Open Access Open Access  Restricted Access Subscription Access

An Evaluation of Various Techniques for Classifying Histopathological Images of Lung Cancer

Mahfujur Rahman

Abstract


This study explores the use of advanced deep learning algorithms to forecast lung cancer, employing a range of complex models such as Modified CNN, Modified AlexNet, EfficientNetB4, and DenseNet121. The study used the Histopathological Image Dataset, which consists of intricate lung tissue images, to examine intricate patterns in three primary forms of lung cancer: Lung Adenocarcinoma, Lung Benign Tissue, and Lung Squamous Cell Carcinoma. The main goal is to improve the iden- tification of lung cancer in its early stages and influence the prognosis of patients. The deep learning models unveil intricate results by undergoing rigorous training and testing, emphasizing their distinct talents and constraints. The Modified AlexNet has exceptional performance, with an accuracy rate of 98.81%and, notable precision, recall, and F1 scores for all categories. However, the need to optimize computing ef- ficiency and manage intricate pattern complexity becomes apparent, highlighting the crucial trade-off between performance and computational requirements. The Mod- ified AlexNet has high accuracy in identifying Lung Benign Tissue but encounters difficulties in accurately classifying Lung Adenocarcinoma, suggesting room for en- hancement. EfficientNetB4 demonstrates satisfactory performance, but DenseNet121 is a strong contender, exceptionally skilled at distinguishing non-cancerous lung tissue. Confusion matrices offer valuable insights into the classification capabilities, aiding in selecting the most appropriate model for specific application objectives. This study establishes a fundamental basis for future progress in deep learning applied to medical imaging, offering the potential for more precise and practical techniques in diagnosing lung cancer.


Full Text:

PDF

References


M. Z. Rehman, N. M. Nawi, A. Tanveer, H. Zafar, H. Munir, and S. Hassan, “Lungs cancer nodules detection from ct scan images with convolutional neural networks,” in Recent Advances on Soft Computing and Data Mining: Proceedings of the Fourth International Conference on Soft Computing and Data Mining (SCDM 2020), Melaka, Malaysia, January 22– 23, 2020, pp. 382–391, Springer,

P. M. Shakeel, M. Burhanuddin, and M. I. Desa, “Automatic lung cancer detec- tion from ct image using improved deep neural network and ensemble classifier,” Neural Computing and Applications, pp. 1–14, 2022.

H. Sung, J. Ferlay, R. L. Siegel, M. Laversanne, I. Soerjomataram, A. Jemal, and F. Bray, “Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries,” CA: a cancer journal for clinicians, vol. 71, no. 3, pp. 209–249, 2021.

R. Anirudh, J. J. Thiagarajan, T. Bremer, and H. Kim, “Lung nodule detec- tion using 3d convolutional neural networks trained on weakly labeled data,” in Medical Imaging 2016: Computer-Aided Diagnosis, vol. 9785, pp. 791–796, Spie, 2016.

R. Sujitha and V. Seenivasagam, “Retracted article: Classification of lung cancer stages with machine learning over big data healthcare framework,” Journal of Ambient Intelligence and Humanized Computing, vol. 12, no. 5, pp. 5639–5649, 2021.

L. A. Cooper, J. Kong, D. A. Gutman, W. D. Dunn, M. Nalisnik, and D. J. Brat, “Novel genotype-phenotype associations in human cancers enabled by ad- vanced molecular platforms and computational analysis of whole slide images,” Laboratory investigation, vol. 95, no. 4, pp. 366–376, 2015.

H. A. Alturkistani, F. M. Tashkandi, and Z. M. Mohammedsaleh, “Histological stains: a literature review and case study,” Global journal of health science, vol. 8, no. 3, p. 72, 2016.

M. A. Talukder, M. M. Islam, M. A. Uddin, A. Akhter, K. F. Hasan, and

M. A. Moni, “Machine learning-based lung and colon cancer detection using deep feature extraction and ensemble learning,” Expert Systems with Applica- tions, vol. 205, p. 117695, 2022.

S. Demyanov, R. Chakravorty, M. Abedini, A. Halpern, and R. Garnavi, “Classifi- cation of dermoscopy patterns using deep convolutional neural networks,” in 2016 IEEE 13th International symposium on biomedical imaging (ISBI), pp. 364–368, IEEE, 2016.

D. P. Kaucha, P. Prasad, A. Alsadoon, A. Elchouemi, and S. Sreedharan, “Early detection of lung cancer using svm classifier in biomedical image processing,” in 2017 IEEE international conference on power, control, signals and instrumenta- tion engineering (ICPCSI), pp. 3143–3148, IEEE, 2017.


Refbacks

  • There are currently no refbacks.