Colorectal cancer detection with enhanced precision using a hybrid supervised and unsupervised learning approach
Abstract The current work introduces the hybrid ensemble framework for the detection and segmentation of colorectal cancer. This framework will incorporate both supervised classification and unsupervised clustering methods to present more understandable and accurate diagnostic results. The method en...
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/s41598-025-86590-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585856009895936 |
|---|---|
| author | Akella S. Narasimha Raju K. Venkatesh Ranjith Kumar Gatla Eswara Prasad Konakalla Marwa M. Eid Nataliia Titova Sherif S. M. Ghoneim Ramy N. R. Ghaly |
| author_facet | Akella S. Narasimha Raju K. Venkatesh Ranjith Kumar Gatla Eswara Prasad Konakalla Marwa M. Eid Nataliia Titova Sherif S. M. Ghoneim Ramy N. R. Ghaly |
| author_sort | Akella S. Narasimha Raju |
| collection | DOAJ |
| description | Abstract The current work introduces the hybrid ensemble framework for the detection and segmentation of colorectal cancer. This framework will incorporate both supervised classification and unsupervised clustering methods to present more understandable and accurate diagnostic results. The method entails several steps with CNN models: ADa-22 and AD-22, transformer networks, and an SVM classifier, all inbuilt. The CVC ClinicDB dataset supports this process, containing 1650 colonoscopy images classified as polyps or non-polyps. The best performance in the ensembles was done by the AD-22 + Transformer + SVM model, with an AUC of 0.99, a training accuracy of 99.50%, and a testing accuracy of 99.00%. This group also saw a high accuracy of 97.50% for Polyps and 99.30% for Non-Polyps, together with a recall of 97.80% for Polyps and 98.90% for Non-Polyps, hence performing very well in identifying both cancerous and healthy regions. The framework proposed here uses K-means clustering in combination with the visualisation of bounding boxes, thereby improving segmentation and yielding a silhouette score of 0.73 with the best cluster configuration. It discusses how to combine feature interpretation challenges into medical imaging for accurate localization and precise segmentation of malignant regions. A good balance between performance and generalization shall be done by hyperparameter optimization-heavy learning rates; dropout rates and overfitting shall be suppressed effectively. The hybrid schema of this work treats the deficiencies of the previous approaches, such as incorporating CNN-based effective feature extraction, Transformer networks for developing attention mechanisms, and finally the fine decision boundary of the support vector machine. Further, we refine this process via unsupervised clustering for the purpose of enhancing the visualisation of such a procedure. Such a holistic framework, hence, further boosts classification and segmentation results by generating understandable outcomes for more rigorous benchmarking of detecting colorectal cancer and with higher reality towards clinical application feasibility. |
| format | Article |
| id | doaj-art-8f366ca137474deab740c83c5367d3c4 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-8f366ca137474deab740c83c5367d3c42025-01-26T12:27:08ZengNature PortfolioScientific Reports2045-23222025-01-0115113710.1038/s41598-025-86590-yColorectal cancer detection with enhanced precision using a hybrid supervised and unsupervised learning approachAkella S. Narasimha Raju0K. Venkatesh1Ranjith Kumar Gatla2Eswara Prasad Konakalla3Marwa M. Eid4Nataliia Titova5Sherif S. M. Ghoneim6Ramy N. R. Ghaly7Department 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 Computer Science and Engineering (Data Science), Institute of Aeronautical EngineeringDepartment of Physics and Electronics, B.V.Raju College, BhimavaramCollege of Applied Medical Science, Taif UniversityBiomedical Engineering Department, National University Odesa PolytechnicDepartment of Electrical Engineering, College of Engineering, Taif UniversityMinistry of Higher Education, Mataria Technical CollegeAbstract The current work introduces the hybrid ensemble framework for the detection and segmentation of colorectal cancer. This framework will incorporate both supervised classification and unsupervised clustering methods to