Browsing by Author "Attallah, Omneya"

Now showing 1 - 2 of 2
  • Thumbnail Image
    AI-Based Pipeline for Classifying Pediatric Medulloblastoma Using Histopathological and Textural Images
    Attallah, Omneya; Zaghlool, Shaza (MDPI, 2022-02-03)
    Pediatric medulloblastomas (MBs) are the most common type of malignant brain tumors in children. They are among the most aggressive types of tumors due to their potential for metastasis. Although this disease was initially considered a single disease, pediatric MBs can be considerably heterogeneous. Current MB classification schemes are heavily reliant on histopathology. However, the classification of MB from histopathological images is a manual process that is expensive, time-consuming, and prone to error. Previous studies have classified MB subtypes using a single feature extraction method that was based on either deep learning or textural analysis. Here, we combine textural analysis with deep learning techniques to improve subtype identification using histopathological images from two medical centers. Three state-of-the-art deep learning models were trained with textural images created from two texture analysis methods in addition to the original histopathological images, enabling the proposed pipeline to benefit from both the spatial and textural information of the images. Using a relatively small number of features, we show that our automated pipeline can yield an increase in the accuracy of classification of pediatric MB compared with previously reported methods. A refined classification of pediatric MB subgroups may provide a powerful tool for individualized therapies and identification of children with increased risk of complications.
  • Thumbnail Image
    Wearable Accelerometer and sEMG-Based Upper Limb BSN for Tele-Rehabilitation
    Baraka, Ahmed; Shaban, Heba; Abou El-Nasr, Mohamad; Attallah, Omneya (MDPI, 2019-07-12)
    Assessment of human locomotion using wearable sensors is an efficient way of getting useful information about human health status, and determining human locomotion abnormalities. Wearable sensors do not only provide the opportunity to assess the behavior of patients as it happens in their daily life activities, but also provide quantitative, meaningful feedback data of patients to their therapists. This can pinpoint the cause of problems and help in maximizing their recovery rates. The popularity of using wearable sensors has received attention from a number of researchers from both the academic and industrial fields in the past few years. The different types of wearable sensors have given birth to the realization of a standard measurement model that can support different types of applications. Wireless body area networks (WBANs) are starting to replace traditional healthcare systems by enabling long-term monitoring of patients and tele-rehabilitation, especially those who suffer from chronic diseases. This paper investigates using wearable accelerometers and surface electromyography (EMG) in human locomotion monitoring for tele-rehabilitation. It proposes and investigates new positions for the proposed sensors, and compares the measured signals to similar techniques proposed in the literature. Realistic measurements show that the proposed positions of surface EMG sensors (on the forearm muscles) provide more reliable results in the classification of motion abnormality as compared to the sensor positions proposed in the literature (biceps muscles). Seven statistical features were extracted from accelerometer signals, and four time domain (TD) features are extracted from EMG signals. These features are used to construct six machine learning classifiers for automatic classification of Parkinson’s tremor. These models include; decision tree (DT), linear discriminant analysis analysis (LDA), k-nearest-neighbor (kNN), support vector machine (SVM), boosted tree and bagged tree classifiers. The performance of the applied classifiers is analyzed using accuracy, confusion matrix, and area under ROC (AUC) curve. The results are also compared to corresponding findings in the literature. The experimental results show that the highest classification accuracy is achieved when using the proposed measurement set and bagged tree classifier with a value of 99.6%.