Hittauppsatser.se

Uppsats

Correlating microscopy and ToF-SIMS images to cellulose size using deep learning

H

FERNANDEZ, BRUNO

Chalmers tekniska högskola / Institutionen för data och informationsteknik

Publicerad: 2022

Språk: Engelska

Nyckelord

klicka för att söka
⌕Deep Learning⌕Transfer Learning⌕explainability⌕Convolutional neural network⌕imaging⌕tof-sims⌕ethyl cellulose⌕hydroxypropyl-cellulose⌕hydroxypropylmethyl-cellulose⌕time of flight secondary ion mass-spectroscopy

Sammanfattning

In pharmaceutical formulations, chemically modified celluloses are used in severalapplications and it is often critical to have good quality control for these materials.In this thesis, spot testing after chromatographic separation has been evaluated asa method for material structure analysis. A highly non-linear correlation betweenmaterial quality and spot appearance was expected and therefore supervised deeplearning was used to model this relationship.Optical microscopy images were subjected to a pretrained resnet-18 image modelto identify differences in chemical properties between spots. After suitable preprocessing,models could successfully be built to tell the difference between spotsfrom early and late mass fractions.The cellulose fractions were also analyzed as parts of spots by ToF-SIMS. A 3D CNNmodel was trained from scratch. The model could successfully distinguish betweenfractions in this case as well.

Information

Författare
FERNANDEZ, BRUNO
Lärosäte / institution
Chalmers tekniska högskola / Institutionen för data och informationsteknik
Publiceringsdatum
2022
Uppsatstyp
H
Språk
Engelska
Nyckelord
⌕Deep Learning⌕Transfer Learning⌕explainability⌕Convolutional neural network⌕imaging⌕tof-sims⌕ethyl cellulose⌕hydroxypropyl-cellulose⌕hydroxypropylmethyl-cellulose⌕time of flight secondary ion mass-spectroscopy

Utforska vidare

Liknande uppsatser

Uppsatser med liknande ämnen och nyckelord.