A Hybrid VGG 19 and Capsule Network Based Deep Learning Model for Lung Cancer Diagnosis using CT S can Images

Objectives: Lung cancer is one of the most prevalent causes of carcinoma-related fatalities globally; precise and effective diagnostic instruments are desperately needed. Researchers and physicians continue to encounter difficulties when aiming to employ deep learning models in healthcare environments for recognizing lung cancer and to achieve higher sensitivity and accuracy on large data sets, despite several advancements in this field. Our study builds upon an extensive review of existing lung cancer detection methods, highlighting their strengths and weaknesses. The performance of this model deteriorates when there are variances in Lung CT image features such as rotation, tiling, and other aberrant image orientations. This study aims to address the issues associated with variations in lung CT images. Methods: A hybrid deep learning model that blends the potency of CNNs with the cutting-edge design of capsule networks is proposed. Inspired by recent advancements, our model integrates the VGG19 and Capsule Network architectures to address orientation-related challenges often encountered in traditional CNN-based approaches. The creation, training, and assessment of this hybrid model for lung nodule identification and categorization are our main research goals. Findings: We anticipate that our research has yielded several valuable outcomes, including improved nodule classification accuracy of 99.20%, reduced false positive rates, and minimized training times. Novelty: This research employing a hybrid deep learning model that combines the capabilities of the VGG-19 and capsule network could lead to more widespread utilization in cancer diagnosis by enhancing early lung cancer detection and developing the field of medical image analysis. The shortcomings of convolutional neural networks are addressed with Capsule Network. Leveraging the knowledge and insights gained from lung cancer detection, our research also investigates the potential applicability of our methodology to identify other types of medical image classification such as breast and ovarian cancer. Keywords: Computed Tomography, Lung cancer, Deep Learning, CNN, VGG19, Capsule Network