Loading…
Computational model for breast cancer diagnosis using HFSE framework
Mammography is one of the imaging modalities used in diagnosing breast cancer at an earlier stage. Misdiagnosis leads to risks for the patients. Better feature extraction and selection techniques can reduce misdiagnoses as they are essential in better-performing classifiers. The proposed approach in...
Saved in:
Published in: | Biomedical signal processing and control 2023-09, Vol.86, p.105121, Article 105121 |
---|---|
Main Authors: | , , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c300t-b49894027a0fb087e7d231332b03fb4a51a9b0ebdb858a151437db5f1ec6579c3 |
---|---|
cites | cdi_FETCH-LOGICAL-c300t-b49894027a0fb087e7d231332b03fb4a51a9b0ebdb858a151437db5f1ec6579c3 |
container_end_page | |
container_issue | |
container_start_page | 105121 |
container_title | Biomedical signal processing and control |
container_volume | 86 |
creator | Kumari, Deepa Yannam, Pavan Kumar Reddy Gohel, Isha Nilesh Naidu, Mutyala Venkata Sai Subhash Arora, Yash Rajita, B.S.A.S. Panda, Subhrakanta Christopher, Jabez |
description | Mammography is one of the imaging modalities used in diagnosing breast cancer at an earlier stage. Misdiagnosis leads to risks for the patients. Better feature extraction and selection techniques can reduce misdiagnoses as they are essential in better-performing classifiers. The proposed approach in this paper introduces a novel Hybrid Feature Extraction and Hybrid Feature Selection (HFSE) framework. It uses mammograms from Digital Database for Screening Mammography (DDSM) datasets to classify mammograms into benign and malignant images. This paper presents a novel hybrid feature extraction approach from the Gray level co-occurrence matrix (GLCM), Linear local binary pattern (LBP), Gabor, and Tamura. Combinedly, it extracts 104 features to train the advanced classifiers such as Logistic Regression, Linear Perceptron, Support Vector Machine, Decision Tree, and Artificial Neural Network. The proposed Hybrid feature extraction method vigorously compares combinations of existing single feature extraction methods. The paper also presents a novel hybrid feature selection approach to choose a subset of the most relevant feature. It compares the Intrinsic feature with the proposed hybrid feature selection method. Hyperparameter tuning and Pipeline optimization techniques applied to the classifiers improve their performance metrics. The experimental results show that the proposed framework performs better using Hybrid feature extraction and feature selection on Artificial Neural Networks. This paper makes a comparative analysis of the related works. It outperforms by achieving a classifier accuracy of 94.57%, specificity of 91.80%, the sensitivity of 95.59 %, and an F1-score of 94.89% on Artificial Neural Networks.
[Display omitted]
•The proposed HFSE framework uses hybrid features extraction algorithm by extracting texture features through Gray Level Concurrence Matrix (GLCM), Gabor, Tamura, and Local Binary Pattern (LBP).•This research uses hyperparameter tuning through GridSearch and RandomSearch and pipeline optimization techniques to improve the classifier’s performance.•It also innovatively uses Hybrid feature selection on 104 features extracted from hybrid feature extraction. It selects 23 important features on the standard scale as it gives the best performance.•It also performs comparative analysis on the performance of proposed hybrid feature extraction, hyperparameter tuning, intrinsic-Tree Based Feature Selection, and Hybrid Feature Selection techniques |
