Brain tumor classification using deep CNN features via transfer learning.

Magnetic resonance imaging-based brain tumor grades classification and grading via convolutional neural networks and genetic algorithms

Brain tumor is one of the most dangerous cancers in people of all ages, and its grade recognition is a challenging problem for radiologists in health monitoring and automated diagnosis. Recently, numerous methods based on deep learning have been presented in the literature for brain tumor classification (BTC) in order to assist radiologists for a better diagnostic analysis. In this overview, we present an in-depth review of the surveys published so far and recent deep learning-based methods for BTC. Our survey covers the main steps of deep learning-based BTC methods, including preprocessing, features extraction, and classification, along with their achievements and limitations. We also investigate the state-of-the-art convolutional neural network models for BTC by performing extensive experiments using transfer learning with and without data augmentation. Furthermore, this overview describes available benchmark data sets used for the evaluation of BTC. Finally, this survey does not only look into the past literature on the topic but also steps on it to delve into the future of this area and enumerates some research directions that should be followed in the future, especially for personalized and smart healthcare.

Deep Learning for Multigrade Brain Tumor Classification in Smart Healthcare Systems: A Prospective Survey

Skin cancer diagnosis based on optimized convolutional neural network

A Review on Brain Tumor Diagnosis from MRI Images : Practical Implications, Key Achievements, and Lessons Learned

MRI based medical image analysis: Survey on brain tumor grade classification

A review of how machine learning methodology can be incorporated into the diagnosis of brain tumor and the recent segmentation and classification techniques on brain magnetic resonance images (MRI) is the objective of this paper. Early detection of a brain tumor and its grade facilitates easy diagnosis and treatment. In MRI, the tumor might appear clear to a physician but to extract all features that are not visible to human eye, digital image processing along with machine learning methodology is applied. This article aims to review the current trends in the grading of brain tumor with a focus on gliomas which include astrocytoma and also the reasons why gliomas are to be focused and studied. The leading-edge software packages, evaluation and validation metrics used in various approaches are discussed. With escalating brain tumor cases being reported, there is a demand for more and more advanced imaging methodologies, for their quicker grading and identification. The methodologies used in processing a digital image, when used along with machine learning, aids further diagnosis, treatment, prognosis and pre- and post-surgical procedures. In-depth understanding of medical images and diagnosis provided improvements in terms of accuracy. This was possible because these hybrid techniques assisted radiologists in taking a second opinion. The review article aims to give a brief introduction to brain tumors and imaging of brain tumors with a focus on gliomas. We discuss the different types of tumor and summarize about gliomas, tumor grading, symptoms, diagnosis, and treatment of brain tumor. The review extends with sections on imaging techniques, supervised and unsupervised methods of machine learning, deep learning, the different software's used in the area of medical imaging for image analysis segmentation, visualization, computing, reconstruction, registration, etc. The various imaging protocols that can be embedded and integrated into clinical practices are also listed. An in-depth review of why there is a need for advanced and efficient automated grading methods is exemplified in this work. This multidisciplinary work integrates various disciplines of pathology, radiology, machine learning and image processing. Finally, the current works, future developments, and trends are also discussed.

Medical Imaging With Intelligent Systems: A Review

A Combinational Network for High Density Noise Removal and Texture Classification Using Back Propagation Network

ABSTRACT The analysis of digital pathology images, catalyzes research and automate diagnosis for improving clinical care. Regardless of the advances in high-resolution and speedy scanning devices, the clinical analysis of Whole Slide Image (WSI) remains mainly as the work of an image analyst. The complications when working on these images are primarily, its enormous image size, as well as the heterogeneous nature of tissue regions. These reasons may lead to inefficient computer analysis. We propose a comprehensive algorithm to analyse, these large images by using small tile image analysis. The small tile images can be learnt individually in detail, rather than processing the whole high resolution WSI. The analysis of these small tile images helps us configure, the localised pathology image characteristics. The work flow involves extracting Perceptual Features (PF), Fourier Local Binary Patterns (FLBP), Histogram, Gabor and Gray Level Co-occurrence Matrix (GLCM) features from the tiled WSI. Then, the multidimensional feature set is provided to the classifiers like K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Naive Bayes (NB) and Logistic Regression (LR) for performance analysis. We evaluated our predictive models by automatically classifying image datasets (186 and 124) of brain tumour cases, using 10 fold cross validation. The model classified the images into Low Grade Glioma (LGG) and Glioblastoma Multiforme (GBM). It gives the highest accuracy of 93.5% for a feature combination of PF+FLBP+GLCM+GABOR with linear Support Vector Machine (linSVM) and Area under the Curve (AUC) of 0.9741 for the 186 image dataset. Also linSVM gives an accuracy of 96.8% with various feature combinations for the 124 image dataset. We did an exhaustive study on the performance of various sets of texture descriptors and classification models. This resulted in finding an optimised classification approach with a combined feature set that outperformed the original feature set classification. The proposed work is unique because it combines a wide range of feature extracting methods and an exhaustive list of classifiers showcasing the best method. The idea that, rather than selecting a region of interest from WSI for grade designation, all the regions in a slide are considered. This enables the involvement of each tile in making the final diagnostic decision, considering the heterogeneous nature of WSI. Our work can be extended for different tumour subtypes. Also, the experiment can be scaled with different sample sizes and finally the method works without a pathologist input.

Intelligent framework for brain tumor grading using advanced feature analysis

In the past, we only know robots that looked like a machine. Well nowadays, with the contribution of robots in our life and technological development, we can find many robots that look like human. Humanoid robotics can be said as the most complex robot types because the robots are completed with various components and programs so it can imitate human perfectly. Currently humanoid robots are being implemented in a wide range of industries. The most common place to find humanoid robots is in the entertainment industry. In present time robots has go into a wide development and innovation for real life needs. Depending on the applications a wide variety of humanoids have being developed in the field of space exploration, military, agriculture, construction and manufacture, education, sports, medical, research, entertainment etc. The new applications will require social interaction between humans and robots. If a robot is able to analyze and synthesize speech, eye movements, mimics, gestures, and body language, it will be capable of intuitive communication with humans. Last, but not least, humanoid robots are used as a tool to understand human intelligence. A detailed survey on the current types of humanoid based on its application is dealt in this paper. This is a complete paper on humanoid robotics.

https://www.jetir.org/papers/JETIR1407022.pdf

Geethu Mohan

Papers

MRI based medical image analysis: Survey on brain tumor grade classification

Medical Imaging With Intelligent Systems: A Review

A Combinational Network for High Density Noise Removal and Texture Classification Using Back Propagation Network

Intelligent framework for brain tumor grading using advanced feature analysis

A Survey on the Latest Types of Humanoids and Its Applications