Citation :

Suraj Vinod Dhole, Amit Kamalakar Gaikwad, "A Lightweight Attention based Deep Learning Framework for Pancreatic Cancer Detection in CT Images," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 10, pp. 479-501, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I10P134

Abstract

Pancreatic Cancer is one of the deadliest cancers, with a five-year survival rate of about 11% because it is often diagnosed late. Current deep learning methods for detecting Pancreatic Cancer from Computed Tomography (CT) images frequently struggle with overfitting, high computational demands, and poor multi-scale feature representation. This paper presents a Lightweight Convolutional Neural Network (LWCNN) framework based on the Electrophorus Chain Hunt Algorithm (ECHA) for automated PDAC detection. In this study, firstly, an efficient segmentation of the pancreas and multi-level feature extraction from the image using a BAM-based U-Net architecture are performed. Subsequently, Modified Local Ternary Pattern (MLTP), Statistical Texture Pattern (STP), and LayerCAM features are integrated to construct a comprehensive feature representation. The fused features are classified by a light-weight CNN with the help of ECHA. The proposed framework is evaluated on the publicly available Medical Segmentation Decathlon (MSD) dataset, which comprises 420 three-dimensional CT volumes. The experimental results showed 95.80% accuracy, 96.39% sensitivity, and 95.20% specificity. Additionally, 10-fold cross-validation resulted in an accuracy of 94.05%, demonstrating solid robustness and generalization. Comparative and ablation studies confirm that integrating BAM-based segmentation, hybrid feature fusion, and ECHA optimization improves pancreatic cancer detection performance while keeping computational efficiency.

Keywords

Deep learning, Pancreatic cancer, Attention module, and Convolutional Neural Network.

