Healthcare Data Classification for Lung Cancer Detection Using Efficient Net with Cloud Storage

Abstract

Lung carcinoma is one of the deadliest cancers globally, and early diagnosis is crucial for improving patient survival rates. This study introduces an innovative approach to detect lung cancer using a combination of Efficient Net and cloud storage, which ensures scalable and efficient processing of medical images. By leveraging deep learning and cloud computing, the system automatically analyzes CT scans and X-rays to identify potential signs of lung cancer. Efficient Net, a lightweight deep learning model, optimizes computational resources while maintaining high accuracy in image classification, thereby reducing costs. The cloud infrastructure facilitates real-time data access, allowing healthcare providers to quickly retrieve and analyze patient images from anywhere. Additionally, the cloud supports continuous model updates, ensuring that the detection system improves over time. The model's performance has been evaluated across multiple metrics, demonstrating its effectiveness as a reliable tool for early lung cancer detection, which can be integrated into clinical practices for enhanced patient outcomes.