Search

Automated retinal image analysis holds prime significance in the accurate diagnosis of various critical eye diseases that include diabetic retinopathy (DR), age-related macular degeneration (AMD), atherosclerosis, and glaucoma. Manual diagnosis of retinal diseases by ophthalmologists takes time, effort, and financial resources, and is prone to error, in comparison to computer-aided diagnosis systems. In this context, robust classification and segmentation of retinal images are primary operations that aid clinicians in the early screening of patients to ensure the prevention and/or treatment of these diseases. This paper conducts an extensive review of the state-of-the-art methods for the detection and segmentation of retinal image features. Existing notable techniques for the detection of retinal features are categorized into essential groups and compared in depth. Additionally, a summary of quantifiable performance measures for various important stages of retinal image analysis, such as image acquisition and preprocessing, is provided. Finally, the widely used in the literature datasets for analyzing retinal images are described and their significance is emphasized.

Achieving accurate retinal vessel segmentation is critical in the progression and diagnosis of vision-threatening diseases such as diabetic retinopathy and age-related macular degeneration. Existing vessel segmentation methods are based on encoder-decoder architectures, which frequently fail to take into account the retinal vessel structure's context in their analysis. As a result, such methods have difficulty bridging the semantic gap between encoder and decoder characteristics. This paper proposes a Prompt Deep Light-weight Vessel Segmentation Network (PLVS-Net) to address these issues by using prompt blocks. Each prompt block use combination of asymmetric kernel convolutions, depth-wise separable convolutions, and ordinary convolutions to extract useful features. This novel strategy improves the performance of the segmentation network while simultaneously decreasing the number of trainable parameters. Our method outperformed competing approaches in the literature on three benchmark datasets, including DRIVE, STARE, and CHASE.

Glaucoma is an incurable eye disease that leads to slow progressive degeneration of the retina. It cannot be fully cured, however, its progression can be controlled in case of early diagnosis. Unfortunately, due to the absence of clear symptoms during the early stages, early diagnosis are rare. Glaucoma must be detected at early stages since late diagnosis can lead to permanent vision loss. Glaucoma affects the retina by damaging the Optic Nerve Head (ONH). Its diagnosis is dependent on the measurements of Optic Cup (OC) and Optic Disc (OD) in the retina. Computer vision techniques have been shown to diagnose glaucoma effectively and correctly with little overhead. These techniques measure OC and OC dimensions using machine learning based classification and segmentation algorithms. This article aims to provide a comprehensive overview of various existing techniques that use machine learning to detect and diagnose glaucoma based on fundus images. Readers would be able to understand the challenges glaucoma presents from an image processing and machine learning stand-point and will be able to identify gaps in current research.

The performance of cross-correlation functions can decrease computational complexity under optimal fingerprint feature selection. In this paper, a technique is proposed to perform alignment of fingerprints followed by their matching in fewer computations. Minutiae points are extracted and alignment is performed on the basis of their spatial locations and orientation fields. Unlike traditional cross-correlation based matching algorithms, ridges are not included in the matching process to avoid redundant computations. However, optimal cross-correlation is chosen by correlating feature vectors accompanying x-y locations of minutiae points and their aligned orientation fields. As a result, matching time is significantly reduced with much improved accuracy.

Diabetes mellitus (DM) is a major health problem, with a high prevalence worldwide, including in Pakistan. Insulin is a main treatment of type 1 DM (T1D) and type 2 DM (T2D). Many challenges and complications are linked with insulin self-administration (ISA). A cross-sectional survey was conducted at a single teaching hospital in Pakistan. Study participants were adults with T1D or T2D treated with insulin who attended the hospital. Data were collected using a pretested questionnaire that determined the participants’ knowledge of DM and ISA and their attitudes towards ISA. Mann–Whitney tests and Kruskal–Wallis tests were applied to check the association between demographic characteristics and knowledge and attitude. The Spearman rho correlation test was used to check the correlation between knowledge and attitude scores. Data were analyzed by applying SPSS version 24.0. Of the 105 survey participants, 66.9% were male and 33.1% were female, with a median age of 45 years. Only 22.9% of the participants had good knowledge about DM, 50.5% had average knowledge, and 26.7% had poor knowledge. The attitude towards ISA was favorable in 30.5% of participants, but unfavorable in 69.5%. Age and duration of insulin use were significantly related to knowledge and attitude scores, and there was positive linear correlation between knowledge score and attitude score. Overall, participants had poor knowledge and unfavorable attitudes regarding DM and ISA therapy. The positive linear correlation between knowledge and attitude score suggests that if patients are knowledgeable about DM, their attitude regarding DM and ISA will also be favorable.

