Detection of Lung Cancer from CT images using SVM Classification and Compare the survival rate of patients using 3D CNN on lung nodule dataset.

The presentation describes about the title - Detection of Lung cancer using SVM classification and 3D Convolution Neural Networks. It includes Abstract, Existing system, Software and Hardware Requirements, Dataset that is used in the upcoming project.

1. Detection of Lung cancer from CT image using SVM classification and compare the survival rate of patients using 3D Convolutional neural network (3D CNN) on lung nodules data set. Title

2. In this technological era, we are determined to computerize everything using Artificial intelligence and Machine Learning. The medical industry is no exception. As we previously had known the wonders of AI and data analytics technologies has done in the medical industry. In this project, we are pre-processing the medical picture or a CT scan image. The image is segmented and augmented into small pictures using the methods. Once, the region of interest(ROI) in the image is identified which is related to the lung cancer cell, the segmentation process proceeds to the next pixel of the CT image. The process includes – data gathering , data cleaning, segmentation, data analytics, and conclusion of the problem. The mentioned procedures are all based on the deep learning, CNN and image processing techniques. ABSTRACT

3. In the proposed system, we leverage Convolutional Neural Networks (CNNs) to significantly enhance lung cancer detection accuracy and efficiency. By employing advanced deep learning techniques, particularly 3D CNN architectures, our system aims to automate the process of identifying suspicious nodules in CT images with high sensitivity and specificity. This approach not only reduces the reliance on manual interpretation but also improves the overall reliability of lung cancer screening. Additionally, the proposed system enables real-time analysis, facilitating prompt interventions and personalized treatment plans based on predictive modeling of survival rates, thereby improving patient outcomes and optimizing healthcare resources. PROPOSED SYSTEM

4. Operating System: Ubuntu 20.04 LTS or higher, or Windows 10 with WSL 2 . Python : Python 3.11.4, with support for numpy, pandas, matplotlib, scikit-learn, and tensorflow-gpu . Deep Learning Framework: TensorFlow 2.6 or higher, with support for Keras and GPU acceleration. Data Analysis Tools: Jupyter Notebook or Google Colab for data exploration and visualization. Tools : Visual Studio Code. SOFTWARE REQUIREMENTS REQUIREMENTS

5. CPU : A modern multi-core processor with at least 8 cores, such as an Intel i7 or AMD Ryzen 7 . RAM : At least 8 GB of memory, preferably 64 GB or more, to handle large datasets and multi-tasking . GPU : A powerful graphics card with at least 8 GB of memory, preferably 11 GB or more, such as an NVIDIA RTX 3080 or higher, to accelerate deep learning computations . Storage : A fast solid-state drive (SSD) with at least 1 TB of capacity, preferably 2 TB or more, to store datasets and trained models. HARDWARE REQUIREMENTS

6. Data Set Test :  Adeno Carcinoma Large Cell Carcinoma Normal Squamous Cell Carcinoma Train : Adeno Carcinoma Large Cell Carcinoma Normal Squamous Cell Carcinoma Valid :  Adeno Carcinoma Large Cell Carcinoma Normal Squamous Cell Carcinoma

7. Data Set Samples: Test Train V alid Adeno Carcinoma

8. Large Cell Carcinoma Test Train Valid

9. Normal Test Train Valid

10. Squamous Cell Carcinoma Test Train Valid