Study
PLCO
(Learn more about this study)
Project ID
PLCOI-1365
Initial CDAS Request Approval
Oct 31, 2023
Title
Integrating CNN and RNN for Precise Lung Cancer Detection from Patient Data and Medical Imaging
Summary
The technology for extracting actionable information from data for decision-making are provided by data mining. Finding valuable information within the massive database is a key component of data mining. One of the most fascinating and difficult challenges of data mining is forecasting the course of a disease. As the amount of data grows dramatically, certain strategies are required to assist extract important information. The development of neural networks has shown to be important for medical diagnosis. Cancer is the most deadly and devasting disease that is one of main cause of mortality in human world. Globally, lung cancer is one of the main causes of cancer-related mortality. Improving patient outcomes depends on early and precise detection can lead to more success rate. This proposal uses neural network algorithms to present a novel method of lung cancer detection. Our system combines deep learning methods to analyse patient data and medical imagery, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs). Our goal is to improve the early detection of malignancies and the accuracy of lung cancer diagnosis by using a large dataset of lung pictures and clinical data to train neural network models. In addition to helping radiologists make better decisions, the proposed research has the potential to provide accessible and affordable screening. With the potential to have a major influence on patient care and results, this initiative is a key advancement in the fields of medical imaging and oncology.
Aims
1. To design and execute a resilient neural network-based model that can effectively detect malignancies in the early stages of cancer.
2. Employ clinical data to enhance the precision and effectiveness of cancer diagnosis, thereby facilitating the timely identification of critical illnesses.
3. Examine the relationship between early disease diagnosis and mortality rates to illustrate the substantial reduction in mortality achieved by integrating clinical data and neural networks in high-risk patient populations.
4. Determine whether the developed neural network model is scalable and generalizable, facilitating its prospective implementation in various clinical contexts such as oncology and medical imaging.
Collaborators
Dr. Sapna Arora, IILM University, Gurugram, Haryana, India.