doi_str_mv | 10.1016/j.bspc.2023.105121 |
format | article |
fullrecord | <record><control><sourceid>elsevier_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1016_j_bspc_2023_105121</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1746809423005542</els_id><sourcerecordid>S1746809423005542</sourcerecordid><originalsourceid>FETCH-LOGICAL-c300t-b49894027a0fb087e7d231332b03fb4a51a9b0ebdb858a151437db5f1ec6579c3</originalsourceid><addsrcrecordid>eNp9kMtKAzEUhoMoWKsv4CovMPXkMpMMuJHaWqHgQl2HXEtqZ1KSqeLbO6W6dXUOB77D_38I3RKYESDN3XZmyt7OKFA2HmpCyRmaEMGbShKQ5387tPwSXZWyBeBSED5Bj_PU7Q-DHmLq9Q53yfkdDiljk70uA7a6tz5jF_WmTyUWfCix3-DV8nWBQ9ad_0r54xpdBL0r_uZ3TtH7cvE2X1Xrl6fn-cO6sgxgqAxvZcuBCg3BgBReOMoIY9QAC4brmujWgDfOyFpqUhPOhDN1IN42tWgtmyJ6-mtzKiX7oPY5djp_KwLq6EFt1dGDOnpQJw8jdH-C_JjsM_qsio1-bOVi9nZQLsX_8B8cKWZG</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Computational model for breast cancer diagnosis using HFSE framework</title><source>Elsevier</source><creator>Kumari, Deepa ; Yannam, Pavan Kumar Reddy ; Gohel, Isha Nilesh ; Naidu, Mutyala Venkata Sai Subhash ; Arora, Yash ; Rajita, B.S.A.S. ; Panda, Subhrakanta ; Christopher, Jabez</creator><creatorcontrib>Kumari, Deepa ; Yannam, Pavan Kumar Reddy ; Gohel, Isha Nilesh ; Naidu, Mutyala Venkata Sai Subhash ; Arora, Yash ; Rajita, B.S.A.S. ; Panda, Subhrakanta ; Christopher, Jabez</creatorcontrib><description>Mammography is one of the imaging modalities used in diagnosing breast cancer at an earlier stage. Misdiagnosis leads to risks for the patients. Better feature extraction and selection techniques can reduce misdiagnoses as they are essential in better-performing classifiers. The proposed approach in this paper introduces a novel Hybrid Feature Extraction and Hybrid Feature Selection (HFSE) framework. It uses mammograms from Digital Database for Screening Mammography (DDSM) datasets to classify mammograms into benign and malignant images. This paper presents a novel hybrid feature extraction approach from the Gray level co-occurrence matrix (GLCM), Linear local binary pattern (LBP), Gabor, and Tamura. Combinedly, it extracts 104 features to train the advanced classifiers such as Logistic Regression, Linear Perceptron, Support Vector Machine, Decision Tree, and Artificial Neural Network. The proposed Hybrid feature extraction method vigorously compares combinations of existing single feature extraction methods. The paper also presents a novel hybrid feature selection approach to choose a subset of the most relevant feature. It compares the Intrinsic feature with the proposed hybrid feature selection method. Hyperparameter tuning and Pipeline optimization techniques applied to the classifiers improve their performance metrics. The experimental results show that the proposed framework performs better using Hybrid feature extraction and feature selection on Artificial Neural Networks. This paper makes a comparative analysis of the related works. It outperforms by achieving a classifier accuracy of 94.57%, specificity of 91.80%, the sensitivity of 95.59 %, and an F1-score of 94.89% on Artificial Neural Networks.
