Prognostic correlation between specialized capillary endothelial cells and lung adenocarcinoma.

Background: In-depth analysis of the functional changes occurring in endothelial cells (ECs) involved in capillary formation can help to elucidate the mechanism of tumour vascular growth. Methods: Appropriate datasets were retrieved from the GEO database to obtain single-cell data on LUAD samples and adjacent normal tissue samples. ECs were selected by an automatic annotation program in R and further subdivided based on reported EC marker genes. Functional changes in different types of capillary ECs were then visualized, and the concrete expression was classified by genetic data in the TCGA. Finally, a prognostic model was constructed to predict immunoinfiltration status, survival and drug therapy effects. Results: The LUAD data contained in the GSE183219 dataset were suitable for our analysis. After dimensionality reduction analysis and cell annotation, EC general capillary and EC aerocyte subsets as capillary specialized phenotypes showed a series of functional changes in tumour samples, with a total of 108 genes found to undergo functional changes. Use of CellPhoneDB revealed a close interaction of activity between ECs. After integration of TCGA, GSE68465 and GSE11969 datasets, the genes obtained were analysed by cluster analysis and risk model construction, identifying 8 genes. Drug sensitivity, immune cell and molecular differences can be accurately predicted. Conclusions: EC general capillary and EC aerocyte subsets are recognized capillary ECs in the tumour microenvironment, and the functional changes between them are relevant to the prognosis and treatment of LUAD patients and have the potential to be used in target therapy.

Prognosis Forecast of Re-Irradiation for Recurrent Nasopharyngeal Carcinoma Based on Deep Learning Multi-Modal Information Fusion.

Radiation therapy is the primary treatment for recurrent nasopharyngeal carcinoma. However, it may induce necrosis of the nasopharynx, leading to severe complications such as bleeding and headache. Therefore, forecasting necrosis of the nasopharynx and initiating timely clinical intervention has important implications for reducing complications caused by re-irradiation. This research informs clinical decision-making by making predictions on re-irradiation of recurrent nasopharyngeal carcinoma using deep learning multi-modal information fusion between multi-sequence nuclear magnetic resonance imaging and plan dose. Specifically, we assume that the hidden variables of model data can be divided into two categories: task-consistency and task-inconsistency. The task-consistency variables are characteristic variables contributing to target tasks, while the task-inconsistency variables are not apparently helpful. These modal characteristics are adaptively fused when the relevant tasks are expressed through the construction of supervised classification loss and self-supervised reconstruction loss. The cooperation of supervised classification loss and self-supervised reconstruction loss simultaneously reserves the information of characteristic space and controls potential interference simultaneously. Finally, multi-modal fusion effectively fuses information through an adaptive linking module. We evaluated this method on a multi-center dataset. and found the prediction based on multi-modal features fusion outperformed predictions based on single-modal, partial modal fusion or traditional machine learning methods.

FDCT: Fusion-Guided Dual-View Consistency Training for semi-supervised tissue segmentation on MRI.

Accurate tissue segmentation on MRI is important for physicians to make diagnosis and treatment for patients. However, most of the models are only designed for single-task tissue segmentation, and tend to lack generality to other MRI tissue segmentation tasks. Not only that, the acquisition of labels is time-consuming and laborious, which remains a challenge to be solved. In this study, we propose the universal Fusion-Guided Dual-View Consistency Training(FDCT) for semi-supervised tissue segmentation on MRI. It can obtain accurate and robust tissue segmentation for multiple tasks, and alleviates the problem of insufficient labeled data. Especially, for building bidirectional consistency, we feed dual-view images into a single-encoder dual-decoder structure to obtain view-level predictions, then put them into a fusion module to generate image-level pseudo-label. Moreover, to improve boundary segmentation quality, we propose the Soft-label Boundary Optimization Module(SBOM). We have conducted extensive experiments on three MRI datasets to evaluate the effectiveness of our method. Experimental results demonstrate that our method outperforms the state-of-the-art semi-supervised medical image segmentation methods.

Long Noncoding RNA IPW Is a Novel Diagnostic and Predictive Biomarker in Lung Adenocarcinoma.

