Citation :

Mullakuri Anusha, D. Srinivasulu Reddy, "Handcrafted-Guided, Token Fusion with Learnable Attention Priors for Robust Lung and Colon Histopathology Subtype Recognition," International Journal of Electronics and Communication Engineering, vol. 13, no. 5, pp. 88-96, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I5P109

Abstract

Precise multi-class classification of lung and colon histopathology is of great clinical value but still poses a challenge because of the variability of stains and the subtle overlap of morphologies among different types of tissue. In this paper, a lightweight hybrid approach is proposed for the five-class classification of LC25000 patches (benign colon, benign lung, colon adenocarcinoma, lung adenocarcinoma, and lung squamous cell carcinoma). The proposed approach learns deep spatial morphology features from a convolutional encoder and represents compact handcrafted stain-prior features by L1-normalized RGB histograms. The novelty of this work is the employment of pre-pooling token fusion by means of directional handcrafted-to-morphology cross-attention, which is further reinforced by a learnable bias to improve the robustness of color-region affinity learning against appearance variation. The fused features are then enhanced by residual feed-forward blocks and classified by a compact head. The experimental results show that the proposed approach can bring consistent improvements in class-wise discrimination and agreement above chance level over attention and late fusion baselines, with accuracy, macro-F1, macro-AUC, and Cohen’s κ values of 0.9947, 0.9947, 0.9999, and 0.9933, respectively.

Keywords

Lung And Colon Cancer, Histopathology Image Classification, Efficientnetb0, Cross-Attention Feature Fusion, Lc25000 Dataset.

References

1. Jie Ji et al., “Automated Lung and Colon Cancer Classification Using Histopathological Images,” Biomedical Engineering and Computational Biology, vol. 15, pp. 1-8, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. A. Hasib Uddin et al., “Colon and Lung Cancer Classification from Multi-Modal Images using Resilient and Efficient Neural Network Architectures,” Heliyon, vol. 10, no. 9, pp. 1-23, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Raquel Ochoa-Ornelas et al., “A Robust Transfer Learning Approach with Histopathological Images for Lung and Colon Cancer Detection using EfficientNetB3,” Healthcare Analytics, vol. 7, pp. 1-15, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
4. MehmetGül, “An Effective Study on the Diagnosis of Colon Cancer with the Developed Local Binary Pattern Method,” Scientific Reports, vol. 15, pp. 1-20, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Marwa Obayya et al., “Biomedical Image Analysis for Colon and Lung Cancer Detection using Tuna Swarm Algorithm with Deep Learning Model,” IEEE Access, vol. 11, pp. 94705-94712, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Md. Al-Mamun Provath et al., “Classification of Lung and Colon Cancer Histopathological Images Using Global Context Attention Based Convolutional Neural Network,” IEEE Access, vol. 11, pp. 110164-110183, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Indu Chhillar, and Ajmer Singh, “A Feature Engineering-Based Machine Learning Technique to Detect and Classify Lung and Colon Cancer from Histopathological Images,” Medical & Biological Engineering & Computing, vol. 62, pp. 913-924, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Saeed Iqbal et al., “A Novel Heteromorphous Convolutional Neural Network for Automated Assessment of Tumors in Colon and Lung Histopathology Images,” Biomimetics, vol. 8, no. 4, pp. 1-22, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Sunila Anjum et al., “Lung Cancer Classification in Histopathology Images Using Multiresolution Efficient Nets,” Computational Intelligence and Neuroscience, vol. 2023, no. 1, pp. 1-12, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Omneya Attallah et al., “Lung and Colon Cancer Classification Using Multiscale Deep Features Integration of Compact Convolutional Neural Networks and Feature Selection,” Technologies, vol. 13, no. 2, pp. pp. 1-28, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Mohammed Al-Jabbar et al., “Histopathological Analysis for Detecting Lung and Colon Cancer Malignancies Using Hybrid Systems with Fused Features,” Bioengineering, vol. 10, no. 3, pp. 1-25, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Abdulkream A. Alsulami et al., “Identification of Anomalies in Lung and Colon Cancer Using Computer Vision-Based Swin Transformer with Ensemble Model on Histopathological Images,” Bioengineering, vol. 11, no. 10, pp. 1-22, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]