IRO Journals
Journal of Ubiquitous Computing and Communication Technologies

Medical Image Recognition and Classification for Lung Cancer Disease Diagnosis using Deep Learning

Open Access
Published: 21 October, 2026
Pages: 382-395
  • Nagaprakash N. , Nagaprakash N.
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
  • Indira J. , Indira J.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
  • Jeyaarthi S. , Jeyaarthi S.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
  • Kowsalya S. Kowsalya S.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
view PDF
view PDF

How to Cite

N., Nagaprakash, Indira J., Jeyaarthi S., and Kowsalya S. 2026. “Medical Image Recognition and Classification for Lung Cancer Disease Diagnosis Using Deep Learning”. Journal of Ubiquitous Computing and Communication Technologies 8 (4): 382-95. https://doi.org/10.36548/jucct.2026.4.006.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Lung CT Image Classification
IQ-OTH/NCCD Dataset
Threshold-Based Lung Segmentation
Contrast-Enhanced CT Preprocessing
CNN Feature Learning
Softmax Multiclass Discrimination
Pulmonary Abnormality Recognition

Abstract

The automated recognition of lung cancer in Computed Tomography (CT) images requires effective variability reduction in the images with maintaining important pulmonary features. In this research proposes a preprocessing, segmentation, and CNN-based model for the classification of lung CT images in three classes. The pipeline applies Gaussian filter for noise reduction, normalization and contrast enhancement of the image inputs and subsequently, thresholding segmentation for isolating the lungs. The segmented CT images are then fed into the convolutional extraction of features, rectified linear unit (ReLU), max pooling and fully connected feature transformation layers. The output of the model comes from the Softmax classification layer which discriminates between normal, benign and malignant classes. Evaluation of the model performance is assessed through class-specific measures of accuracy, precision, recall and F1 score, supported with confusion matrix and technical comparisons. The reported evaluation demonstrates consistent classification performance across all three diagnostic classes, confirming the feasibility of using the entire preprocessing, segmentation, and CNN-based classification process for analyzing lung CT images.

References

  1. Chen, Suting, Liangchen Zhang, Rui Feng, and Chuang Zhang. "High-Resolution Remote Sensing Image Classification with RmRMR-Enhanced Bag of Visual Words." Computational Intelligence and Neuroscience, 2021, vol. 2021, no. 1: 7589481.
  2. Shafiq, Muhammad, and Zhaoquan Gu. "Deep residual learning for image recognition: A survey." Applied Sciences, 2022, vol. 12, no. 18: 8972.
  3. Wang, Pin, En Fan, and Peng Wang. "Comparative analysis of image classification algorithms based on traditional machine learning and deep learning." Pattern Recognition Letters, 2021, vol. 141: 61-67.
  4. Cheng, Lu, Yicai Ji, Chao Li, Xiaojun Liu, and Guangyou Fang. "Improved SSD network for fast concealed object detection and recognition in passive terahertz security images." Scientific Reports, 2022, vol. 12, no. 1: 12082.
  5. Singh, Vipul Kumar, and Maheshkumar H. Kolekar. "Deep learning empowered COVID-19 diagnosis using chest CT scan images for collaborative edge-cloud computing platform." Multimedia Tools and Applications, 2022, vol. 81, no. 1: 3-30.
  6. Liu, Fangjian, Lei Dong, Xueli Chang, and Xinyi Guo. "Remote sensing image classification based on object-oriented convolutional neural network." Frontiers in Earth Science, 2022, vol. 10: 988556.
  7. Lu, Tingyu, Meixiang Gao, and Lei Wang. "Crop classification in high-resolution remote sensing images based on multi-scale feature fusion semantic segmentation model." Frontiers in Plant Science, 2023, vol. 14: 1196634.
  8. Zhang, Guanjin, Siti Nur Aliaa Binti Roslan, Ci Wang, and Ling Quan. "Research on land cover classification of multi-source remote sensing data based on improved U-net network." Scientific Reports, 2023, vol. 13, no. 1: 16275.
  9. Adegun, Adekanmi, Serestina Viriri, and Jules-Raymond Tapamo. "Automated classification of remote sensing satellite images using deep learning-based vision transformer: A. Adegun et al." Applied Intelligence, 2024, vol. 54, no. 24: 13018-13037.
  10. Abdelmonem, Ahmed M., Mohamed Maher Ata, Abdelhamied A. Atey, A. A. Shaalan, and Rania A. El-Sayed. "High-performance scene classification in remote sensing imagery using a custom deep CNN architecture." Scientific Reports, 2026, vol. 16, no. 1: 5946.
  11. The IQ-OTH/NCCD lung cancer dataset - https://data.mendeley.com/datasets/bhmdr45bh2/4