Gabor filter and machine learning based diabetic retinopathy analysis and detection

The automated detection of suspicious anomalies in electrocardiogram (ECG) recordings allows frequent personal heart health monitoring and can drastically reduce the number of ECGs that need to be manually examined by the cardiologists, excluding those classified as normal, facilitating healthcare decision-making and reducing a considerable amount of time and money. In this paper, we present a system able to automatically detect the suspect of cardiac pathologies in ECG signals from personal monitoring devices, with the aim to alert the patient to send the ECG to the medical specialist for a correct diagnosis and a proper therapy. The main contributes of this work are: (a) the implementation of a binary classifier based on a 1D-CNN architecture for detecting the suspect of anomalies in ECGs, regardless of the kind of cardiac pathology; (b) the analysis was carried out on 21 classes of different cardiac pathologies classified as anomalous; and (c) the possibility to classify anomalies even in ECG segments containing, at the same time, more than one class of cardiac pathologies. Moreover, 1D-CNN based architectures can allow an implementation of the system on cheap smart devices with low computational complexity. The system was tested on the ECG signals from the MIT-BIH ECG Arrhythmia Database for the MLII derivation. Two different experiments were carried out, showing remarkable performance compared to other similar systems. The best result showed high accuracy and recall, computed in terms of ECG segments and even higher accuracy and recall in terms of patients alerted, therefore considering the detection of anomalies with respect to entire ECG recordings.

https://www.mdpi.com/2313-433X/7/2/26/pdf

Personal Heart Health Monitoring Based on 1D Convolutional Neural Network.

https://robots.iopscience.iop.org/article/10.1088/1742-6596/2040/1/012001/pdf

Lung Cancer Detection using VGG NET 16 Architecture

Background: Anemia is the most common hematological disorder. The purpose of this study was to establish and validate a deep-learning model to predict Hgb concentrations and screen anemia using ultra-wide-field (UWF) fundus images. Methods: The study was conducted at Peking Union Medical College Hospital. Optos color images taken between January 2017 and June 2021 were screened for building the dataset. ASModel_UWF using UWF images was developed. Mean absolute error (MAE) and area under the receiver operating characteristics curve (AUC) were used to evaluate its performance. Saliency maps were generated to make the visual explanation of the model. Results: ASModel_UWF acquired the MAE of the prediction task of 0.83 g/dl (95%CI: 0.81–0.85 g/dl) and the AUC of the screening task of 0.93 (95%CI: 0.92–0.95). Compared with other screening approaches, it achieved the best performance of AUC and sensitivity when the test dataset size was larger than 1000. The model tended to focus on the area around the optic disc, retinal vessels, and some regions located at the peripheral area of the retina, which were undetected by non-UWF imaging. Conclusion: The deep-learning model ASModel_UWF could both predict Hgb concentration and screen anemia in a non-invasive and accurate way with high efficiency.

/pdf/deep-learning-based-hemoglobin-concentration-prediction-and-123q0r8h.pdf

Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images

The application of electronic findings to biology and medicine has significantly impacted health and wellbeing [...]

https://www.mdpi.com/2079-9292/10/11/1242/pdf

Bioelectronic technologies and artificial intelligence for medical diagnosis and healthcare

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.

https://www.mdpi.com/2079-9292/9/8/1309/pdf

Semantic Segmentation of Conjunctiva Region for Non-Invasive Anemia Detection Applications

Anaemia is one of the most prevalent nutritional deficiency disorders in the world that affects 1.62 billion people of all age groups. Its effects are more significant in the preschool-age children and pregnant women. The objective of this work is to develop a noninvasive method for identifying the anaemic status of a person by estimating their haemoglobin (Hb) level. Data collected from 135 participants is used for developing this model in which 80% of them (108 participants) were classified as a training group and the rest (27 participants) were grouped into a test group and their data is used for testing the model that’s based on the Ridge Regression algorithm. Haemoglobin level of a person is predicted from their digital image of the lower palpebral conjunctiva and basic details like age, sex, height, weight and BMI. These predicted values are closer to the values measured by the standard invasive methods and the Pearson correlation coefficients between the measured haemoglobin value and the predicted haemoglobin value are 0.722 and 0.705 for training and testing respectively. This model is trained to perform well with any smartphone in almost any non-ideal lighting condition without the usage of any external hardware. A web application and mobile application both called 'Chromanalysis' were developed and made available to anyone for screening their anaemic condition with their conjunctiva image and other basic details. This application will help users to assess their haemoglobin levels frequently without undergoing invasive procedures.

Ridge regression algorithm based non-invasive anaemia screening using conjunctiva images

- A multi modality biometric authentication system can combine information from various modalities and provides accurate results compared to biometric systems used individually. A novel ensemble classifier-based multimodal biometric authentication system has been proposed in this work. The performance of the proposed multimodal authentication system is measured using parameters such as Accuracy, Sensitivity and Specificity and compared with the SVM classifier, Decision tree classifier when fingerprint, Iris, and Face features are used. The results of the multimodal biometric system are also compared with the biometric authentication system when fingerprint features are used and combined with Fingerprint & Iris features. The proposed ensemble classifier-based multimodal biometric authentication system provides an accuracy of 96.75%, Sensitivity of 94.74%, Specificity of 98.95%, FAR of 1.04 and FRR of 5.26. The proposed ensemble classifier outperforms SVM and decision tree classifiers regarding performance measures.

/pdf/design-and-development-of-an-improved-multimodal-biometric-3g5eo0qe.pdf

Sivachandar Kasiviswanathan

Papers

Semantic Segmentation of Conjunctiva Region for Non-Invasive Anemia Detection Applications

Ridge regression algorithm based non-invasive anaemia screening using conjunctiva images

Design and Development of an Improved Multimodal Biometric Authentication System using Machine learning Classifiers