Citation :

Venkata Anupama Chitturi, Dharmaiah Devarapalli, "A Transformer-Based Few-Shot Learning Model for Cervical Cancer Prediction with High Quality Imaging Model Cancer Classification from Pap Smear Images," International Journal of Electronics and Communication Engineering, vol. 13, no. 4, pp. 66-80, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I4P105

Abstract

Cervical Cancer (CC) diagnosis using medical images has advanced significantly thanks to deep learning. This article attempts to give a thorough explanation of the operations and uses of frequently utilized radiological imaging methods and histology. One of the main areas of Computer Vision and Artificial Intelligence study is applying deep learning technologies to identify cervical cancer from medical photographs. Due to the intrinsic complexity of medical imaging, few-shot cervical cancer diagnosis requires excellent Accuracy and Rapidity, especially given the rapid improvements in Deep Learning. It looks at both traditional pre-trained models and the fundamental architecture of deep learning. This work explicitly suggests a Novel Vision Transformer (ViT). Batch normalization, initialization, dropout, and augmentation are listed as ViT strategies in the article to prevent over-fitting. Picture classification, picture reconstruction, detection, segmentation, registration, and synthesis are several categories of deep learning approaches to cancer analysis using medical images. Despite its achievements, deep learning’s ability to diagnose uncommon tumors, model explainability, and generalization is limited by the absence of high-quality labeled datasets. More open, standardized databases for cancer research are desperately needed. Enhancements to Deep Neural Network-based pre-trained models are crucial, and data fusion and supervised paradigms should be prioritized. It is anticipated that new technologies like few-shot learning would significantly improve the use of medical pictures for cancer diagnosis.

Keywords

Cervical Cancer, Prediction, Accuracy, Transformers, Tumors.

