Machine Learning Techniques for Medical Image Processing
Authors:
- 18 November 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
In last decade, machine learning (ML) techniques increased the capability to automatically learn the experience without being explicitly programmed. Different machine learning methods are used for a number of tasks such as image processing, predictive analytics, data mining, and are used for classification, regression, clustering, and dimensionality reduction. ML is widely utilized in medical imaging research field. This paper introduces a survey on ML used in medical image processing and it focuses on two main types (supervised and unsupervised learning) to importance them in medical image processing with explains the foremost important algorithms of machine learning, discussing the most important advantages and drawbacks of applying Machine Learning techniques in medical imaging. In addition, some common algorithms were applied like k-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Trees, Logistic Regression and Random Forest on medical dataset in order to check the efficiency of algorithms.Keywords
This publication has 7 references indexed in Scilit:
- Machine Learning: Algorithms, Real-World Applications and Research DirectionsSN Computer Science, 2021
- Machine Learning Algorithms and their Real-life Applications: A SurveySSRN Electronic Journal, 2020
- Research on Machine Learning and Its Algorithms and DevelopmentJournal of Physics: Conference Series, 2020
- A Quick Review of Machine Learning Algorithms2019
- A survey on deep learning in medical image analysisMedical Image Analysis, 2017
- Machine learning approaches in medical image analysis: From detection to diagnosisMedical Image Analysis, 2016
- A survey on artificial intelligence approaches for medical image classificationIndian Journal of Science and Technology, 2011