Abstract
This thesis focuses on the importance of early detection in lung cancer through the use of medical imaging techniques and deep learning models. The current practice of examining nodules larger than 7 mm can delay detection and allow cancerous nodules to grow undetected. The project aims to detect nodules as small as 3 mm to improve the chances of early cancer identification. The use of constrained volume datasets and transfer learning techniques addresses the scarcity of medical data, and deep neural networks are employed for classification and segmentation tasks. Despite the limited dataset, the results demonstrate the effectiveness of the proposed models. Class activation maps and segmentation techniques enhance accuracy and provide insights into the most critical areas for diagnosis. This research contributes to the understanding of lung disease diagnosis and highlights the potential of deep learning in medical imaging.
Reference35 articles.
1. Aherne, F. J., Thacker, N. A., & Rockett, P. I. (1998). The Bhattacharyya metric as an absolute similarity measure for frequency coded data. Kybernetika, 34(4), 363-368.
2. Al-Huseiny, M. S., & Sajit, A. S. (2021). Transfer learning with GoogLeNet for detection of lung cancer. Indonesian Journal of Electrical Engineering and computer science, 22(2), 1078-1086. https://doi.org/10.11591/IJEECS.V22.I2.PP1078-1086
3. Arbib, M. A. (Ed.). (2003). The handbook of brain theory and neural networks. MIT press.
4. Beylkin, G. (1987). Discrete radon transform. IEEE transactions on acoustics, speech, and signal processing, 35(2), 162-172. https://doi.org/10.1109/TASSP.1987.1165108
5. Del Piccolo, N., Shirure, V. S., Bi, Y., Goedegebuure, S. P., Gholami, S., Hughes, C. C., ... & George, S. C. (2021). Tumor-on-chip modeling of organ-specific cancer and metastasis. Advanced drug delivery reviews, 175, 113798. https://doi.org/10.1016/j.addr.2021.05.008