[Display omitted]
•The proposed HFSE framework uses hybrid features extraction algorithm by extracting texture features through Gray Level Concurrence Matrix (GLCM), Gabor, Tamura, and Local Binary Pattern (LBP).•This research uses hyperparameter tuning through GridSearch and RandomSearch and pipeline optimization techniques to improve the classifier’s performance.•It also innovatively uses Hybrid feature selection on 104 features extracted from hybrid feature extraction. It selects 23 important features on the standard scale as it gives the best performance.•It also performs comparative analysis on the performance of proposed hybrid feature extraction, hyperparameter tuning, intrinsic-Tree Based Feature Selection, and Hybrid Feature Selection techniques. It helps in concluding the best possible scenario for the HFSE framework for overall improvement in the classification process.•This approach not only gives better accuracy of 94.57% on the Artificial Neural Network (ANN) classifier but also performs better for other important metrics. It results in a better sensitivity of 95.59%, specificity of 91.80% and F1-score of 94.89% on the ANN classifier.</description><identifier>ISSN: 1746-8094</identifier><identifier>EISSN: 1746-8108</identifier><identifier>DOI: 10.1016/j.bspc.2023.105121</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Classifier ; Hybrid feature extraction ; Hybrid feature selection ; Mammogram ; Texture feature</subject><ispartof>Biomedical signal processing and control, 2023-09, Vol.86, p.105121, Article 105121</ispartof><rights>2023 Elsevier Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c300t-b49894027a0fb087e7d231332b03fb4a51a9b0ebdb858a151437db5f1ec6579c3</citedby><cites>FETCH-LOGICAL-c300t-b49894027a0fb087e7d231332b03fb4a51a9b0ebdb858a151437db5f1ec6579c3</cites><orcidid>0000-0002-7089-8763 ; 0000-0003-4768-772X ; 0000-0002-3117-4690 ; 0000-0002-0696-9790</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Kumari, Deepa</creatorcontrib><creatorcontrib>Yannam, Pavan Kumar Reddy</creatorcontrib><creatorcontrib>Gohel, Isha Nilesh</creatorcontrib><creatorcontrib>Naidu, Mutyala Venkata Sai Subhash</creatorcontrib><creatorcontrib>Arora, Yash</creatorcontrib><creatorcontrib>Rajita, B.S.A.S.</creatorcontrib><creatorcontrib>Panda, Subhrakanta</creatorcontrib><creatorcontrib>Christopher, Jabez</creatorcontrib><title>Computational model for breast cancer diagnosis using HFSE framework</title><title>Biomedical signal processing and control</title><description>Mammography is one of the imaging modalities used in diagnosing breast cancer at an earlier stage. Misdiagnosis leads to risks for the patients. Better feature extraction and selection techniques can reduce misdiagnoses as they are essential in better-performing classifiers. The proposed approach in this paper introduces a novel Hybrid Feature Extraction and Hybrid Feature Selection (HFSE) framework. It uses mammograms from Digital Database for Screening Mammography (DDSM) datasets to classify mammograms into benign and malignant images. This paper presents a novel hybrid feature extraction approach from the Gray level co-occurrence matrix (GLCM), Linear local binary pattern (LBP), Gabor, and Tamura. Combinedly, it extracts 104 features to train the advanced classifiers such as Logistic Regression, Linear Perceptron, Support Vector Machine, Decision Tree, and Artificial Neural Network. The proposed Hybrid feature extraction method vigorously compares combinations of existing single feature extraction methods. The paper also presents a novel hybrid feature selection approach to choose a subset of the most relevant feature. It compares the Intrinsic feature with the proposed hybrid feature selection method. Hyperparameter tuning and Pipeline optimization techniques applied to the classifiers improve their performance metrics. The experimental results show that the proposed framework performs better using Hybrid feature extraction and feature selection on Artificial Neural Networks. This paper makes a comparative analysis of the related works. It outperforms by achieving a classifier accuracy of 94.57%, specificity of 91.80%, the sensitivity of 95.59 %, and an F1-score of 94.89% on Artificial Neural Networks.
