A Novel Retinal Identification System

Diabetic retinopathy (DR) is the retinal disease caused by diabetes that involves damage to the small blood vessels in the posterior of the eye. Early stage of DR may not cause symptoms. But the progression of the disease leads to the proliferative stage. This causes leakage of protein and blood in the retina. Blood vessel segmentation is a helpful tool in the treatment of diabetic retinopathy. Many studies have been carried out in the last decade in order to derive an accurate blood vessel detection and segmentation in retinal images because vascular anomalies are one of the strongest signs of DR. An user friendly graphical user interface (GUI) which is MATLAB based that segments the blood vessels by means of adaptive median thresholding is proposed in this paper. From the segmented image, various features of blood vessels like area, mean, standard deviation, energy, entropy and histogram are calculated, in order to distinguish the image as normal or abnormal. With respect to the ground truth, performance measures like accuracy, specificity and sensitivity are calculated. The GUI is implemented using MATLAB and the feature parameters are calculated. The average accuracy, specificity and sensitivity were found to be 0.95, 0.99 and 0.77 respectively for drive images using Adaptive median thresholding.

Diabetic retinopathy is one of the most significant retinal diseases that can lead to blindness. As a result, it is critical to receive a prompt diagnosis of the disease. Manual screening can result in misdiagnosis due to human error and limited human capability. In such cases, using a deep learning-based automated diagnosis of the disease could aid in early detection and treatment. In deep learning-based analysis, the original and segmented blood vessels are typically used for diagnosis. However, it is still unclear which approach is superior. In this study, a comparison of two deep learning approaches (Inception v3 and DenseNet-121) was performed on two different datasets of colored images and segmented images. The study’s findings revealed that the accuracy for original images on both Inception v3 and DenseNet-121 equaled 0.8 or higher, whereas the segmented retinal blood vessels under both approaches provided an accuracy of just greater than 0.6, demonstrating that the segmented vessels do not add much utility to the deep learning-based analysis. The study’s findings show that the original-colored images are more significant in diagnosing retinopathy than the extracted retinal blood vessels.

Retinal fundus image is a crucial tool for ophthalmologists to diagnose eye-related diseases. These images provide visual information of the interior layer of the retina structures such as optic disc, optic cup, blood vessels and macula that can assist ophthalmologist in determining the health of an eye. Segmentation of blood vessels in fundus images is one of the most fundamental phase in detecting diseases such as diabetic retinopathy. However, the ambiguity of the retina structures in the retinal fundus images presents a challenge for researcher to segment the blood vessels. Extensive pre-processing and training of the images is necessary for precise segmentation, which is very intricate and laborious. This paper proposes the implementation of object-oriented-based metadata (OOM) structures of each pixel in the retinal fundus images. These structures comprise of additional metadata towards the conventional red, green, and blue data for each pixel within the images. The segmentation of the blood vessels in the retinal fundus images are performed by considering these additional metadata that enunciates the location, color spaces, and neighboring pixels of each individual pixel. From the results, it is shown that accurate segmentation of retinal fundus blood vessels can be achieved by purely employing straightforward thresholding method via the OOM structures without extensive pre-processing image processing technique or data training.

A wide variety of security applications like computers, laptops, mobile phones, ATM machines, physical access control to property etc. are using biometrics based system for human identification. Today’s Biometrics authentication system can provide highest level of security to the user of the service and the service providers. Today’s uni-modal biometric systems has become mature system and being used for low level to medium level security applications. But, for extremely higher level of security requirements like military base, nuclear plants, research laboratories etc., Finger knuckle image and Retina image based combination can be used, as this combinations provides the highest level of accuracy, low error rates, universality etc. Also the security of Multi-modal biometric templates is very importance as biometric template store vital information of the user. In this research work, Multi-modal Biometric system for higher level security using Finger Knuckle image and Retina image with templates security is developed, experiments are carried out and results are calculated using PolyU database for Finger Knuckle image and DRIVE for Retina images. A Finger Knuckle Image processing starts with Median Filtering, CLAHE method and Canny edge detection. The features extraction is carried using SURF feature method. Once the finger knuckle image template is generated, it is encrypted using RSA algorithm and stored in database. The Retina Image Processing is carried out by applying Green channel followed by Gaussian filtering, CLAHE method is applied on outcome of Gaussian filtering. SURF features set is extracted from retina ROI. Retina image template is generated which is later encrypted using RSA algorithm. The final experiment shows that genuine acceptance rate = 100% is achieved for threshold value 0.35 and False Acceptance Rate is only 1%. The scientific contribution of proposed research work is a multi-biometric system with higher accuracy (GAR is 100%), low error rate (FAR is 1%), better template protection by RSA encryption and efficient hybrid model using finger knuckle image and retina image.