References

1. Rebecca L. Siegel et al., “Colorectal Cancer Statistics, 2020,” CA: A Cancer Journal for Clinicians, vol. 70, no. 3, pp. 145-164, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
2. C. Güngör et al., “Pancreatic Cancer,” British Journal of Pharmacology, vol. 171, no. 4, pp. 849-858, 2014.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Deepesh Agarwal et al., “Early Detection of Pancreatic Cancers using Liquid Biopsies and Hierarchical Decision Structure,” IEEE Journal of Translational Engineering in Health and Medicine, vol. 10, pp. 1-8, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Shang-Long Liu et al., “Establishment and Application of an Artificial Intelligence Diagnosis System for Pancreatic Cancer with a Faster Region-based Convolutional Neural Network,” Chinese Medical Journal, vol. 132, no. 23, pp. 2795-2803, 2019.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Janjhyam Venkata Naga Ramesh et al., “Sparrow Search Algorithm with Stacked Deep Learning based Medical Image Analysis for Pancreatic Cancer Detection and Classification,” IEEE Access, vol. 11, pp. 111927-111935, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Madumali Kalubowilage et al., “Early Detection of Pancreatic Cancers in Liquid Biopsies by Ultrasensitive Fluorescence Nanobiosensors,” Nanomedicine: Nanotechnology, Biology and Medicine, vol. 14, no. 6, pp. 1823-1832, 2018.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Tamotsu Kuroki, and Susumu Eguchi, “No-Touch Isolation Techniques for Pancreatic Cancer,” Surgery Today, vol. 47, pp. 8-13, 2017.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Ralph Santos et al., “Clinical Prediction Models for Pancreatic Cancer in General and At-Risk Populations: A Systematic Review,” American Journal of Gastroenterology, vol. 118, no. 1, pp. 26-40, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Davide Placido et al., “A Deep Learning Algorithm to Predict Risk of Pancreatic Cancer from Disease Trajectories,” Nature Medicine, vol. 29, no. 5, pp. 1113-1122, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Seok Jin Hong et al., “Convolutional Neural Network Model for Automatic Recognition and Classification of Pancreatic Cancer Cell based on Analysis of Lipid Droplet on Unlabeled Sample by 3D Optical Diffraction Tomography,” Computer Methods and Programs in Biomedicine, vol. 246, pp. 1-9, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Simon Lebech Cichosz et al., “Prediction of Pancreatic Cancer Risk in Patients with New-Onset Diabetes using a Machine Learning Approach based on Routine Biochemical Parameters,” Computer Methods and Programs in Biomedicine, vol. 244, pp. 1-7, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436-444, 2015.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Benjamin Shickel et al., “Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis,” IEEE Journal of Biomedical and Health Informatics, vol. 22, no. 5, pp. 1589-1604, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Stephanie L. Hyland et al., “Early Prediction of Circulatory Failure in the Intensive Care Unit using Machine Learning,” Nature Medicine, vol. 26, no. 3, pp. 364-373, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Jessica X. Hu et al., “A Large-Cohort, Longitudinal Study Determines Precancer Disease Routes Across Different Cancer Types,” Cancer Research, vol. 79, no. 4, pp. 864-872, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Scott Mayer McKinney et al., “International Evaluation of an AI System for Breast Cancer Screening,” Nature, vol. 577, no. 7788, pp. 89-94, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Natália Alves et al., “Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography,” Cancers, vol. 14, no. 2, pp. 1-10, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Catherine Park et al., “Machine Learning-based Aggression Detection in Children with ADHD using Sensor-based Physical Activity Monitoring,” Sensors, vol. 23, no. 10, pp. 1-14, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Leang Sim Nguon et al., “Deep Learning-based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas using Endoscopic Ultrasonography,” Diagnostics, vol. 11, no. 6, pp. 1-11, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Julius Keyl et al., “Multimodal Survival Prediction in Advanced Pancreatic Cancer using Machine Learning,” ESMO Open, vol. 7, no. 5, pp. 1-9, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Wansu Chen et al., “Risk Prediction of Pancreatic Cancer in Patients with Abnormal Morphologic Findings Related to Chronic Pancreatitis: A Machine Learning Approach,” Gastro Hep Advances, vol. 1, no. 6, pp. 1014-1026, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Tong Tong et al., “Deep Learning Radiomics based on Contrast-Enhanced Ultrasound Images for Assisted Diagnosis of Pancreatic Ductal Adenocarcinoma and Chronic Pancreatitis,” BMC Medicine, vol. 20, no. 1, pp. 1-15, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Wenjie Liang et al., “Classification Prediction of Pancreatic Cystic Neoplasms based on Radiomics Deep Learning Models,” BMC Cancer, vol. 22, no. 1, pp. 1-10, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Jongchan Park et al., “BAM: Bottleneck Attention Module,” arXiv, pp. 1-14, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Hanaa M. Al Abboodi et al., “High-Resolution Model for Segmenting and Predicting Brain Tumor based on Deep UNet with Multi Attention Mechanism,” International Journal of Intelligent Engineering and Systems, vol. 17, no. 2, pp. 294-310, 2024.
    [Google Scholar] [Publisher Link]
26. Jiheum Park et al., “Deep Learning on Time Series Laboratory Test Results from Electronic Health Records for Early Detection of Pancreatic Cancer,” Journal of Biomedical Informatics, vol. 131, pp. 1-10, 2022. 
    [CrossRef] [Google Scholar] [Publisher Link]
27. Iraj Naruei, and Farshid Keynia, “A New Optimization Method based on COOT Bird Natural Life Model,” Expert Systems with Applications, vol. 183, pp. 1-25, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Nourhan A. Maged, Hany M. Hasanien, and Mohammed Alharbi et al., “Electric Eel Foraging Algorithm-based Optimal Control for Low Voltage Ride through Capability Improvement of Grid-Connected Photovoltaic Power Plants,” Ain Shams Engineering Journal, vol. 15, no. 7, pp. 1-13, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Rui-Yang Ju, and Weiming Cai, “Fracture Detection in Pediatric Wrist Trauma X-Ray Images using YOLOv8,” Scientific Reports, vol. 13, no. 1, pp. 1-13, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
30. Khan Fashee Monowar, Md. Al Mehedi Hasan, and Jungpil Shin, “A Lightweight Convolutional Neural Network Model for Child Pneumonia Classification,” 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD), Dhaka, Bangladesh, pp. 269-273, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
31. Medical Segmentation Decathlon, 2018. [Online]. Available: http://medicaldecathlon.com/
32. Rong Yang et al., “CT Classification Model of Pancreatic Serous Cystic Neoplasms and Mucinous Cystic Neoplasms based on a Deep Neural Network,” Abdominal Radiology, vol. 47, no. 1, pp. 232-241, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
33. Ramalingegowda et al., “Image based Person Re-Identification using GAN, DWT, and MLTP with ANN Classifier,” International Journal of Intelligent Engineering and Systems, vol. 16, no. 5, pp. 124-137, 2023.
    [CrossRef] [Google Scholar]
34. Peng-Tao Jiang et al., “LayerCAM: Exploring Hierarchical Class Activation Maps for Localization,” IEEE Transactions on Image Processing, vol. 30, pp. 5875-5888, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]