Background: Long non-coding RNAs (lncRNAs), as functional components of the human genome, are widely involved in cell proliferation, differentiation, apoptosis, migration and invasion by several types of cancer, including lung cancer. However, the role of lncRNA IPW in lung cancer has not been fully elucidated. The aim of the present study was to characterize the expression and clinical significance of lncRNA IPW in lung cancer. Materials and Methods: IPW expression in tumor samples and cells was assessed using the Oncomine and Cancer Cell Line Encyclopedia (CCLE) database, respectively. Reverse transcription-quantitative polymerase chain reaction (RT-qPCR) was used to determine IPW expression and microRNA-370 (miR-370) expression. The clinical significance of IPW was evaluated by Chi-square test and Kaplan-Meier pot analyses. In addition, the sulforhodamine blue (SRB) assays was used to detect cell proliferation in IPW-overexpressed A549 cells. Results: IPW expression was significantly down-regulated in NSCLC tissues and was significantly associated with many clinicopathological data, including smoking history, differentiation, pT factor, pN factor and pTNM stage (p < 0.05). Decreased IPW expression was correlated with poor survival (p = 1.5e-05) and was positively associated with first progression in patients with lung adenocarcinoma (p = 0.00041). Furthermore, IPW could inhibit A549 cell proliferation and expression of miR-370. High miR-370 expression was associated with poor overall survival (OS) among lung adenocarcinoma patients (p = 0.045). Conclusions: These findings provide evidence that down-regulation of IPW might be considered as a beneficial prognostic biomarker and that it could potentially serve as therapeutic target in lung adenocarcinoma.

CT synthesis from MR in the pelvic area using Residual Transformer Conditional GAN.

Magnetic resonance (MR) image-guided radiation therapy is a hot topic in current radiation therapy research, which relies on MR to generate synthetic computed tomography (SCT) images for radiation therapy. Convolution-based generative adversarial networks (GAN) have achieved promising results in synthesizing CT from MR since the introduction of deep learning techniques. However, due to the local limitations of pure convolutional neural networks (CNN) structure and the local mismatch between paired MR and CT images, particularly in pelvic soft tissue, the performance of GAN in synthesizing CT from MR requires further improvement. In this paper, we propose a new GAN called Residual Transformer Conditional GAN (RTCGAN), which exploits the advantages of CNN in local texture details and Transformer in global correlation to extract multi-level features from MR and CT images. Furthermore, the feature reconstruction loss is used to further constrain the image potential features, reducing over-smoothing and local distortion of the SCT. The experiments show that RTCGAN is visually closer to the reference CT (RCT) image and achieves desirable results on local mismatch tissues. In the quantitative evaluation, the MAE, SSIM, and PSNR of RTCGAN are 45.05 HU, 0.9105, and 28.31 dB, respectively. All of them outperform other comparison methods, such as deep convolutional neural networks (DCNN), Pix2Pix, Attention-UNet, WPD-DAGAN, and HDL.

Macular Microvascular Density as a Diagnostic Biomarker for Alzheimer's Disease.

BACKGROUND: Some previous studies showed abnormal pathological and vascular changes in the retina of patients with Alzheimer's disease (AD). However, whether retinal microvascular density is a diagnostic indicator for AD remains unclear. OBJECTIVE: This study evaluated the macular vessel density (m-VD) in the superficial capillary plexus and fovea avascular zone (FAZ) area in AD, explored their correlations with clinical parameters, and finally confirmed an optimal machine learning model for AD diagnosis. METHODS: 77 patients with AD and 145 healthy controls (HCs) were enrolled. The m-VD and the FAZ area were measured using optical coherence tomography angiography (OCTA) in all participants. Additionally, AD underwent neuropsychological assessment, brain magnetic resonance imaging scan, cerebrospinal fluid (CSF) biomarker detection, and APOE ɛ4 genotyping. Finally, the performance of machine learning algorithms based on the OCTA measurements was evaluated by Python programming language. RESULTS: The m-VD was noticeably decreased in AD compared with HCs. Moreover, m-VD in the fovea, superior inner, inferior inner, nasal inner subfields, and the whole inner ring declined significantly in mild AD, while it was more serious in moderate/severe AD. However, no significant difference in the FAZ was noted between AD and HCs. Furthermore, we found that m-VD exhibited a significant correlation with cognitive function, medial temporal atrophy and Fazekas scores, and APOE ɛ4 genotypes. No significant correlations were observed between m-VD and CSF biomarkers. Furthermore, results revealed the Adaptive boosting algorithm exhibited the best diagnostic performance for AD. CONCLUSION: Macular vascular density could serve as a diagnostic biomarker for AD.