present more understandable and accurate diagnostic results. The method entails several steps with CNN models: ADa-22 and AD-22, transformer networks, and an SVM classifier, all inbuilt. The CVC ClinicDB dataset supports this process, containing 1650 colonoscopy images classified as polyps or non-polyps. The best performance in the ensembles was done by the AD-22 + Transformer + SVM model, with an AUC of 0.99, a training accuracy of 99.50%, and a testing accuracy of 99.00%. This group also saw a high accuracy of 97.50% for Polyps and 99.30% for Non-Polyps, together with a recall of 97.80% for Polyps and 98.90% for Non-Polyps, hence performing very well in identifying both cancerous and healthy regions. The framework proposed here uses K-means clustering in combination with the visualisation of bounding boxes, thereby improving segmentation and yielding a silhouette score of 0.73 with the best cluster configuration. It discusses how to combine feature interpretation challenges into medical imaging for accurate localization and precise segmentation of malignant regions. A good balance between performance and generalization shall be done by hyperparameter optimization-heavy learning rates; dropout rates and overfitting shall be suppressed effectively. The hybrid schema of this work treats the deficiencies of the previous approaches, such as incorporating CNN-based effective feature extraction, Transformer networks for developing attention mechanisms, and finally the fine decision boundary of the support vector machine. Further, we refine this process via unsupervised clustering for the purpose of enhancing the visualisation of such a procedure. Such a holistic framework, hence, further boosts classification and segmentation results by generating understandable outcomes for more rigorous benchmarking of detecting colorectal cancer and with higher reality towards clinical application feasibility.https://doi.org/10.1038/s41598-025-86590-yColorectal cancerIntegrated CNNsTransformersSupport vector machinesK-Means clustering |
| spellingShingle | Akella S. Narasimha Raju K. Venkatesh Ranjith Kumar Gatla Eswara Prasad Konakalla Marwa M. Eid Nataliia Titova Sherif S. M. Ghoneim Ramy N. R. Ghaly Colorectal cancer detection with enhanced precision using a hybrid supervised and unsupervised learning approach Scientific Reports Colorectal cancer Integrated CNNs Transformers Support vector machines K-Means clustering |
| title | Colorectal cancer detection with enhanced precision using a hybrid supervised and unsupervised learning approach |
| title_full | Colorectal cancer detection with enhanced precision using a hybrid supervised and unsupervised learning approach |
| title_fullStr | Colorectal cancer detection with enhanced precision using a hybrid supervised and unsupervised learning approach |
| title_full_unstemmed | Colorectal cancer detection with enhanced precision using a hybrid supervised and unsupervised learning approach |
| title_short | Colorectal cancer detection with enhanced precision using a hybrid supervised and unsupervised learning approach |
| title_sort | colorectal cancer detection with enhanced precision using a hybrid supervised and unsupervised learning approach |
| topic | Colorectal cancer Integrated CNNs Transformers Support vector machines K-Means clustering |
| url | https://doi.org/10.1038/s41598-025-86590-y |
| work_keys_str_mv | AT akellasnarasimharaju colorectalcancerdetectionwithenhancedprecisionusingahybridsupervisedandunsupervisedlearningapproach AT kvenkatesh colorectalcancerdetectionwithenhancedprecisionusingahybridsupervisedandunsupervisedlearningapproach AT ranjithkumargatla colorectalcancerdetectionwithenhancedprecisionusingahybridsupervisedandunsupervisedlearningapproach AT eswaraprasadkonakalla colorectalcancerdetectionwithenhancedprecisionusingahybridsupervisedandunsupervisedlearningapproach AT marwameid colorectalcancerdetectionwithenhancedprecisionusingahybridsupervisedandunsupervisedlearningapproach AT nataliiatitova colorectalcancerdetectionwithenhancedprecisionusingahybridsupervisedandunsupervisedlearningapproach AT sherifsmghoneim colorectalcancerdetectionwithenhancedprecisionusingahybridsupervisedandunsupervisedlearningapproach AT ramynrghaly colorectalcancerdetectionwithenhancedprecisionusingahybridsupervisedandunsupervisedlearningapproach |