Accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning model
BackgroundBreast cancer is the most common malignant tumor in women worldwide, and early detection is crucial to improving patient prognosis. However, traditional ultrasound examinations rely heavily on physician judgment, and diagnostic results are easily influenced by individual experience, leadin...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-06-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2025.1526260/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849434856984936448 |
|---|---|
| author | Baoqin Liu Shouyao Liu Zijian Cao Junning Zhang Xiaoqi Pu Junjie Yu |
| author_facet | Baoqin Liu Shouyao Liu Zijian Cao Junning Zhang Xiaoqi Pu Junjie Yu |
| author_sort | Baoqin Liu |
| collection | DOAJ |
| description | BackgroundBreast cancer is the most common malignant tumor in women worldwide, and early detection is crucial to improving patient prognosis. However, traditional ultrasound examinations rely heavily on physician judgment, and diagnostic results are easily influenced by individual experience, leading to frequent misdiagnosis or missed diagnosis. Therefore, there is a pressing need for an automated, highly accurate diagnostic method to support the detection and classification of breast cancer. This study aims to build a reliable breast ultrasound image benign and malignant classification model through deep learning technology to improve the accuracy and consistency of diagnosis.MethodsThis study proposed an innovative deep learning model RcdNet. RcdNet combines deep separable convolution and Convolutional Block Attention Module (CBAM) attention modules to enhance the ability to identify key lesion areas in ultrasound images. The model was internally validated and externally independently tested, and compared with commonly used models such as ResNet, MobileNet, RegNet, ViT and ResNeXt to verify its performance advantage in benign and malignant classification tasks. In addition, the model’s attention area was analyzed by heat map visualization to evaluate its clinical interpretability.ResultsThe experimental results show that RcdNet outperforms other mainstream deep learning models, including ResNet, MobileNet, and ResNeXt, across all key evaluation metrics. On the external test set, RcdNet achieved an accuracy of 0.9351, a precision of 0.9168, a recall of 0.9495, and an F1-score of 0.9290, demonstrating superior classification performance and strong generalization ability. Furthermore, heat map visualizations confirm that RcdNet accurately attends to clinically relevant features such as tumor edges and irregular structures, aligning well with radiologists’ diagnostic focus and enhancing the interpretability and credibility of the model in clinical applications.ConclusionThe RcdNet model proposed in this study performs well in the classification of benign and malignant breast ultrasound images, with high classification accuracy, strong generalization ability and good interpretability. RcdNet can be used as an auxiliary diagnostic tool to help physicians quickly and accurately screen breast cancer, improve the consistency and reliability of diagnosis, and provide strong support for early detection and precise diagnosis and treatment of breast cancer. Future work will focus on integrating RcdNet into real-time ultrasound diagnostic systems and exploring its potential in multi-modal imaging workflows. |
| format | Article |
| id | doaj-art-d71eeb4078fc4c77af8c8bde5f4efa41 |
| institution | Kabale University |
| issn | 2296-4185 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj-art-d71eeb4078fc4c77af8c8bde5f4efa412025-08-20T03:26:30ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852025-06-011310.3389/fbioe.2025.15262601526260Accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning modelBaoqin Liu0Shouyao Liu1Zijian Cao2Junning Zhang3Xiaoqi Pu4Junjie Yu5Department of TCM gynecology, China-Japan Friendship Hospital, Beijing, ChinaDepartment of TCM surgery, China-Japan Friendship Hospital, Beijing, ChinaSchool of Biomedical Engineering, Tsinghua Medicine, Tsinghua University, Beijing, ChinaGraduate School, Beijing University of Chinese Medicine, Beijing, ChinaDepartment of Diagnostic Radiology, China-Japan Friendship Hospital, Beijing, ChinaDepartment of TCM gynecology, China-Japan Friendship Hospital, Beijing, ChinaBackgroundBreast cancer is the most common malignant tumor in women worldwide, and early detection is crucial to improving patient prognosis. However, traditional ultrasound examinations rely heavily on physician judgment, and diagnostic results are easily influenced by individual experience, leading to frequent misdiagnosis or missed diagnosis. Therefore, there is a pressing need for an automated, highly accurate diagnostic method to support the detection and classification of breast cancer. This study aims to build a reliable breast ultrasound image benign and malignant classification model through deep learning technology to improve the accuracy and consistency of diagnosis.MethodsThis study proposed an innovative deep learning model RcdNet. RcdNet combines deep separable convolution and Convolutional Block Attention Module (CBAM) attention modules to enhance the ability to identify key lesion areas in ultrasound images. The model was internally validated and externally independently tested, and compared with commonly used models such as ResNet, MobileNet, RegNet, ViT and ResNeXt to verify its performance advantage in benign and malignant classification tasks. In addition, the model’s attention area was analyzed by heat map visualization to evaluate its clinical interpretability.ResultsThe experimental results show that RcdNet outperforms other mainstream deep learning models, including ResNet, MobileNet, and ResNeXt, across all key evaluation metrics. On the external test set, RcdNet achieved an accuracy of 0.9351, a precision of 0.9168, a recall of 0.9495, and an F1-score of 0.9290, demonstrating superior classification performance and strong generalization ability. Furthermore, heat map visualizations confirm that RcdNet accurately attends to clinically relevant features such as tumor edges and irregular structures, aligning well with radiologists’ diagnostic focus and enhancing the interpretability and credibility of the model in clinical applications.ConclusionThe RcdNet model proposed in this study performs well in the classification of benign and malignant breast ultrasound images, with high classification accuracy, strong generalization ability and good interpretability. RcdNet can be used as an auxiliary diagnostic tool to help physicians quickly and accurately screen breast cancer, improve the consistency and reliability of diagnosis, and provide strong support for early detection and precise diagnosis and treatment of breast cancer. Future work will focus on integrating RcdNet into real-time ultrasound diagnostic systems and exploring its potential in multi-modal imaging workflows.https://www.frontiersin.org/articles/10.3389/fbioe.2025.1526260/fullbreast ultrasounddeep learningdeep separable convolutionattention mechanismbenign and malignant diagnosis |
| spellingShingle | Baoqin Liu Shouyao Liu Zijian Cao Junning Zhang Xiaoqi Pu Junjie Yu Accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning model Frontiers in Bioengineering and Biotechnology breast ultrasound deep learning deep separable convolution attention mechanism benign and malignant diagnosis |
| title | Accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning model |
| title_full | Accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning model |
| title_fullStr | Accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning model |
| title_full_unstemmed | Accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning model |
| title_short | Accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning model |
| title_sort | accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning model |
| topic | breast ultrasound deep learning deep separable convolution attention mechanism benign and malignant diagnosis |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2025.1526260/full |
| work_keys_str_mv | AT baoqinliu accurateclassificationofbenignandmalignantbreasttumorsinultrasoundimagingwithanenhanceddeeplearningmodel AT shouyaoliu accurateclassificationofbenignandmalignantbreasttumorsinultrasoundimagingwithanenhanceddeeplearningmodel AT zijiancao accurateclassificationofbenignandmalignantbreasttumorsinultrasoundimagingwithanenhanceddeeplearningmodel AT junningzhang accurateclassificationofbenignandmalignantbreasttumorsinultrasoundimagingwithanenhanceddeeplearningmodel AT xiaoqipu accurateclassificationofbenignandmalignantbreasttumorsinultrasoundimagingwithanenhanceddeeplearningmodel AT junjieyu accurateclassificationofbenignandmalignantbreasttumorsinultrasoundimagingwithanenhanceddeeplearningmodel |