Blood Cell Data Augmentation using Deep Learning Methods
(2020) In Master's Theses in Mathematical Sciences FMAM05 20192Mathematics (Faculty of Engineering)
- Abstract
- In this thesis we aim to improve classification performance on blood cell imagesby using deep learning techniques to augment data. The thesis was conductedat CellaVision, a company providing digital solutions for medical microscopy inthe field of hematology. The goal of CellaVision’s technology is to replace man-ual microscopes used for cell differentials in blood tests with digital microscopesthat perform cell differentials automatically. Classyfying white blood cells is animportant part of this technology and is achieved by using an artificial neuralnetwork. This classifier network requires a great amount of training data inorder to perform well.With the objective to improve the performance of the classifier, we augmenttraining data... (More)
- In this thesis we aim to improve classification performance on blood cell imagesby using deep learning techniques to augment data. The thesis was conductedat CellaVision, a company providing digital solutions for medical microscopy inthe field of hematology. The goal of CellaVision’s technology is to replace man-ual microscopes used for cell differentials in blood tests with digital microscopesthat perform cell differentials automatically. Classyfying white blood cells is animportant part of this technology and is achieved by using an artificial neuralnetwork. This classifier network requires a great amount of training data inorder to perform well.With the objective to improve the performance of the classifier, we augmenttraining data consisting of blood cell images by generating synthetic data usinga Generative Adversarial Network (GAN). Our goal is to generate images withclose to equal quality of the real images and to use the generated images forclassifier improvement. The results show that the GAN is able to generate im-ages that, apart from some small artefacts, very much resemble the real images,so much that a medical technologist struggled to differentiate them from realimages.In order to generate class specific blood cell images, we implement a versionof the Auxiliary Classifier GAN (AC-GAN), where we use a pre-trained gener-ator and discriminator from a GAN able to produce high quality images. Thegenerator and discriminator are freezed and connected to fully connected lay-ers to be trained. By augmenting the training data with the generated imagesfrom this AC-GAN, classifier performance improved for the majority of classesresulting in an increased F1-score. This leads us to believe that augmentingblood cell image data by using synthetic images is a viable method for classifierperformance improvement. (Less)
- Popular Abstract (Swedish)
- De bästa bildklassificeringsmodellerna, så kallade deep learning-modeller, är bra men i stort behov av data för att prestera. För att förbättra sådana modellers prestation kan man utöka redan existerande dataset som används för träning av dessa modeller. Vi har använt oss av en modell som kallas GAN för att producera konstgjord träningsdata och visat att det kan förbättra en blodcellsklassificerare.
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9007154
- author
- Klang, Oskar LU and Carlberg, Martin
- supervisor
- organization
- alternative title
- Utökning av blodcellsdata med hjälp av deep learning
- course
- FMAM05 20192
- year
- 2020
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- Image analysis, deep learning, data augmentation, generative adversarial networks, GAN
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3401-2020
- ISSN
- 1404-6342
- other publication id
- 2020:E15
- language
- English
- id
- 9007154
- date added to LUP
- 2020-04-27 14:16:10
- date last changed
- 2020-04-27 14:16:10
@misc{9007154, abstract = {{In this thesis we aim to improve classification performance on blood cell imagesby using deep learning techniques to augment data. The thesis was conductedat CellaVision, a company providing digital solutions for medical microscopy inthe field of hematology. The goal of CellaVision’s technology is to replace man-ual microscopes used for cell differentials in blood tests with digital microscopesthat perform cell differentials automatically. Classyfying white blood cells is animportant part of this technology and is achieved by using an artificial neuralnetwork. This classifier network requires a great amount of training data inorder to perform well.With the objective to improve the performance of the classifier, we augmenttraining data consisting of blood cell images by generating synthetic data usinga Generative Adversarial Network (GAN). Our goal is to generate images withclose to equal quality of the real images and to use the generated images forclassifier improvement. The results show that the GAN is able to generate im-ages that, apart from some small artefacts, very much resemble the real images,so much that a medical technologist struggled to differentiate them from realimages.In order to generate class specific blood cell images, we implement a versionof the Auxiliary Classifier GAN (AC-GAN), where we use a pre-trained gener-ator and discriminator from a GAN able to produce high quality images. Thegenerator and discriminator are freezed and connected to fully connected lay-ers to be trained. By augmenting the training data with the generated imagesfrom this AC-GAN, classifier performance improved for the majority of classesresulting in an increased F1-score. This leads us to believe that augmentingblood cell image data by using synthetic images is a viable method for classifierperformance improvement.}}, author = {{Klang, Oskar and Carlberg, Martin}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master's Theses in Mathematical Sciences}}, title = {{Blood Cell Data Augmentation using Deep Learning Methods}}, year = {{2020}}, }