Detection of Lungs Cancer through Computed Tomographic Images using Deep Learning
IEEE Base Paper Title:
Detection of Lungs Cancer through Computed Tomographic Images using Deep Learning
(or)
Our Proposed Project Title:
Enhancing Healthcare with AI: CNN-Based Lung Cancer Detection System
IEEE BASE PAPER ABSTRACT:
Lung cancer has become a particularly lethal disease in the last decade. Lung cancer is the second most common cause of death for women and the primary cause of death for men. Therefore, early detection of lung knobs is one of the most effective ways to treat lung infections. Similarly, computer-aided diagnosis (CAD) of lung knobs has gotten a huge interest over the last decade. As a result of the broad variety of lung knobs and the complications of the entire environment, developing a robust knob detection approach is extremely difficult. A convolutional neural network (CNN) based framework is proposed to detect tumors that are identified as risky or benign in lung disease screening using CT images. Two publicly available datasets LUNA-16 and LIDC are employed to detect lung cancer. The dataset is augmented to maximize the volume of images in it. Also, preprocessing is done on CT images for better noise removal. Additionally, segmentation is performed to specify the infected area. Three pre-trained architectures, DenseNet, AlexNet, and VGG-16, are utilized to classify the cancerous and normal images. The DenseNet classifier achieved 98% classification accuracy, 98.93% sensitivity, and 99% specificity, which exhibits outstanding performance than other classifiers. The efficient results of the proposed framework show better performance than existing state-of-art studies.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
CNN Model Architecture, Resnet, Naive Bayes, and K-nearest Neighbors
OUR PROPOSED ABSTRACT:
Lung cancer is one of the most prevalent and lethal forms of cancer worldwide. Early and accurate diagnosis is crucial for improving patient outcomes. In this project, we propose a novel approach for the detection of lung cancer through computed tomographic (CT) images using a Convolutional Neural Network (CNN) model in Python. Our CNN model achieved exceptional results with a training accuracy of 100% and a validation accuracy of 100%.
Our dataset comprised a total of 554 CT scan images, including 358 cancerous images and 196 non-cancerous images, distributed across both the training and test sets. This diverse dataset allowed us to train our model comprehensively and ensured a robust evaluation of its performance.
Furthermore, we conducted experiments with three other models, including Resnet Model Architecture, Naive Bayes, and K-nearest Neighbors. Notably, the Resnet Model Architecture achieved a training accuracy of 97% and a validation accuracy of 95%. The Naive Bayes model demonstrated impressive results with a training score of 99% and a testing score of 100%. Finally, the K-nearest Neighbors model achieved a training score of 95% and a testing score of 97%.
Despite the success of these alternative models, our proposed CNN Model Architecture outperformed them all, achieving a remarkable 100% accuracy in both training and validation. This unparalleled accuracy underscores the potential of deep learning techniques, particularly CNNs, in the early detection of lung cancer from CT images.
Our research represents a significant advancement in the field of medical image analysis, offering a highly reliable and accurate tool for lung cancer diagnosis. Early detection facilitated by our CNN model can lead to timely interventions, ultimately saving lives and improving patient care.
SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED.
- Input Devices : Keyboard, Mouse.
- Ram : 8 GB.
SOFTWARE REQUIREMENTS:
- Operating system : Windows 10 / 11.
- Coding Language : Python 3.10.9.
- Web Framework : Flask.
- Frontend : HTML, CSS, JavaScript.
REFERENCE:
Madiha Abid; Shahzad Akbar; Sabeen Abid; Syed Ale Hassan; Sahar Gull, “Detection of Lungs Cancer through Computed Tomographic Images using Deep Learning”, 2023 4th International Conference on Advancements in Computational Sciences (ICACS), IEEE Conference, 2023.
👉CLICK HERE TO BUY THIS PROJECT SOURCE CODE👈
