International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 03 | Mar 2024
p-ISSN: 2395-0072
www.irjet.net
LUNG CANCER DETECTION USING VISUAL GEOMETRY GROUP-16 (VGG-16) K. Himavanth1, B. Sharath2, A. Balaji3, M. Sujan4,T.Himaja Sumasri5 12345Student, Dept. Of Computer Science Engineering, GITAM Deemed University, Visakhapatnam, AP, INDIA
--------------------------------------------------------------------***----------------------------------------------------------Abstract - Lung cancer is a common and life-threatening
Differentiation between benign and malignant lung lesions on CT scan images can alter the clinical picture and diagnosis. Using VGG-16, we aim to improve the correctness and efficacy of Bronchogenic Carcinoma detection, emerging in best fallout for patients. This report shows how to implement our system step by step. It focuses on classifying the CT scan images using the VGG16 algorithm.
disease with a high mortality rate all over the world. Detecting this early plays an important role in improving patient outcomes and reducing mortality. In recent years, deep learning models have shown significant potential in medical image analysis, especially in the field of cancer detection. This paper presents a new approach for lung cancer detection using the VGG-16 algorithm, a convolutional neural network (CNN) architecture known for its performance in image classification tasks. We provide a comprehensive methodology that includes lung image preprocessing, VGG-16 model training on an annotated lung scan and model performance evaluation using various metrics such as accuracy, sensitivity and specificity. In addition, we investigate the effect of different hyperparameters and data augmentation techniques on model performance. Experimental results show the effectiveness of the VGG-16 algorithm for accurate detection of lung cancer based on medical image data. The proposed approach holds significant promise for improving the early diagnosis and treatment planning of patients with lung cancer, ultimately contributing to improved clinical outcomes and quality of life.
1.1 Lung Cancer Detection Lung cancer is one of the deadly and most common cancers in the world. Early detection is critical to improving patient outcomes and survival. Traditionally, the detection of lung cancer was based on methods such as chest X-ray, computed tomography (CT), and tissue biopsy. However, these methods often require extensive manual inspection by radiologists and may not always detect cancer at an early stage. In recent years, interest in using deep learning techniques for early detection and diagnosis of lung cancer has increased. . Deep learning is a subset of artificial intelligence (AI) that involves training neural networks to recognize patterns and make predictions from large amounts of data. In medical imaging such as CT scanning and X-rays, deep learning algorithms can help radiologists identify suspicious areas that may indicate the presence of cancer. One of the main advantages of deep learning for lung cancer detection is its ability to analyze a huge number of medical images quickly and accurately. Deep learning models can be trained on datasets containing thousands of annotated images, allowing them to learn complex patterns associated with cancer lesions. These models can then be used to analyze new images and make recommendations to radiologists for further evaluation. Several deep learning techniques have been developed for lung cancer detection, including Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). In particular, CNNs have shown promising results in detecting lung nodules and other abnormalities in medical images. Designed to automatically learn hierarchical representations of image features, these networks are well suited for tasks such as lung cancer detection.
Keywords: Lung cancer (Bronchogenic Carcinoma) detection,VGG-16,Image classification, Convolutional neural networks
1.INTRODUCTION Bronchogenic Carcinoma is a vital global haleness problem, requiring urgent attention due to its impact on patient prognosis and survival rates. Timely detection is essential, and computed tomography(CT) scans have emerged as important diagnostic tools for lung cancer and its stages. To address this, considerable research has focused on lung cancer detection systems from CT images. This project report presents our attempt to use a deep learning model, specifically the VGG-16 algorithm, to predict lung cancer using CT scan images. Bronchogenic Carcinoma is the major cause of mortality related to cancer worldwide, underscoring the need for accurate diagnostic tools, Although CT scanning provides detailed information, manual interpretation is time-consuming and prone to errors. Our project uses Deep Learning to automate and improve Bronchogenic Carcinoma detection. The core of the solution is the VGG-16 algorithm, which is known for its image segmentation capabilities.
© 2024, IRJET
|
Impact Factor value: 8.226
2. LITERATURE REVIEW Recent advancements in deep learning and machine learning have propelled significant strides in the detection
|
ISO 9001:2008 Certified Journal
|
Page 1404