Adenoma Dysplasia Grading of Colorectal Polyps Using Fast Fourier Convolutional ResNet (FFC-ResNet)

Simple item page
dc.contributor.authorPaing, May Phu
dc.contributor.authorPintavirooj, Chuchart
dc.date.accessioned2026-08-06T10:40:24Z
dc.date.available2026-08-06T10:40:24Z
dc.date.issued2023-01-01
dc.description.abstractColorectal polyps are precursor lesions of colorectal cancer; hence, early detection and dysplasia grading of polyps are essential for determining cancer risk, the possibility of developing subsequent polyps, and follow-up recommendations. The significant contribution of this study is the development of an enhanced deep-learning model called Fast Fourier Convolutional ResNet (FFC-ResNet) to classify dysplasia grades of polyps. It is based on the ResNet-50 architecture and uses cross-feature fusion, which combines local features extracted by traditional spatial convolution with global features extracted by Fourier convolution. Due to the compensatory effect between local and global features, the learnability and performance of FFC-ResNet have increased. The proposed FFC-ResNet was developed and tested using UniToPatho, a dataset containing 7000 μm and 800 μm hematoxylin-and-eosin (H&E)-stained colorectal images. And a favorable performance of sensitivity 0.95, specificity 0.93, balance accuracy 0.94, precision 0.95, F1 score 0.95, and AUC 0.99 was obtained using 800 μm polyp patches.
dc.identifier.citationIEEE Access, 11, 16644-16656, 2023
dc.identifier.doi10.1109/ACCESS.2023.3246730
dc.identifier.issn21693536
dc.identifier.other2-s2.0-85149182364
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/14136
dc.sourceIEEE Access
dc.subjectColorectal cancer
dc.subjectcomputer-aided diagnosis
dc.subjectdeep learning
dc.subjectfrequency domain
dc.subjectprincipal component analysis
dc.titleAdenoma Dysplasia Grading of Colorectal Polyps Using Fast Fourier Convolutional ResNet (FFC-ResNet)
dc.typeArticle

Files

Collections

Research