Brain pathology identification using computer aided diagnostic tool: A systematic review. (April 2020)

• Record Type: Journal Article
• Authors: Gudigar, Anjan; Raghavendra, U.; Hegde, Ajay; Kalyani, M.; Ciaccio, Edward J.; Rajendra Acharya, U.
• Is Part Of: Computer methods and programs in biomedicine. Volume 187(2020)
• Publication Date: 2020-04
• Subjects: Brain pathology -- Computer aided diagnostic -- Classification -- Deep learning -- Feature extraction -- Magnetic resonance imaging; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2019.105205
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: The state-of-the-art techniques for brain pathology identification (BPI) with two-class and multiclass are analyzed using brain magnetic resonance imaging. The detailed investigation of handcrafted feature learning based approach and deep neural network based approach is performed. The open issues for further advancement in BPI are discussed. Abstract: Computer aided diagnostic (CAD) has become a significant tool in expanding patient quality-of-life by reducing human errors in diagnosis. CAD can expedite decision-making on complex clinical data automatically. Since brain diseases can be fatal, rapid identification of brain pathology to prolong patient life is an important research topic. Many algorithms have been proposed for efficient brain pathology identification (BPI) over the past decade. Constant refinement of the various image processing algorithms must take place to expand performance of the automatic BPI task. In this paper, a systematic survey of contemporary BPI algorithms using brain magnetic resonance imaging (MRI) is presented. A summarization of recent literature provides investigators with a helpful synopsis of the domain. Furthermore, to enhance the performance of BPI, future research directions are indicated.