Search: onr:"swepub:oai:DiVA.org:umu-176322" >
When Texture Matters :
When Texture Matters : Texture-Focused Cnns Outperform General Data Augmentation and Pretraining in Oral Cancer Detection
-
- Wetzer, Elisabeth (author)
- Uppsala universitet,Avdelningen för visuell information och interaktion,Bildanalys och människa-datorinteraktion,Centre for image analysis
-
- Gay, Jo (author)
- Uppsala universitet,Institutionen för informationsteknologi,Centre for image analysis
-
- Harlin, Hugo (author)
- Umeå universitet,Institutionen för ekologi, miljö och geovetenskap,Umeå Univ, Dept Ecol & Environm Sci, Umeå, Sweden
-
show more...
-
- Lindblad, Joakim (author)
- Uppsala universitet,Avdelningen för visuell information och interaktion,Bildanalys och människa-datorinteraktion,Centre for image analysis
-
- Sladoje, Natasa (author)
- Uppsala universitet,Avdelningen för visuell information och interaktion,Bildanalys och människa-datorinteraktion,Centre for image analysis
-
show less...
-
(creator_code:org_t)
- IEEE, 2020
- 2020
- English.
-
In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI 2020). - : IEEE. - 9781538693308 - 9781538693315 ; , s. 517-521
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- Early detection is essential to reduce cancer mortality. Oral cancer could be subject to screening programs (similar as for cervical cancer) by collecting Pap smear samples at any dentist visit. However, manual analysis of the resulting massive amount of data is prohibitively costly. Convolutional neural networks (CNNs) have shown promising results in discriminating between cancerous and non-cancerous cells, which enables efficient automated processing of cancer screening data. We investigate different CNN architectures which explicitly aim to utilize texture information, for cytological cancer classification, motivated by studies showing that chromatin texture is among the most important discriminative features for that purpose. Results show that CNN classifiers inspired by Local Binary Patterns (LBPs) achieve better performance than general purpose CNNs. This holds also when different levels of general data augmentation, as well as pre-training, are considered.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Medicinteknik -- Medicinsk bildbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Medical Engineering -- Medical Image Processing (hsv//eng)
Keyword
- Texture Analysis
- Cancer Detection
- CNN
- Brightfield Microscopy
- Local Binary Patterns
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database