. We achieve this using a Bayesian tracking framework that is: 1) robust, conditioning shape estimates on the entire history of image observations; and 2) flexible, enforcing only a very weak Gaussian Process shape prior that requires fascicles to be locally smooth. The method allows us to track and quantify fascicle behavior in vivo during a range of movements, providing insight into dynamic changes in muscle geometric properties which may be linked to patterns of activation and intramuscular forces and pressures.