Enhancing Breast Cancer Diagnosis With Bidirectional Recurrent Neural Networks: A Novel Approach for Histopathological Image Multi-Classification
In recent years, deep learning methods have dramatically improved medical image analysis, though earlier models faced difficulties in capturing intricate spatial and contextual details. These challenges highlighted the necessity for more powerful and flexible models. In this study, we introduce an i...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10891589/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850069625243435008 |
|---|---|
| author | Rajendra Babu Chikkala Chinta Anuradha Patnala S. R. Chandra Murty S. Rajeswari N. Rajeswaran M. Murugappan Muhammad E. H. Chowdhury |
| author_facet | Rajendra Babu Chikkala Chinta Anuradha Patnala S. R. Chandra Murty S. Rajeswari N. Rajeswaran M. Murugappan Muhammad E. H. Chowdhury |
| author_sort | Rajendra Babu Chikkala |
| collection | DOAJ |
| description | In recent years, deep learning methods have dramatically improved medical image analysis, though earlier models faced difficulties in capturing intricate spatial and contextual details. These challenges highlighted the necessity for more powerful and flexible models. In this study, we introduce an innovative method for the multi-classification of breast cancer histopathological images utilizing Bidirectional Recurrent Neural Networks (BRNN). The BRNN structure consists of four unique elements: the backbone branch for transfer learning, the Gated Recurrent Unit (GRU), the residual collaborative branch, and the feature fusion module. Specifically, the transfer learning aspect exploits a Convolutional Neural Network (CNN) based on the ResNet50 architecture to draw image features from the ImageNet dataset, enhanced with an attention mechanism for improved feature representation. Additionally, the residual branch identifies specific pathological features using Floating Point Operations (FLOP). This cooperative method ensures thorough extraction of breast cancer classification features. The BRNN model was tested on the BreaKHis breast cancer dataset, comprising 7,909 microscopic images across 8 various classes from 82 patients. Our model achieved an average classification accuracy of 97.25 percent, exceeding current leading techniques. The BRNN model, refined using the Adagrad optimization algorithm, efficiently integrates the learned features from both branches. This tool provides oncologists with a substantial enhancement in diagnosing and planning treatment for breast cancer. |
| format | Article |
| id | doaj-art-7caec7c3131f4f9cab87fcd0245d222b |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7caec7c3131f4f9cab87fcd0245d222b2025-08-20T02:47:44ZengIEEEIEEE Access2169-35362025-01-0113416824170710.1109/ACCESS.2025.354298910891589Enhancing Breast Cancer Diagnosis With Bidirectional Recurrent Neural Networks: A Novel Approach for Histopathological Image Multi-ClassificationRajendra Babu Chikkala0https://orcid.org/0000-0002-8753-6830Chinta Anuradha1https://orcid.org/0000-0002-8580-3202Patnala S. R. Chandra Murty2https://orcid.org/0000-0002-2241-2220S. Rajeswari3https://orcid.org/0000-0002-3551-0284N. Rajeswaran4https://orcid.org/0000-0002-3303-9206M. Murugappan5https://orcid.org/0000-0002-5839-4589Muhammad E. H. Chowdhury6https://orcid.org/0000-0003-0744-8206Department of AI and DS, Lakireddy Bali Reddy College of Engineering, Mylavaram, Andhra Pradesh, IndiaDepartment of Computer Science and Engineering, Siddhartha Academy of Higher Education (Deemed to be University), Vijayawada, Andra Pradesh, IndiaDepartment of Computer Science and Engineering, Malla Reddy Engineering College, Maisammaguda, Secunderabad, Telangana, IndiaDepartment of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, IndiaSchool of Computer Applications, IMS Unison University, Dehradun, Uttrakhand, IndiaDepartment of Electronics and Communication Engineering, Intelligent Signal Processing (ISP) Research Laboratory, Kuwait College of Science and Technology, Doha, KuwaitDepartment of Electrical Engineering, Qatar University, Doha, QatarIn recent years, deep