Machine learning based on Optical Coherence Tomography images as a diagnostic tool for Alzheimer's disease.

AIMS: We mainly evaluate retinal alterations in Alzheimer's disease (AD) patients, investigate the associations between retinal changes with AD biomarkers, and explore an optimal machine learning (ML) model for AD diagnosis based on retinal thickness. METHODS: A total of 159 AD patients and 299 healthy controls were enrolled. The retinal parameters of each participant were measured using optical coherence tomography (OCT). Additionally, cognitive impairment severity, brain atrophy, and cerebrospinal fluid (CSF) biomarkers were measured in AD patients. RESULTS: AD patients demonstrated a significant decrease in the average, superior, and inferior quadrant peripapillary retinal nerve fiber layer, macular retinal nerve fiber layer, ganglion cell layer (GCL), inner plexiform layer (IPL) thicknesses, as well as total macular volume (TMV) (all p < 0.05). Moreover, TMV was positively associated with Mini-Mental State Examination and Montreal Cognitive Assessment scores, IPL thickness was correlated negatively with the medial temporal lobe atrophy score, and the GCL thickness was positively correlated with CSF Aß42 /Aß40 and negatively associated with p-tau level. Based on the significantly decreased OCT variables between both groups, the XGBoost algorithm exhibited the best diagnostic performance for AD, whose four references, including accuracy, area under the curve, f1 score, and recall, ranged from 0.69 to 0.74. Moreover, the macular retinal thickness exhibited an absolute superiority for AD diagnosis compared with other enrolled variables in all ML models. CONCLUSION: We identified the retinal alterations in AD patients and found that macular thickness and volume were associated with AD severity and biomarkers. Furthermore, we confirmed that OCT combined with ML could serve as a potential diagnostic tool for AD.

Dual-consistency semi-supervision combined with self-supervision for vessel segmentation in retinal OCTA images.

Optical coherence tomography angiography(OCTA) is an advanced noninvasive vascular imaging technique that has important implications in many vision-related diseases. The automatic segmentation of retinal vessels in OCTA is understudied, and the existing segmentation methods require large-scale pixel-level annotated images. However, manually annotating labels is time-consuming and labor-intensive. Therefore, we propose a dual-consistency semi-supervised segmentation network incorporating multi-scale self-supervised puzzle subtasks(DCSS-Net) to tackle the challenge of limited annotations. First, we adopt a novel self-supervised task in assisting semi-supervised networks in training to learn better feature representations. Second, we propose a dual-consistency regularization strategy that imposed data-based and feature-based perturbation to effectively utilize a large number of unlabeled data, alleviate the overfitting of the model, and generate more accurate segmentation predictions. Experimental results on two OCTA retina datasets validate the effectiveness of our DCSS-Net. With very little labeled data, the performance of our method is comparable with fully supervised methods trained on the entire labeled dataset.

Predicting Differences in Treatment Response and Survival Time of Lung Adenocarcinoma Patients Based on a Prognostic Risk Model of Glycolysis-Related Genes.

Background: Multiple factors influence the survival of patients with lung adenocarcinoma (LUAD). Specifically, the therapeutic outcomes of treatments and the probability of recurrence of the disease differ among patients with the same stage of LUAD. Therefore, effective prognostic predictors need to be identified. Methods: Based on the tumor mutation burden (TMB) data obtained from The Cancer Genome Atlas (TCGA) database, LUAD patients were divided into high and low TMB groups, and differentially expressed glycolysis-related genes between the two groups were screened. The least absolute shrinkage and selection operator (LASSO) and Cox regression were used to obtain a prognostic model. A receiver operating characteristic (ROC) curve and a calibration curve were generated to evaluate the nomogram that was constructed based on clinicopathological characteristics and the risk score. Two data sets (GSE68465 and GSE11969) from the Gene Expression Omnibus (GEO) were used to verify the prognostic performance of the gene. Furthermore, differences in immune cell distribution, immune-related molecules, and drug susceptibility were assessed for their relationship with the risk score. Results: We constructed a 5-gene signature (FKBP4, HMMR, B4GALT1, SLC2A1, STC1) capable of dividing patients into two risk groups. There was a significant difference in overall survival (OS) times between the high-risk group and the low-risk group (p < 0.001), with the low-risk group having a better survival outcome. Through multivariate Cox analysis, the risk score was confirmed to be an independent prognostic factor (HR = 2.709, 95% CI = 1.981-3.705, p < 0.001), and the ROC curve and nomogram exhibited accurate prediction performance. Validation of the data obtained in the GEO database yielded similar results. Furthermore, there were significant differences in sensitivity to immunotherapy, cisplatin, paclitaxel, gemcitabine, docetaxel, gefitinib, and erlotinib between the low-risk and high-risk groups. Conclusion: Our results reveal that glycolysis-related genes are feasible predictors of survival and the treatment response of patients with LUAD.

