Options
Deep learning methods for automated segmentation of medical ultrasound images
Citation Link: https://doi.org/10.15480/882.9021
Publikationstyp
Doctoral Thesis
Date Issued
2024
Sprache
English
Author(s)
Holstein, Lennart
Advisor
Referee
Title Granting Institution
Technische Universität Hamburg
Place of Title Granting Institution
Hamburg
Examination Date
2023-12-18
TORE-DOI
Citation
Technische Universität Hamburg (2024)
For deep learning-based image segmentation, large training datasets are required to achieve satisfactory results. However, assembling large annotated datasets in the medical field is difficult and sometimes even impossible. Therefore, we have developed and investigated new deep learning methods that aim to improve segmentation performance with smaller ultrasound datasets. These methods include wavelet scattering, tissue shape priors with independent component analysis, topological loss functions, and synthetic data augmentation with a new generative adversarial network. The results show that the various methods offer different advantages depending on tissue type, dataset size, and CNN architecture.
Subjects
deep learning
ultrasound
segmentation
IVUS
GAN
neural network
DDC Class
004: Computer Sciences
Loading...
Name
Holstein_Lennart_Deep-Learning-Methods-for-Automated-Segmentation-of-Medical-Ultrasound-Images.pdf
Size
23.58 MB
Format
Adobe PDF