•Diabetic retinopathy (DR) detection from Fundus Images has been proposed.•Parallel CNN with fewer parameters and layers for distinctive feature extraction.•Extreme Learning Machine (ELM) technique ...was utilized for the DR classification.•The model demonstrated robustness for different types of datasets.•Accuracy upto 97.27 % was achieved and outscored state-of-the-art models.
Diabetic retinopathy (DR) is an incurable retinal condition caused by excessive blood sugar that, if left untreated, can result in even blindness. A novel automated technique for DR detection has been proposed in this paper. To accentuate the lesions, the fundus images (FIs) were preprocessed using Contrast Limited Adaptive Histogram Equalization (CLAHE). A parallel convolutional neural network (PCNN) was employed for feature extraction and then the extreme learning machine (ELM) technique was utilized for the DR classification. In comparison to the similar CNN structure, the PCNN design uses fewer parameters and layers, which minimizes the time required to extract distinctive features. The effectiveness of the technique was evaluated on two datasets (Kaggle DR 2015 competition (Dataset 1; 34,984 FIs) and APTOS 2019 (3,662 FIs)), and the results are promising. For the two datasets mentioned, the proposed technique attained accuracies of 91.78 % and 97.27 % respectively. However, one of the study's subsidiary discoveries was that the proposed framework demonstrated stability for both larger and smaller datasets, as well as for balanced and imbalanced datasets. Furthermore, in terms of classifier performance metrics, model parameters and layers, and prediction time, the suggested approach outscored existing state-of-the-art models, which would add significant benefit for the medical practitioners in accurately identifying the DR.
Fuzzy logic systems play a significant role in various fields including image processing. Addressing the challenge of enhancing low-illumination images, which often contain a high degree of uncertain ...information, is a complex task. To overcome this issue, this study introduces a novel intuitionistic fuzzy generator for enhancing low-contrast images. Initially, a low-illumination image is considered and the image is then fuzzified using a fuzzification technique. The fuzzified image is converted into a intuitionistic fuzzy image using the proposed novel intuitionistic fuzzy generator and then applied a contrast limited adaptive histogram equalization method to obtain the enhanced image. The obtained results are compared with the existing studies. With the outcome of the performance measures such as entropy, no-reference low-light image enhancement evaluation and contrast improvement index, it is perceived that the proposed technique yields a finer results than the previous studies.
•A novel intuitionistic fuzzy generator is designed.•A new algorithm is proposed for low-light enhancement using the proposed generator.•Performance measures are employed to show the superiority of the proposed technique.
The diagnosis of gingivitis often occurs years later using a series of conventional oral examination, and they depended a lot on dental records, which are physically and mentally laborious task for ...dentists. In this study, our research presented a new method to diagnose gingivitis, which is based on contrast‐limited adaptive histogram equalization (CLAHE), gray‐level co‐occurrence matrix (GLCM), and extreme learning machine (ELM). Our dataset contains 93 images: 58 gingivitis images and 35 healthy control images. The experiments demonstrate that the average sensitivity, specificity, precision, and accuracy of our method is 75%, 73%, 74% and 74%, respectively. This method is more accurate and sensitive than three state‐of‐the‐art approaches.
Diabetic Retinopathy (DR) refers to a medical condition that affects the eye; it occurs due to diabetes, and, if not detected early on, results in a reduction of visual capacity and may even result ...in blindness. The process of diagnosing DR manually by ophthalmologists can be both time-consuming and expensive, and there is a risk of misdiagnosis. On the other hand, computer-aided diagnostic systems can provide a more accurate and efficient diagnosis and can help ophthalmic specialists by offering a second opinion for effective treatments. This paper presents a method in which the feature extraction is based on the multiresolution-based decomposition of Discrete Wavelet Transform (DWT), and classification is performed using Convolutional Neural Network (CNN) for grading DR images. The suggested approach begins by utilizing Contrast Limited Adaptive Histogram Equalization (CLAHE) to refine the contrast level of the fundus images as a pre-processing technique. The images in the datasets (IDRiD, DDR, and EyePACS) are not balanced, so oversampling is applied to ensure that an equal number of images from each of the grade categories are present during the training process. The results of the experiments demonstrate that the proposed model achieves a classification accuracy of 90.07%, 96.20%, and 93.53% for all DR stages, outperforming existing models on all the three datasets. Therefore, the proposed method offers a superior alternative to current approaches.
Display omitted
•A model based on the combination of CNN and multiresolution analysis is designed to detect the severity level of Diabetic Retinopathy.•By utilizing both the low-frequency and high-frequency components within the CNN, this model ensures that no information from the input is lost.•SMOTE is applied to balance the classes along with data augmentation.•Experiments show that the method outperforms the existing models on IDRiD, DDR and EyePACS datasets.
Accurate classification of pancreatic cystic lesions is crucial to differentiate mucinous lesions of malignant potential. We utilized the ResNet-50 and ResNet-101 network to develop a model for ...classification of the pancreatic cystic lesions. A total of 50 videos, 13,425 images, from five types of pancreatic cystic lesions and utilize the image rotation and contrast reversal scheme for the training. We adopt a contrast limited adaptive histogram equalization method onto the test video. Our method can automatically classify the feature type and record the prediction results frame by frame. The method has been evaluated on 18 test videos and achieves an accuracy 94% overall.
