ABSTRACT
Diabetic retinopathy is a condition that affects the retina and causes vision loss due to blood vessel destruction. The retina is the layer of the eye responsible for visual processing and nerve signaling. Diabetic retinopathy causes vision loss, floaters, and sometimes blindness; however, it often shows no warning signals in the early stages. Deep learning-based techniques have emerged as viable options for automated illness classification as large-scale medical imaging datasets have become more widely available. To adapt to medical image analysis tasks, transfer learning makes use of pre-trained models to extract high-level characteristics from natural images. In this research, an intelligent recommendation-based fine-tuned EfficientNetB0 model has been proposed for quick and precise assessment for the diagnosis of diabetic retinopathy from fundus images, which will help ophthalmologists in early diagnosis and detection. The proposed EfficientNetB0 model is compared with three transfer learning-based models, namely, ResNet152, VGG16, and DenseNet169. The experimental work is carried out using publicly available datasets from Kaggle consisting of 3,200 fundus images. Out of all the transfer learning models, the EfficientNetB0 model has outperformed with an accuracy of 0.91, followed by DenseNet169 with an accuracy of 0.90. In comparison to other approaches, the proposed intelligent recommendation-based fine-tuned EfficientNetB0 approach delivers state-of-the-art performance on the accuracy, recall, precision, and F1-score criteria. The system aims to assist ophthalmologists in early detection, potentially alleviating the burden on healthcare units.
ABSTRACT
The research focuses on the segmentation and classification of leukocytes, a crucial task in medical image analysis for diagnosing various diseases. The leukocyte dataset comprises four classes of images such as monocytes, lymphocytes, eosinophils, and neutrophils. Leukocyte segmentation is achieved through image processing techniques, including background subtraction, noise removal, and contouring. To get isolated leukocytes, background mask creation, Erythrocytes mask creation, and Leukocytes mask creation are performed on the blood cell images. Isolated leukocytes are then subjected to data augmentation including brightness and contrast adjustment, flipping, and random shearing, to improve the generalizability of the CNN model. A deep Convolutional Neural Network (CNN) model is employed on augmented dataset for effective feature extraction and classification. The deep CNN model consists of four convolutional blocks having eleven convolutional layers, eight batch normalization layers, eight Rectified Linear Unit (ReLU) layers, and four dropout layers to capture increasingly complex patterns. For this research, a publicly available dataset from Kaggle consisting of a total of 12,444 images of four types of leukocytes was used to conduct the experiments. Results showcase the robustness of the proposed framework, achieving impressive performance metrics with an accuracy of 97.98% and precision of 97.97%. These outcomes affirm the efficacy of the devised segmentation and classification approach in accurately identifying and categorizing leukocytes. The combination of advanced CNN architecture and meticulous pre-processing steps establishes a foundation for future developments in the field of medical image analysis.
Subject(s)
Deep Learning , Humans , Data Curation , Leukocytes , Neural Networks, Computer , Blood Cells , Image Processing, Computer-Assisted/methodsABSTRACT
Generally, cloud computing is integrated with wireless sensor network to enable the monitoring systems and it improves the quality of service. The sensed patient data are monitored with biosensors without considering the patient datatype and this minimizes the work of hospitals and physicians. Wearable sensor devices and the Internet of Medical Things (IoMT) have changed the health service, resulting in faster monitoring, prediction, diagnosis, and treatment. Nevertheless, there have been difficulties that need to be resolved by the use of AI methods. The primary goal of this study is to introduce an AI-powered, IoMT telemedicine infrastructure for E-healthcare. In this paper, initially the data collection from the patient body is made using the sensed devices and the information are transmitted through the gateway/Wi-Fi and is stored in IoMT cloud repository. The stored information is then acquired, preprocessed to refine the collected data. The features from preprocessed data are extracted by means of high dimensional Linear Discriminant analysis (LDA) and the best optimal features are selected using reconfigured multi-objective cuckoo search algorithm (CSA). The prediction of abnormal/normal data is made by using Hybrid ResNet 18 and GoogleNet classifier (HRGC). The decision is then made whether to send alert to hospitals/healthcare personnel or not. If the expected results are satisfactory, the participant information is saved in the internet for later use. At last, the performance analysis is carried so as to validate the efficiency of proposed mechanism.