The safety and proper utilization of a drug depends not only on its pharmacological action, but also its interactions with other drugs and their metabolites. Therefore, a multifaceted biochemical system must be considered when prescribing any drug. The purpose of the present study is to identify potential drug–drug interactions (pDDIs) and investigate their level of severity, onset of action, mechanism of action, and incidence in the medical wards of Benazir Bhutto Shaheed Teaching Hospital, Abbottabad, Pakistan. A prospective cross-sectional study was conducted from November 2016 to January 2017 in the medical wards of a teaching hospital. A systematic random sampling technique was used to select patients from the available settings with one in every seven patients selected to provide a sample of 384 patients. A total of 388 pDDIs were identified, which comprised 86 types of drug combinations. Across all pDDIs, most were of major severity (39.9%), followed by moderate (39.6%) and minor (19.5%) severity and contraindicated (0.7%). A majority of the study participants were male (292; 76%) and the mean age of the patients was 50 years. Overall, 51.0% patients had at least one pDDI. The overall prevalence of pDDIs is very high in medical wards, and the incidence of pDDIs is primarily associated with polypharmacy and patient age.

As part of industrial quality control in the leather industry, it is important to segment features/defects in wet-blue leather samples. Manual inspection of leather samples is the current norm in industrial settings. To comply with the current industrial standards that advocate large-scale automation, visual inspection based leather processing is imperative. Visual inspection of wet-blue leather features is a challenging problem as the characteristics of these features can take on a variety of shapes and colour variations to constitute various normal and abnormal surface regions. The aim of this work is to automatically segment leather images to detect various features/defects along with the background through visual analysis of the surfaces. To accomplish this, a deep learning-based technique is developed that learns to segment wet-blue leather surface features. On our own curated leather images dataset, the proposed ensemble network performed well, with an F1-Score of 74 percent.

The diagnosis of diseases using the retinal vasculature has long been a focus of medical research. Segmenting the vessels from retinal images is still a difficult task because of the variability in retinal vascular thickness and the inhomogeneity of image intensity. In this research work, a two-stage retinal vessel segmentation method is proposed. At the first stage, the large vessels are segmented by using multi-scale line detection by suppressing the small vessels through non-local mean filtering. At the second stage, the image is enhanced through noise suppression attributed largely to the block-matching 3-D filtering inside the nonsubsampled contourlet transform. Then a patch-based multi-scale line detector with adaptive statistical thresholding is used. Finally, both large and small vessels are combined to reconstruct the final vessel segmented image. The proposed method is evaluated on two publicly available databases and achieves an average sensitivity of 82.61%, and 81.67% on the DRIVE and STARE datasets respectively. The proposed method outperforms other state-of-the-art methods and has proven to be effective in boosting the sensitivity of retinal vessel segmentation.

Recent progress in encoder-decoder neural network architecture design has led to significant performance improvements in a wide range of medical image segmentation tasks. However, state-of-the-art networks for a given task may be too computationally demanding to run on affordable hardware, and thus users often resort to practical workarounds by modifying various macro-level design aspects. Two common examples are downsampling of the input images and reducing the network depth or size to meet computer memory constraints. In this paper, we investigate the effects of these changes on segmentation performance and show that image complexity can be used as a guideline in choosing what is best for a given dataset. We consider four statistical measures to quantify image complexity and evaluate their suitability on ten different public datasets. For the purpose of our illustrative experiments, we use DeepLabV3+ (deep large-size), M2U-Net (deep lightweight), U-Net (shallow large-size), and U-Net Lite (shallow lightweight). Our results suggest that median frequency is the best complexity measure when deciding on an acceptable input down-sampling factor and using a deep versus shallow, large-size versus lightweight network. For high-complexity datasets, a lightweight network running on the original images may yield better segmentation results than a large-size network running on downsampled images, whereas the opposite may be the case for low-complexity images.