learning methods have dramatically improved medical image analysis, though earlier models faced difficulties in capturing intricate spatial and contextual details. These challenges highlighted the necessity for more powerful and flexible models. In this study, we introduce an innovative method for the multi-classification of breast cancer histopathological images utilizing Bidirectional Recurrent Neural Networks (BRNN). The BRNN structure consists of four unique elements: the backbone branch for transfer learning, the Gated Recurrent Unit (GRU), the residual collaborative branch, and the feature fusion module. Specifically, the transfer learning aspect exploits a Convolutional Neural Network (CNN) based on the ResNet50 architecture to draw image features from the ImageNet dataset, enhanced with an attention mechanism for improved feature representation. Additionally, the residual branch identifies specific pathological features using Floating Point Operations (FLOP). This cooperative method ensures thorough extraction of breast cancer classification features. The BRNN model was tested on the BreaKHis breast cancer dataset, comprising 7,909 microscopic images across 8 various classes from 82 patients. Our model achieved an average classification accuracy of 97.25 percent, exceeding current leading techniques. The BRNN model, refined using the Adagrad optimization algorithm, efficiently integrates the learned features from both branches. This tool provides oncologists with a substantial enhancement in diagnosing and planning treatment for breast cancer.https://ieeexplore.ieee.org/document/10891589/Breast cancerBRNNGRUCNNResNetFLOP |
| spellingShingle | Rajendra Babu Chikkala Chinta Anuradha Patnala S. R. Chandra Murty S. Rajeswari N. Rajeswaran M. Murugappan Muhammad E. H. Chowdhury Enhancing Breast Cancer Diagnosis With Bidirectional Recurrent Neural Networks: A Novel Approach for Histopathological Image Multi-Classification IEEE Access Breast cancer BRNN GRU CNN ResNet FLOP |
| title | Enhancing Breast Cancer Diagnosis With Bidirectional Recurrent Neural Networks: A Novel Approach for Histopathological Image Multi-Classification |
| title_full | Enhancing Breast Cancer Diagnosis With Bidirectional Recurrent Neural Networks: A Novel Approach for Histopathological Image Multi-Classification |
| title_fullStr | Enhancing Breast Cancer Diagnosis With Bidirectional Recurrent Neural Networks: A Novel Approach for Histopathological Image Multi-Classification |
| title_full_unstemmed | Enhancing Breast Cancer Diagnosis With Bidirectional Recurrent Neural Networks: A Novel Approach for Histopathological Image Multi-Classification |
| title_short | Enhancing Breast Cancer Diagnosis With Bidirectional Recurrent Neural Networks: A Novel Approach for Histopathological Image Multi-Classification |
| title_sort | enhancing breast cancer diagnosis with bidirectional recurrent neural networks a novel approach for histopathological image multi classification |
| topic | Breast cancer BRNN GRU CNN ResNet FLOP |
| url | https://ieeexplore.ieee.org/document/10891589/ |
| work_keys_str_mv | AT rajendrababuchikkala enhancingbreastcancerdiagnosiswithbidirectionalrecurrentneuralnetworksanovelapproachforhistopathologicalimagemulticlassification AT chintaanuradha enhancingbreastcancerdiagnosiswithbidirectionalrecurrentneuralnetworksanovelapproachforhistopathologicalimagemulticlassification AT patnalasrchandramurty enhancingbreastcancerdiagnosiswithbidirectionalrecurrentneuralnetworksanovelapproachforhistopathologicalimagemulticlassification AT srajeswari enhancingbreastcancerdiagnosiswithbidirectionalrecurrentneuralnetworksanovelapproachforhistopathologicalimagemulticlassification AT nrajeswaran enhancingbreastcancerdiagnosiswithbidirectionalrecurrentneuralnetworksanovelapproachforhistopathologicalimagemulticlassification AT mmurugappan enhancingbreastcancerdiagnosiswithbidirectionalrecurrentneuralnetworksanovelapproachforhistopathologicalimagemulticlassification AT muhammadehchowdhury enhancingbreastcancerdiagnosiswithbidirectionalrecurrentneuralnetworksanovelapproachforhistopathologicalimagemulticlassification |