An enhanced deep learning architecture for classification of Tuberculosis types from CT lung images
Conference paper
Gao, X., Comley, R. and Khan, M. 2020. An enhanced deep learning architecture for classification of Tuberculosis types from CT lung images. ICIP 2020: 27th IEEE International Conference on Image Processing. Abu Dhabi, Unites Arab Emirates (Virtual Conference) 25 - 28 Oct 2020 IEEE. pp. 2486-2490 https://doi.org/10.1109/ICIP40778.2020.9190815
Type | Conference paper |
---|---|
Title | An enhanced deep learning architecture for classification of Tuberculosis types from CT lung images |
Authors | Gao, X., Comley, R. and Khan, M. |
Abstract | In this work, an enhanced ResNet deep learning network, depth-ResNet, has been developed to classify the five types of Tuberculosis (TB) lung CT images. Depth-ResNet takes 3D CT images as a whole and processes the volumatic blocks along depth directions. It builds on the ResNet-50 model to obtain 2D features on each frame and injects depth information at each process block. As a result, the averaged accuracy for classification is 71.60% for depth-ResNet and 68.59% for ResNet. The datasets are collected from the ImageCLEF 2018 competition with 1008 training data in total, where the top reported accuracy was 42.27%. |
Keywords | deep learning; Tuberculosis classification ; CT lung images; 3D image analysis |
Conference | ICIP 2020: 27th IEEE International Conference on Image Processing |
Page range | 2486-2490 |
Proceedings Title | 2020 IEEE International Conference on Image Processing (ICIP) |
ISSN | 1522-4880 |
Electronic | 2381-8549 |
ISBN | |
Electronic | 9781728163956 |
Paperback | 9781728163963 |
Publisher | IEEE |
Publication dates | |
Online | 30 Sep 2020 |
26 Oct 2020 | |
Publication process dates | |
Deposited | 26 May 2020 |
Accepted | 16 May 2020 |
Output status | Published |
Accepted author manuscript | File Access Level Open |
Copyright Statement | © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.” |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ICIP40778.2020.9190815 |
Scopus EID | 2-s2.0-85098672230 |
Web of Science identifier | WOS:000646178502119 |
Web address (URL) of conference proceedings | https://ieeexplore.ieee.org/xpl/conhome/9184803/proceeding |
Related Output | |
Has metadata | http://www.scopus.com/inward/record.url?eid=2-s2.0-85098672230&partnerID=MN8TOARS |
Language | English |
https://repository.mdx.ac.uk/item/88z3q
Download files
71
total views17
total downloads0
views this month1
downloads this month