LCDctCNN: Lung Cancer Diagnosis of CT scan Images Using CNN Based Model

Aim: 

To create a robust and accurate diagnostic tool employing Convolutional Neural Networks (CNNs) for the analysis of CT scan images, aiming to enhance the efficiency, precision, and early detection of lung cancer, ultimately contributing to improved patient outcomes and healthcare practices

Abstract:

The most deadly and life-threatening disease in the world is lung cancer. Though early diagnosis and accurate treatment are necessary for lowering the lung cancer mortality rate. A computerized tomography (CT) scan-based image is one of the most effective imaging techniques for lung cancer detection using deep learning models. In this article, we proposed a deep learning model- based Convolutional Neural Network (CNN) framework for the early detection of lung cancer using CT scan images. We also have analyzed other models for instance Inception V3, Xception, and ResNet-50 models to compare with our proposed model. We compared our models with each other considering the metrics of accuracy, Area Under Curve (AUC), recall, and loss. After evaluating the model’s performance, we observed that CNN outperformed other models and has been shown to be promising compared to traditional methods. 

Introduction:

            Lung cancer is one of the most deadly and devastating types of cancer in the world. It is challenging to detect cancer, and its symptoms only become noticeable in the final stages. Although this cancer’s death rate could be decreased by early detection and appropriate treatment for patients. Lung cancer often starts in the lungs; however, it occasionally appears as early symptoms prior to spread . In recent years, numerous techniques have been developed, and research is ongoing to effectively identify lung cancer. The greatest imaging method for early diagnosis of lung cancer will be CT scan images, although it can be challenging for medical professionals to interpret and detect cancer from CT scan images. The death rate of lung cancer is higher than any other cancer, which is around 0.13 million all over the world. Every year, there are a lot of new cases, with an estimated 0.237 million cases in 2022. The mortality rate is significant in the absence of appropriate treatment because this cancer is only discovered in its advanced stages and the ratio of new cases and the death rate is higher than any other cancer. Nowadays, the deep learning model is widely used for detecting, analyzing, and classifying critical medical healthcare treatment. Convolutional Neural Network (CNN) based deep learning model can be the best for early detection, observing, and classifying lung cancer using CT scan images.

Proposed System:

Lung cancer is one of the most deadly and devastating types of cancer in the world. The death rate for lung cancer is high. It indicates that it is one of the most prevalent and leading cancers worldwide. Although it cannot be prevented, a quick diagnosis can help the patient live longer than expected. We proposed CNN based deep learning model for the early detection of lung cancer using CT scan images. we detect early-stage in cancer, it might be possible to cure cancer. Compare to existing system our new CNN based deep learning model system gives results are more Accuracy and low lose rate.

Algorithm: CNN –Convolutional Neural Network

            Convolutional neural networks are distinguished from other neural networks by their superior performance with image, speech, or audio signal inputs. They have three main types of layers, which are:

• Convolutional layer
• Pooling layer
• Fully-connected (FC) layer

The Convolutional layer is the first layer of a Convolutional network. While Convolutional layers can be followed by additional Convolutional layers or pooling layers, the fully-connected layer is the final layer. With each layer, the CNN increases in its complexity, identifying greater portions of the image. Earlier layers focus on simple features, such as colors and edges. As the image data progresses through the layers of the CNN, it starts to recognize larger elements or shapes of the object until it finally identifies the intended object.

The Keras algorithm is used to train the dataset and predict the outputs in terms such as precision, recall, accuracy, and support. Keras, which is a high-level neural network. It allows multiple inputs or outputs for models that have layers .In the below figure, we are sorting the dataset based on the basics of the number of images in each class and then plotting the number of images in each class.

Advantages:

Convolutional Neural Networks (CNNs) are powerful in extracting features from complex image data, leading to improved accuracy in distinguishing between cancerous and non-cancerous patterns in CT scans.

Automated analysis through CNNs helps reduce the potential for human error, providing a consistent and objective approach to lung cancer diagnosis. It provide a quantitative assessment of CT scan images, offering a more standardized and reproducible approach to lung cancer diagnosis compared to subjective human interpretations.

CNNs can be designed to continuously learn and adapt to new data, allowing the model to improve over time as more information becomes available.By automating certain aspects of the diagnostic process, CNNs can help optimize the allocation of human resources, allowing healthcare professionals to focus on more complex tasks that require their expertise.