The macular inner plexiform layer thickness as an early diagnostic indicator for Parkinson's disease.

Whether structural alterations of intraretinal layers are indicators for the early diagnosis of Parkinson's disease (PD) remains unclear. We assessed the retinal layer thickness in different stages of PD and explored whether it can be an early diagnostic indicator for PD. In total, 397 [131, 146, and 120 with Hoehn-Yahr I (H-Y I), H-Y II, and H-Y III stages, respectively] patients with PD and 427 healthy controls (HCs) were enrolled. The peripapillary retinal nerve fiber layer (pRNFL), total macular retinal thickness (MRT), and macular volume (TMV) were measured by high-definition optical coherence tomography, and the macular intraretinal thickness was analyzed by the Iowa Reference Algorithms. As a result, the PD group had a significantly lower average, temporal quadrant pRNFL, MRT, and TMV than the HCs group (all p < 0.001). Moreover, the ganglion cell layer (GCL), inner plexiform layer (IPL), and outer nuclear layer were thinner in patients with PD with H-Y I, and significantly decreased as the H-Y stage increased. In addition, we observed that GCL and IPL thicknesses were both correlated with Movement Disorder Society-Unified Parkinson's Disease Rating Scale III (MDS-UPDRS III) scores and non-motor symptoms assessment scores. Furthermore, macular IPL thickness in the superior inner (SI) quadrant (IPL-SI) had the best diagnostic performance in patients with PD with H-Y I versus HCs, with a sensitivity and specificity of 75.06% and 81.67%, respectively. In conclusion, we confirmed the retinal structure was significantly altered in patients with PD in different clinical stages, and that GCL and IPL changes occurred during early PD disease and were correlated with MDS-UPDRS III scores and non-motor symptoms assessment scores. Furthermore, macular IPL-SI thickness might be performed as an early diagnostic indicator for PD.

Diagnosing glaucoma on imbalanced data with self-ensemble dual-curriculum learning.

Glaucoma diagnosis often suffers from two types of data imbalances: 1) class imbalance, i.e., the non-glaucoma majority cases occupy most of the data; 2) rare cases, i.e., few cases present the uncommon retinopathy e.g., bayoneting or physiologic cupping. This dual-imbalances make glaucoma diagnosis model easy to be dominated by the majority cases but cannot correctly classify the minority and/or rare ones. In this paper, we propose an adaptive re-balancing strategy in the feature space, Self-Ensemble Dual-Curriculum learning (SEDC), to improve the glaucoma diagnosis on imbalanced data by augmenting feature distribution with feature distilling and feature re-weighting. Firstly, the self-ensembling (SEL) is developed to reinforce the discriminative ability of feature representations for the minority class and rare cases by distilling the features learned from the abundant majority cases. Secondly, the dual-curriculum (DCL) is designed to adaptively re-weight the imbalanced data in the feature space to learn a balanced decision function for accurate glaucoma diagnosis. Benefiting from feature distilling and re-weighting, the proposed SEDC fairly represents fundus images, regardless of the majority or rare cases, by augmenting the feature distribution to obtains the optimal decision boundary for accurate glaucoma diagnosis on the imbalanced dataset. Experimental results on three challenging glaucoma datasets show that our SEDC successfully delivers accurate glaucoma diagnosis by the adaptive re-balancing strategy, with the average mean value of Accuracy 0.9712, Sensitivity 0.9520, Specificity 0.9816, AUC 0.9928, F2-score 0.9547. Ablation and comparison studies demonstrate that our method outperforms state-of-the-art methods and traditional re-balancing strategies. The experiment also shows that the adaptive re-balancing strategy proposed in our method provides a more effective training approach with optimal convergence performance. It endows our SEDC a great advantage to handle the disease diagnosis on imbalanced data distribution.

