BC<sup>2</sup>NetRF: Breast Cancer Classification from Mammogram Images Using Enhanced Deep Learning Features and Equilibrium-Jaya Controlled Regula Falsi-Based Features Selection
One of the most frequent cancers in women is breast cancer, and in the year 2022, approximately 287,850 new cases have been diagnosed. From them, 43,250 women died from this cancer. An early diagnosis of this cancer can help to overcome the mortality rate. However, the manual diagnosis of this cance...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/13/7/1238 |
_version_ | 1797608150870786048 |
---|---|
author | Kiran Jabeen Muhammad Attique Khan Jamel Balili Majed Alhaisoni Nouf Abdullah Almujally Huda Alrashidi Usman Tariq Jae-Hyuk Cha |
author_facet | Kiran Jabeen Muhammad Attique Khan Jamel Balili Majed Alhaisoni Nouf Abdullah Almujally Huda Alrashidi Usman Tariq Jae-Hyuk Cha |
author_sort | Kiran Jabeen |
collection | DOAJ |
description | One of the most frequent cancers in women is breast cancer, and in the year 2022, approximately 287,850 new cases have been diagnosed. From them, 43,250 women died from this cancer. An early diagnosis of this cancer can help to overcome the mortality rate. However, the manual diagnosis of this cancer using mammogram images is not an easy process and always requires an expert person. Several AI-based techniques have been suggested in the literature. However, still, they are facing several challenges, such as similarities between cancer and non-cancer regions, irrelevant feature extraction, and weak training models. In this work, we proposed a new automated computerized framework for breast cancer classification. The proposed framework improves the contrast using a novel enhancement technique called haze-reduced local-global. The enhanced images are later employed for the dataset augmentation. This step aimed at increasing the diversity of the dataset and improving the training capability of the selected deep learning model. After that, a pre-trained model named EfficientNet-b0 was employed and fine-tuned to add a few new layers. The fine-tuned model was trained separately on original and enhanced images using deep transfer learning concepts with static hyperparameters’ initialization. Deep features were extracted from the average pooling layer in the next step and fused using a new serial-based approach. The fused features were later optimized using a feature selection algorithm known as Equilibrium-Jaya controlled Regula Falsi. The Regula Falsi was employed as a termination function in this algorithm. The selected features were finally classified using several machine learning classifiers. The experimental process was conducted on two publicly available datasets—CBIS-DDSM and INbreast. For these datasets, the achieved average accuracy is 95.4% and 99.7%. A comparison with state-of-the-art (SOTA) technology shows that the obtained proposed framework improved the accuracy. Moreover, the confidence interval-based analysis shows consistent results of the proposed framework. |
first_indexed | 2024-03-11T05:39:27Z |
format | Article |
id | doaj.art-0354784c25d749e7b8b945389984d1c9 |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-11T05:39:27Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-0354784c25d749e7b8b945389984d1c92023-11-17T16:29:46ZengMDPI AGDiagnostics2075-44182023-03-01137123810.3390/diagnostics13071238BC<sup>2</sup>NetRF: Breast Cancer Classification from Mammogram Images Using Enhanced Deep Learning Features and Equilibrium-Jaya Controlled Regula Falsi-Based Features SelectionKiran Jabeen0Muhammad Attique Khan1Jamel Balili2Majed Alhaisoni3Nouf Abdullah Almujally4Huda Alrashidi5Usman Tariq6Jae-Hyuk Cha7Department of Computer Science, HITEC University, Taxila 47080, PakistanDepartment of Computer Science, HITEC University, Taxila 47080, PakistanCollege of Computer Science, King Khalid University, Abha 61413, Saudi ArabiaCollege of Computer Science and Engineering, University of Ha’il, Ha’il 81451, Saudi ArabiaDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaFaculty of Information Technology and Computing, Arab Open University, Ardiya 92400, KuwaitDepartment of Management, CoBA, Prince Sattam bin Abdulaziz University, Al-Kharj 11942, Saudi ArabiaDepartment of Computer Science, Hanyang University, Seoul 04763, Republic of KoreaOne of the most frequent cancers in women is breast cancer, and in the year 2022, approximately 287,850 new cases have been diagnosed. From them, 43,250 women died from this cancer. An early diagnosis of this cancer can help to overcome the mortality rate. However, the manual diagnosis of this cancer using mammogram images is not an easy process and always requires an expert person. Several AI-based techniques have been suggested in the literature. However, still, they are facing several challenges, such as similarities between