3D fully convolutional network-based segmentation of lung nodules in CT images with a clinically inspired data synthesis method

Atsushi Yaguchi, Kota Aoyagi, Akiyuki Tanizawa, Yoshiharu Ohno

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In the management of lung nodules, it is important to precisely assess nodule size on computed tomography (CT) images. Given that the malignancy of nodules varies according to their composition, component-wise assessment is useful for diagnosing lung cancer. To improve the accuracy of volumetric measurement of lung nodules, we propose a deep learning-based method for segmenting nodules into multiple components, namely, solid, ground glass opacity (GGO), and cavity. We train a 3D fully convolutional network (FCN) with component-wise dice loss and apply a conditional random field (CRF) to refine the segmentation boundaries. To further gain the accuracy, we artificially generate synthetic cavitary nodules based on clinical observations and then augment the dataset for training the network. In experiments using about 300 CT images of clinical nodules, we evaluated our method in terms of mean absolute percentage error of volumetric measurement. We confirmed that our method achieved 15.84% lower error (averaged over 2 components of solid and GGO) compared with a conventional method based on image processing, and the error for cavity was decreased by 2.87% with our data-synthesis method.

Original languageEnglish
Title of host publicationMedical Imaging 2019
Subtitle of host publicationComputer-Aided Diagnosis
EditorsKensaku Mori, Horst K. Hahn
PublisherSPIE
ISBN (Electronic)9781510625471
DOIs
Publication statusPublished - 2019
EventMedical Imaging 2019: Computer-Aided Diagnosis - San Diego, United States
Duration: 17-02-201920-02-2019

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10950
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2019: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego
Period17-02-1920-02-19

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of '3D fully convolutional network-based segmentation of lung nodules in CT images with a clinically inspired data synthesis method'. Together they form a unique fingerprint.

  • Cite this

    Yaguchi, A., Aoyagi, K., Tanizawa, A., & Ohno, Y. (2019). 3D fully convolutional network-based segmentation of lung nodules in CT images with a clinically inspired data synthesis method. In K. Mori, & H. K. Hahn (Eds.), Medical Imaging 2019: Computer-Aided Diagnosis [109503G] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10950). SPIE. https://doi.org/10.1117/12.2511438