Watershed Segmentation with CAFIS and RCNN Classification for Pulmonary Nodule Detection

Abstract

The premier cause for high cancer deaths in the world is the lung cancer. It is important for the radiologists to predict lung cancer at an early stage. Various research works on such nodule segmentation clearly manifest that they are ineffective. These investigations brought to the development of watershed segmentation-based topological interpretation (WSBTI) and an advanced optimized segmentation method of nodule detection. The supreme goal of this research work is to effectively recognize small anomalous nodule in the lung region. The noise discrimination can be eradicated by the primary step adaptive median filter with discrete-time complex wavelet transform enhancement technique. In the consequent step, WSBTI algorithm is effectively implemented for the prediction on abnormal node of lung. Ultimately, the procurement of nodule can be done by using coactive adaptive neuro fuzzy interference system classifier (CAFIS) and recurrent convolutional neural network classifier (RCNN). The average time of segmentation is 1.05 s. The high accuracy classification is 97% by using CAFIS method and 97.6% by RCNN method.

KEYWORDS:

• Coactive adaptive neuro-fuzzy interference system classifier (CAFIS)
• Lung cancer
• Recurrent convolutional neural network classifier (RCNN)
• Watershed segmentation-based topological interpretation (WSBTI) algorithm

Acknowledgements

First, the author thanks the management of Udaya School of Engineering and Noorul Islam Centre for Higher Education, for their continuous support and encouragement throughout the work. Then the authors thank the National Cancer Institute and then acknowledge for free public available online LIDC-IDRI database and in-house clinical database used in this study. Finally, the authors wish to thank the anonymous reviewers for helping to strengthen this paper.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The author(s) reported there is no funding associated with the work featured in this article.

Notes on contributors

S. Albert Jerome

S Albert Jerome received his BE degree first class in electrical and electronics engineering from Bharathidhasan University, Trichy, Tamil Nadu in 2001 and MTech degree first class with distinction in biomedical signal processing and instrumentation from Shanmuga Arts, Science, Technology & Research Academy (Sastra University), Tanjavur, Tamil Nadu, India, in 2002. He completed his PhD degree on the topic “Automatic Segmentation of Intervertebral Discs of Cervical Spine Magnetic Resonance Images” in the Department of Electrical and Electronics Engineering at Noourl Islam Centre for Higher Education, Kumaracoil, Tamil Nadu, India, in 2016. He is currently working as associate professor in the Department of Biomedical Engineering, Noourl Islam Centre for Higher Education, Kumaracoil, Tamilnadu, India. He has 19 years of teaching experience. He has published 11 papers in national and international conferences and 7 papers in international journals. His research interest includes biomedical signal processing and medical image processing and analysis. Email: [email protected]

K. Vijila Rani

K Vijila Rani received her bachelor's degree in electronics and communication engineering from Anna University Chennai, master's degree in communication system from Anna University, Chennai. She completed her PhD degree in Arunachala College of Engineering for Women, Vellichanthai at Anna University Chennai, India. She is working as assistant professor in the Department of Electronics and Communication Engineering, Udaya School of Engineering, Vellichanthai. She completed four diploma software courses such as DCA,.NET, DJP, DWD, in Computer Software College (CSC) at, Kanyakumari District. She published 8 SCI/SCIE Papers, 2 Indian Patents and nearly 12 papers in both international and national journals. She is a member of academia. Her research interests include medical image processing, nanotechnology, image segmentation methodology and tumour detection scheme.

K. S. Mithra

K S Mithra MCA, MPhil, PhD, received her MPhil (Computer Science) degree in 2010 and MCA degree in 2009 from Manonmaniam Sundaranar University, Tirunelveli. She completed her PhD degree in 2020 from Manonmaniam Sundaranar University, Tirunelveli. Now she is working as assistant professor in computer science, in St Alphonsa College of Arts and Science, Karungal. Her interested research areas are steganography, medical imaging and image segmentation. She has published more than 10 articles. She attended four international conferences and reviewed more than five SCI-indexed journal articles. She has published book chapters in the field of medical image analysis. Email: [email protected]

M. Eugine Prince

M Eugine Prince MSc, MPhil, PhD, received his BSc degree in physics in the year 1992, MSc degree in physics in the year 1994, BEd degree in the year 1995, MPhil degree in physics in the year 2007 and PhD in physics in the year 2013. His research focuses on the areas of crystal growth and electronics. He has published five papers in refereed journals. He has 12 years of teaching experience as P G assistant (Physics) and 3 years of teaching experience as assistant professor. Currently, he is working as assistant professor in the Physics Department of S T Hindu College, Nagercoil, Tamil Nadu, India Email: [email protected]