Technology is changing the future of healthcare, technology-supported non-invasive medical procedures are more preferable in the medical diagnosis. Anemia is one of the widespread diseases affecting the wellbeing of individuals around the world especially childbearing age women and children and addressing this issue with the advanced technology will reduce the prevalence in large numbers. The objective of this work is to perform segmentation of the conjunctiva region for non-invasive anemia detection applications using deep learning. The proposed U-Net Based Conjunctiva Segmentation Model (UNBCSM) uses fine-tuned U-Net architecture for effective semantic segmentation of conjunctiva from the digital eye images captured by consumer-grade cameras in an uncontrolled environment. The ground truth for this supervised learning was given as Pascal masks obtained by manual selection of conjunctiva pixels. Image augmentation and pre-processing was performed to increase the data size and the performance of the model. UNBCSM showed good segmentation results and exhibited a comparable value of Intersection over Union (IoU) score between the ground truth and the segmented mask of 96% and 85.7% for training and validation, respectively.
Anaemia is predicted as one of the serious communal health issue in the world. The deficiency exists most common among children and women. A substantial issue prevails in providing quality healthcare services to rural communities, which remains a challenge to health service providers throughout the world. Traditionally physician and health workers recognized anaemia from certain clinical findings, such as pallor of the conjunctivae, nail beds, lips, tongue, and oral mucosa. Confirmation of anaemic condition through physical examination of Dorsum of a tongue or lower bulbar conjunctiva is a subjective analysis. Invasive methods have a possibility to spread infection through the needle. The existing non-invasive techniques need costly equipment and qualified technicians. Growing developments in science and technologies play an important role in medicine. This proposal introduces a new non-invasive diagnostic tool correlating the hemoglobin with conjunctiva pallor colour scores and classification using neural networks. In this study, the eye images were obtained using a mobile camera were processed using the HSI model, which estimates different colour scores of the selected region. These scores were correlated with laboratory haemoglobin value. Feedforward neural network and Elman neural network were used for classifying anaemic and non-anaemic cases. This proposed tool will be useful for the health workers to identify the mass screening of anaemia in rural areas.
Summary
The brain computer interface (BCI) can provide a direct channel of communication between an external device and the brain without including any type of muscular activity. Various applications of BCI have been stated in literature, and one of the most exciting areas which have not been extensively investigated is the field of multimedia. BCI can find huge potential in the area of command and control of video games. Video games have found huge potential for improving the gait and balance of people struggling with Parkinson's disease. Such systems make use of the brain signals which are captured through electrodes on scalp as electroencephalogram (EEG) or through implanted electrodes as electrocorticography (ECoG). The signals are then used as input commands to get desired output in an external device. To address the memory management issue arising due to the huge volume of ECoG data and to achieve distributed computation for improving the efficiency of BCI, the computations are implemented in Cloud. In this work, ECoG signals are pre‐processed, and all features are extracted by using the wavelet packet transform (WPT), common spatial patterns (CSPs), Laplacian filter, and the Kalman filter. The Adaboost classifier was employed for ECoG signal classification.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.