Ensembling and transfer learning for multi-domain microscopy image segmentation

Misko, Oleh

Домівка
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Освітня програма наук про дані
→
2020
→
Перегляд матеріалів

dc.contributor.author	Misko, Oleh
dc.date.accessioned	2020-02-21T14:31:16Z
dc.date.available	2020-02-21T14:31:16Z
dc.date.issued	2020
dc.identifier.citation	Misko, Oleh. Ensembling and transfer learning for multi-domain microscopy image segmentation : Master Thesis : manuscript rights / Oleh Misko ; Supervisor Dmytro Fishman ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2020. – 52 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/2037
dc.language.iso	en	uk
dc.subject	Ensembling learning	uk
dc.subject	transfer learning	uk
dc.subject	Master model	uk
dc.title	Ensembling and transfer learning for multi-domain microscopy image segmentation	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	A lot of imaging data is generated in medical, and particularly in the microscopy ﬁeld. Researchers spend a lot of time analyzing this data due to slow algorithms and exhaustive manual work. Recent advancements in machine learning and especially deep learning areas resulted in methods that could be used to efﬁciently solve challenges in the microscopy imaging ﬁeld. Image segmentation is one of the most common labor-intensive tasks that could be automated with deep learning approaches. One of the biggest challenges for computer algorithms in this domain is the problem of domain shift. The domain shift is the difference between the distribution of the data used for training and the distribution of the new upcoming data. In this work, we show that deep neural networks could efﬁciently segment microscopy images with the domain shift present. Moreover, we show that transfer learning from other medical tasks is an effective strategy to reduce the amount of required annotated data, whereas ﬁne-tuning ImageNet models for microscopy segmentation gain little beneﬁt.	uk