A Brief Survey on Multi Dimensional Feature Subset Based Lung Tumor Identification Model using Machine Learning Techniques

Identifying malignant lung nodules from Computed Tomography (CT) scans is a complex and time-consuming task for radiologists. To ease this burden, Computer-Aided Diagnostic (CAD) systems have been developed. Over the past few years, approaches to deep learning have demonstrated excellent outcomes, often beating classical methods. Researchers are currently experimenting with a variety of deep learning strategies to boost the efficiency of CAD systems used in CT-based lung cancer detection. Each year, India sees around 75,000 new cases. The disease has a potential to be asymptomatic largely in its initial stages thus making it practically impossible to detect. In addition, the elements such as respiration nodules can generate blurry photos and introduce other noises in the images. Many researchers have recommended alternative strategies based on their studies for lung tumor detection. Several CAD techniques and systems have been proposed, developed, and introduced recently in an effort to leverage computer technology to address this issue. Machine learning and deep learning are used by these systems, and there are also other ways based on image processing that can be used to gauge the cancer's malignancy. In this research, numerous techniques for lung cancer detection is analyzed and the limitations are identified that helps the researchers for designing efficient and accurate models for lung cancer detection