Optimizing Region of Interest Size and Placement for Opportunistic CT

ObjectiveTo investigate the effect of position and size of tumor region of interest (ROI) on the estimation of lung cancer vascular parameters using 256-slice computed tomography (CT) perfusion.MethodsAfter institutional review board approval and written informed consent, 16 men and 11 women with lung cancer were enrolled in this CT perfusion study. Perfusion, blood volume, and peak enhancement were determined for 60 or 120 mm2 circular ROIs placed at the edge, center, and around (outlining) the visible tumor. Average values were obtained by performing ROI analysis twice by the same observers without any procedural changes.ResultsPerfusion, blood volume, and peak enhancement measurements were substantially higher at the edge than at the center for both 60 and 120 mm2 ROIs (all P<0.05). Measurements varied substantially depending on the ROI size. Perfusion, blood volume, and peak enhancement for the ROIs outlining tumor were intermediate between those at the tumor edge and center. There were significant correlations between median values and interquartile ranges as follows; perfusion (12.51 [7.91–28.10] mL⋅min−1⋅100 mL−1), blood volume (29.31 [21.82–37.65] mL⋅100 g−1), peak enhancement (12.93 [2.42–22.50]) for the ROIs outlining the tumor, and microvascular density ([19.43±8.78] vessels/0.74 mm2), respectively (r values were 0.732, 0.590, and 0.544 respectively, all P<0.05).ConclusionSpatial and size selection of ROI significantly affects CT perfusion analysis. ROI outlining of entire tumor provides efficient and reliable measurements for clinical assessment of lung cancer using CT perfusion.

The structure of the optic disc is impacted by the devastating eye disease glaucoma. Most doctors rely on viewing and screening the retinal fundus images to detect it. Identifying the optic disc is a crucial stage for automated diagnosis of glaucoma. This study presents a transfer learning-based approach to locate the optic disc in the retinal fundus image. The fundus images are categorized into four distinct classes according to the positions of optic disc to learn the in-depth specific features.Based on the YOLOv3 model, the optic disc detection method is then fine-tuned using the specialised image dataset. The model involved is trained and evaluated on 2178 retinal fundus images obtained from database at a nearby hospital and publically accessible datasets. In 2103 of the retinal fundus images, the suggested approach successfully detected the optical disc, yielding an average accuracy of 96.56%.

This paper describes a methodology for the segmentation of blood vessels in digital images of human eye retina. The proposed method is based on the background subtraction between a filtered retinal image by anisotropic diffusion and an approximation of the retinal background, obtained by a median filtering. The subtraction operation results in an image of differences, which is enhanced by a local histogram stretching and thresholded to detect the blood vessels. Finally, the obtained binary image is filtered aiming to remove small signals and false responses which are related to retina pathologies. We evaluated the proposed method using STARE and DRIVE image sets, in which the results have shown higher accuracy rates when compared with similar approaches.

