Semisupervised learning using denoising autoencoders for brain lesion detection and segmentation

The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. Stacked denoising autoencoders (SDAEs) were pretrained using a large number of unlabeled patient volumes and fine-tuned with patches drawn from a limited number of patie...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of medical imaging (Bellingham, Wash.) Ročník 4; číslo 4; s. 041311
Hlavní autoři: Alex, Varghese, Vaidhya, Kiran, Thirunavukkarasu, Subramaniam, Kesavadas, Chandrasekharan, Krishnamurthi, Ganapathy
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 01.10.2017
Témata:
deep learning
stacked denoising autoencoder
magnetic resonance imaging
denoising autoencoder
gliomas
brain lesion
ISSN:2329-4302
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. Stacked denoising autoencoders (SDAEs) were pretrained using a large number of unlabeled patient volumes and fine-tuned with patches drawn from a limited number of patients ([Formula: see text], 40, 65). The results show negligible loss in performance even when SDAE was fine-tuned using 20 labeled patients. Low grade glioma (LGG) segmentation was achieved using a transfer learning approach in which a network pretrained with high grade glioma data was fine-tuned using LGG image patches. The networks were also shown to generalize well and provide good segmentation on unseen BraTS 2013 and BraTS 2015 test data. The manuscript also includes the use of a single layer DAE, referred to as novelty detector (ND). ND was trained to accurately reconstruct nonlesion patches. The reconstruction error maps of test data were used to localize lesions. The error maps were shown to assign unique error distributions to various constituents of the glioma, enabling localization. The ND learns the nonlesion brain accurately as it was also shown to provide good segmentation performance on ischemic brain lesions in images from a different database.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2329-4302
DOI:10.1117/1.JMI.4.4.041311