References

1. Arman Afrasiyabi, Jean-François Lalonde, and Christian Gagné, “Mixture-based Feature Space Learning for Few-shot Image Classification,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 9021-9031, 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Arman Afrasiyabi et al., “Matching Feature Sets for Few-Shot Image Classification,” arXiv Preprint, pp. 9004-9014, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Arman Afrasiyabi, Jean-François Lalonde, and Christian Gagné, “Associative Alignment for Few-Shot Image Classification,” 16^th European Conference Computer Vision – ECCV 2020, Glasgow, UK, pp. 18-35, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Narenthirakumar Appavu, “Analysing the Effect of Edge-Optimized Deep Learning Models on Improving Low-Powered Iot Devices Real-Time Object Detection,” 2025 9^th International Conference on Inventive Systems and Control (ICISC), Coimbatore, India, pp. 1663-1669, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Sungyong Baik et al., “Meta-Learning with Task-adaptive Loss Function for Few-shot Learning,” arXiv Preprint, pp. 9465-9474, 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Narenthirakumar Appavu, “Skin Cancer Detection Using A Multi-Scale AI Deep Learning Approach,” 2025 Fifth International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), Bhilai, India, pp. 1-5, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Gianni Brauwers, and Flavius Frasincar, “A General Survey on Attention Mechanisms in Deep Learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 4, pp. 3279-3298, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Qi Cai et al., “Memory Matching Networks for One-Shot Image Recognition,” arXiv Preprint, pp. 1-9, 2018.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Xuewei Chao, and Lixin Zhang, “Few-Shot Imbalanced Classification based on Data Augmentation,” Multimedia Systems, vol. 29, pp. 2843-2851, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Yinbo Chen et al., “Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning,” arXiv Preprint, pp. 1-2, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Guanqi Ding et al., “Attribute Group Editing for Reliable Few-shot Image Generation,” arXiv Preprint, pp. 1-17, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Junhao Dong et al., “Improving Adversarially Robust Few-shot Image Classification with Generalizable Representations,” 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 9015-9024
    [CrossRef] [Google Scholar] [Publisher Link]
13. Jaejun Do, Minjung Yoo, and Sunok Kim, “A Semi-supervised SAR Image Classification with Data Augmentation and Pseudo Labeling,” 2022 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), Yeosu, Korea, Republic of pp. 1-4, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Narenthirakumar Appavu, “Detection and Categorisation of Brain Tumours Using Hybrid AI Deep Learning Methods,” 2025 6^th International Conference on Mobile Computing and Sustainable Informatics, Goathgaun, Nepal, pp. 1227-1234, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Soroor Malekmohamadi Faradonbe, Faramarz Safi-Esfahani, and Morteza Karimian-kelishadrokhi, “A Review on Neural Turing Machine (NTM),” SN Computer Science, vol. 1, pp. 1-23, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Chelsea Finn, Pieter Abbeel, and Sergey Levine, “Model-Agnostic Meta-learning for Fast Adaptation of Deep Networks,” arXiv Preprint, pp. 1-13, 2017.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Madhava Gaikwad, and Ashwini Doke, “Survey on Meta Learning Algorithms for Few Shot Learning,” 2022 6^th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, pp. 1876-1879, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Katelyn Gao, and Ozan Sener, “Modeling and Optimization Trade-off in Meta-learning,” NeurIPS, pp. 1-12, 2020.
    [Google Scholar] [Publisher Link]
19. Spyros Gidaris, and Nikos Komodakis, “Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning,” 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 21-30, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Jiuxiang Gu et al., “Recent Advances in Convolutional Neural Networks,” Pattern Recognition, vol. 77, pp. 354-377, 2018. 
    [CrossRef] [Google Scholar] [Publisher Link]
21. Yunhui Guo et al., “A Broader Study of Cross-Domain Few-Shot Learning,” 16^th European Conference Computer Vision – ECCV, Glasgow, UK, pp. 124-141, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Guangxing Han et al., “Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting,” arXiv Preprint, pp. 1-17, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Tianhao Hu et al., “A Simple Data Augmentation Algorithm and a Self-adaptive Convolutional Architecture for Few-shot Fault Diagnosis under Different Working Conditions,” Measurement, vol. 156, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Huaxi Huang et al., “Compare More Nuanced: Pairwise Alignment Bilinear Network for Few-Shot Fine-Grained Learning,” 2019 IEEE International Conference on Multimedia and Expo (ICME), Shanghai, China, pp. 91-96, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Bingyi Kang et al., “Few-Shot Object Detection via Feature Reweighting,” 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp. 8419-8428, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Geethan Karunaratne et al., “Robust High-Dimensional Memory-Augmented Neural Networks,” Nature Communications, vol. 12, pp. 1-12, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Abdullatif Köksal, Timo Schick, and Hinrich Schuetze, “MEAL: Stable and Active Learning for Few-Shot Prompting,” Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, pp. 506-517, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Narenthirakumar Appavu, “Deep Learning for Predicting Invasive Ductal Carcinoma in Histopathological Tissue Images,” 2025 Eleventh International Conference on Bio Signals, Images, and Instrumentation (ICBSII), Chennai, India, pp. 1-5, 2025. 
    [CrossRef] [Google Scholar] [Publisher Link]
29. Xiaoxu Li et al., “BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification,” IEEE Transactions on Image Processing, vol. 30, pp. 1318-1331, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
30. Ishak Pacal, “MaxCerVixT: A Novel Lightweight Vision Transformer-based Approach for Precise Cervical Cancer Detection,” Knowledge-Based Systems, vol. 289, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
31. Narenthirakumar Appavu, “Skin Cancer Detection Using A Multi-Scale AI Deep Learning CNN Techniques,” 2025 6^th International Conference on Recent Advances in Information Technology (RAIT), Dhanbad, India, pp. 1-6, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
32. Ahmet Karaman et al., “Robust Real-time Polyp Detection System Design Based on YOLO Algorithms by Optimizing Activation Functions and Hyper-parameters with Artificial Bee Colony (ABC),” Expert Systems with Applications, vol. 221, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
33. Ahmet Karaman et al., “Hyper-Parameter Optimization of Deep Learning Architectures using Artificial Bee Colony (ABC) Algorithm for High Performance Real-Time Automatic Colorectal Cancer (CRC) Polyp Detection,” Applied Intelligence, vol. 53, pp. 15603-15620, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]