Breast Cancer Detection in Thermographic Images Using Hybrid Networks
Introduction: Breast cancer is the most common cancer in women that causes more deaths than other cancers. Thermography is one of the methods of breast cancer diagnosis. The most important challenge in early detection of these images can be human error or lack of access to a skilled person. The use...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Kerman University of Medical Sciences
2023-12-01
|
| Series: | مجله انفورماتیک سلامت و زیست پزشکی |
| Subjects: | |
| Online Access: | http://jhbmi.ir/article-1-786-en.pdf |
| _version_ | 1797209597601120256 |
|---|---|
| author | Hanieh Rezazadeh Tamrin Elham Saniei Mehdi Salehi Barough |
| author_facet | Hanieh Rezazadeh Tamrin Elham Saniei Mehdi Salehi Barough |
| author_sort | Hanieh Rezazadeh Tamrin |
| collection | DOAJ |
| description | Introduction: Breast cancer is the most common cancer in women that causes more deaths than other cancers. Thermography is one of the methods of breast cancer diagnosis. The most important challenge in early detection of these images can be human error or lack of access to a skilled person. The use of artificial intelligence methods in image processing can be effective in early detection and reduction of human error. The main aim of this research was to introduce hybrid networks for intelligent diagnosis of breast cancer from thermographic images.
Method: The thermographic images used in this study were collected from the DMR-IR database. First, the main features of the images were extracted by deep convolutional network (CNN). Then, FCNNs and SVM algorithms were used to classify breast cancer from thermographic images.
Results: The accuracy rate for CNN_FC and CNN-SVM algorithms was 94.2% and 0.95%, respectively. In addition, the reliability parameters for these classifiers were calculated as 92.1%, and 97.5%, and the sensitivity for each of these classifiers as 95.5%, and 94.1%, respectively.
Conclusion: The proposed model based on the deep hybrid network has good accuracy compared to similar algorithms; therefore, it can help doctors in the early diagnosis of breast cancer through thermographic images and minimize human error. |
| first_indexed | 2024-04-24T09:57:14Z |
| format | Article |
| id | doaj.art-016d1ecac7e5497e960b57c2122f1967 |
| institution | Directory Open Access Journal |
| issn | 2423-3870 2423-3498 |
| language | fas |
| last_indexed | 2024-04-24T09:57:14Z |
| publishDate | 2023-12-01 |
| publisher | Kerman University of Medical Sciences |
| record_format | Article |
| series | مجله انفورماتیک سلامت و زیست پزشکی |
| spelling | doaj.art-016d1ecac7e5497e960b57c2122f19672024-04-14T09:30:24ZfasKerman University of Medical Sciencesمجله انفورماتیک سلامت و زیست پزشکی2423-38702423-34982023-12-01103260268Breast Cancer Detection in Thermographic Images Using Hybrid NetworksHanieh Rezazadeh Tamrin0Elham Saniei1Mehdi Salehi Barough2 Master of Nuclear Engineering, Medical Radiation Research Center, Central Tehran Branch Islamic Azad University, Tehran, Iran Ph.D. in Nuclear Engineering, Assistant Professor, Medical Radiation Research Center, Central Tehran Branch Islamic Azad University, Tehran, Iran Ph.D. in Nuclear Engineering, Assistant Professor, Medical Radiation Research Center, Central Tehran Branch Islamic Azad University, Tehran, Iran Introduction: Breast cancer is the most common cancer in women that causes more deaths than other cancers. Thermography is one of the methods of breast cancer diagnosis. The most important challenge in early detection of these images can be human error or lack of access to a skilled person. The use of artificial intelligence methods in image processing can be effective in early detection and reduction of human error. The main aim of this research was to introduce hybrid networks for intelligent diagnosis of breast cancer from thermographic images. Method: The thermographic images used in this study were collected from the DMR-IR database. First, the main features of the images were extracted by deep convolutional network (CNN). Then, FCNNs and SVM algorithms were used to classify breast cancer from thermographic images. Results: The accuracy rate for CNN_FC and CNN-SVM algorithms was 94.2% and 0.95%, respectively. In addition, the reliability parameters for these classifiers were calculated as 92.1%, and 97.5%, and the sensitivity for each of these classifiers as 95.5%, and 94.1%, respectively. Conclusion: The proposed model based on the deep hybrid network has good accuracy compared to similar algorithms; therefore, it can help doctors in the early diagnosis of breast cancer through thermographic images and minimize human error.http://jhbmi.ir/article-1-786-en.pdfdiagnosisbreast cancerdeep learningconvolutional neural networkthermography |
| spellingShingle | Hanieh Rezazadeh Tamrin Elham Saniei Mehdi Salehi Barough Breast Cancer Detection in Thermographic Images Using Hybrid Networks مجله انفورماتیک سلامت و زیست پزشکی diagnosis breast cancer deep learning convolutional neural network thermography |
| title | Breast Cancer Detection in Thermographic Images Using Hybrid Networks |
| title_full | Breast Cancer Detection in Thermographic Images Using Hybrid Networks |
| title_fullStr | Breast Cancer Detection in Thermographic Images Using Hybrid Networks |
| title_full_unstemmed | Breast Cancer Detection in Thermographic Images Using Hybrid Networks |
| title_short | Breast Cancer Detection in Thermographic Images Using Hybrid Networks |
| title_sort | breast cancer detection in thermographic images using hybrid networks |
| topic | diagnosis breast cancer deep learning convolutional neural network thermography |
| url | http://jhbmi.ir/article-1-786-en.pdf |
| work_keys_str_mv | AT haniehrezazadehtamrin breastcancerdetectioninthermographicimagesusinghybridnetworks AT elhamsaniei breastcancerdetectioninthermographicimagesusinghybridnetworks AT mehdisalehibarough breastcancerdetectioninthermographicimagesusinghybridnetworks |