The Use of Deep Learning for Segmentation of Bone Marrow Histological Images

Proposed solution gives the segmentation of bone marrow histological images, required for further analysis via different methods. Proposed algorithm is based on deep learning using Convolutional Neural Network. More then 50 of ConvNNs where tested with different configurations and learning parameter...

Full description

Saved in:
Bibliographic Details
Published inArtificial Intelligence Trends in Intelligent Systems Vol. 573; pp. 466 - 473
Main Authors Oszutowska–Mazurek, Dorota, Knap, Oktawian
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2017
Springer International Publishing
SeriesAdvances in Intelligent Systems and Computing
Subjects
Artificial intelligence
Bone marrow images
Convolutional Neural Networks
Deep learning
Image segmentation
Online AccessGet full text
ISBN3319572601
9783319572604
ISSN2194-5357
2194-5365
DOI10.1007/978-3-319-57261-1_46

Cover

More Information
Summary:Proposed solution gives the segmentation of bone marrow histological images, required for further analysis via different methods. Proposed algorithm is based on deep learning using Convolutional Neural Network. More then 50 of ConvNNs where tested with different configurations and learning parameters (learning rate, weight decay). Obtained effectiveness is more then 92%.
ISBN:3319572601
9783319572604
ISSN:2194-5357
2194-5365
DOI:10.1007/978-3-319-57261-1_46