Binary and Multi-Class Classification of Colorectal Polyps Using CRP-ViT: A Comparative Study Between CNNs and QNNs
Background: Colorectal cancer (CRC) is a major contributor to cancer mortality on a global scale, with polyps being critical precursors. The accurate classification of colorectal polyps (CRPs) from colonoscopy images is essential for the timely diagnosis and treatment of CRC. Method: This research p...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Life |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1729/15/7/1124 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849406512006430720 |
|---|---|
| author | Jothiraj Selvaraj Fadhiyah Almutairi Shabnam M. Aslam Snekhalatha Umapathy |
| author_facet | Jothiraj Selvaraj Fadhiyah Almutairi Shabnam M. Aslam Snekhalatha Umapathy |
| author_sort | Jothiraj Selvaraj |
| collection | DOAJ |
| description | Background: Colorectal cancer (CRC) is a major contributor to cancer mortality on a global scale, with polyps being critical precursors. The accurate classification of colorectal polyps (CRPs) from colonoscopy images is essential for the timely diagnosis and treatment of CRC. Method: This research proposes a novel hybrid model, CRP-ViT, integrating ResNet50 with Vision Transformers (ViTs) to enhance feature extraction and improve classification performance. This study conducted a comprehensive comparison of the CRP-ViT model against traditional convolutional neural networks (CNNs) and emerging quantum neural networks (QNNs). Experiments were conducted for binary classification to predict the presence of polyps and multi-classification to predict specific polyp types (hyperplastic, adenomatous, and serrated). Results: The results demonstrate that CRP<sub>QNN</sub>-ViT achieved superior classification performance while maintaining computational efficiency. CRP<sub>QNN</sub>-ViT achieved an accuracy of 98.18% for training and 97.73% for validation on binary classification and 98.13% during training and 97.92% for validation on multi-classification tasks. In addition to the key metrics, computational parameters were compared, where CRP<sub>QNN</sub>-ViT excelled in computational time. Conclusions: This comparative analysis reveals the potential of integrating quantum computing into medical image analysis and underscores the effectiveness of transformer-based architectures for CRP classification. |
| format | Article |
| id | doaj-art-6f26259983ce46b297880c58d3192bcc |
| institution | Kabale University |
| issn | 2075-1729 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Life |
| spelling | doaj-art-6f26259983ce46b297880c58d3192bcc2025-08-20T03:36:21ZengMDPI AGLife2075-17292025-07-01157112410.3390/life15071124Binary and Multi-Class Classification of Colorectal Polyps Using CRP-ViT: A Comparative Study Between CNNs and QNNsJothiraj Selvaraj0Fadhiyah Almutairi1Shabnam M. Aslam2Snekhalatha Umapathy3Department of Biomedical Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu 603203, IndiaDepartment of Information Systems, College of Computer and Information Sciences, Majmaah University, Al Majmaah 11952, Saudi ArabiaDepartment of Information Technology, College of Computer and Information Sciences, Majmaah University, Al Majmaah 11952, Saudi ArabiaDepartment of Biomedical Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu 603203, IndiaBackground: Colorectal cancer (CRC) is a major contributor to cancer mortality on a global scale, with polyps being critical precursors. The accurate classification of colorectal polyps (CRPs) from colonoscopy images is essential for the timely diagnosis and treatment of CRC. Method: This research proposes a novel hybrid model, CRP-ViT, integrating ResNet50 with Vision Transformers (ViTs) to enhance feature extraction and improve classification performance. This study conducted a comprehensive comparison of the CRP-ViT model against traditional convolutional neural networks (CNNs) and emerging quantum neural networks (QNNs). Experiments were conducted for binary classification to predict the presence of polyps and multi-classification to predict specific polyp types (hyperplastic, adenomatous, and serrated). Results: The results demonstrate that CRP<sub>QNN</sub>-ViT achieved superior classification performance while maintaining computational efficiency. CRP<sub>QNN</sub>-ViT achieved an accuracy of 98.18% for training and 97.73% for validation on binary classification and 98.13% during training and 97.92% for validation on multi-classification tasks. In addition to the key metrics, computational parameters were compared, where CRP<sub>QNN</sub>-ViT excelled in computational time. Conclusions: This comparative analysis reveals the potential of integrating quantum computing into medical image analysis and underscores the effectiveness of transformer-based architectures for CRP classification.https://www.mdpi.com/2075-1729/15/7/1124colorectal polyp classificationCRP-ViTvision transformerCNNQNNcolonoscopy images |
| spellingShingle | Jothiraj Selvaraj Fadhiyah Almutairi Shabnam M. Aslam Snekhalatha Umapathy Binary and Multi-Class Classification of Colorectal Polyps Using CRP-ViT: A Comparative Study Between CNNs and QNNs Life colorectal polyp classification CRP-ViT vision transformer CNN QNN colonoscopy images |
| title | Binary and Multi-Class Classification of Colorectal Polyps Using CRP-ViT: A Comparative Study Between CNNs and QNNs |
| title_full | Binary and Multi-Class Classification of Colorectal Polyps Using CRP-ViT: A Comparative Study Between CNNs and QNNs |
| title_fullStr | Binary and Multi-Class Classification of Colorectal Polyps Using CRP-ViT: A Comparative Study Between CNNs and QNNs |
| title_full_unstemmed | Binary and Multi-Class Classification of Colorectal Polyps Using CRP-ViT: A Comparative Study Between CNNs and QNNs |
| title_short | Binary and Multi-Class Classification of Colorectal Polyps Using CRP-ViT: A Comparative Study Between CNNs and QNNs |
| title_sort | binary and multi class classification of colorectal polyps using crp vit a comparative study between cnns and qnns |
| topic | colorectal polyp classification CRP-ViT vision transformer CNN QNN colonoscopy images |
| url | https://www.mdpi.com/2075-1729/15/7/1124 |
| work_keys_str_mv | AT jothirajselvaraj binaryandmulticlassclassificationofcolorectalpolypsusingcrpvitacomparativestudybetweencnnsandqnns AT fadhiyahalmutairi binaryandmulticlassclassificationofcolorectalpolypsusingcrpvitacomparativestudybetweencnnsandqnns AT shabnammaslam binaryandmulticlassclassificationofcolorectalpolypsusingcrpvitacomparativestudybetweencnnsandqnns AT snekhalathaumapathy binaryandmulticlassclassificationofcolorectalpolypsusingcrpvitacomparativestudybetweencnnsandqnns |