Improved Lung Cancer Detection through Use of Large Language Systems with Graphical Attributes
Gopi Vardhan Vallabhaneni, Yelisetty Shanmukh Rahul, K. Shantha Kumari · 2024
Lung cancer remains a dangerous global health challenge, which desires for innovation for early detection and personalized treatment. This research paper introduces an integration of deep learning framework that uses the power of large language models (LLMs) on medical and image data for increasing the accuracy in lung cancer detection. Our proposed system focuses on integrating patient-report symptoms, medical images, and prescription from the doctor to create a comprehensive dataset. Increasing the state-of-the-art deep learning techniques, which consists of convolutional neural networks (CNNs) for analysis on images and LLM’s for understanding the text from the Textual data. Our model is interdependent which understand from diverse data modalities. The deep learning model is trained on a dataset which consists of various range of lung cancer cases. The textual information from doctors’ prescriptions provides a valuable contextual understanding, which enhances the model’s ability to interpret medical information. Through evaluation on a diverse set of patient data, our model demonstrates better performance in detecting lung cancer. The model is not only used for classification, but it is used to obtain textual information from the image which helps in more diagnostic prediction. The comprehensive approach helps in early detection, improve the patient outcome, and check on various treatments approaching conclusion, our research introduces a novel which integrates the deep learning techniques with the strength of LLM and medical images for advanced image detection. This approach marks a significant step towards the pursuit of precision medicine and utilizing the potential of AI-driven solutions for the lung cancer diagnosis.