Microscopic malaria parasitemia diagnosis and grading on benchmark datasets

Nazir

et al. 2019

Self Cite

The emergence of cloud infrastructure has the potential to provide significant benefits in a variety of areas in the medical imaging field. The driving force behind the extensive use of cloud infrastructure for medical image processing is the exponential increase in the size of computed tomography (CT) and magnetic resonance imaging (MRI) data. The size of a single CT/MRI image has increased manifold since the inception of these imagery techniques. This demand for the introduction of effective and efficient frameworks for extracting relevant and most suitable information (features) from these sizeable images. As early detection of lungs cancer can significantly increase the chances of survival of a lung scanner patient, an effective and efficient nodule detection system can play a vital role. In this article, we have proposed a novel classification framework for lungs nodule classification with less false positive rates (FPRs), high accuracy, sensitivity rate, less computationally expensive and uses a small set of features while preserving edge and texture information. The proposed framework comprises multiple phases that include image contrast enhancement, segmentation, feature extraction, followed by an employment of these features for training and testing of a selected classifier. Image preprocessing and feature selection being the primary steps—playing their vital role in achieving improved classification accuracy. We have empirically tested the efficacy of our technique by utilizing the well‐known Lungs Image Consortium Database dataset. The results prove that the technique is highly effective for reducing FPRs with an impressive sensitivity rate of 97.45%.

Section: Introductionmentioning

confidence: 99%

Lungs nodule detection framework from computed tomography images using support vector machine

Nazir

et al. 2019

Self Cite

“…One of the challenging tasks in machine learning is to handle class imbalance issue. Due to an unequal number of samples of different classes in training data, the trained model can become biased towards one class leading to model poor performance (Rehman, Abbas, Saba, Mahmood, et al, ; Rehman, Abbas, Saba, Mehmood, et al, ; Rehman, Abbas, Saba, Rahman, et al, ). To address this problem, we worked on three different methods of class balancing as listed below: No balancing : Training models without any class imbalance handling technique. Sample‐based balancing : Let U is set of all patches, equal number of random samples ( E ) from each class are selected and these samples are assumed to be representative of its particular class.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…Brain tumors are also categorized based on their origin: primary brain tumors are the lesions that emerge within the brain whereas secondary brain tumors (metastatic tumors) originate at a different location of the body and move to the brain. There are different categorization schemes designed by researchers but the scheme designed by the World Health Organization (WHO) is considered to be the standard (Aurangzeb, Muhammad Attique, Saba, Javed, & Iqbal, ; Fahad, Khan, Saba, Rehman, & Iqbal, ; Husham, Alkawaz, Saba, Rehman, & Alghamdi, ; Jamal, Hazim Alkawaz, Rehman, & Saba, ; Khan et al, , ; Rehman, Abbas, Saba, Rahman, et al, ; Rehman, Abbas, Saba, Mehmood, et al, ; Rehman, Abbas, Saba, Mahmood, & Kolivand, ; Saba, ; Saba, Al‐Zahrani, & Rehman, ; Saba, Rehman, Mehmood, Kolivand, Uddin, et al, ; Saba, Rehman, Mehmood, Kolivand, & Sharif, ). WHO has made more than 120 categories for a brain tumor and each category is further graded from I to IV (Louis et al, ).…”

Section: Introductionmentioning

confidence: 99%

Deep learning model integrating features and novel classifiers fusion for brain tumor segmentation

Iqbal

Saba

et al. 2019

Self Cite

Automatic and precise segmentation and classification of tumor area in medical images is still a challenging task in medical research. Most of the conventional neural network based models usefully connected or convolutional neural networks to perform segmentation and classification. In this research, we present deep learning models using long short term memory (LSTM) and convolutional neural networks (ConvNet) for accurate brain tumor delineation from benchmark medical images. The two different models, that is, ConvNet and LSTM networks are trained using the same data set and combined to form an ensemble to improve the results. We used publicly available MICCAI BRATS 2015 brain cancer data set consisting of MRI images of four modalities T1, T2, T1c, and FLAIR. To enhance the quality of input images, multiple combinations of preprocessing methods such as noise removal, histogram equalization, and edge enhancement are formulated and best performer combination is applied. To cope with the class imbalance problem, class weighting is used in proposed models. The trained models are tested on validation data set taken from the same image set and results obtained from each model are reported. The individual score (accuracy) of ConvNet is found 75% whereas for LSTM based network produced 80% and ensemble fusion produced 82.29% accuracy.

“…The advancement in the medical images analysis has significantly improved the health care system in the last two decades (Rehman, Abbas, Saba, Mahmood, & Kolivand, ; Rehman et al, b, 2018c). Generally, diagnosing DR is performed by an ophthalmologist through manual or visual interpretation of patient, which is time‐consuming as well prone to human error.…”

Section: Introduction and Related Workmentioning

confidence: 99%

An ensemble classification of exudates in color fundus images using an evolutionary algorithm based optimal features selection

Ullah

Saba

Islam

et al. 2019

Self Cite

Atomic recognition of the Exudates (EXs), the major symbol of diabetic retinopathy is essential for automated retinal images analysis. In this article, we proposed a novel machine learning technique for early detection and classification of EXs in color fundus images. The major challenge observed in the classification technique is the selection of optimal features to reduce computational time and space complexity and to provide a high degree of classification accuracy. To address these challenges, this article proposed an evolutionary algorithm based solution for optimal feature selection, which accelerates the classification process and reduces computational complexity. Similarly, three well‐known classifiers that is, Naïve Bayes classifier, Support Vector Machine, and Artificial Neural Network are used for the classification of EXs. Moreover, an ensemble‐based classifier is used for the selection of best classifier on the basis of majority voting technique. Experiments are performed on three well‐known benchmark datasets and a real dataset developed at local Hospital. It has been observed that the proposed technique achieved an accuracy of 98% in the detection and classification of EXs in color fundus images.