Soft Computing Techniques Based Computer Aided System for Efficient Lung Nodule Detection – A Survey
S.Ashwin1, S. Aravind Kumar2, S. Arun Kumar3
1Ashwin S, Embedded and Real, Time Systems, PSG College of Technology, Coimbatore, India.
2Aravind Kumar S, Graphics Hardware Engineer, Intel Technologies India.
3Arun Kumar S, Assistant Professor, Department of Electronics and Communication Engineering, and Technology, Coimbatore, India.
Manuscript received on November 25, 2012. | Revised Manuscript received on December 07, 2012. | Manuscript published on December 30, 2012. | PP: 121-127 | Volume-2, Issue-2, December 2012.  | Retrieval Number: B0869112212 /2012©BEIESP

Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Early detection and treatment of lung cancer can significantly advance the survival rate of patient. However, this is a challenging problem due to structure of cancer cells. Lung cancer detection, classification, scoring and grading of histopathological images is the standard clinical practice for the diagnosis and prognosis of lung cancer. It is a very complex and time-consuming duty for a pathologist to manually perform these tasks. Robust and efficient computer aided systems are therefore in dispensible for automatic lung cancer detection. The delineation of anatomical structures and other regions of interest is a key component in CAD systems. This is achieved through soft computing techniques which automatically and accurately highlight potential actionable lung nodules and rapidly compute measurements of detected regions. Soft computing systems like neural networks and fuzzy systems are valuable in lung cancer screening to improve sensitivity of pulmonary nodule detection beyond double reading, at a low false-positive rate when excluding small nodules. Several pilot studies have shown that these CAD modules can successfully locate overlooked pulmonary nodules and serve as a powerful tool for diagnostic quality assurance. This paper reviews the literature pertaining to the different types of novel neural network and fuzzy based automated CAD systems for robust lung nodule detection. Furthermore, prevailing research trends and challenges are acknowledged and guidelines for future research are discussed.
Keywords: Computer Aided Detection (CAD), fuzzy, Lung Nodule, neural network, sensitivity.