Colorectal Lesion diagnosis using transformer and deep learning with multiscale feature interface
- 1Department of Computer Engineering & Applications, G.L.A. University, Mathura, Uttar Pradesh, India
- 2Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, India
- 3Department of Electronics and Communication Engineering, Kuwait College of Science and Technology (KCST), Kuwait City, Kuwait
Abstract
Colorectal cancer is the third most common malignancy worldwide. Manual screening requires expertise and resources. However, advancements in AI (artificial intelligence) have reduced the computation burden and time. Machine and deep learning have recently been used to diagnose colorectal lesions. The requirement of handcrafted features makes machine learning models expertise-dependent. At the same time, classical CNN (convolutional neural network) miss the global attention of the features. This work presents CDCTNet (colorectal diagnosis convolution transformer network), a hierarchical model for colorectal disease detection. Our model utilized two convolution blocks for the local high-dimensional spatial features from the lesion. In addition, the ViT encoder is used in parallel with the CNN block to provide a global correlation of the feature map. Furthermore, we designed an IEM block for the interaction of the features between the convolution block and ViT encoder to improve the attention on the features. The CDCTNet is evaluated on Kather and Kvasir datasets and obtained a precision and Kappa score of 96.60% and 95.02%, respectively. At the same time, CDCTNet has recall and F1 scores of 98.08% and 97.94%.
Related
- Interpretable attention-deficit hyperactivity disorder diagnosis from functional magnetic resonance imaging via hybrid convolutional neural network–transformer learning and multi-level graph-based comprehensibility
- AVMD-ST: attention-variational mode decomposition based spectrogram transformer for differential diagnosis of asthma and COPD
- GAMPoint: Geometry-augmented vision transformer with a multimodal-ready interface for 3D point-cloud segmentation
- Routes to Diagnosis and Stage at Diagnosis of Colorectal Cancer in Patients Aged ≥ 50 Years: A Multicentre Retrospective Cohort Study From North Wales, UK
- Exploring the key genes of colorectal “adenoma-cancer” based on graph transformer
BibTeX
@article{yadav2026colorectal,
title = {{Colorectal Lesion diagnosis using transformer and deep learning with multiscale feature interface}},
author = {Dhirendra Prasad Yadav and Bhisham Sharma and Julian L. Webber and Abolfazl Mehbodniya},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0357664},
url = {https://doi.org/10.1371/journal.pone.0357664},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Colorectal Lesion diagnosis using transformer and deep learning with multiscale feature interface
AU - Dhirendra Prasad Yadav
AU - Bhisham Sharma
AU - Julian L. Webber
AU - Abolfazl Mehbodniya
PY - 2026
DA - 2026/09/03
JO - PLOS One
DO - 10.1371/journal.pone.0357664
UR - https://doi.org/10.1371/journal.pone.0357664
AB - Colorectal cancer is the third most common malignancy worldwide. Manual screening requires expertise and resources. However, advancements in AI (artificial intelligence) have reduced the computation burden and time. Machine and deep learning have recently been used to diagnose colorectal lesions. The requirement of handcrafted features makes machine learning models expertise-dependent. At the same time, classical CNN (convolutional neural network) miss the global attention of the features. This work presents CDCTNet (colorectal diagnosis convolution transformer network), a hierarchical model for colorectal disease detection. Our model utilized two convolution blocks for the local high-dimensional spatial features from the lesion. In addition, the ViT encoder is used in parallel with the CNN block to provide a global correlation of the feature map. Furthermore, we designed an IEM block for the interaction of the features between the convolution block and ViT encoder to improve the attention on the features. The CDCTNet is evaluated on Kather and Kvasir datasets and obtained a precision and Kappa score of 96.60% and 95.02%, respectively. At the same time, CDCTNet has recall and F1 scores of 98.08% and 97.94%.
SN - 1932-6203
ER -