The Lung Adenocarcinoma Microenvironment Mining and Its Prognostic Merit.

BACKGROUND: As a common pathological type of lung cancer, lung adenocarcinoma (LUAD) is mainly treated by surgery, chemotherapy, targeted therapy and radiotherapy. Although a relatively mature treatment system has been established, there are few studies on the microenvironment of LUAD. MATERIAL AND METHODS: The immune and stromal scores of patients from the LUAD cohort in the TCGA database were obtained by using ESTIMATE. The relationship of immune and stromal scores with the clinicopathological characteristics and overall survival of LUAD patients was assessed by R. GO, KEGG and Cox regression analyses were employed to analyze intersecting genes and to identify reliable prognostic markers. The identified genes were also analyzed in the GEPIA database to assess their correlations with survival, and these relationships were verified with the Kaplan-Meier Plotter database. RESULTS: The immune score was related to the survival time and tumor topography of LUAD patients. There was a significant correlation between stromal score and tumor metastasis. Through multivariate analysis, stage (HR = 1.640, 95% CI = 1.019-2.642, P = 0.042) and risk score (HR = 1.036, 95% CI = 1.026-1.046, P < 0.001). The genes (ARHGAP15, BTLA, CASS4, CLECL1, FAM129C, STAP1, TESPA1, and S100P) showed credible prognostic value in LUAD patients in TCGA through GEPIA database online analysis and verification in the Kaplan-Meier plotter database. CONCLUSIONS: In the microenvironment of lung adenocarcinoma, the differentially expressed genes screened by immune score and stromal score have certain value in evaluating the survival/prognosis of patients, as well as the invasion and progression of tumors.

Direct Cup-to-Disc Ratio Estimation for Glaucoma Screening via Semi-Supervised Learning.

Glaucoma is a chronic eye disease that leads to irreversible vision loss. The Cup-to-Disc Ratio (CDR) serves as the most important indicator for glaucoma screening and plays a significant role in clinical screening and early diagnosis of glaucoma. In general, obtaining CDR is subjected to measuring on manually or automatically segmented optic disc and cup. Despite great efforts have been devoted, obtaining CDR values automatically with high accuracy and robustness is still a great challenge due to the heavy overlap between optic cup and neuroretinal rim regions. In this paper, a direct CDR estimation method is proposed based on the well-designed semi-supervised learning scheme, in which CDR estimation is formulated as a general regression problem while optic disc/cup segmentation is cancelled. The method directly regresses CDR value based on the feature representation of optic nerve head via deep learning technique while bypassing intermediate segmentation. The scheme is a two-stage cascaded approach comprised of two phases: unsupervised feature representation of fundus image with a convolutional neural networks (MFPPNet) and CDR value regression by random forest regressor. The proposed scheme is validated on the challenging glaucoma dataset Direct-CSU and public ORIGA, and the experimental results demonstrate that our method can achieve a lower average CDR error of 0.0563 and a higher correlation of around 0.726 with measurement before manual segmentation of optic disc/cup by human experts. Our estimated CDR values are also tested for glaucoma screening, which achieves the areas under curve of 0.905 on dataset of 421 fundus images. The experiments show that the proposed method is capable of state-of-the-art CDR estimation and satisfactory glaucoma screening with calculated CDR value.

Clinical Interpretable Deep Learning Model for Glaucoma Diagnosis.

Despite the potential to revolutionise disease diagnosis by performing data-driven classification, clinical interpretability of ConvNet remains challenging. In this paper, a novel clinical interpretable ConvNet architecture is proposed not only for accurate glaucoma diagnosis but also for the more transparent interpretation by highlighting the distinct regions recognised by the network. To the best of our knowledge, this is the first work of providing the interpretable diagnosis of glaucoma with the popular deep learning model. We propose a novel scheme for aggregating features from different scales to promote the performance of glaucoma diagnosis, which we refer to as M-LAP. Moreover, by modelling the correspondence from binary diagnosis information to the spatial pixels, the proposed scheme generates glaucoma activations, which bridge the gap between global semantical diagnosis and precise location. In contrast to previous works, it can discover the distinguish local regions in fundus images as evidence for clinical interpretable glaucoma diagnosis. Experimental results, performed on the challenging ORIGA datasets, show that our method on glaucoma diagnosis outperforms state-of-the-art methods with the highest AUC (0.88). Remarkably, the extensive results, optic disc segmentation (dice of 0.9) and local disease focus localization based on the evidence map, demonstrate the effectiveness of our methods on clinical interpretability.