Fundus images are broadly used by medical ophthalmologists to detect and assess any customary abnormalities. Fundus imaging sensors capture the eye's rigid portion, which characteristically covers ...the core, tangential retina, optic disc, and macula. Existing state‐of‐the‐art fundus sensors have the drawback of producing low contrast and noisy information, which makes scientific and algorithmic evaluation very complicated. This article proposes an Adaptive Histogram Equalization—Tuned with Nonsimilar Grouping Curvelet (HET‐NOSCU), which works through a joint denoising enhancement approach. The proposed algorithm's main contribution includes (i) use of curvelet features to better preserve edges during denoising. (ii) Adaptive enhancement using the histogram to prevent halo ringing and specular artifacts, which yields superior results than the very recently established state‐of ‐the‐art methods, using similar performing parameters such as peak signal to noise ratio (PSNR), structural similarity index (SSIM), and correlation coefficient (CoC). We observe an improvement of 17.66%, 0.93%, and 0.24%, respectively, for the above parameters.
Low-light images suffer from poor visibility, severe noise, low contrast, and low brightness. To overcome these issues, many image enhancement methods have been proposed. Few techniques solve these ...problems simultaneously. This paper presents a low-light image enhancement method. The proposed method first applies the HSV (Hue, Saturation, Value) transform to the input image. Here, a multi-scale decomposition of the Sharpening-Smoothing Image Filter (SSIF) is proposed to obtain approximation and detail sub-images of the V component. After the decomposition process, Contrast-Limited Adaptive Histogram Equalization (CLAHE) is applied to the final approximation image to provide higher contrast. The detail sub-images are amplified and added to the enhanced approximation image to reconstruct the enhanced V component. Finally, inverse HSV transform is applied to the enhanced V component and H, S components to obtain the enhanced image. The experimental results show that the proposed method provides better visual quality and more natural colors than the compared state-of-the-art methods.
Diabetic retinopathy is a medical condition of the damaged retina that is caused by diabetes and lack of proper monitoring and treatment, which usually leads to blindness. However, diabetic ...retinopathy monitoring requires an expert ophthalmologist. Recently, automatic monitoring models with acceptable efficiency are suggested as an alternative for expert ophthalmologists. In this paper, a new diabetic retinopathy monitoring model is proposed by using the Contrast Limited Adaptive Histogram Equalization method to improve the image quality and equalize intensities uniformly as the pre-processing step. Then, EfficientNet-B5 architecture is used for the classification step. The efficiency of this network is in uniformly scaling all dimensions of the network. The final model is trained once on a mixture of two datasets, Messidor-2 and IDRiD, and evaluated on the Messidor dataset. The area under the curve (AUC) is enhanced from 0.936, which is the highest value in all recent works, to 0.945. Also, once again, to further evaluate the performance of the model, it is trained on a mixture of two datasets, Messidor-2 and Messidor, and evaluated on the IDRiD dataset. In this case, the AUC is enhanced from 0.796, which is the highest value in all recent works, to 0.932. In comparison to other studies, our proposed model improves the AUC.
Nowadays, image enhancement has become a major area of research because of the development of applications that are based on vision.Several digital image processing systems employ such image ...enhancement strategies with the help of graph theory. As the visibility level in low contrast image features is very less,several image enhancement strategies have been introduced with spatial transformations to enhance image qualityfor improved visualization. Nowadays, image processing plays an important role in the analysis of a patient’s health status and has become extremely popular in medical areas for a wide range of clinical assessments. Generally, medical images contain several complex areas and thereby,few pre-processing approaches are applied to reduce the challenges that occur during different phases of the CAD system. Furthermore, because of external noise interferences, poor illuminating settings as well as other imaging device limitations, the clinical diagnosis becomes a challenging process and medical images do not provide important information for precise categorization. Medical images are available in a variety of applications such as computed tomography, Magnetic Resonance Imaging (MRI), mammography, chest X-ray (CXR), and many more. Only the pixel intensity variations between different areas as well as object boundary information are essential for categorization and must be enhanced simultaneously. As a result, the rate of classification in medical images and intensity are increased so that every object during the analysis can be easily identified. The main goal of any image enhancement process is to enhance the quality of the image by reducing noise and on other hand by using three different algorithms such as Luminance Modulation (LM), Gradient Modulation (GM), and Dynamic Histogram Equalization (DHE). These three algorithms are designed with the help of graph theory for effective preservation of edges, losses, and efficient smoothing and to preserve the basic information without any modifications. Image restoration is also referred to as image enhancement and it is concerned with the precise assessment of real images. Generally, the degradation process is not included in many of the image-enhancement approaches that are already existing. Furthermore, with the application of enhancement techniques, the degradation process for medical images results in some significant performance loss. Several techniques have been proposed and the technique which is examined in this research is image enhancement that is based on histogram which mainly concentrates on equalizing the histogram of values. Histogram Equalization (HE) possesses a few basic properties such as altering spatial patterns as well as intensity which in turn results in significant challenges in medical imaging. As a result,Contrast Limited Adaptive Histogram Equalization (CLAHE) is proposed in this work as a feasible approach for medical image analysis to address the problem. The suggested research work demonstrates that the intensity limiting image enhancement with histogram equalization detects the irregularities in dense mammograms with enhanced quality.