Advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical images
Abstract Colorectal cancer (CRC) is the second popular cancer in females and third in males, with an increased number of cases. Pathology diagnoses complemented with predictive and prognostic biomarker information is the first step for personalized treatment. Histopathological image (HI) analysis is...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83466-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862504428666880 |
|---|---|
| author | Sultan Refa Alotaibi Manal Abdullah Alohali Mashael Maashi Hamed Alqahtani Moneerah Alotaibi Ahmed Mahmud |
| author_facet | Sultan Refa Alotaibi Manal Abdullah Alohali Mashael Maashi Hamed Alqahtani Moneerah Alotaibi Ahmed Mahmud |
| author_sort | Sultan Refa Alotaibi |
| collection | DOAJ |
| description | Abstract Colorectal cancer (CRC) is the second popular cancer in females and third in males, with an increased number of cases. Pathology diagnoses complemented with predictive and prognostic biomarker information is the first step for personalized treatment. Histopathological image (HI) analysis is the benchmark for pathologists to rank colorectal cancer of various kinds. However, pathologists’ diagnoses are highly subjective and susceptible to inaccurate diagnoses. The improved diagnosis load in the pathology laboratory, incorporated with the reported intra- and inter-variability in the biomarker assessment, has prompted the quest for consistent machine-based techniques to be integrated into routine practice. In the healthcare field, artificial intelligence (AI) has achieved extraordinary achievements in healthcare applications. Lately, computer-aided diagnosis (CAD) based on HI has progressed rapidly with the increase of machine learning (ML) and deep learning (DL) based models. This study introduces a novel Colorectal Cancer Diagnosis using the Optimal Deep Feature Fusion Approach on Biomedical Images (CCD-ODFFBI) method. The primary objective of the CCD-ODFFBI technique is to examine the biomedical images to identify colorectal cancer (CRC). In the CCD-ODFFBI technique, the median filtering (MF) approach is initially utilized for noise elimination. The CCD-ODFFBI technique utilizes a fusion of three DL models, MobileNet, SqueezeNet, and SE-ResNet, for feature extraction. Moreover, the DL models’ hyperparameter selection is performed using the Osprey optimization algorithm (OOA). Finally, the deep belief network (DBN) model is employed to classify CRC. A series of simulations is accomplished to highlight the significant results of the CCD-ODFFBI method under the Warwick-QU dataset. The comparison of the CCD-ODFFBI method showed a superior accuracy value of 99.39% over existing techniques. |
| format | Article |
| id | doaj-art-a526cf6959af41cab5251ef88f9bde28 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a526cf6959af41cab5251ef88f9bde282025-02-09T12:31:17ZengNature PortfolioScientific Reports2045-23222025-02-0115112510.1038/s41598-024-83466-5Advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical imagesSultan Refa Alotaibi0Manal Abdullah Alohali1Mashael Maashi2Hamed Alqahtani3Moneerah Alotaibi4Ahmed Mahmud5Department of Computer Science, College of Science and Humanities Dawadmi, Shaqra UniversityDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman UniversityDepartment of Software Engineering, College of Computer and Information Sciences, King Saud UniversityDepartment of Information Systems, College of Computer Science, Center of Artificial Intelligence, Unit of Cybersecurity, King Khalid UniversityDepartment of Computer Science, College of Science and Humanities Dawadmi, Shaqra UniversityResearch Center, Future University in EgyptAbstract Colorectal cancer (CRC) is the second popular cancer in females and third in males, with an increased number of cases. Pathology diagnoses complemented with predictive and prognostic biomarker information is the first step for personalized treatment. Histopathological image (HI) analysis is the benchmark for pathologists to rank colorectal cancer of various kinds. However, pathologists’ diagnoses are highly subjective and susceptible to inaccurate diagnoses. The improved diagnosis load in the pathology laboratory, incorporated with the reported intra- and inter-variability in the biomarker assessment, has prompted the quest for consistent machine-based techniques to be integrated into routine practice. In the healthcare field, artificial intelligence (AI) has achieved extraordinary achievements in healthcare applications. Lately, computer-aided diagnosis (CAD) based on HI has progressed rapidly with the increase of machine learning (ML) and deep learning (DL) based models. This study introduces a novel Colorectal Cancer Diagnosis using the Optimal Deep Feature Fusion Approach on Biomedical Images (CCD-ODFFBI) method. The primary objective of the CCD-ODFFBI technique is to examine the biomedical images to identify colorectal cancer (CRC). In the CCD-ODFFBI technique, the median filtering (MF) approach is initially utilized for noise elimination. The CCD-ODFFBI technique utilizes a fusion of three DL models, MobileNet, SqueezeNet, and SE-ResNet, for feature extraction. Moreover, the DL models’ hyperparameter selection is performed using the Osprey optimization algorithm (OOA). Finally, the deep belief network (DBN) model is employed to classify CRC. A series of simulations is accomplished to highlight the significant results of the CCD-ODFFBI method under the Warwick-QU dataset. The comparison of the CCD-ODFFBI method showed a superior accuracy value of 99.39% over existing techniques.https://doi.org/10.1038/s41598-024-83466-5Colorectal CancerBiomedical imagesOsprey optimization AlgorithmFeature FusionComputer-aided diagnosis |
| spellingShingle | Sultan Refa Alotaibi Manal Abdullah Alohali Mashael Maashi Hamed Alqahtani Moneerah Alotaibi Ahmed Mahmud Advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical images Scientific Reports Colorectal Cancer Biomedical images Osprey optimization Algorithm Feature Fusion Computer-aided diagnosis |
| title | Advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical images |
| title_full | Advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical images |
| title_fullStr | Advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical images |
| title_full_unstemmed | Advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical images |
| title_short | Advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical images |
| title_sort | advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical images |
| topic | Colorectal Cancer Biomedical images Osprey optimization Algorithm Feature Fusion Computer-aided diagnosis |
| url | https://doi.org/10.1038/s41598-024-83466-5 |
| work_keys_str_mv | AT sultanrefaalotaibi advancesincolorectalcancerdiagnosisusingoptimaldeepfeaturefusionapproachonbiomedicalimages AT manalabdullahalohali advancesincolorectalcancerdiagnosisusingoptimaldeepfeaturefusionapproachonbiomedicalimages AT mashaelmaashi advancesincolorectalcancerdiagnosisusingoptimaldeepfeaturefusionapproachonbiomedicalimages AT hamedalqahtani advancesincolorectalcancerdiagnosisusingoptimaldeepfeaturefusionapproachonbiomedicalimages AT moneerahalotaibi advancesincolorectalcancerdiagnosisusingoptimaldeepfeaturefusionapproachonbiomedicalimages AT ahmedmahmud advancesincolorectalcancerdiagnosisusingoptimaldeepfeaturefusionapproachonbiomedicalimages |