A novel systematic approach to diagnose brain tumor using integrated type-II fuzzy logic and ANFIS (adaptive neuro-fuzzy inference system) model.
Saved in:
| Title: | A novel systematic approach to diagnose brain tumor using integrated type-II fuzzy logic and ANFIS (adaptive neuro-fuzzy inference system) model. |
|---|---|
| Authors: | Chatterjee, Subhashis1 (AUTHOR), Das, Ananya1 (AUTHOR) ananyadas16@gmail.com |
| Source: | Soft Computing - A Fusion of Foundations, Methodologies & Applications. Aug2020, Vol. 24 Issue 15, p11731-11754. 24p. |
| Subjects: | Brain tumors, Fuzzy logic, Markov random fields, Feature extraction, Fuzzy systems, Algorithms |
| Abstract: | Brain tumor is an alarming threat among children and adults worldwide. Early detection and proper diagnosis of the tumor can enhance the chance of accurate survival among the individuals. Segmentation and classification of the detected tumor are based on its grade, i.e., criticality intensifies the survival rate and accurate treatment planning. However, manual segmentation of gliomas is time-consuming and results in an inaccurate diagnosis. Prompted by these facts, a multi-module automated framework has been developed to segment the brain multi-resonance images and classify it into two major classes, namely benign (low-grade) and malignant (high-grade). The present work is divided into four distinct modules: pre-processing, segmentation (clustering), feature extraction and classification. An efficient segmentation technique of the glioma images is proposed, which thereby provides a novel approach for the detection algorithm. Subsequently, prominent features characterizing mass effect, contrast, midline shift and irregularity of the edges of the tumor that are necessary for the physicians to detect tumor, are extracted. Using an ensemble of type-II fuzzy inference system and adaptive neuro-fuzzy inference system, a novel classifying technique has been developed to classify the detected tumor incorporating the extracted features. Finally, the research is tested and validated to show its consistency and accuracy using the images of patients of the BRATS dataset where the ground truth is made available. The detailed implementation of the proposed hybrid model is accomplished to establish its superiority in recognizing the grade of the tumor over other models mentioned in the literature survey. [ABSTRACT FROM AUTHOR] |
| Copyright of Soft Computing - A Fusion of Foundations, Methodologies & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 144404774 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A novel systematic approach to diagnose brain tumor using integrated type-II fuzzy logic and ANFIS (adaptive neuro-fuzzy inference system) model. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Chatterjee%2C+Subhashis%22">Chatterjee, Subhashis</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Das%2C+Ananya%22">Das, Ananya</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> ananyadas16@gmail.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Soft+Computing+-+A+Fusion+of+Foundations%2C+Methodologies+%26+Applications%22">Soft Computing - A Fusion of Foundations, Methodologies & Applications</searchLink>. Aug2020, Vol. 24 Issue 15, p11731-11754. 24p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Brain+tumors%22">Brain tumors</searchLink><br /><searchLink fieldCode="DE" term="%22Fuzzy+logic%22">Fuzzy logic</searchLink><br /><searchLink fieldCode="DE" term="%22Markov+random+fields%22">Markov random fields</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Fuzzy+systems%22">Fuzzy systems</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Brain tumor is an alarming threat among children and adults worldwide. Early detection and proper diagnosis of the tumor can enhance the chance of accurate survival among the individuals. Segmentation and classification of the detected tumor are based on its grade, i.e., criticality intensifies the survival rate and accurate treatment planning. However, manual segmentation of gliomas is time-consuming and results in an inaccurate diagnosis. Prompted by these facts, a multi-module automated framework has been developed to segment the brain multi-resonance images and classify it into two major classes, namely benign (low-grade) and malignant (high-grade). The present work is divided into four distinct modules: pre-processing, segmentation (clustering), feature extraction and classification. An efficient segmentation technique of the glioma images is proposed, which thereby provides a novel approach for the detection algorithm. Subsequently, prominent features characterizing mass effect, contrast, midline shift and irregularity of the edges of the tumor that are necessary for the physicians to detect tumor, are extracted. Using an ensemble of type-II fuzzy inference system and adaptive neuro-fuzzy inference system, a novel classifying technique has been developed to classify the detected tumor incorporating the extracted features. Finally, the research is tested and validated to show its consistency and accuracy using the images of patients of the BRATS dataset where the ground truth is made available. The detailed implementation of the proposed hybrid model is accomplished to establish its superiority in recognizing the grade of the tumor over other models mentioned in the literature survey. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Soft Computing - A Fusion of Foundations, Methodologies & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=144404774 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00500-019-04635-7 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 24 StartPage: 11731 Subjects: – SubjectFull: Brain tumors Type: general – SubjectFull: Fuzzy logic Type: general – SubjectFull: Markov random fields Type: general – SubjectFull: Feature extraction Type: general – SubjectFull: Fuzzy systems Type: general – SubjectFull: Algorithms Type: general Titles: – TitleFull: A novel systematic approach to diagnose brain tumor using integrated type-II fuzzy logic and ANFIS (adaptive neuro-fuzzy inference system) model. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Chatterjee, Subhashis – PersonEntity: Name: NameFull: Das, Ananya IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 08 Text: Aug2020 Type: published Y: 2020 Identifiers: – Type: issn-print Value: 14327643 Numbering: – Type: volume Value: 24 – Type: issue Value: 15 Titles: – TitleFull: Soft Computing - A Fusion of Foundations, Methodologies & Applications Type: main |
| ResultId | 1 |
