Breast Cancer Segmentation From Ultrasound Images Using Deep Dual-Decoder Technology With Attention Network
This paper introduces a deep learning approach for breast cancer segmentation from ultrasound imaging using a Dual Decoder Attention ResUNet (DDA-AttResUNet). DDA-AttResUNet utilizes a Dual Decoder Attention structure to simultaneously focus on tumor segmentation while also capturing supplementary c...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10384335/ |
| _version_ | 1827376436114096128 |
|---|---|
| author | Asmaa A. Hekal Ahmed Elnakib Hossam El-Din Moustafa Hanan M. Amer |
| author_facet | Asmaa A. Hekal Ahmed Elnakib Hossam El-Din Moustafa Hanan M. Amer |
| author_sort | Asmaa A. Hekal |
| collection | DOAJ |
| description | This paper introduces a deep learning approach for breast cancer segmentation from ultrasound imaging using a Dual Decoder Attention ResUNet (DDA-AttResUNet). DDA-AttResUNet utilizes a Dual Decoder Attention structure to simultaneously focus on tumor segmentation while also capturing supplementary contextual information, leading to enhanced segmentation accuracy. An Attention mechanism is incorporated to enhance the representation of segmented regions by effectively combining information from multiple sources. The model’s performance is validated on a public challenging dataset of 780 Breast Ultrasound Images (BUSI), achieving a Dice similarity coefficient of 92.92±0.69%, Intersection over Union of 87.39 ± 1.10%, Sensitivity of 92.16 ± 0.92%, Precision of 93.90 ± 0.40%, and Accuracy of 98.82 ± 0.10%, using 10-fold cross-validation. These results, comparable to other leading methods, indicate that our DDA-AttResUNet can significantly advance breast tumor segmentation in BUS imaging, with implications for improved diagnosis and patient outcomes. |
| first_indexed | 2024-03-08T12:09:50Z |
| format | Article |
| id | doaj.art-9d590aa606b84d5faf6775528a7a8451 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T12:09:50Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9d590aa606b84d5faf6775528a7a84512024-01-23T00:05:12ZengIEEEIEEE Access2169-35362024-01-0112100871010110.1109/ACCESS.2024.335156410384335Breast Cancer Segmentation From Ultrasound Images Using Deep Dual-Decoder Technology With Attention NetworkAsmaa A. Hekal0Ahmed Elnakib1https://orcid.org/0000-0001-6084-3622Hossam El-Din Moustafa2Hanan M. Amer3Electronics and Communications Engineering (ECE) Department, Faculty of Engineering, Mansoura University, Mansoura, EgyptElectronics and Communications Engineering (ECE) Department, Faculty of Engineering, Mansoura University, Mansoura, EgyptElectronics and Communications Engineering (ECE) Department, Faculty of Engineering, Mansoura University, Mansoura, EgyptElectronics and Communications Engineering (ECE) Department, Faculty of Engineering, Mansoura University, Mansoura, EgyptThis paper introduces a deep learning approach for breast cancer segmentation from ultrasound imaging using a Dual Decoder Attention ResUNet (DDA-AttResUNet). DDA-AttResUNet utilizes a Dual Decoder Attention structure to simultaneously focus on tumor segmentation while also capturing supplementary contextual information, leading to enhanced segmentation accuracy. An Attention mechanism is incorporated to enhance the representation of segmented regions by effectively combining information from multiple sources. The model’s performance is validated on a public challenging dataset of 780 Breast Ultrasound Images (BUSI), achieving a Dice similarity coefficient of 92.92±0.69%, Intersection over Union of 87.39 ± 1.10%, Sensitivity of 92.16 ± 0.92%, Precision of 93.90 ± 0.40%, and Accuracy of 98.82 ± 0.10%, using 10-fold cross-validation. These results, comparable to other leading methods, indicate that our DDA-AttResUNet can significantly advance breast tumor segmentation in BUS imaging, with implications for improved diagnosis and patient outcomes.https://ieeexplore.ieee.org/document/10384335/Breast ultrasoundtumor segmentationdeep learningimage segmentationimage detection |
| spellingShingle | Asmaa A. Hekal Ahmed Elnakib Hossam El-Din Moustafa Hanan M. Amer Breast Cancer Segmentation From Ultrasound Images Using Deep Dual-Decoder Technology With Attention Network IEEE Access Breast ultrasound tumor segmentation deep learning image segmentation image detection |
| title | Breast Cancer Segmentation From Ultrasound Images Using Deep Dual-Decoder Technology With Attention Network |
| title_full | Breast Cancer Segmentation From Ultrasound Images Using Deep Dual-Decoder Technology With Attention Network |
| title_fullStr | Breast Cancer Segmentation From Ultrasound Images Using Deep Dual-Decoder Technology With Attention Network |
| title_full_unstemmed | Breast Cancer Segmentation From Ultrasound Images Using Deep Dual-Decoder Technology With Attention Network |
| title_short | Breast Cancer Segmentation From Ultrasound Images Using Deep Dual-Decoder Technology With Attention Network |
| title_sort | breast cancer segmentation from ultrasound images using deep dual decoder technology with attention network |
| topic | Breast ultrasound tumor segmentation deep learning image segmentation image detection |
| url | https://ieeexplore.ieee.org/document/10384335/ |
| work_keys_str_mv | AT asmaaahekal breastcancersegmentationfromultrasoundimagesusingdeepdualdecodertechnologywithattentionnetwork AT ahmedelnakib breastcancersegmentationfromultrasoundimagesusingdeepdualdecodertechnologywithattentionnetwork AT hossameldinmoustafa breastcancersegmentationfromultrasoundimagesusingdeepdualdecodertechnologywithattentionnetwork AT hananmamer breastcancersegmentationfromultrasoundimagesusingdeepdualdecodertechnologywithattentionnetwork |