[Display omitted]
•The proposed HFSE framework uses hybrid features extraction algorithm by extracting texture features through Gray Level Concurrence Matrix (GLCM), Gabor, Tamura, and Local Binary Pattern (LBP).•This research uses hyperparameter tuning through GridSearch and RandomSearch and pipeline optimization techniques to improve the classifier’s performance.•It also innovatively uses Hybrid feature selection on 104 features extracted from hybrid feature extraction. It selects 23 important features on the standard scale as it gives the best performance.•It also performs comparative analysis on the performance of proposed hybrid feature extraction, hyperparameter tuning, intrinsic-Tree Based Feature Selection, and Hybrid Feature Selection techniques. It helps in concluding the best possible scenario for the HFSE framework for overall improvement in the classification process.•This approach not only gives better accuracy of 94.57% on the Artificial Neural Network (ANN) classifier but also performs better for other important metrics. It results in a better sensitivity of 95.59%, specificity of 91.80% and F1-score of 94.89% on the ANN classifier.</description><subject>Classifier</subject><subject>Hybrid feature extraction</subject><subject>Hybrid feature selection</subject><subject>Mammogram</subject><subject>Texture feature</subject><issn>1746-8094</issn><issn>1746-8108</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp9kMtKAzEUhoMoWKsv4CovMPXkMpMMuJHaWqHgQl2HXEtqZ1KSqeLbO6W6dXUOB77D_38I3RKYESDN3XZmyt7OKFA2HmpCyRmaEMGbShKQ5387tPwSXZWyBeBSED5Bj_PU7Q-DHmLq9Q53yfkdDiljk70uA7a6tz5jF_WmTyUWfCix3-DV8nWBQ9ad_0r54xpdBL0r_uZ3TtH7cvE2X1Xrl6fn-cO6sgxgqAxvZcuBCg3BgBReOMoIY9QAC4brmujWgDfOyFpqUhPOhDN1IN42tWgtmyJ6-mtzKiX7oPY5djp_KwLq6EFt1dGDOnpQJw8jdH-C_JjsM_qsio1-bOVi9nZQLsX_8B8cKWZG</recordid><startdate>202309</startdate><enddate>202309</enddate><creator>Kumari, Deepa</creator><creator>Yannam, Pavan Kumar Reddy</creator><creator>Gohel, Isha Nilesh</creator><creator>Naidu, Mutyala Venkata Sai Subhash</creator><creator>Arora, Yash</creator><creator>Rajita, B.S.A.S.</creator><creator>Panda, Subhrakanta</creator><creator>Christopher, Jabez</creator><general>Elsevier Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-7089-8763</orcidid><orcidid>https://orcid.org/0000-0003-4768-772X</orcidid><orcidid>https://orcid.org/0000-0002-3117-4690</orcidid><orcidid>https://orcid.org/0000-0002-0696-9790</orcidid></search><sort><creationdate>202309</creationdate><title>Computational model for breast cancer diagnosis using HFSE framework</title><author>Kumari, Deepa ; Yannam, Pavan Kumar Reddy ; Gohel, Isha Nilesh ; Naidu, Mutyala Venkata Sai Subhash ; Arora, Yash ; Rajita, B.S.A.S. ; Panda, Subhrakanta ; Christopher, Jabez</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c300t-b49894027a0fb087e7d231332b03fb4a51a9b0ebdb858a151437db5f1ec6579c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Classifier</topic><topic>Hybrid feature extraction</topic><topic>Hybrid feature selection</topic><topic>Mammogram</topic><topic>Texture feature</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kumari, Deepa</creatorcontrib><creatorcontrib>Yannam, Pavan Kumar Reddy</creatorcontrib><creatorcontrib>Gohel, Isha Nilesh</creatorcontrib><creatorcontrib>Naidu, Mutyala Venkata Sai Subhash</creatorcontrib><creatorcontrib>Arora, Yash</creatorcontrib><creatorcontrib>Rajita, B.S.A.S.</creatorcontrib><creatorcontrib>Panda, Subhrakanta</creatorcontrib><creatorcontrib>Christopher, Jabez</creatorcontrib><collection>CrossRef</collection><jtitle>Biomedical signal processing and control</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kumari, Deepa</au><au>Yannam, Pavan Kumar Reddy</au><au>Gohel, Isha Nilesh</au><au>Naidu, Mutyala Venkata Sai Subhash</au><au>Arora, Yash</au><au>Rajita, B.S.A.S.