Devising automated procedures for accurate vessel segmentation (retinal) is crucial for timely prognosis of vision-threatening eye diseases. In this paper, a novel supervised deep learning-based approach is proposed which extends a variant of the fully convolutional neural network. The existing fully convolutional neural network-based counterparts have associated critical drawbacks of involving a large number of tunable hyper-parameters and an increased end-to-end training time furnished by their decoder structure. The proposed approach addresses these intricate challenges by using a skip-connections strategy by sharing indices obtained through max-pooling to the decoder from the encoder stage (respective stages) for enhancing the resolution of the feature map. This significantly reduces the number of required tunable hyper-parameters and the computational overhead of the training as well as testing stages. Furthermore, the proposed approach particularly helps in eradicating the requirement for employing both post-processing and pre-processing steps. In the proposed approach, the retinal vessel segmentation problem is formulated as a semantic pixel-wise segmentation task which helps in spanning the gap between semantic segmentation and medical image segmentation. A prime contribution of the proposed approach is the introduction of external skip-connection for passing the preserved low-level semantic edge information in order to reliably detect tiny vessels in the retinal fundus images. The performance of the proposed scheme is analyzed based on the three publicly available notable fundus image datasets, while the widely recognized evaluation metrics of specificity, sensitivity, accuracy, and the Receiver Operating Characteristics curves are used. Based on the assessment of the images in {DRIVE, CHASE_DB1, and STARE}; datasets, the proposed approach achieves a sensitivity, specificity, accuracy, and ROC performance of {0.8252, 0.8440, and 0.8397};, {0.9787, 0.9810, and 0.9792};, {0.9649, 0.9722, and 0.9659};, and {0.9780, 0.9830, and 0.9810};, respectively. The reduced computational complexity and memory overhead along with improved segmentation performance advocates employing the proposed approach in the automated diagnostic systems for eye diseases.

Skin segmentation plays an important role in human activity recognition, video surveillance, hand gesture identification, face detection, human tracking and robotic surgery. The accurate segmentation of the skin is necessary to recognize the human activity. Segmentation of skin is easy to realize in ideal situations because of similar backgrounds. But it becomes complicated because of presence of skin-like pixels, background illuminations, and certain changes in environment. These problems are addressed by incorporating preprocessing stages in current studies, but this raises the total cost of the system. However, there are some limitations associated with these methods in terms of accuracy and processing speed. In this work, we propose a skin semantic segmentation network (SSS-Net) that is able to capture the multi-scale contextual information and refines the segmentation results especially along object boundaries. Moreover our network helps to reduce the cost of the preprocessing as well. We have performed experiments on the five open datasets of human activity recognition for the segmentation of skin. Experimental results show SSS-Net outperforms the state-of-the-art methods in skin segmentation in terms of accuracies.

Leather defect analysis is important for leather quality grading which directly effects the leather exports. Automated leather sample classification is vital due to slow and subjective nature of the manual process. The major challenges that exist in visual inspection of leather samples for categorization are: the morphology of defects significantly differs and their close examples are not available for transfer learning, unavailability of publicly available data and a benchmark. In this paper, we discuss three important aspects in the identification of industrial leather defects, i.e. the creation of an annotated wet-blue leather image dataset, the transfer of information from different domains to the leather image domain and the design of ensemble networks tailored to the task. We are therefore introducing a new database of wet-blue leather images (Wet-blue Leather Image Dataset (WBLID)) for the classification of defects along with expert annotation data. We proposed a new network EfficientNet-B3+ ResNext-101. The proposed EfficientNet-B3+ ResNext-101 ensemble architecture significantly outperforms all other state-of-the-art methods in terms of AUC and F1-score.

Glaucoma is an eye disease that can cause loss of vision by damaging the optic nerve. It is the world's second leading cause of blindness after cataracts. Early diagnosis of glaucoma is a key to prevent permanent blindness as it has no noticeable symptoms in its early stages. Color fundus photography is used for examining the optic disc (OD) which is an important step in the diagnoses of glaucoma. This is done by estimating the cup-to-disc ratio (CDR). In this paper, we proposed a Cup Disc Encoder Decoder Network (CDED-Net) for the joint segmentation of optic disc (OD) and optic cup (OC). We have eradicated the pre-processing and post-processing steps to reduce the computational cost of the overall system. Segmentation of (OD) and OC is modeled as a semantic pixel-wise labeling problem. The model was trained on the DRISHTI-GS, RIM-ONE and REFUGE datasets. Experiments show that our CDED-Net system achieves state-of-the-art OD and OC segmentation results on these datasets.

Glaucoma along with diabetic retinopathy is a major cause of vision blindness and is projected to affect over 80 million people by 2020. Recently, expert systems have matched human performance in disease diagnosis and proven to be highly useful in assisting medical experts in the diagnosis and detection of diseases. Hence, automated optic disc detection through intelligent systems is vital for early diagnosis and detection of Glaucoma. This paper presents a multi-parametric optic disk detection and localization method for retinal fundus images using region-based statistical and textural features. Highly discriminative features are selected based on the mutual information criterion and a comparative analysis of four benchmark classifiers: Support Vector Machine, Random Forest (RF), AdaBoost and RusBoost is presented. The results of the proposed RF classifier based pipeline demonstrate its highly competitive performance (accuracies of 0.993, 0.988 and 0.993 on the DRIONS, MESSIDOR and ONHSD databases) with the state-of-the-art, thus making it a suitable candidate for patient management systems for early diagnosis of the Glaucoma.

