The Role of Deep Learning in Automated Lung Cancer Detection using Nodule Segmentation and Classification

DOI: https://doie.org/10.1220/Jbse.2024277500

Manoj M. Mhaske, Ramesh R. Manza, Pallavi K. Pradhan

Keywords:

Deep Learning, Lung Cancer Detection, Nodule Segmentation, Classification, Automated Detection, Computer-Aided Diagnosis, Medical Imaging, Cancer Diagnosis, Artificial Intelligence, Machine Learning.

Abstract:

Lung cancer remains one of the leading causes of cancer-related deaths globally, emphasizing the need for effective and early detection methods. Deep learning, a subset of artificial intelligence (AI), has emerged as a powerful tool in medical image analysis, particularly in the automated detection of lung cancer. This paper explores the role of deep learning in lung cancer detection, with a focus on two critical tasks: nodule segmentation and classification. Nodule segmentation involves identifying and delineating the precise location of lung nodules from medical images, while classification assigns a malignancy grade to the detected nodules. This paper discusses the evolution of deep learning techniques, key architectures, datasets used for training, performance evaluation metrics, challenges, and future directions in this rapidly advancing field.

PDF