Performance analysis of texture characterization techniques for lung nodule classification

Ishan Devdatt Kawathekar, Anu Shaju Areeckal

Research output: Contribution to journalConference articlepeer-review

2 Citations (Scopus)

Abstract

Lung cancer ranks very high on a global index for cancer-related casualties. With early detection of lung cancer, the rate of survival increases to 80-90%. The standard method for diagnosing lung cancer from Computed Tomography (CT) scans is by manual annotation and detection of the cancerous regions, which is a tedious task for radiologists. This paper proposes a machine learning approach for multi-class classification of the lung nodules into solid, semisolid, and Ground Glass Object texture classes. We employ feature extraction techniques, such as gray-level co-occurrence matrix, Gabor filters, and local binary pattern, and validate the performance on the LNDb dataset. The best performing classifier displays an accuracy of 94% and an F1-score of 0.92. The proposed approach was compared with related work using the same dataset. The results are promising, and the proposed method can be used to diagnose lung cancer accurately.

Original languageEnglish
Article number012045
JournalJournal of Physics: Conference Series
Volume2161
Issue number1
DOIs
Publication statusPublished - 11-01-2022
Event1st International Conference on Artificial Intelligence, Computational Electronics and Communication System, AICECS 2021 - Manipal, Virtual, India
Duration: 28-10-202130-10-2021

All Science Journal Classification (ASJC) codes

  • Physics and Astronomy(all)

Fingerprint

Dive into the research topics of 'Performance analysis of texture characterization techniques for lung nodule classification'. Together they form a unique fingerprint.

Cite this