Computer-aided classification of lung nodules on computed tomography images via deep learning technique

Kai Lung Hua, Che Hao Hsu, Shintami Chusnul Hidayati, Wen-Huang Cheng, Yu Jen Chen*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

258 Scopus citations

Abstract

Lung cancer has a poor prognosis when not diagnosed early and unresectable lesions are present. The management of small lung nodules noted on computed tomography scan is controversial due to uncertain tumor characteristics. A conventional computer-aided diagnosis (CAD) scheme requires several image processing and pattern recognition steps to accomplish a quantitative tumor differentiation result. In such an ad hoc image analysis pipeline, every step depends heavily on the performance of the previous step. Accordingly, tuning of classification performance in a conventional CAD scheme is very complicated and arduous. Deep learning techniques, on the other hand, have the intrinsic advantage of an automatic exploitation feature and tuning of performance in a seamless fashion. In this study, we attempted to simplify the image analysis pipeline of conventional CAD with deep learning techniques. Specifically, we introduced models of a deep belief network and a convolutional neural network in the context of nodule classification in computed tomography images. Two baseline methods with feature computing steps were implemented for comparison. The experimental results suggest that deep learning methods could achieve better discriminative results and hold promise in the CAD application domain.

Original languageEnglish
Pages (from-to)2015-2022
Number of pages8
JournalOncoTargets and Therapy
Volume8
DOIs
StatePublished - 4 Aug 2015

Keywords

  • Convolutional neural network
  • Deep belief network
  • Deep learning
  • Nodule classification

Fingerprint Dive into the research topics of 'Computer-aided classification of lung nodules on computed tomography images via deep learning technique'. Together they form a unique fingerprint.

Cite this