cancer and non-cancer regions, irrelevant feature extraction, and weak training models. In this work, we proposed a new automated computerized framework for breast cancer classification. The proposed framework improves the contrast using a novel enhancement technique called haze-reduced local-global. The enhanced images are later employed for the dataset augmentation. This step aimed at increasing the diversity of the dataset and improving the training capability of the selected deep learning model. After that, a pre-trained model named EfficientNet-b0 was employed and fine-tuned to add a few new layers. The fine-tuned model was trained separately on original and enhanced images using deep transfer learning concepts with static hyperparameters’ initialization. Deep features were extracted from the average pooling layer in the next step and fused using a new serial-based approach. The fused features were later optimized using a feature selection algorithm known as Equilibrium-Jaya controlled Regula Falsi. The Regula Falsi was employed as a termination function in this algorithm. The selected features were finally classified using several machine learning classifiers. The experimental process was conducted on two publicly available datasets—CBIS-DDSM and INbreast. For these datasets, the achieved average accuracy is 95.4% and 99.7%. A comparison with state-of-the-art (SOTA) technology shows that the obtained proposed framework improved the accuracy. Moreover, the confidence interval-based analysis shows consistent results of the proposed framework.https://www.mdpi.com/2075-4418/13/7/1238breast cancermammogram imagescontrast enhancementaugmentationdeep learningfeature optimization |
spellingShingle | Kiran Jabeen Muhammad Attique Khan Jamel Balili Majed Alhaisoni Nouf Abdullah Almujally Huda Alrashidi Usman Tariq Jae-Hyuk Cha BC<sup>2</sup>NetRF: Breast Cancer Classification from Mammogram Images Using Enhanced Deep Learning Features and Equilibrium-Jaya Controlled Regula Falsi-Based Features Selection Diagnostics breast cancer mammogram images contrast enhancement augmentation deep learning feature optimization |
title | BC<sup>2</sup>NetRF: Breast Cancer Classification from Mammogram Images Using Enhanced Deep Learning Features and Equilibrium-Jaya Controlled Regula Falsi-Based Features Selection |
title_full | BC<sup>2</sup>NetRF: Breast Cancer Classification from Mammogram Images Using Enhanced Deep Learning Features and Equilibrium-Jaya Controlled Regula Falsi-Based Features Selection |
title_fullStr | BC<sup>2</sup>NetRF: Breast Cancer Classification from Mammogram Images Using Enhanced Deep Learning Features and Equilibrium-Jaya Controlled Regula Falsi-Based Features Selection |
title_full_unstemmed | BC<sup>2</sup>NetRF: Breast Cancer Classification from Mammogram Images Using Enhanced Deep Learning Features and Equilibrium-Jaya Controlled Regula Falsi-Based Features Selection |
title_short | BC<sup>2</sup>NetRF: Breast Cancer Classification from Mammogram Images Using Enhanced Deep Learning Features and Equilibrium-Jaya Controlled Regula Falsi-Based Features Selection |
title_sort | bc sup 2 sup netrf breast cancer classification from mammogram images using enhanced deep learning features and equilibrium jaya controlled regula falsi based features selection |
topic | breast cancer mammogram images contrast enhancement augmentation deep learning feature optimization |
url | https://www.mdpi.com/2075-4418/13/7/1238 |
work_keys_str_mv | AT kiranjabeen bcsup2supnetrfbreastcancerclassificationfrommammogramimagesusingenhanceddeeplearningfeaturesandequilibriumjayacontrolledregulafalsibasedfeaturesselection AT muhammadattiquekhan bcsup2supnetrfbreastcancerclassificationfrommammogramimagesusingenhanceddeeplearningfeaturesandequilibriumjayacontrolledregulafalsibasedfeaturesselection AT jamelbalili bcsup2supnetrfbreastcancerclassificationfrommammogramimagesusingenhanceddeeplearningfeaturesandequilibriumjayacontrolledregulafalsibasedfeaturesselection AT majedalhaisoni bcsup2supnetrfbreastcancerclassificationfrommammogramimagesusingenhanceddeeplearningfeaturesandequilibriumjayacontrolledregulafalsibasedfeaturesselection AT noufabdullahalmujally bcsup2supnetrfbreastcancerclassificationfrommammogramimagesusingenhanceddeeplearningfeaturesandequilibriumjayacontrolledregulafalsibasedfeaturesselection AT hudaalrashidi bcsup2supnetrfbreastcancerclassificationfrommammogramimagesusingenhanceddeeplearningfeaturesandequilibriumjayacontrolledregulafalsibasedfeaturesselection AT usmantariq bcsup2supnetrfbreastcancerclassificationfrommammogramimagesusingenhanceddeeplearningfeaturesandequilibriumjayacontrolledregulafalsibasedfeaturesselection AT jaehyukcha bcsup2supnetrfbreastcancerclassificationfrommammogramimagesusingenhanceddeeplearningfeaturesandequilibriumjayacontrolledregulafalsibasedfeaturesselection |