Multi-indices quantification of optic nerve head in fundus image via multitask collaborative learning.

Multi-indices quantification of optic nerve head (ONH), measuring ONH appearance with multiple types of indices simultaneously from fundus images, is the most clinically significant tasks for accurate ONH assessment and ophthalmic disease diagnosis. However, no attempt has been reported due to its challenges of the large variation of fundus appearance across patients, heavy overlap and extremely weak contrast between optic nerve head areas. In this paper, we propose a multitask collaborative learning framework (MCL-Net) for multi-indices ONH quantification. The proposed MCL-Net, a two-branch neural network, first obtains expressive shared and task-specific representations with the backbone network and its two branches; then models the feature exchanges and aggregations between two branches with a well-designed feature interaction module (FIM) to promote each other collaboratively. After that, it estimates multiple types of ONH indices under a multitask ensemble module (MEM) that is capable of learning aggregation of multiple outputs automatically. Therefore, the proposed MCL-Net is consisted of the feature representation, inter-task feature interaction, dual-branch task-specific prediction, and multitask quantification ensemble, which establish an effective framework which takes full advantages of segmentation and estimation tasks for multi-indices ONH quantification. Rather than the low-level feature sharing and individual prediction, the proposed MCL-Net collaboratively learns an optimal combination of shared and task-specific representation, as well as the aggregated prediction, therefore leads to accurate quantification of ONH with multiple types of indices. Experimental results on the dataset of 650 fundus images show that MCL-Net successfully delivers accurate quantification of all the three types of ONH indices, with average mean absolute error of 0.98 ±â€¯0.20, 0.97 ±â€¯0.16, 1.19 ±â€¯0.18, as well as average correlation coefficient of 0.699, 0.708 and 0.691, for diameters, whole areas and regional areas, respectively. In addition, the experiments demonstrate that quantitative indices obtained by our method provide more effective glaucoma diagnosis with AUC of 0.8698. This endows our proposed MCL-Net a great potential in clinical assessment from focal to global for ophthalmic disease diagnosis.

A novel glaucomatous representation method based on Radon and wavelet transform.

BACKGROUND: Glaucoma is an irreversible eye disease caused by the optic nerve injury. Therefore, it usually changes the structure of the optic nerve head (ONH). Clinically, ONH assessment based on fundus image is one of the most useful way for glaucoma detection. However, the effective representation for ONH assessment is a challenging task because its structural changes result in the complex and mixed visual patterns. METHOD: We proposed a novel feature representation based on Radon and Wavelet transform to capture these visual patterns. Firstly, Radon transform (RT) is used to map the fundus image into Radon domain, in which the spatial radial variations of ONH are converted to a discrete signal for the description of image structural features. Secondly, the discrete wavelet transform (DWT) is utilized to capture differences and get quantitative representation. Finally, principal component analysis (PCA) and support vector machine (SVM) are used for dimensionality reduction and glaucoma detection. RESULTS: The proposed method achieves the state-of-the-art detection performance on RIMONE-r2 dataset with the accuracy and area under the curve (AUC) at 0.861 and 0.906, respectively. CONCLUSION: In conclusion, we showed that the proposed method has the capacity as an effective tool for large-scale glaucoma screening, and it can provide a reference for the clinical diagnosis on glaucoma.

Retinal vessel optical coherence tomography images for anemia screening.

Anemia is a disease that leads to low oxygen carrying capacity in the blood. Early detection of anemia is critical for the diagnosis and treatment of blood diseases. We find that retinal vessel optical coherence tomography (OCT) images of patients with anemia have abnormal performance because the internal material of the vessel absorbs light. In this study, an automatic anemia screening method based on retinal vessel OCT images is proposed. The method consists of seven steps, namely, denoising, region of interest (ROI) extraction, layer segmentation, vessel segmentation, feature extraction, feature dimensionality reduction, and classification. We propose gradient and threshold algorithm for ROI extraction and improve region growing algorithm based on adaptive seed point for vessel segmentation. We also conduct a statistical analysis of the correlation between hemoglobin concentration and intravascular brightness and vascular shadow in OCT images before feature extraction. Eighteen statistical features and 118 texture features are extracted for classification. This study is the first to use retinal vessel OCT images for anemia screening. Experimental results demonstrate the accuracy of the proposed method is 0.8358, which indicates that the method has clinical potential for anemia screening. Graphical abstract.

