An adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound images
Abstract Convolutional Neural Networks (CNNs), a sophisticated deep learning technique, have proven highly effective in identifying and classifying abnormalities related to various diseases. The manual classification of these is a hectic and time-consuming process; therefore, it is essential to deve...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-03402-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849334826455269376 |
|---|---|
| author | Mamuna Fatima Muhammad Attique Khan Anwar M. Mirza Jungpil Shin Areej Alasiry Mehrez Marzougui Jaehyuk Cha Byoungchol Chang |
| author_facet | Mamuna Fatima Muhammad Attique Khan Anwar M. Mirza Jungpil Shin Areej Alasiry Mehrez Marzougui Jaehyuk Cha Byoungchol Chang |
| author_sort | Mamuna Fatima |
| collection | DOAJ |
| description | Abstract Convolutional Neural Networks (CNNs), a sophisticated deep learning technique, have proven highly effective in identifying and classifying abnormalities related to various diseases. The manual classification of these is a hectic and time-consuming process; therefore, it is essential to develop a computerized technique. Most existing methods are designed to address a single specific problem, limiting their adaptability. In this work, we proposed a novel adaptive deep-learning framework for simultaneously classifying breast cancer and maternal-fetal ultrasound datasets. Data augmentation was applied in the preprocessing phase to address the data imbalance problem. After, two novel architectures are proposed: InBnFUS and CNNDen-GRU. The InBnFUS network combines 5-Blocks inception-based architecture (Model 1) and 5-Blocks inverted bottleneck-based architecture (Model 2) through a depth-wise concatenation layer, while CNNDen-GRU incorporates 5-Blocks dense architecture with an integrated GRU layer. Post-training features were extracted from the global average pooling and GRU layer and classified using neural network classifiers. The experimental evaluation achieved enhanced accuracy rates of 99.0% for breast cancer, 96.6% for maternal-fetal (common planes), and 94.6% for maternal-fetal (brain) datasets. Additionally, the models consistently achieve high precision, recall, and F1 scores across both datasets. A comprehensive ablation study has been performed, and the results show the superior performance of the proposed models. |
| format | Article |
| id | doaj-art-0d69fb3820cb4c2b93d6ad50caef3592 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-0d69fb3820cb4c2b93d6ad50caef35922025-08-20T03:45:28ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-03402-zAn adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound imagesMamuna Fatima0Muhammad Attique Khan1Anwar M. Mirza2Jungpil Shin3Areej Alasiry4Mehrez Marzougui5Jaehyuk Cha6Byoungchol Chang7Department of Computer Science, COMSATS University IslamabadDepartment of AI, College of Computer Engineering and Science, Prince Mohammad Bin Fahd UniversityDepartment of AI, College of Computer Engineering and Science, Prince Mohammad Bin Fahd UniversitySchool of Computer Science and Engineering, The University of AizuCollege of Computer Science, King Khalid UniversityCollege of Computer Science, King Khalid UniversityHanynag UniversityHanynag UniversityAbstract Convolutional Neural Networks (CNNs), a sophisticated deep learning technique, have proven highly effective in identifying and classifying abnormalities related to various diseases. The manual classification of these is a hectic and time-consuming process; therefore, it is essential to develop a computerized technique. Most existing methods are designed to address a single specific problem, limiting their adaptability. In this work, we proposed a novel adaptive deep-learning framework for simultaneously classifying breast cancer and maternal-fetal ultrasound datasets. Data augmentation was applied in the preprocessing phase to address the data imbalance problem. After, two novel architectures are proposed: InBnFUS and CNNDen-GRU. The InBnFUS network combines 5-Blocks inception-based architecture (Model 1) and 5-Blocks inverted bottleneck-based architecture (Model 2) through a depth-wise concatenation layer, while CNNDen-GRU incorporates 5-Blocks dense architecture with an integrated GRU layer. Post-training features were extracted from the global average pooling and GRU layer and classified using neural network classifiers. The experimental evaluation achieved enhanced accuracy rates of 99.0% for breast cancer, 96.6% for maternal-fetal (common planes), and 94.6% for maternal-fetal (brain) datasets. Additionally, the models consistently achieve high precision, recall, and F1 scores across both datasets. A comprehensive ablation study has been performed, and the results show the superior performance of the proposed models.https://doi.org/10.1038/s41598-025-03402-zBreast cancerSparse autoencodersData augmentationImage processingFusionClassification |
| spellingShingle | Mamuna Fatima Muhammad Attique Khan Anwar M. Mirza Jungpil Shin Areej Alasiry Mehrez Marzougui Jaehyuk Cha Byoungchol Chang An adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound images Scientific Reports Breast cancer Sparse autoencoders Data augmentation Image processing Fusion Classification |
| title | An adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound images |
| title_full | An adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound images |
| title_fullStr | An adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound images |
| title_full_unstemmed | An adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound images |
| title_short | An adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound images |
| title_sort | adaptive deep learning approach based on inbnfus and cnnden gru networks for breast cancer and maternal fetal classification using ultrasound images |
| topic | Breast cancer Sparse autoencoders Data augmentation Image processing Fusion Classification |
| url | https://doi.org/10.1038/s41598-025-03402-z |
| work_keys_str_mv | AT mamunafatima anadaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT muhammadattiquekhan anadaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT anwarmmirza anadaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT jungpilshin anadaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT areejalasiry anadaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT mehrezmarzougui anadaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT jaehyukcha anadaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT byoungcholchang anadaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT mamunafatima adaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT muhammadattiquekhan adaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT anwarmmirza adaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT jungpilshin adaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT areejalasiry adaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT mehrezmarzougui adaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT jaehyukcha adaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages AT byoungcholchang adaptivedeeplearningapproachbasedoninbnfusandcnndengrunetworksforbreastcancerandmaternalfetalclassificationusingultrasoundimages |