Literature DB >> 29845453

Evolutionary image simplification for lung nodule classification with convolutional neural networks.

Daniel Lückehe1, Gabriele von Voigt2.   

Abstract

PURPOSE: Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions.
METHODS: In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image.
RESULTS: In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development.
CONCLUSIONS: Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.

Keywords:  Convolutional neural networks; Evolutionary algorithm; Image simplification; Understanding deep learning

Mesh:

Year:  2018        PMID: 29845453     DOI: 10.1007/s11548-018-1794-7

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  17 in total

1.  Challenges for data storage in medical imaging research.

Authors:  Steve G Langer
Journal:  J Digit Imaging       Date:  2011-04       Impact factor: 4.056

2.  Automatic detection of large pulmonary solid nodules in thoracic CT images.

Authors:  Arnaud A A Setio; Colin Jacobs; Jaap Gelderblom; Bram van Ginneken
Journal:  Med Phys       Date:  2015-10       Impact factor: 4.071

3.  Are artificial neural networks black boxes?

Authors:  J M Benitez; J L Castro; I Requena
Journal:  IEEE Trans Neural Netw       Date:  1997

4.  A large-scale evaluation of automatic pulmonary nodule detection in chest CT using local image features and k-nearest-neighbour classification.

Authors:  K Murphy; B van Ginneken; A M R Schilham; B J de Hoop; H A Gietema; M Prokop
Journal:  Med Image Anal       Date:  2009-07-30       Impact factor: 8.545

5.  A neural network model for selective attention in visual pattern recognition.

Authors:  K Fukushima
Journal:  Biol Cybern       Date:  1986       Impact factor: 2.086

6.  The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository.

Authors:  Kenneth Clark; Bruce Vendt; Kirk Smith; John Freymann; Justin Kirby; Paul Koppel; Stephen Moore; Stanley Phillips; David Maffitt; Michael Pringle; Lawrence Tarbox; Fred Prior
Journal:  J Digit Imaging       Date:  2013-12       Impact factor: 4.056

7.  The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans.

Authors:  Samuel G Armato; Geoffrey McLennan; Luc Bidaut; Michael F McNitt-Gray; Charles R Meyer; Anthony P Reeves; Binsheng Zhao; Denise R Aberle; Claudia I Henschke; Eric A Hoffman; Ella A Kazerooni; Heber MacMahon; Edwin J R Van Beeke; David Yankelevitz; Alberto M Biancardi; Peyton H Bland; Matthew S Brown; Roger M Engelmann; Gary E Laderach; Daniel Max; Richard C Pais; David P Y Qing; Rachael Y Roberts; Amanda R Smith; Adam Starkey; Poonam Batrah; Philip Caligiuri; Ali Farooqi; Gregory W Gladish; C Matilda Jude; Reginald F Munden; Iva Petkovska; Leslie E Quint; Lawrence H Schwartz; Baskaran Sundaram; Lori E Dodd; Charles Fenimore; David Gur; Nicholas Petrick; John Freymann; Justin Kirby; Brian Hughes; Alessi Vande Casteele; Sangeeta Gupte; Maha Sallamm; Michael D Heath; Michael H Kuhn; Ekta Dharaiya; Richard Burns; David S Fryd; Marcos Salganicoff; Vikram Anand; Uri Shreter; Stephen Vastagh; Barbara Y Croft
Journal:  Med Phys       Date:  2011-02       Impact factor: 4.071

8.  Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images.

Authors:  Colin Jacobs; Eva M van Rikxoort; Thorsten Twellmann; Ernst Th Scholten; Pim A de Jong; Jan-Martin Kuhnigk; Matthijs Oudkerk; Harry J de Koning; Mathias Prokop; Cornelia Schaefer-Prokop; Bram van Ginneken
Journal:  Med Image Anal       Date:  2013-12-17       Impact factor: 8.545

9.  Rising use of diagnostic medical imaging in a large integrated health system.

Authors:  Rebecca Smith-Bindman; Diana L Miglioretti; Eric B Larson
Journal:  Health Aff (Millwood)       Date:  2008 Nov-Dec       Impact factor: 6.301

10.  Using Deep Learning for Classification of Lung Nodules on Computed Tomography Images.

Authors:  QingZeng Song; Lei Zhao; XingKe Luo; XueChen Dou
Journal:  J Healthc Eng       Date:  2017-08-09       Impact factor: 2.682

View more
  3 in total

1.  Lung nodule classification using deep Local-Global networks.

Authors:  Mundher Al-Shabi; Boon Leong Lan; Wai Yee Chan; Kwan-Hoong Ng; Maxine Tan
Journal:  Int J Comput Assist Radiol Surg       Date:  2019-04-24       Impact factor: 2.924

2.  Multi-model Ensemble Learning Architecture Based on 3D CNN for Lung Nodule Malignancy Suspiciousness Classification.

Authors:  Hong Liu; Haichao Cao; Enmin Song; Guangzhi Ma; Xiangyang Xu; Renchao Jin; Chuhua Liu; Chih-Cheng Hung
Journal:  J Digit Imaging       Date:  2020-10       Impact factor: 4.056

3.  Classification of lung nodules based on CT images using squeeze-and-excitation network and aggregated residual transformations.

Authors:  Guobin Zhang; Zhiyong Yang; Li Gong; Shan Jiang; Lu Wang; Hongyun Zhang
Journal:  Radiol Med       Date:  2020-01-08       Impact factor: 3.469

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.