Retinal vessel segmentation in colour fundus images using Extreme Learning Machine.

Attributes of the retinal vessel play important role in systemic conditions and ophthalmic diagnosis. In this paper, a supervised method based on Extreme Learning Machine (ELM) is proposed to segment retinal vessel. Firstly, a set of 39-D discriminative feature vectors, consisting of local features, morphological features, phase congruency, Hessian and divergence of vector fields, is extracted for each pixel of the fundus image. Then a matrix is constructed for pixel of the training set based on the feature vector and the manual labels, and acts as the input of the ELM classifier. The output of classifier is the binary retinal vascular segmentation. Finally, an optimization processing is implemented to remove the region less than 30 pixels which is isolated from the retinal vascilar. The experimental results testing on the public Digital Retinal Images for Vessel Extraction (DRIVE) database demonstrate that the proposed method is much faster than the other methods in segmenting the retinal vessels. Meanwhile the average accuracy, sensitivity, and specificity are 0.9607, 0.7140 and 0.9868, respectively. Moreover the proposed method exhibits high speed and robustness on a new Retinal Images for Screening (RIS) database. Therefore it has potential applications for real-time computer-aided diagnosis and disease screening.

Orientation Histogram-Based Center-Surround Interaction: An Integration Approach for Contour Detection.

Contour is a critical feature for image description and object recognition in many computer vision tasks. However, detection of object contour remains a challenging problem because of disturbances from texture edges. This letter proposes a scheme to handle texture edges by implementing contour integration. The proposed scheme integrates structural segments into contours while inhibiting texture edges with the help of the orientation histogram-based center-surround interaction model. In the model, local edges within surroundings exert a modulatory effect on central contour cues based on the co-occurrence statistics of local edges described by the divergence of orientation histograms in the local region. We evaluate the proposed scheme on two well-known challenging boundary detection data sets (RuG and BSDS500). The experiments demonstrate that our scheme achieves a high [Formula: see text]-measure of up to 0.74. Results show that our scheme achieves integrating accurate contour while eliminating most of texture edges, a novel approach to long-range feature analysis.

Quantitation of rare circulating tumor cells by folate receptor α ligand-targeted PCR in bladder transitional cell carcinoma and its potential diagnostic significance.

Numerous attempts for detection of circulating tumor cells (CTC) have been made to develop reliable assays for early diagnosis of cancers. In this study, we validated the application of folate receptor α (FRα) as the tumor marker to detect CTC through tumor-specific ligand PCR (LT-PCR) and assessed its utility for diagnosis of bladder transitional cell carcinoma (TCC). Immunohistochemistry for FRα was performed on ten bladder TCC tissues. Enzyme-linked immunosorbent assay (ELISA) for FRα was performed on both urine and serum specimens from bladder TCC patients (n = 64 and n = 20, respectively) and healthy volunteers (n = 20 and n = 23, respectively). Western blot analysis and qRT-PCR were performed to confirm the expression of FRα in bladder TCC cells. CTC values in 3-mL peripheral blood were measured in 57 bladder TCC patients, 48 healthy volunteers, and 15 subjects with benign urologic pathologies by the folate receptor α ligand-targeted PCR. We found that FRα protein was overexpressed in both bladder TCC cells and tissues. The levels of FRα mRNA were also much higher in bladder cancer cell lines 5637 and SW780 than those of leukocyte. Values of FRα were higher in both serum and urine specimens of bladder TCC patients than those of control. CTC values were also higher in 3-mL peripheral blood of bladder TCC patients than those of control (median 26.5 Cu/3 mL vs 14.0 Cu/3 mL). Area under the receiver operating characteristic (ROC) curve for bladder TCC detection was 0.819, 95 % CI (0.738-0.883). At the cutoff value of 15.43 Cu/3 mL, the sensitivity and the specificity for detecting bladder cancer are 82.14 and 61.9 %, respectively. We concluded that quantitation of CTCs through FRα ligand-PCR could be a promising method for noninvasive diagnosis of bladder TCC.