Computer-aided optic disk (OD) detection and segmentation is at the heart of modern fundus image screening systems for early detection and diagnosis of glaucoma and diabetic retinopathy. Algorithms that generalize well on fundus images with diseases, as well as screening images, are of utmost importance. This paper presents a method based on OD homogenization and subsequent contour estimation to address the challenges of OD detection in cases where either the OD boundary is discontinuous or very smooth, due to the presence of disease. This is achieved by local Laplacian filtering-based inpainting of the major vascular structure to complete the OD boundary and gradient-independent active contour estimation for unconstrained OD boundary detection. Experimental evaluation of the proposed method on three benchmark datasets and quantitative comparison with the best performing state-of-the-art methods in terms of four quantitative measures demonstrate its competitive performance and reliability for OD screening.

This paper presents a fully automated brain tissue classification method for normal and abnormal tissues and its associated region from Fluid Attenuated Inversion Recovery modality of Magnetic Resonance (MR) images. The proposed regional classification method is able to simultaneously detect and segment tumours to pixel-level accuracy. The region-based features considered in this study are statistical, texton histograms, and fractal features. This is the first study to address the class imbalance problem at the regional level using Random Majority Down-sampling-Synthetic Minority Over-sampling Technique (RMD-SMOTE). A comparison of benchmark supervised techniques including Support Vector Machine, AdaBoost and Random Forest (RF) classifiers is presented, where the RF-based regional classifier is selected in the proposed approach due to its better generalization performance. The robustness of the proposed method is evaluated on the standard publicly available BRATS 2012 dataset using five standard benchmark measures. We demonstrate that the proposed method consistently outperforms three benchmark tumour classification methods in terms of Dice score and obtains significantly better results as compared to its SVM and AdaBoost counterparts in terms of precision and specificity at the 5% confidence interval. The promising results of the proposed method support its application for early detection and diagnosis of brain tumours in clinical settings.

This paper presents a real-time iris segmentation technique that is well suited to a fast implementation on an FPGA. One major hurdle associated with iris segmentation techniques is the use of iterative processes that lead to expensive hardware implementations. To circumvent this, the proposed algorithm uses the sign image obtained from subtracting the background, along with morphological operators to localise the pupil. The outer boundary is located by first normalising a selected image region that contains the iris, and then using a first-order gradient operator. The proposed non-iterative algorithm is implemented on an FPGA. Four near infrared (NIR) iris public databases, namely: CASIA-IrisV3-Lamp, MMU v1.0, ND-IRIS-0405 and NIST ICE 2005, are used to test the proposed algorithm. The proposed method for iris segmentation and normalization gives much better accuracy than the existing state-of-the-art methods implemented on hardware. The proposed realisation requires about 45% fewer logic registers and 52% fewer logic elements than the existing state-of-the-art implementations.

As part of industrial quality control in the leather industry, it is important to identify the abnormal features in wet-blue leather samples. Manual inspection of leather samples is the current norm in industrial settings. To comply with the current industrial standards that advocate large-scale automation, visual inspection based leather processing is imperative. Visual inspection of irregular surfaces is a challenging problem as the characteristics of the abnormalities can take a variety of shape and color variations. The aim of this work is to automatically categorize leather images into normal or abnormal by visual analysis of the surfaces. To achieve this aim, a deep learning based approach is devised that learns to recognize regular and irregular leather surfaces and categorize leather images on its basis. To this end, we propose an ensemble of multiple convolutional neural networks for classifying leather images. The proposed ensemble network exhibited competitive performance obtaining 92.68% test accuracy on our own curated leather images dataset.

In this paper, Coherence Enhancement Diffusion (CED) is boosted feeding external orientation using new robust orientation estimation. In CED, proper scale selection is very important as the gradient vector at that scale reflects the orientation of local ridge. For this purpose a new scheme is proposed in which pre calculated orientation, by using local and integration scales. From the experiments it is found the proposed scheme is working much better in noisy environment as compared to the traditional Coherence Enhancement Diffusion KEYWORDS Fingerprint Image Enhancement, Coherence Enhancement Diffusion Directional Filter Bank (DFB), Decimation free Directional Filter Bank (DDFB).

