WFRF:(Runow Stark Christina)
Sökning: WFRF:(Runow Stark Christina) > Visualization of co...
- Koriakina, Nadezhda,1991-Uppsala universitet,Avdelningen för visuell information och interaktion,Bildanalys och människa-datorinteraktion,MIDA (författare)
Visualization of convolutional neural network class activations in automated oral cancer detection for interpretation of malignancy associated changes
- Artikel/kapitelEngelska2019
Förlag, utgivningsår, omfång ...
- 2019
- printrdacarrier
Nummerbeteckningar
- LIBRIS-ID:oai:DiVA.org:uu-398145
- https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-398145URI
Kompletterande språkuppgifter
- Språk:engelska
- Sammanfattning på:engelska
Ingår i deldatabas
- SwePubSwePub
Klassifikation
Anmärkningar
- Introduction: Cancer of the oral cavity is one of the most common malignancies in the world. The incidence of oral cavity and oropharyngeal cancer is increasing among young people. It is noteworthy that the oral cavity can be relatively easily accessed for routine screening tests that could potentially decrease the incidence of oral cancer. Automated deep learning computer aided methods show promising ability for detection of subtle precancerous changes at a very early stage, also when visual examination is less effective. Although the biological nature of these malignancy associated changes is not fully understood, the consistency of morphology and textural changes within a cell dataset could shed light on the premalignant state. In this study, we are aiming to increase understanding of this phenomenon by exploring and visualizing what parts of cell images are considered as most important when trained deep convolutional neural networks (DCNNs) are used to differentiate cytological images into normal and abnormal classes.Materials and methods: Cell samples are collected with a brush at areas of interest in the oral cavity and stained according to standard PAP procedures. Digital images from the slides are acquired with a 0.32 micron pixel size in greyscale format (570 nm bandpass filter). Cell nuclei are manually selected in the images and a small region is cropped around each nucleus resulting in images of 80x80 pixels. Medical knowledge is not used for choosing the cells but they are just randomly selected from the glass; for the learning process we are only providing ground truth on the patient level and not on the cell level. Overall, 10274 images of cell nuclei and the surrounding region are used to train state-of-the-art DCNNs to distinguish between cells from healthy persons and persons with precancerous lesions. Data augmentation through 90 degrees rotations and mirroring is applied to the datasets. Different approaches for class activation mapping and related methods are utilized to determine what image regions and feature maps are responsible for the relevant class differentiation.Results and Discussion:The best performing of the observed deep learning architectures reaches a per cell classification accuracy surpassing 80% on the observed material. Visualizing the class activation maps confirms our expectation that the network is able to learn to focus on specific relevant parts of the sample regions. We compare and evaluate our findings related to detected discriminative regions with the subjective judgements of a trained cytotechnologist. We believe that this effort on improving understanding of decision criteria used by machine and human leads to increased understanding of malignancy associated changes and also improves robustness and reliability of the automated malignancy detection procedure.
Ämnesord och genrebeteckningar
- NATURVETENSKAP Data- och informationsvetenskap Annan data- och informationsvetenskap hsv//swe
- NATURAL SCIENCES Computer and Information Sciences Other Computer and Information Science hsv//eng
- TEKNIK OCH TEKNOLOGIER Medicinteknik Medicinsk bildbehandling hsv//swe
- ENGINEERING AND TECHNOLOGY Medical Engineering Medical Image Processing hsv//eng
- Oral cancer
- saliency methods
- deep convolutional neural networks
- Computerized Image Processing
- Datoriserad bildbehandling
Biuppslag (personer, institutioner, konferenser, titlar ...)
- Sladoje, NatasaUppsala universitet,Avdelningen för visuell information och interaktion,Bildanalys och människa-datorinteraktion(Swepub:uu)namat934 (författare)
- Bengtsson, Ewert,1948-Uppsala universitet,Avdelningen för visuell information och interaktion,Bildanalys och människa-datorinteraktion,Reglerteknik(Swepub:uu)ewertbs (författare)
- Ramqvist, Eva DaraiPathology and Cytology, Karolinska Institute, Stockholm, Sweden (författare)
- Hirsch, Jan M.Uppsala universitet,Käkkirurgi(Swepub:uu)jahir257 (författare)
- Runow Stark, ChristinaPublic Dental Service, Södersjukhuset, Stockholm, Sweden (författare)
- Lindblad, JoakimUppsala universitet,Bildanalys och människa-datorinteraktion,Avdelningen för visuell information och interaktion(Swepub:uu)joali534 (författare)
- Uppsala universitetAvdelningen för visuell information och interaktion (creator_code:org_t)
Sammanhörande titlar
- Ingår i:3rd NEUBIAS Conference, Luxembourg, 2-8 February 2019
Internetlänk
Till lärosätets databas
Hitta mer i SwePub
- Av författaren/redakt...
- Koriakina, Nadez ...
- Sladoje, Natasa
- Bengtsson, Ewert ...
- Ramqvist, Eva Da ...
- Hirsch, Jan M.
- Runow Stark, Chr ...
- visa fler...
- Lindblad, Joakim
- visa färre...
- Om ämnet
-
- NATURVETENSKAP
- NATURVETENSKAP
- och Data och informa ...
- och Annan data och i ...
-
- TEKNIK OCH TEKNOLOGIER
- TEKNIK OCH TEKNO ...
- och Medicinteknik
- och Medicinsk bildbe ...
- Artiklar i publikationen
- 3rd NEUBIAS Conf ...
- Av lärosätet
- Uppsala universitet
Sök utanför SwePub
- Sök vidare i:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - Nationella bibliotekssystem
- LIBRIS.kb.se
