A hybrid framework for colorectal cancer detection and U-Net segmentation using polynetDWTCADx
Abstract “PolynetDWTCADx” is a sophisticated hybrid model that was developed to identify and distinguish colorectal cancer. In this study, the CKHK-22 dataset, comprising 24 classes, served as the introduction. The proposed method, which combines CNNs, DWTs, and SVMs, enhances the accuracy of featur...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-85156-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559638727720960 |
|---|---|
| author | Akella S Narasimha Raju K Venkatesh Makineedi Rajababu Ranjith Kumar Gatla Marwa M. Eid Enas Ali Nataliia Titova Ahmed B. Abou Sharaf |
| author_facet | Akella S Narasimha Raju K Venkatesh Makineedi Rajababu Ranjith Kumar Gatla Marwa M. Eid Enas Ali Nataliia Titova Ahmed B. Abou Sharaf |
| author_sort | Akella S Narasimha Raju |
| collection | DOAJ |
| description | Abstract “PolynetDWTCADx” is a sophisticated hybrid model that was developed to identify and distinguish colorectal cancer. In this study, the CKHK-22 dataset, comprising 24 classes, served as the introduction. The proposed method, which combines CNNs, DWTs, and SVMs, enhances the accuracy of feature extraction and classification. The study employs DWT to optimize and enhance two integrated CNN models before classifying them with SVM following a systematic procedure. PolynetDWTCADx was the most effective model that we evaluated. It was capable of attaining a moderate level of recall, as well as an area under the curve (AUC) and accuracy during testing. The testing accuracy was 92.3%, and the training accuracy was 95.0%. This demonstrates that the model is capable of distinguishing between noncancerous and cancerous lesions in the colon. We can also employ the semantic segmentation algorithms of the U-Net architecture to accurately identify and segment cancerous colorectal regions. We assessed the model’s exceptional success in segmenting and providing precise delineation of malignant tissues using its maximal IoU value of 0.93, based on intersection over union (IoU) scores. When these techniques are added to PolynetDWTCADx, they give doctors detailed visual information that is needed for diagnosis and planning treatment. These techniques are also very good at finding and separating colorectal cancer. PolynetDWTCADx has the potential to enhance the recognition and management of colorectal cancer, as this study underscores. |
| format | Article |
| id | doaj-art-137e889522ce4665bdad81099f67957f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-137e889522ce4665bdad81099f67957f2025-01-05T12:19:08ZengNature PortfolioScientific Reports2045-23222025-01-0115113010.1038/s41598-025-85156-2A hybrid framework for colorectal cancer detection and U-Net segmentation using polynetDWTCADxAkella S Narasimha Raju0K Venkatesh1Makineedi Rajababu2Ranjith Kumar Gatla3Marwa M. Eid4Enas Ali5Nataliia Titova6Ahmed B. Abou Sharaf7Department of Computer Science and Engineering (Data Science), Institute of Aeronautical EngineeringDepartment of Networking and Communications, School of Computing, SRM Institute of Science and TechnologyDepartment of Information Technology, Aditya UniversityDepartment of Computer Science and Engineering (Data Science), Institute of Aeronautical EngineeringDepartment of physical therapy, College of Applied Medical Science, Taif UniversityUniversity Centre for Research and Development, Chandigarh UniversityBiomedical Engineering Department, National University Odesa PolytechnicMinistry of Higher Education & Scientific Research, Industrial Technical Institute in MatariaAbstract “PolynetDWTCADx” is a sophisticated hybrid model that was developed to identify and distinguish colorectal cancer. In this study, the CKHK-22 dataset, comprising 24 classes, served as the introduction. The proposed method, which combines CNNs, DWTs, and SVMs, enhances the accuracy of feature extraction and classification. The study employs DWT to optimize and enhance two integrated CNN models before classifying them with SVM following a systematic procedure. PolynetDWTCADx was the most effective model that we evaluated. It was capable of attaining a moderate level of recall, as well as an area under the curve (AUC) and accuracy during testing. The testing accuracy was 92.3%, and the training accuracy was 95.0%. This demonstrates that the model is capable of distinguishing between noncancerous and cancerous lesions in the colon. We can also employ the semantic segmentation algorithms of the U-Net architecture to accurately identify and segment cancerous colorectal regions. We assessed the model’s exceptional success in segmenting and providing precise delineation of malignant tissues using its maximal IoU value of 0.93, based on intersection over union (IoU) scores. When these techniques are added to PolynetDWTCADx, they give doctors detailed visual information that is needed for diagnosis and planning treatment. These techniques are also very good at finding and separating colorectal cancer. PolynetDWTCADx has the potential to enhance the recognition and management of colorectal cancer, as this study underscores.https://doi.org/10.1038/s41598-025-85156-2Colorectal CancerDiscrete Wavelet transform (DWT)Integrated CNNsCKHK-22 datasetsSupport Vector machines |
| spellingShingle | Akella S Narasimha Raju K Venkatesh Makineedi Rajababu Ranjith Kumar Gatla Marwa M. Eid Enas Ali Nataliia Titova Ahmed B. Abou Sharaf A hybrid framework for colorectal cancer detection and U-Net segmentation using polynetDWTCADx Scientific Reports Colorectal Cancer Discrete Wavelet transform (DWT) Integrated CNNs CKHK-22 datasets Support Vector machines |
| title | A hybrid framework for colorectal cancer detection and U-Net segmentation using polynetDWTCADx |
| title_full | A hybrid framework for colorectal cancer detection and U-Net segmentation using polynetDWTCADx |
| title_fullStr | A hybrid framework for colorectal cancer detection and U-Net segmentation using polynetDWTCADx |
| title_full_unstemmed | A hybrid framework for colorectal cancer detection and U-Net segmentation using polynetDWTCADx |
| title_short | A hybrid framework for colorectal cancer detection and U-Net segmentation using polynetDWTCADx |
| title_sort | hybrid framework for colorectal cancer detection and u net segmentation using polynetdwtcadx |
| topic | Colorectal Cancer Discrete Wavelet transform (DWT) Integrated CNNs CKHK-22 datasets Support Vector machines |
| url | https://doi.org/10.1038/s41598-025-85156-2 |
| work_keys_str_mv | AT akellasnarasimharaju ahybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT kvenkatesh ahybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT makineedirajababu ahybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT ranjithkumargatla ahybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT marwameid ahybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT enasali ahybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT nataliiatitova ahybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT ahmedbabousharaf ahybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT akellasnarasimharaju hybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT kvenkatesh hybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT makineedirajababu hybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT ranjithkumargatla hybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT marwameid hybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT enasali hybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT nataliiatitova hybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx AT ahmedbabousharaf hybridframeworkforcolorectalcancerdetectionandunetsegmentationusingpolynetdwtcadx |