&lt;span&gt;Segmentation of blood vessels (BVs) from retinal image is one of the important steps in developing a computer-assisted retinal diagnosis system and has been widely researched especially for implementing automatic BV segmentation methods. This paper proposes an improvement to an existing retinal BV (RBV) segmentation method by combining the trainable B-COSFIRE filter with adaptive thresholding methods. The proposed method can automatically configure its selectivity given a prototype pattern to be detected. Its segmentation performance is comparable to many published methods with the advantage of robustness against noise on retinal background. Instead of using grid search to find the optimal threshold value for a whole dataset, adaptive thresholding (AT) is used to determine the threshold for each retinal image. Two AT methods investigated in this study were ISODATA and Otsu’s method. The proposed method was validated using 40 images from two benchmark datasets for retinal BV segmentation validation, namely DRIVE and STARE. The validation results indicated that the segmentation performance of the proposed unsupervised method is comparable to the original B-COSFIRE method and other published methods, without requiring the availability of ground truth data for new dataset. The Sensitivity and Specificity values achieved for DRIVE and STARE are 0.7818, 0.9688, 0.7957 and 0.9648, respectively.&lt;/span&gt;

An automatic blood vessel segmentation is considered as important due to the presence of similar properties between blood vessels and the early stage pathologies (i.e. Microaneurysm and hemorrhages) in retinal diseases [1,2]. Blood vessel segmentation is considered as a challenging task, if a retinal images having inadequate contrast, lightning variations, and different pathologies like exudates. In literature, there is a number of blood vessel segmentation algorithms exist, but they are not compared on similar datasets and thus, it is difficult to choose which one is best. In this paper, we have implemented five different blood vessel segmentation techniques based on Gaussian matched filter [4], edge based techniques [5,8] (Sobel, Prewitt and Kirsch) and entropy based thresholding [6] technique and compare them on similar datasets with low quality and pathological retinal images. Secondly, in low quality images, most of the pixels have lost their color intensity information and considered as noise. In order to retrieve their color information of pixels, initial pre-processing is needed. Thus, a different pre-processing approach includes mask generation and contrast enhancement to retrieve the pixel information are proposed in retinal images and compared. The results obtained are verified broadly on two publicly available standard datasets DIARETDB0 and STARE dataset comprises of 211 retinal images.

With depth cameras and LiDAR improving and generating more data, their applications in 3D point clouds are growing rapidly. However, the vast amount of generated data increases the computational load and results in a shortage of storage space. Therefore, a preprocessing step to reduce the number of points is required before using the 3D point cloud. This study proposes region of interest (ROI) determination methods that sequentially construct circular and rectangular ROIs along the target trajectory of the robot to extract only crucial data for the target task. These two ROI determination methods have two benefits. First, they maintain the resolution of the raw data; second, they create two ROIs that match perfectly regardless of the complexity of the trajectory. To verify the high performance of these two ROI determination methods, we conducted simulations and experiments using various data; artificial frames, keyframes, and sequential frames. As a result, when the distance between the center points was small, 25% of the diameter or height of the circular and rectangular ROIs, the classification evaluation results were closer to 1 and the processing speed was faster than the raw data acquisition rate. However, we confirm that there is a trade-off relationship between the classification results and the processing time according to the distance parameter. In addition, through the qualitative comparison with the previous study, the long cuboid ROI determination method, we identified the limitations of the previous study and the advantages of the two proposed ROI determination methods.

In this research, retinal blood vessel fundus images will be segmented. Moreover, bifurcation point of the segmented blood vessel images will be determined. The data used for this research was obtained from fundus image database of DRIVE (Digital Retinal Images for Vessel Extraction) dataset. The preprocessing phases contain of several steps such as green channel extraction, histogram equalization and optic disc elimination. Meanwhile, the segmentation phase was performed by combining two filtering methods. These methods are median and derivative of Gaussian filter. Median filter was used to reduce the noise on retinal fundus image such as hard and soft exudates as well as dot and blot hemorrhages. Combination of these two filtering methods were also employed to determine the bifurcation point of segmented blood vessel image. The bifurcation points and the result from blood vessel segmentation were among two of the unique parameters of retinal fundus image. These parameters will be used eventually as unique features of the advanced research which is a biometric system to identify an individual based on his/her unique retinal pattern.

In this study texture differentiation associated to bone regeneration properties, around loaded oral implants immersed to Platelets Rich Plasma (PRP), was investigated in panoramic radiographs. The bone-to-implant contact region was analyzed in a follow up clinical sample of 30 digitized panoramic radiographs, 15 corresponding to implant loading (Class I) and 15 after an 8 month period (Class II). This region was sampled by circular Regions of Interest (ROIs) resulting from a specifically designed segmentation stage resulting in 518 ROIs (254 Class I and 264 class II). From each ROI, 42 textural features were extracted, and subjected to statistical analysis in order to evaluate osseo integration of oral implants. A subset of 6 features, selected with stepwise discriminant analysis method, achieved Area Under Curve (AUC) values greater than 0.73, indicating that these features are capable of capturing temporal textural differentiation attributed bone regeneration properties in the bone-to-implant contact region.

A comprehensive survey on segmentation techniques for retinal vessel segmentation

Purpose To determine the impact of three different methods of region of interest (ROI) positioning for apparent diffusion coefficient (ADC) measurements on the assessment of complete response (CR) to neoadjuvant combined chemotherapy and radiation therapy (CRT) in patients with rectal cancer. Materials and Methods Institutional review board approval was obtained for this study; all patients gave written informed consent. ADCs were measured by two radiologists using three circular ROIs (three-ROIs), single-section (SS), and whole-tumor volume (WTV) methods in 62 patients with locally advanced rectal cancer on pre- and post-CRT images. Interobserver variability was analyzed by calculating intraclass correlation coefficient (ICC). Descriptive statistics and areas under the receiver operating characteristic curves (AUCs) were calculated to evaluate performance in determining CR from pre- and post-CRT ADCs and ADC change. Histopathologic tumor regression grade was the reference standard. Results SS and WTV methods yielded higher AUCs than did the three-ROIs method when determining CR from post-CRT ADC (0.874 [95% confidence interval {CI}: 0.778, 0.970] and 0.886 [95% CI: 0.781, 0.990] vs 0.731 [95% CI: 0.583, 0.878], respectively; P = .033 and P = .003) and numeric change (0.892 [95% CI: 0.812, 0.972] and 0.897 [95% CI: 0.801, 0.994] vs 0.740 [95% CI: 0.591, 0.890], respectively; P = .048 and P = .0021). Respective accuracies of SS, WTV, and three-ROIs methods were 79% (49 of 62), 77% (48 of 62), and 61% (38 of 62) for post-CRT, 79% (49 of 62), 86% (53 of 62), and 60% (37 of 62) for numeric ADC change, and 77% (48 of 62), 84% (52 of 62), and 57% (35 of 62) for percentage ADC change (ADC cut-offs: 1.21, 1.30, and 1.05 × 10-3 mm2/sec, 0.33, 0.45, and 0.27 × 10-3 mm2/sec increases, and 40%, 54%, and 27% increases, respectively). Post-CRT and ADC change measurements achieved negative predictive values of 96% (44 of 46) to 100% (39 of 39). Intraobserver agreement was highest for WTV-derived ADCs (ICC, 0.742 [95% CI: 0.316, 0.892] to 0.891 [95% CI: 0.615, 0.956]) and higher for all pretreatment than posttreatment measurements (ICC, 0.761 [95% CI: 0.209, 0.930] and 0.648 [95% CI: 0.164, 0.895] for three-ROIs method, 0.608 [95% CI: 0.287, 0.844] and 0.582 [95% CI: 0.176, 0.870] for SS method, 0.891 [95% CI: 0.615, 0.956] and 0.742 for WTV method [95% CI: 0.316, 0.892]). Conclusion Tumor ADCs are highly dependent on the ROI positioning method used. Larger area measurements yield greater accuracy in response assessment. Post-CRT ADCs and values of ADC changes accurately identify noncomplete responders. WTV measurement of percentage ADC change provides the best results. © RSNA, 2016 An earlier incorrect version of this article appeared online. This article was corrected on September 19, 2016.