Automated detection of vision threatening eye disease based on high resolution retinal fundus images requires accurate segmentation of the blood vessels. In this regard, detection and segmentation of finer vessels, which are obscured by a considerable degree of noise and poor illumination, is particularly challenging. These noises include (systematic) additive noise and multiplicative (speckle) noise, which arise due to various practical limitations of the fundus imaging systems. To address this inherent issue, we present an efficient unsupervised vessel segmentation strategy as a step towards accurate classification of eye diseases from the noisy fundus images. To that end, an ensemble block matching 3D (BM3D) speckle filter is proposed for removal of unwanted noise leading to improved detection. The BM3D-speckle filter, despite its ability to recover finer details (i.e., vessels in fundus images), yields a pattern of checkerboard artifacts in the aftermath of multiplicative (speckle) noise removal. These artifacts are generally ignored in the case of satellite images, however, in the case of fundus images, these artifacts have a degenerating effect on the segmentation or detection of fine vessels. To counter that, an ensemble of BM3D-speckle filter is proposed to suppress these artifacts while further sharpening the recovered vessels. This is subsequently used to devise an improved unsupervised segmentation strategy that can detect fine vessels even in the presence of dominant noise and yields an overall much improved accuracy. Testing was carried out on three publicly available databases namely Structured Analysis of the Retina (STARE), Digital Retinal Images for Vessel Extraction (DRIVE) and CHASE_DB1. We have achieved a sensitivity of 82.88, 81.41 and 82.03 on DRIVE, SATARE, and CHASE_DB1, respectively. The accuracy is also boosted to 95.41, 95.70 and 95.61 on DRIVE, SATARE, and CHASE_DB1, respectively. The performance of the proposed methods on images with pathologies was observed to be more convincing than the performance of similar state-of-the-art methods.

In a fundus image, Vessel local characteristics like direction, illumination and noise vary considerably, making vessel segmentation a challenging task. Methods based upon deep convolutional networks have consistently yield state of the art performance. Despite effective, of the drawbacks of these methods is their computational complexity, whereby testing and training of these networks require substantial computational resources and can be time consuming. Here we present a multi-scale kernel based on fully convolutional layers that is quite lightweight and can effectively segment large, medium, and thin vessels over a wide variations of contrast, position and size of the optic disk. Moreover, the architecture presented here makes use of these multi-scale kernels, reduced application of pooling operations and skip connections to achieve faster training. We illustrate the utility of our method for retinal vessel segmentation on the DRIVE, CHASE_DB and STARE data sets. We also compare the results delivered by our method with a number of alternatives elsewhere in the literature. In our experiments, our method always provides a margin of improvement on specificity, accuracy, AUC and sensitivity with respect to the alternative.

Introduction Acute myocardial infarction (AMI) is a devastating medical emergency that requires immediate pharmacological and radiological intervention. With the advent of techniques such as percutaneous coronary intervention (PCI), pacemakers, and percussion pacing, survival rates have improved significantly. However, there are certain factors and complications associated with AMI that still lead to a high mortality rate, such as old age, advanced heart disease, diabetes mellitus (DM), and arrhythmias. Factors such as the type of arrhythmia, the heart rate, and the level at which dissociation occurs between atrial and ventricular rhythm all influence mortality and morbidity rates. Outcomes are further influenced by the sex of the patient, the type of AMI [ST-elevation myocardial infarction (STEMI) or non-ST-elevation myocardial infarction (NSTEMI)], history of smoking, arrival times at the hospital, presence of hyperglycemia, previous history of cardiac surgery, and the need for a temporary pacemaker or a permanent pacemaker. As with most scientific studies, local data from Pakistan is hard to find on this topic as well. With this study, we hope to contribute valuable information and updates to the study of a developing problem from the developing world. Objective We aimed to analyze the frequency and outcomes of different types of arrhythmia in AMI. Methods This study involved a retrospective observational cohort. It was conducted at the National Institute of Cardiovascular Diseases (NICVD), Karachi from January 2019 to July 2019 (six months). All data were retrieved from the online database at the NICVD. Written consent was obtained from all patients. Patient confidentiality was ensured at all times. Results A total of 500 patients were included in the study. The mean age of our cohort was 56.17 ±14.01 years. NSTEMI was more prevalent than STEMI. Sinus arrhythmia (SA) was the most frequently recorded arrhythmia and had the best survival rates. Atrioventricular (AV) nodal blocks and ventricular tachycardia (VT) had the worst outcomes. The overall mortality rate was 11.4%, and the mean in-hospital length of stay was 2.07 ±1.54 days. Smoking increased mortality in all cases. Conclusions AMI is complicated by several types of arrhythmia. SA is the most common arrhythmia in AMI. Mortality in AMI is largely due to AV nodal blocks and VT. Smoking increases mortality in all cases.