</au><au>Panda, Subhrakanta</au><au>Christopher, Jabez</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Computational model for breast cancer diagnosis using HFSE framework</atitle><jtitle>Biomedical signal processing and control</jtitle><date>2023-09</date><risdate>2023</risdate><volume>86</volume><spage>105121</spage><pages>105121-</pages><artnum>105121</artnum><issn>1746-8094</issn><eissn>1746-8108</eissn><abstract>Mammography is one of the imaging modalities used in diagnosing breast cancer at an earlier stage. Misdiagnosis leads to risks for the patients. Better feature extraction and selection techniques can reduce misdiagnoses as they are essential in better-performing classifiers. The proposed approach in this paper introduces a novel Hybrid Feature Extraction and Hybrid Feature Selection (HFSE) framework. It uses mammograms from Digital Database for Screening Mammography (DDSM) datasets to classify mammograms into benign and malignant images. This paper presents a novel hybrid feature extraction approach from the Gray level co-occurrence matrix (GLCM), Linear local binary pattern (LBP), Gabor, and Tamura. Combinedly, it extracts 104 features to train the advanced classifiers such as Logistic Regression, Linear Perceptron, Support Vector Machine, Decision Tree, and Artificial Neural Network. The proposed Hybrid feature extraction method vigorously compares combinations of existing single feature extraction methods. The paper also presents a novel hybrid feature selection approach to choose a subset of the most relevant feature. It compares the Intrinsic feature with the proposed hybrid feature selection method. Hyperparameter tuning and Pipeline optimization techniques applied to the classifiers improve their performance metrics. The experimental results show that the proposed framework performs better using Hybrid feature extraction and feature selection on Artificial Neural Networks. This paper makes a comparative analysis of the related works. It outperforms by achieving a classifier accuracy of 94.57%, specificity of 91.80%, the sensitivity of 95.59 %, and an F1-score of 94.89% on Artificial Neural Networks.
[Display omitted]
•The proposed HFSE framework uses hybrid features extraction algorithm by extracting texture features through Gray Level Concurrence Matrix (GLCM), Gabor, Tamura, and Local Binary Pattern (LBP).•This research uses hyperparameter tuning through GridSearch and RandomSearch and pipeline optimization techniques to improve the classifier’s performance.•It also innovatively uses Hybrid feature selection on 104 features extracted from hybrid feature extraction. It selects 23 important features on the standard scale as it gives the best performance.•It also performs comparative analysis on the performance of proposed hybrid feature extraction, hyperparameter tuning, intrinsic-Tree Based Feature Selection, and Hybrid Feature Selection techniques. It helps in concluding the best possible scenario for the HFSE framework for overall improvement in the classification process.•This approach not only gives better accuracy of 94.57% on the Artificial Neural Network (ANN) classifier but also performs better for other important metrics. It results in a better sensitivity of 95.59%, specificity of 91.80% and F1-score of 94.89% on the ANN classifier.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.bspc.2023.105121</doi><orcidid>https://orcid.org/0000-0002-7089-8763</orcidid><orcidid>https://orcid.org/0000-0003-4768-772X</orcidid><orcidid>https://orcid.org/0000-0002-3117-4690</orcidid><orcidid>https://orcid.org/0000-0002-0696-9790</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1746-8094 |
ispartof | Biomedical signal processing and control, 2023-09, Vol.86, p.105121, Article 105121 |
issn | 1746-8094 1746-8108 |
language | eng |
recordid | cdi_crossref_primary_10_1016_j_bspc_2023_105121 |
source | Elsevier |
subjects | Classifier Hybrid feature extraction Hybrid feature selection Mammogram Texture feature |
title | Computational model for breast cancer diagnosis using HFSE framework |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T19%3A59%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Computational%20model%20for%20breast%20cancer%20diagnosis%20using%20HFSE%20framework&rft.jtitle=Biomedical%20signal%20processing%20and%20control&rft.au=Kumari,%20Deepa&rft.date=2023-09&rft.volume=86&rft.spage=105121&rft.pages=105121-&rft.artnum=105121&rft.issn=1746-8094&rft.eissn=1746-8108&rft_id=info:doi/10.1016/j.bspc.2023.105121&rft_dat=%3Celsevier_cross%3ES1746809423005542%3C/elsevier_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c300t-b49894027a0fb087e7d231332b03fb4a51a9b0ebdb858a151437db5f1ec6579c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |